todo

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>
Co-authored-by: houseme <housemecn@gmail.com>

.copilot-rules.md

@@ -1,58 +0,0 @@
-# GitHub Copilot Rules for RustFS Project
-
-## Core Rules Reference
-
-This project follows the comprehensive AI coding rules defined in `.rules.md`. Please refer to that file for the complete set of development guidelines, coding standards, and best practices.
-
-## Copilot-Specific Configuration
-
-When using GitHub Copilot for this project, ensure you:
-
-1. **Review the unified rules**: Always check `.rules.md` for the latest project guidelines
-2. **Follow branch protection**: Never attempt to commit directly to main/master branch
-3. **Use English**: All code comments, documentation, and variable names must be in English
-4. **Clean code practices**: Only make modifications you're confident about
-5. **Test thoroughly**: Ensure all changes pass formatting, linting, and testing requirements
-
-## Quick Reference
-
-### Critical Rules
-- 🚫 **NEVER commit directly to main/master branch**
-- ✅ **ALWAYS work on feature branches**
-- 📝 **ALWAYS use English for code and documentation**
-- 🧹 **ALWAYS clean up temporary files after use**
-- 🎯 **ONLY make confident, necessary modifications**
-
-### Pre-commit Checklist
-```bash
-# Before committing, always run:
-cargo fmt --all
-cargo clippy --all-targets --all-features -- -D warnings
-cargo check --all-targets
-cargo test
-```
-
-### Branch Workflow
-```bash
-git checkout main
-git pull origin main
-git checkout -b feat/your-feature-name
-# Make your changes
-git add .
-git commit -m "feat: your feature description"
-git push origin feat/your-feature-name
-gh pr create
-```
-
-## Important Notes
-
-- This file serves as an entry point for GitHub Copilot
-- All detailed rules and guidelines are maintained in `.rules.md`
-- Updates to coding standards should be made in `.rules.md` to ensure consistency across all AI tools
-- When in doubt, always refer to `.rules.md` for authoritative guidance
-
-## See Also
-
-- [.rules.md](./.rules.md) - Complete AI coding rules and guidelines
-- [CONTRIBUTING.md](./CONTRIBUTING.md) - Contribution guidelines
-- [README.md](./README.md) - Project overview and setup instructions

.cursorrules

@@ -1,927 +0,0 @@
-# RustFS Project Cursor Rules
-
-## 🚨🚨🚨 CRITICAL DEVELOPMENT RULES - ZERO TOLERANCE 🚨🚨🚨
-
-### ⛔️ ABSOLUTE PROHIBITION: NEVER COMMIT DIRECTLY TO MASTER/MAIN BRANCH ⛔️
-
-**🔥 THIS IS THE MOST CRITICAL RULE - VIOLATION WILL RESULT IN IMMEDIATE REVERSAL 🔥**
-
-- **🚫 ZERO DIRECT COMMITS TO MAIN/MASTER BRANCH - ABSOLUTELY FORBIDDEN**
-- **🚫 ANY DIRECT COMMIT TO MAIN BRANCH MUST BE IMMEDIATELY REVERTED**
-- **🚫 NO EXCEPTIONS FOR HOTFIXES, EMERGENCIES, OR URGENT CHANGES**
-- **🚫 NO EXCEPTIONS FOR SMALL CHANGES, TYPOS, OR DOCUMENTATION UPDATES**
-- **🚫 NO EXCEPTIONS FOR ANYONE - MAINTAINERS, CONTRIBUTORS, OR ADMINS**
-
-### 📋 MANDATORY WORKFLOW - STRICTLY ENFORCED
-
-**EVERY SINGLE CHANGE MUST FOLLOW THIS WORKFLOW:**
-
-1. **Check current branch**: `git branch` (MUST NOT be on main/master)
-2. **Switch to main**: `git checkout main`
-3. **Pull latest**: `git pull origin main`
-4. **Create feature branch**: `git checkout -b feat/your-feature-name`
-5. **Make changes ONLY on feature branch**
-6. **Test thoroughly before committing**
-7. **Commit and push to feature branch**: `git push origin feat/your-feature-name`
-8. **Create Pull Request**: Use `gh pr create` (MANDATORY)
-9. **Wait for PR approval**: NO self-merging allowed
-10. **Merge through GitHub interface**: ONLY after approval
-
-### 🔒 ENFORCEMENT MECHANISMS
-
-- **Branch protection rules**: Main branch is protected
-- **Pre-commit hooks**: Will block direct commits to main
-- **CI/CD checks**: All PRs must pass before merging
-- **Code review requirement**: At least one approval needed
-- **Automated reversal**: Direct commits to main will be automatically reverted
-
-## Project Overview
-
-RustFS is a high-performance distributed object storage system written in Rust, compatible with S3 API. The project adopts a modular architecture, supporting erasure coding storage, multi-tenant management, observability, and other enterprise-level features.
-
-## Core Architecture Principles
-
-### 1. Modular Design
-
-- Project uses Cargo workspace structure, containing multiple independent crates
-- Core modules: `rustfs` (main service), `ecstore` (erasure coding storage), `common` (shared components)
-- Functional modules: `iam` (identity management), `madmin` (management interface), `crypto` (encryption), etc.
-- Tool modules: `cli` (command line tool), `crates/*` (utility libraries)
-
-### 2. Asynchronous Programming Pattern
-
-- Comprehensive use of `tokio` async runtime
-- Prioritize `async/await` syntax
-- Use `async-trait` for async methods in traits
-- Avoid blocking operations, use `spawn_blocking` when necessary
-
-### 3. Error Handling Strategy
-
-- **Use modular, type-safe error handling with `thiserror`**
-- Each module should define its own error type using `thiserror::Error` derive macro
-- Support error chains and context information through `#[from]` and `#[source]` attributes
-- Use `Result<T>` type aliases for consistency within each module
-- Error conversion between modules should use explicit `From` implementations
-- Follow the pattern: `pub type Result<T> = core::result::Result<T, Error>`
-- Use `#[error("description")]` attributes for clear error messages
-- Support error downcasting when needed through `other()` helper methods
-- Implement `Clone` for errors when required by the domain logic
-- **Current module error types:**
-  - `ecstore::error::StorageError` - Storage layer errors
-  - `ecstore::disk::error::DiskError` - Disk operation errors
-  - `iam::error::Error` - Identity and access management errors
-  - `policy::error::Error` - Policy-related errors
-  - `crypto::error::Error` - Cryptographic operation errors
-  - `filemeta::error::Error` - File metadata errors
-  - `rustfs::error::ApiError` - API layer errors
-  - Module-specific error types for specialized functionality
-
-## Code Style Guidelines
-
-### 1. Formatting Configuration
-
-```toml
-max_width = 130
-fn_call_width = 90
-single_line_let_else_max_width = 100
-```
-
-### 2. **🔧 MANDATORY Code Formatting Rules**
-
-**CRITICAL**: All code must be properly formatted before committing. This project enforces strict formatting standards to maintain code consistency and readability.
-
-#### Pre-commit Requirements (MANDATORY)
-
-Before every commit, you **MUST**:
-
-1. **Format your code**:
-
-   ```bash
-   cargo fmt --all
-   ```
-
-2. **Verify formatting**:
-
-   ```bash
-   cargo fmt --all --check
-   ```
-
-3. **Pass clippy checks**:
-
-   ```bash
-   cargo clippy --all-targets --all-features -- -D warnings
-   ```
-
-4. **Ensure compilation**:
-
-   ```bash
-   cargo check --all-targets
-   ```
-
-#### Quick Commands
-
-Use these convenient Makefile targets for common tasks:
-
-```bash
-# Format all code
-make fmt
-
-# Check if code is properly formatted
-make fmt-check
-
-# Run clippy checks
-make clippy
-
-# Run compilation check
-make check
-
-# Run tests
-make test
-
-# Run all pre-commit checks (format + clippy + check + test)
-make pre-commit
-
-# Setup git hooks (one-time setup)
-make setup-hooks
-```
-
-#### 🔒 Automated Pre-commit Hooks
-
-This project includes a pre-commit hook that automatically runs before each commit to ensure:
-
-- ✅ Code is properly formatted (`cargo fmt --all --check`)
-- ✅ No clippy warnings (`cargo clippy --all-targets --all-features -- -D warnings`)
-- ✅ Code compiles successfully (`cargo check --all-targets`)
-
-**Setting Up Pre-commit Hooks** (MANDATORY for all developers):
-
-Run this command once after cloning the repository:
-
-```bash
-make setup-hooks
-```
-
-Or manually:
-
-```bash
-chmod +x .git/hooks/pre-commit
-```
-
-#### 🚫 Commit Prevention
-
-If your code doesn't meet the formatting requirements, the pre-commit hook will:
-
-1. **Block the commit** and show clear error messages
-2. **Provide exact commands** to fix the issues
-3. **Guide you through** the resolution process
-
-Example output when formatting fails:
-
-```
-❌ Code formatting check failed!
-💡 Please run 'cargo fmt --all' to format your code before committing.
-
-🔧 Quick fix:
-   cargo fmt --all
-   git add .
-   git commit
-```
-
-### 3. Naming Conventions
-
-- Use `snake_case` for functions, variables, modules
-- Use `PascalCase` for types, traits, enums
-- Constants use `SCREAMING_SNAKE_CASE`
-- Global variables prefix `GLOBAL_`, e.g., `GLOBAL_Endpoints`
-- Use meaningful and descriptive names for variables, functions, and methods
-- Avoid meaningless names like `temp`, `data`, `foo`, `bar`, `test123`
-- Choose names that clearly express the purpose and intent
-
-### 4. Type Declaration Guidelines
-
-- **Prefer type inference over explicit type declarations** when the type is obvious from context
-- Let the Rust compiler infer types whenever possible to reduce verbosity and improve maintainability
-- Only specify types explicitly when:
-  - The type cannot be inferred by the compiler
-  - Explicit typing improves code clarity and readability
-  - Required for API boundaries (function signatures, public struct fields)
-  - Needed to resolve ambiguity between multiple possible types
-
-**Good examples (prefer these):**
-
-```rust
-// Compiler can infer the type
-let items = vec![1, 2, 3, 4];
-let config = Config::default();
-let result = process_data(&input);
-
-// Iterator chains with clear context
-let filtered: Vec<_> = items.iter().filter(|&&x| x > 2).collect();
-```
-
-**Avoid unnecessary explicit types:**
-
-```rust
-// Unnecessary - type is obvious
-let items: Vec<i32> = vec![1, 2, 3, 4];
-let config: Config = Config::default();
-let result: ProcessResult = process_data(&input);
-```
-
-**When explicit types are beneficial:**
-
-```rust
-// API boundaries - always specify types
-pub fn process_data(input: &[u8]) -> Result<ProcessResult, Error> { ... }
-
-// Ambiguous cases - explicit type needed
-let value: f64 = "3.14".parse().unwrap();
-
-// Complex generic types - explicit for clarity
-let cache: HashMap<String, Arc<Mutex<CacheEntry>>> = HashMap::new();
-```
-
-### 5. Documentation Comments
-
-- Public APIs must have documentation comments
-- Use `///` for documentation comments
-- Complex functions add `# Examples` and `# Parameters` descriptions
-- Error cases use `# Errors` descriptions
-- Always use English for all comments and documentation
-- Avoid meaningless comments like "debug 111" or placeholder text
-
-### 6. Import Guidelines
-
-- Standard library imports first
-- Third-party crate imports in the middle
-- Project internal imports last
-- Group `use` statements with blank lines between groups
-
-## Asynchronous Programming Guidelines
-
-### 1. Trait Definition
-
-```rust
-#[async_trait::async_trait]
-pub trait StorageAPI: Send + Sync {
-    async fn get_object(&self, bucket: &str, object: &str) -> Result<ObjectInfo>;
-}
-```
-
-### 2. Error Handling
-
-```rust
-// Use ? operator to propagate errors
-async fn example_function() -> Result<()> {
-    let data = read_file("path").await?;
-    process_data(data).await?;
-    Ok(())
-}
-```
-
-### 3. Concurrency Control
-
-- Use `Arc` and `Mutex`/`RwLock` for shared state management
-- Prioritize async locks from `tokio::sync`
-- Avoid holding locks for long periods
-
-## Logging and Tracing Guidelines
-
-### 1. Tracing Usage
-
-```rust
-#[tracing::instrument(skip(self, data))]
-async fn process_data(&self, data: &[u8]) -> Result<()> {
-    info!("Processing {} bytes", data.len());
-    // Implementation logic
-}
-```
-
-### 2. Log Levels
-
-- `error!`: System errors requiring immediate attention
-- `warn!`: Warning information that may affect functionality
-- `info!`: Important business information
-- `debug!`: Debug information for development use
-- `trace!`: Detailed execution paths
-
-### 3. Structured Logging
-
-```rust
-info!(
-    counter.rustfs_api_requests_total = 1_u64,
-    key_request_method = %request.method(),
-    key_request_uri_path = %request.uri().path(),
-    "API request processed"
-);
-```
-
-## Error Handling Guidelines
-
-### 1. Error Type Definition
-
-```rust
-// Use thiserror for module-specific error types
-#[derive(thiserror::Error, Debug)]
-pub enum MyError {
-    #[error("IO error: {0}")]
-    Io(#[from] std::io::Error),
-
-    #[error("Storage error: {0}")]
-    Storage(#[from] ecstore::error::StorageError),
-
-    #[error("Custom error: {message}")]
-    Custom { message: String },
-
-    #[error("File not found: {path}")]
-    FileNotFound { path: String },
-
-    #[error("Invalid configuration: {0}")]
-    InvalidConfig(String),
-}
-
-// Provide Result type alias for the module
-pub type Result<T> = core::result::Result<T, MyError>;
-```
-
-### 2. Error Helper Methods
-
-```rust
-impl MyError {
-    /// Create error from any compatible error type
-    pub fn other<E>(error: E) -> Self
-    where
-        E: Into<Box<dyn std::error::Error + Send + Sync>>,
-    {
-        MyError::Io(std::io::Error::other(error))
-    }
-}
-```
-
-### 3. Error Conversion Between Modules
-
-```rust
-// Convert between different module error types
-impl From<ecstore::error::StorageError> for MyError {
-    fn from(e: ecstore::error::StorageError) -> Self {
-        match e {
-            ecstore::error::StorageError::FileNotFound => {
-                MyError::FileNotFound { path: "unknown".to_string() }
-            }
-            _ => MyError::Storage(e),
-        }
-    }
-}
-
-// Provide reverse conversion when needed
-impl From<MyError> for ecstore::error::StorageError {
-    fn from(e: MyError) -> Self {
-        match e {
-            MyError::FileNotFound { .. } => ecstore::error::StorageError::FileNotFound,
-            MyError::Storage(e) => e,
-            _ => ecstore::error::StorageError::other(e),
-        }
-    }
-}
-```
-
-### 4. Error Context and Propagation
-
-```rust
-// Use ? operator for clean error propagation
-async fn example_function() -> Result<()> {
-    let data = read_file("path").await?;
-    process_data(data).await?;
-    Ok(())
-}
-
-// Add context to errors
-fn process_with_context(path: &str) -> Result<()> {
-    std::fs::read(path)
-        .map_err(|e| MyError::Custom {
-            message: format!("Failed to read {}: {}", path, e)
-        })?;
-    Ok(())
-}
-```
-
-### 5. API Error Conversion (S3 Example)
-
-```rust
-// Convert storage errors to API-specific errors
-use s3s::{S3Error, S3ErrorCode};
-
-#[derive(Debug)]
-pub struct ApiError {
-    pub code: S3ErrorCode,
-    pub message: String,
-    pub source: Option<Box<dyn std::error::Error + Send + Sync>>,
-}
-
-impl From<ecstore::error::StorageError> for ApiError {
-    fn from(err: ecstore::error::StorageError) -> Self {
-        let code = match &err {
-            ecstore::error::StorageError::BucketNotFound(_) => S3ErrorCode::NoSuchBucket,
-            ecstore::error::StorageError::ObjectNotFound(_, _) => S3ErrorCode::NoSuchKey,
-            ecstore::error::StorageError::BucketExists(_) => S3ErrorCode::BucketAlreadyExists,
-            ecstore::error::StorageError::InvalidArgument(_, _, _) => S3ErrorCode::InvalidArgument,
-            ecstore::error::StorageError::MethodNotAllowed => S3ErrorCode::MethodNotAllowed,
-            ecstore::error::StorageError::StorageFull => S3ErrorCode::ServiceUnavailable,
-            _ => S3ErrorCode::InternalError,
-        };
-
-        ApiError {
-            code,
-            message: err.to_string(),
-            source: Some(Box::new(err)),
-        }
-    }
-}
-
-impl From<ApiError> for S3Error {
-    fn from(err: ApiError) -> Self {
-        let mut s3e = S3Error::with_message(err.code, err.message);
-        if let Some(source) = err.source {
-            s3e.set_source(source);
-        }
-        s3e
-    }
-}
-```
-
-### 6. Error Handling Best Practices
-
-#### Pattern Matching and Error Classification
-
-```rust
-// Use pattern matching for specific error handling
-async fn handle_storage_operation() -> Result<()> {
-    match storage.get_object("bucket", "key").await {
-        Ok(object) => process_object(object),
-        Err(ecstore::error::StorageError::ObjectNotFound(bucket, key)) => {
-            warn!("Object not found: {}/{}", bucket, key);
-            create_default_object(bucket, key).await
-        }
-        Err(ecstore::error::StorageError::BucketNotFound(bucket)) => {
-            error!("Bucket not found: {}", bucket);
-            Err(MyError::Custom {
-                message: format!("Bucket {} does not exist", bucket)
-            })
-        }
-        Err(e) => {
-            error!("Storage operation failed: {}", e);
-            Err(MyError::Storage(e))
-        }
-    }
-}
-```
-
-#### Error Aggregation and Reporting
-
-```rust
-// Collect and report multiple errors
-pub fn validate_configuration(config: &Config) -> Result<()> {
-    let mut errors = Vec::new();
-
-    if config.bucket_name.is_empty() {
-        errors.push("Bucket name cannot be empty");
-    }
-
-    if config.region.is_empty() {
-        errors.push("Region must be specified");
-    }
-
-    if !errors.is_empty() {
-        return Err(MyError::Custom {
-            message: format!("Configuration validation failed: {}", errors.join(", "))
-        });
-    }
-
-    Ok(())
-}
-```
-
-#### Contextual Error Information
-
-```rust
-// Add operation context to errors
-#[tracing::instrument(skip(self))]
-async fn upload_file(&self, bucket: &str, key: &str, data: Vec<u8>) -> Result<()> {
-    self.storage
-        .put_object(bucket, key, data)
-        .await
-        .map_err(|e| MyError::Custom {
-            message: format!("Failed to upload {}/{}: {}", bucket, key, e)
-        })
-}
-```
-
-## Performance Optimization Guidelines
-
-### 1. Memory Management
-
-- Use `Bytes` instead of `Vec<u8>` for zero-copy operations
-- Avoid unnecessary cloning, use reference passing
-- Use `Arc` for sharing large objects
-
-### 2. Concurrency Optimization
-
-```rust
-// Use join_all for concurrent operations
-let futures = disks.iter().map(|disk| disk.operation());
-let results = join_all(futures).await;
-```
-
-### 3. Caching Strategy
-
-- Use `LazyLock` for global caching
-- Implement LRU cache to avoid memory leaks
-
-## Testing Guidelines
-
-### 1. Unit Tests
-
-```rust
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use test_case::test_case;
-
-    #[tokio::test]
-    async fn test_async_function() {
-        let result = async_function().await;
-        assert!(result.is_ok());
-    }
-
-    #[test_case("input1", "expected1")]
-    #[test_case("input2", "expected2")]
-    fn test_with_cases(input: &str, expected: &str) {
-        assert_eq!(function(input), expected);
-    }
-
-    #[test]
-    fn test_error_conversion() {
-        use ecstore::error::StorageError;
-
-        let storage_err = StorageError::BucketNotFound("test-bucket".to_string());
-        let api_err: ApiError = storage_err.into();
-
-        assert_eq!(api_err.code, S3ErrorCode::NoSuchBucket);
-        assert!(api_err.message.contains("test-bucket"));
-        assert!(api_err.source.is_some());
-    }
-
-    #[test]
-    fn test_error_types() {
-        let io_err = std::io::Error::new(std::io::ErrorKind::NotFound, "file not found");
-        let my_err = MyError::Io(io_err);
-
-        // Test error matching
-        match my_err {
-            MyError::Io(_) => {}, // Expected
-            _ => panic!("Unexpected error type"),
-        }
-    }
-
-    #[test]
-    fn test_error_context() {
-        let result = process_with_context("nonexistent_file.txt");
-        assert!(result.is_err());
-
-        let err = result.unwrap_err();
-        match err {
-            MyError::Custom { message } => {
-                assert!(message.contains("Failed to read"));
-                assert!(message.contains("nonexistent_file.txt"));
-            }
-            _ => panic!("Expected Custom error"),
-        }
-    }
-}
-```
-
-### 2. Integration Tests
-
-- Use `e2e_test` module for end-to-end testing
-- Simulate real storage environments
-
-### 3. Test Quality Standards
-
-- Write meaningful test cases that verify actual functionality
-- Avoid placeholder or debug content like "debug 111", "test test", etc.
-- Use descriptive test names that clearly indicate what is being tested
-- Each test should have a clear purpose and verify specific behavior
-- Test data should be realistic and representative of actual use cases
-
-## Cross-Platform Compatibility Guidelines
-
-### 1. CPU Architecture Compatibility
-
-- **Always consider multi-platform and different CPU architecture compatibility** when writing code
-- Support major architectures: x86_64, aarch64 (ARM64), and other target platforms
-- Use conditional compilation for architecture-specific code:
-
-```rust
-#[cfg(target_arch = "x86_64")]
-fn optimized_x86_64_function() { /* x86_64 specific implementation */ }
-
-#[cfg(target_arch = "aarch64")]
-fn optimized_aarch64_function() { /* ARM64 specific implementation */ }
-
-#[cfg(not(any(target_arch = "x86_64", target_arch = "aarch64")))]
-fn generic_function() { /* Generic fallback implementation */ }
-```
-
-### 2. Platform-Specific Dependencies
-
-- Use feature flags for platform-specific dependencies
-- Provide fallback implementations for unsupported platforms
-- Test on multiple architectures in CI/CD pipeline
-
-### 3. Endianness Considerations
-
-- Use explicit byte order conversion when dealing with binary data
-- Prefer `to_le_bytes()`, `from_le_bytes()` for consistent little-endian format
-- Use `byteorder` crate for complex binary format handling
-
-### 4. SIMD and Performance Optimizations
-
-- Use portable SIMD libraries like `wide` or `packed_simd`
-- Provide fallback implementations for non-SIMD architectures
-- Use runtime feature detection when appropriate
-
-## Security Guidelines
-
-### 1. Memory Safety
-
-- Disable `unsafe` code (workspace.lints.rust.unsafe_code = "deny")
-- Use `rustls` instead of `openssl`
-
-### 2. Authentication and Authorization
-
-```rust
-// Use IAM system for permission checks
-let identity = iam.authenticate(&access_key, &secret_key).await?;
-iam.authorize(&identity, &action, &resource).await?;
-```
-
-## Configuration Management Guidelines
-
-### 1. Environment Variables
-
-- Use `RUSTFS_` prefix
-- Support both configuration files and environment variables
-- Provide reasonable default values
-
-### 2. Configuration Structure
-
-```rust
-#[derive(Debug, Deserialize, Clone)]
-pub struct Config {
-    pub address: String,
-    pub volumes: String,
-    #[serde(default)]
-    pub console_enable: bool,
-}
-```
-
-## Dependency Management Guidelines
-
-### 1. Workspace Dependencies
-
-- Manage versions uniformly at workspace level
-- Use `workspace = true` to inherit configuration
-
-### 2. Feature Flags
-
-```rust
-[features]
-default = ["file"]
-gpu = ["dep:nvml-wrapper"]
-kafka = ["dep:rdkafka"]
-```
-
-## Deployment and Operations Guidelines
-
-### 1. Containerization
-
-- Provide Dockerfile and docker-compose configuration
-- Support multi-stage builds to optimize image size
-
-### 2. Observability
-
-- Integrate OpenTelemetry for distributed tracing
-- Support Prometheus metrics collection
-- Provide Grafana dashboards
-
-### 3. Health Checks
-
-```rust
-// Implement health check endpoint
-async fn health_check() -> Result<HealthStatus> {
-    // Check component status
-}
-```
-
-## Code Review Checklist
-
-### 1. **Code Formatting and Quality (MANDATORY)**
-
-- [ ] **Code is properly formatted** (`cargo fmt --all --check` passes)
-- [ ] **All clippy warnings are resolved** (`cargo clippy --all-targets --all-features -- -D warnings` passes)
-- [ ] **Code compiles successfully** (`cargo check --all-targets` passes)
-- [ ] **Pre-commit hooks are working** and all checks pass
-- [ ] **No formatting-related changes** mixed with functional changes (separate commits)
-
-### 2. Functionality
-
-- [ ] Are all error cases properly handled?
-- [ ] Is there appropriate logging?
-- [ ] Is there necessary test coverage?
-
-### 3. Performance
-
-- [ ] Are unnecessary memory allocations avoided?
-- [ ] Are async operations used correctly?
-- [ ] Are there potential deadlock risks?
-
-### 4. Security
-
-- [ ] Are input parameters properly validated?
-- [ ] Are there appropriate permission checks?
-- [ ] Is information leakage avoided?
-
-### 5. Cross-Platform Compatibility
-
-- [ ] Does the code work on different CPU architectures (x86_64, aarch64)?
-- [ ] Are platform-specific features properly gated with conditional compilation?
-- [ ] Is byte order handling correct for binary data?
-- [ ] Are there appropriate fallback implementations for unsupported platforms?
-
-### 6. Code Commits and Documentation
-
-- [ ] Does it comply with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/)?
-- [ ] Are commit messages concise and under 72 characters for the title line?
-- [ ] Commit titles should be concise and in English, avoid Chinese
-- [ ] Is PR description provided in copyable markdown format for easy copying?
-
-## Common Patterns and Best Practices
-
-### 1. Resource Management
-
-```rust
-// Use RAII pattern for resource management
-pub struct ResourceGuard {
-    resource: Resource,
-}
-
-impl Drop for ResourceGuard {
-    fn drop(&mut self) {
-        // Clean up resources
-    }
-}
-```
-
-### 2. Dependency Injection
-
-```rust
-// Use dependency injection pattern
-pub struct Service {
-    config: Arc<Config>,
-    storage: Arc<dyn StorageAPI>,
-}
-```
-
-### 3. Graceful Shutdown
-
-```rust
-// Implement graceful shutdown
-async fn shutdown_gracefully(shutdown_rx: &mut Receiver<()>) {
-    tokio::select! {
-        _ = shutdown_rx.recv() => {
-            info!("Received shutdown signal");
-            // Perform cleanup operations
-        }
-        _ = tokio::time::sleep(SHUTDOWN_TIMEOUT) => {
-            warn!("Shutdown timeout reached");
-        }
-    }
-}
-```
-
-## Domain-Specific Guidelines
-
-### 1. Storage Operations
-
-- All storage operations must support erasure coding
-- Implement read/write quorum mechanisms
-- Support data integrity verification
-
-### 2. Network Communication
-
-- Use gRPC for internal service communication
-- HTTP/HTTPS support for S3-compatible API
-- Implement connection pooling and retry mechanisms
-
-### 3. Metadata Management
-
-- Use FlatBuffers for serialization
-- Support version control and migration
-- Implement metadata caching
-
-These rules should serve as guiding principles when developing the RustFS project, ensuring code quality, performance, and maintainability.
-
-### 4. Code Operations
-
-#### Branch Management
-
-- **🚨 CRITICAL: NEVER modify code directly on main or master branch - THIS IS ABSOLUTELY FORBIDDEN 🚨**
-- **⚠️ ANY DIRECT COMMITS TO MASTER/MAIN WILL BE REJECTED AND MUST BE REVERTED IMMEDIATELY ⚠️**
-- **🔒 ALL CHANGES MUST GO THROUGH PULL REQUESTS - NO DIRECT COMMITS TO MAIN UNDER ANY CIRCUMSTANCES 🔒**
-- **Always work on feature branches - NO EXCEPTIONS**
-- Always check the .cursorrules file before starting to ensure you understand the project guidelines
-- **MANDATORY workflow for ALL changes:**
-   1. `git checkout main` (switch to main branch)
-   2. `git pull` (get latest changes)
-   3. `git checkout -b feat/your-feature-name` (create and switch to feature branch)
-   4. Make your changes ONLY on the feature branch
-   5. Test thoroughly before committing
-   6. Commit and push to the feature branch
-   7. **Create a pull request for code review - THIS IS THE ONLY WAY TO MERGE TO MAIN**
-   8. **Wait for PR approval before merging - NEVER merge your own PRs without review**
-- Use descriptive branch names following the pattern: `feat/feature-name`, `fix/issue-name`, `refactor/component-name`, etc.
-- **Double-check current branch before ANY commit: `git branch` to ensure you're NOT on main/master**
-- **Pull Request Requirements:**
-  - All changes must be submitted via PR regardless of size or urgency
-  - PRs must include comprehensive description and testing information
-  - PRs must pass all CI/CD checks before merging
-  - PRs require at least one approval from code reviewers
-  - Even hotfixes and emergency changes must go through PR process
-- **Enforcement:**
-  - Main branch should be protected with branch protection rules
-  - Direct pushes to main should be blocked by repository settings
-  - Any accidental direct commits to main must be immediately reverted via PR
-
-#### Development Workflow
-
-## 🎯 **Core Development Principles**
-
-- **🔴 Every change must be precise - don't modify unless you're confident**
-  - Carefully analyze code logic and ensure complete understanding before making changes
-  - When uncertain, prefer asking users or consulting documentation over blind modifications
-  - Use small iterative steps, modify only necessary parts at a time
-  - Evaluate impact scope before changes to ensure no new issues are introduced
-
-- **🚀 GitHub PR creation prioritizes gh command usage**
-  - Prefer using `gh pr create` command to create Pull Requests
-  - Avoid having users manually create PRs through web interface
-  - Provide clear and professional PR titles and descriptions
-  - Using `gh` commands ensures better integration and automation
-
-## 📝 **Code Quality Requirements**
-
-- Use English for all code comments, documentation, and variable names
-- Write meaningful and descriptive names for variables, functions, and methods
-- Avoid meaningless test content like "debug 111" or placeholder values
-- Before each change, carefully read the existing code to ensure you understand the code structure and implementation, do not break existing logic implementation, do not introduce new issues
-- Ensure each change provides sufficient test cases to guarantee code correctness
-- Do not arbitrarily modify numbers and constants in test cases, carefully analyze their meaning to ensure test case correctness
-- When writing or modifying tests, check existing test cases to ensure they have scientific naming and rigorous logic testing, if not compliant, modify test cases to ensure scientific and rigorous testing
-- **Before committing any changes, run `cargo clippy --all-targets --all-features -- -D warnings` to ensure all code passes Clippy checks**
-- After each development completion, first git add . then git commit -m "feat: feature description" or "fix: issue description", ensure compliance with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/)
-- **Keep commit messages concise and under 72 characters** for the title line, use body for detailed explanations if needed
-- After each development completion, first git push to remote repository
-- After each change completion, summarize the changes, do not create summary files, provide a brief change description, ensure compliance with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/)
-- Provide change descriptions needed for PR in the conversation, ensure compliance with [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/)
-- **Always provide PR descriptions in English** after completing any changes, including:
-  - Clear and concise title following Conventional Commits format
-  - Detailed description of what was changed and why
-  - List of key changes and improvements
-  - Any breaking changes or migration notes if applicable
-  - Testing information and verification steps
-- **Provide PR descriptions in copyable markdown format** enclosed in code blocks for easy one-click copying
-
-## 🚫 AI 文档生成限制
-
-### 禁止生成总结文档
-
-- **严格禁止创建任何形式的AI生成总结文档**
-- **不得创建包含大量表情符号、详细格式化表格和典型AI风格的文档**
-- **不得在项目中生成以下类型的文档：**
-  - 基准测试总结文档（BENCHMARK*.md）
-  - 实现对比分析文档（IMPLEMENTATION_COMPARISON*.md）
-  - 性能分析报告文档
-  - 架构总结文档
-  - 功能对比文档
-  - 任何带有大量表情符号和格式化内容的文档
-- **如果需要文档，请只在用户明确要求时创建，并保持简洁实用的风格**
-- **文档应当专注于实际需要的信息，避免过度格式化和装饰性内容**
-- **任何发现的AI生成总结文档都应该立即删除**
-
-### 允许的文档类型
-
-- README.md（项目介绍，保持简洁）
-- 技术文档（仅在明确需要时创建）
-- 用户手册（仅在明确需要时创建）
-- API文档（从代码生成）
-- 变更日志（CHANGELOG.md）

.docker/observability/docker-compose.yml

@@ -14,84 +14,165 @@
 
 services:
 
+  tempo-init:
+    image: busybox:latest
+    command: [ "sh", "-c", "chown -R 10001:10001 /var/tempo" ]
+    volumes:
+      - ./tempo-data:/var/tempo
+    user: root
+    networks:
+      - otel-network
+    restart: "no"
+
   tempo:
     image: grafana/tempo:latest
-    #user: root # The container must be started with root to execute chown in the script
-    #entrypoint: [ "/etc/tempo/entrypoint.sh" ]  # Specify a custom entry point
+    user: "10001" # The container must be started with root to execute chown in the script
     command: [ "-config.file=/etc/tempo.yaml" ] # This is passed as a parameter to the entry point script
     volumes:
-      - ./tempo-entrypoint.sh:/etc/tempo/entrypoint.sh # Mount entry point script
-      - ./tempo.yaml:/etc/tempo.yaml
+      - ./tempo.yaml:/etc/tempo.yaml:ro
       - ./tempo-data:/var/tempo
     ports:
       - "3200:3200" # tempo
       - "24317:4317" # otlp grpc
+      - "24318:4318" # otlp http
+    restart: unless-stopped
     networks:
       - otel-network
+    healthcheck:
+      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3200/metrics" ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+      start_period: 15s
 
   otel-collector:
-    image: otel/opentelemetry-collector-contrib:0.129.1
+    image: otel/opentelemetry-collector-contrib:latest
     environment:
       - TZ=Asia/Shanghai
     volumes:
-      - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml
+      - ./otel-collector-config.yaml:/etc/otelcol-contrib/config.yaml:ro
     ports:
-      - "1888:1888"
-      - "8888:8888"
-      - "8889:8889"
-      - "13133:13133"
-      - "4317:4317"
-      - "4318:4318"
-      - "55679:55679"
+      - "1888:1888" # pprof
+      - "8888:8888" # Prometheus metrics for Collector
+      - "8889:8889" # Prometheus metrics for application indicators
+      - "13133:13133" # health check
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP
+      - "55679:55679" # zpages
     networks:
       - otel-network
+    depends_on:
+      jaeger:
+        condition: service_started
+      tempo:
+        condition: service_started
+      prometheus:
+        condition: service_started
+      loki:
+        condition: service_started
+    healthcheck:
+      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:13133" ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+
   jaeger:
-    image: jaegertracing/jaeger:2.8.0
+    image: jaegertracing/jaeger:latest
     environment:
       - TZ=Asia/Shanghai
+      - SPAN_STORAGE_TYPE=memory
+      - COLLECTOR_OTLP_ENABLED=true
     ports:
-      - "16686:16686"
-      - "14317:4317"
-      - "14318:4318"
+      - "16686:16686" # Web UI
+      - "14317:4317" # OTLP gRPC
+      - "14318:4318" # OTLP HTTP
+      - "18888:8888" # collector
     networks:
       - otel-network
+    healthcheck:
+      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:16686" ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
   prometheus:
-    image: prom/prometheus:v3.4.2
+    image: prom/prometheus:latest
     environment:
       - TZ=Asia/Shanghai
     volumes:
-      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./prometheus-data:/prometheus
     ports:
       - "9090:9090"
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--web.enable-otlp-receiver' # Enable OTLP
+      - '--web.enable-remote-write-receiver' # Enable remote write
+      - '--enable-feature=promql-experimental-functions' # Enable info()
+      - '--storage.tsdb.min-block-duration=15m' # Minimum block duration
+      - '--storage.tsdb.max-block-duration=1h'  # Maximum block duration
+      - '--log.level=info'
+      - '--storage.tsdb.retention.time=30d'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
+    restart: unless-stopped
     networks:
       - otel-network
+    healthcheck:
+      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy" ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
   loki:
-    image: grafana/loki:3.5.1
+    image: grafana/loki:latest
     environment:
       - TZ=Asia/Shanghai
     volumes:
-      - ./loki-config.yaml:/etc/loki/local-config.yaml
+      - ./loki-config.yaml:/etc/loki/local-config.yaml:ro
     ports:
       - "3100:3100"
     command: -config.file=/etc/loki/local-config.yaml
     networks:
       - otel-network
+    healthcheck:
+      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3100/ready" ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
   grafana:
-    image: grafana/grafana:12.0.2
+    image: grafana/grafana:latest
     ports:
       - "3000:3000"  # Web UI
     volumes:
       - ./grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
     environment:
       - GF_SECURITY_ADMIN_PASSWORD=admin
+      - GF_SECURITY_ADMIN_USER=admin
       - TZ=Asia/Shanghai
+      - GF_INSTALL_PLUGINS=grafana-pyroscope-datasource
+    restart: unless-stopped
     networks:
       - otel-network
+    depends_on:
+      - prometheus
+      - tempo
+      - loki
+    healthcheck:
+      test: [ "CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health" ]
+      interval: 10s
+      timeout: 5s
+      retries: 3
 
+volumes:
+  prometheus-data:
+  tempo-data:
 
 networks:
   otel-network:
     driver: bridge
     name: "network_otel_config"
+    ipam:
+      config:
+        - subnet: 172.28.0.0/16
     driver_opts:
-      com.docker.network.enable_ipv6: "true"    
+      com.docker.network.enable_ipv6: "true"

.docker/observability/grafana-datasources.yaml

@@ -29,4 +29,80 @@ datasources:
       serviceMap:
         datasourceUid: prometheus
       streamingEnabled:
-        search: true
+        search: true
+      tracesToLogsV2:
+        # Field with an internal link pointing to a logs data source in Grafana.
+        # datasourceUid value must match the uid value of the logs data source.
+        datasourceUid: 'loki'
+        spanStartTimeShift: '-1h'
+        spanEndTimeShift: '1h'
+        tags: [ 'job', 'instance', 'pod', 'namespace' ]
+        filterByTraceID: false
+        filterBySpanID: false
+        customQuery: true
+        query: 'method="$${__span.tags.method}"'
+        tracesToMetrics:
+          datasourceUid: 'prometheus'
+          spanStartTimeShift: '-1h'
+          spanEndTimeShift: '1h'
+          tags: [ { key: 'service.name', value: 'service' }, { key: 'job' } ]
+          queries:
+            - name: 'Sample query'
+              query: 'sum(rate(traces_spanmetrics_latency_bucket{$$__tags}[5m]))'
+        tracesToProfiles:
+          datasourceUid: 'grafana-pyroscope-datasource'
+          tags: [ 'job', 'instance', 'pod', 'namespace' ]
+          profileTypeId: 'process_cpu:cpu:nanoseconds:cpu:nanoseconds'
+          customQuery: true
+          query: 'method="$${__span.tags.method}"'
+        serviceMap:
+          datasourceUid: 'prometheus'
+        nodeGraph:
+          enabled: true
+        search:
+          hide: false
+        traceQuery:
+          timeShiftEnabled: true
+          spanStartTimeShift: '-1h'
+          spanEndTimeShift: '1h'
+        spanBar:
+          type: 'Tag'
+          tag: 'http.path'
+        streamingEnabled:
+          search: true
+  - name: Jaeger
+    type: jaeger
+    uid: Jaeger
+    url: http://jaeger:16686
+    basicAuth: false
+    access: proxy
+    readOnly: false
+    isDefault: false
+    jsonData:
+      tracesToLogsV2:
+        # Field with an internal link pointing to a logs data source in Grafana.
+        # datasourceUid value must match the uid value of the logs data source.
+        datasourceUid: 'loki'
+        spanStartTimeShift: '1h'
+        spanEndTimeShift: '-1h'
+        tags: [ 'job', 'instance', 'pod', 'namespace' ]
+        filterByTraceID: false
+        filterBySpanID: false
+        customQuery: true
+        query: 'method="$${__span.tags.method}"'
+      tracesToMetrics:
+        datasourceUid: 'Prometheus'
+        spanStartTimeShift: '1h'
+        spanEndTimeShift: '-1h'
+        tags: [ { key: 'service.name', value: 'service' }, { key: 'job' } ]
+        queries:
+          - name: 'Sample query'
+            query: 'sum(rate(traces_spanmetrics_latency_bucket{$$__tags}[5m]))'
+      nodeGraph:
+        enabled: true
+      traceQuery:
+        timeShiftEnabled: true
+        spanStartTimeShift: '1h'
+        spanEndTimeShift: '-1h'
+      spanBar:
+        type: 'None'

.docker/observability/jaeger-config.yaml

@@ -65,6 +65,7 @@ extensions:
       some_store:
         memory:
           max_traces: 1000000
+          max_events: 100000
       another_store:
         memory:
           max_traces: 1000000
@@ -102,6 +103,7 @@ receivers:
 
 processors:
   batch:
+  metadata_keys: [ "span.kind", "http.method", "http.status_code", "db.system", "db.statement", "messaging.system", "messaging.destination", "messaging.operation","span.events","span.links" ]
   # Adaptive Sampling Processor is required to support adaptive sampling.
   # It expects remote_sampling extension with `adaptive:` config to be enabled.
   adaptive_sampling:

.docker/observability/loki-config.yaml

@@ -41,6 +41,9 @@ query_range:
 
 limits_config:
   metric_aggregation_enabled: true
+  max_line_size: 256KB
+  max_line_size_truncate: false
+  allow_structured_metadata: true
 
 schema_config:
   configs:
@@ -51,6 +54,7 @@ schema_config:
       index:
         prefix: index_
         period: 24h
+      row_shards: 16
 
 pattern_ingester:
   enabled: true
@@ -63,6 +67,7 @@ ruler:
 frontend:
   encoding: protobuf
 
+
 # By default, Loki will send anonymous, but uniquely-identifiable usage and configuration
 # analytics to Grafana Labs. These statistics are sent to https://stats.grafana.org/
 #

.docker/observability/otel-collector-config.yaml

@@ -15,67 +15,108 @@
 receivers:
   otlp:
     protocols:
-      grpc: # OTLP gRPC 接收器
+      grpc: # OTLP gRPC receiver
         endpoint: 0.0.0.0:4317
-      http: # OTLP HTTP 接收器
+      http: # OTLP HTTP receiver
         endpoint: 0.0.0.0:4318
 
 processors:
-  batch: # 批处理处理器，提升吞吐量
+  batch: # Batch processor to improve throughput
     timeout: 5s
     send_batch_size: 1000
+    metadata_keys: [ ]
+    metadata_cardinality_limit: 1000
   memory_limiter:
     check_interval: 1s
     limit_mib: 512
+  transform/logs:
+    log_statements:
+      - context: log
+        statements:
+          # Extract Body as attribute "message"
+          - set(attributes["message"], body.string)
+          # Retain the original Body
+          - set(attributes["log.body"], body.string)
 
 exporters:
-  otlp/traces: # OTLP 导出器，用于跟踪数据
-    endpoint: "jaeger:4317"  # Jaeger 的 OTLP gRPC 端点
+  otlp/traces: # OTLP exporter for trace data
+    endpoint: "http://jaeger:4317"  # OTLP gRPC endpoint for Jaeger
     tls:
-      insecure: true  # 开发环境禁用 TLS，生产环境需配置证书
-  otlp/tempo: # OTLP 导出器，用于跟踪数据
-    endpoint: "tempo:4317"  # tempo 的 OTLP gRPC 端点
+      insecure: true  # TLS is disabled in the development environment and a certificate needs to be configured in the production environment.
+    compression: gzip  # Enable compression to reduce network bandwidth
+    retry_on_failure:
+      enabled: true  # Enable retry on failure
+      initial_interval: 1s  # Initial interval for retry
+      max_interval: 30s  # Maximum interval for retry
+      max_elapsed_time: 300s  # Maximum elapsed time for retry
+    sending_queue:
+      enabled: true  # Enable sending queue
+      num_consumers: 10  # Number of consumers
+      queue_size: 5000  # Queue size
+  otlp/tempo: # OTLP exporter for trace data
+    endpoint: "http://tempo:4317"  # OTLP gRPC endpoint for tempo
     tls:
-      insecure: true  # 开发环境禁用 TLS，生产环境需配置证书
-  prometheus: # Prometheus 导出器，用于指标数据
-    endpoint: "0.0.0.0:8889"  # Prometheus 刮取端点
-    namespace: "rustfs"  # 指标前缀
-    send_timestamps: true  # 发送时间戳
-    # enable_open_metrics: true
-  loki: # Loki 导出器，用于日志数据
-    # endpoint: "http://loki:3100/otlp/v1/logs"
-    endpoint: "http://loki:3100/loki/api/v1/push"
+      insecure: true  # TLS is disabled in the development environment and a certificate needs to be configured in the production environment.
+    compression: gzip  # Enable compression to reduce network bandwidth
+    retry_on_failure:
+      enabled: true  # Enable retry on failure
+      initial_interval: 1s  # Initial interval for retry
+      max_interval: 30s  # Maximum interval for retry
+      max_elapsed_time: 300s  # Maximum elapsed time for retry
+    sending_queue:
+      enabled: true  # Enable sending queue
+      num_consumers: 10  # Number of consumers
+      queue_size: 5000  # Queue size
+  prometheus: # Prometheus exporter for metrics data
+    endpoint: "0.0.0.0:8889"  # Prometheus scraping endpoint
+    namespace: "metrics"  # indicator prefix
+    send_timestamps: true  # Send timestamp
+    metric_expiration: 5m  # Metric expiration time
+    resource_to_telemetry_conversion:
+      enabled: true  # Enable resource to telemetry conversion
+  otlphttp/loki: # Loki exporter for log data
+    endpoint: "http://loki:3100/otlp"
     tls:
       insecure: true
+    compression: gzip  # Enable compression to reduce network bandwidth
 extensions:
   health_check:
+    endpoint: 0.0.0.0:13133
   pprof:
+    endpoint: 0.0.0.0:1888
   zpages:
+    endpoint: 0.0.0.0:55679
 service:
-  extensions: [ health_check, pprof, zpages ]  # 启用扩展
+  extensions: [ health_check, pprof, zpages ]  # Enable extension
   pipelines:
     traces:
       receivers: [ otlp ]
-      processors: [ memory_limiter,batch ]
-      exporters: [ otlp/traces,otlp/tempo ]
+      processors: [ memory_limiter, batch ]
+      exporters: [ otlp/traces, otlp/tempo ]
     metrics:
       receivers: [ otlp ]
       processors: [ batch ]
       exporters: [ prometheus ]
     logs:
       receivers: [ otlp ]
-      processors: [ batch ]
-      exporters: [ loki ]
+      processors: [ batch, transform/logs ]
+      exporters: [ otlphttp/loki ]
   telemetry:
     logs:
-      level: "info"  # Collector 日志级别
+      level: "debug"  # Collector log level
+      encoding: "json"  # Log encoding: console or json
     metrics:
-      level: "detailed" # 可以是 basic, normal, detailed
+      level: "detailed" # Can be basic, normal, detailed
       readers:
         - periodic:
             exporter:
               otlp:
                 protocol: http/protobuf
                 endpoint: http://otel-collector:4318
+        - pull:
+            exporter:
+              prometheus:
+                host: '0.0.0.0'
+                port: 8888
 
 

.docker/observability/prometheus-data/.gitignore

@@ -0,0 +1 @@
+*

.docker/observability/prometheus.yml

@@ -13,16 +13,53 @@
 # limitations under the License.
 
 global:
-  scrape_interval: 5s  # 刮取间隔
+  scrape_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  evaluation_interval: 15s
+  external_labels:
+    cluster: 'rustfs-dev'  # Label to identify the cluster
+    relica: '1'  # Replica identifier
 
 scrape_configs:
-  - job_name: 'otel-collector'
+  - job_name: 'otel-collector-internal'
     static_configs:
-      - targets: [ 'otel-collector:8888' ]  # 从 Collector 刮取指标
-  - job_name: 'otel-metrics'
+      - targets: [ 'otel-collector:8888' ]  # Scrape metrics from Collector
+    scrape_interval: 10s
+  - job_name: 'rustfs-app-metrics'
     static_configs:
-      - targets: [ 'otel-collector:8889' ]  # 应用指标
+      - targets: [ 'otel-collector:8889' ]  # Application indicators
+    scrape_interval: 15s
+    metric_relabel_configs:
   - job_name: 'tempo'
     static_configs:
-      - targets: [ 'tempo:3200' ]
-      
+      - targets: [ 'tempo:3200' ]  # Scrape metrics from Tempo
+  - job_name: 'jaeger'
+    static_configs:
+      - targets: [ 'jaeger:8888' ]  # Jaeger admin port
+
+otlp:
+  # Recommended attributes to be promoted to labels.
+  promote_resource_attributes:
+    - service.instance.id
+    - service.name
+    - service.namespace
+    - cloud.availability_zone
+    - cloud.region
+    - container.name
+    - deployment.environment.name
+    - k8s.cluster.name
+    - k8s.container.name
+    - k8s.cronjob.name
+    - k8s.daemonset.name
+    - k8s.deployment.name
+    - k8s.job.name
+    - k8s.namespace.name
+    - k8s.pod.name
+    - k8s.replicaset.name
+    - k8s.statefulset.name
+  # Ingest OTLP data keeping all characters in metric/label names.
+  translation_strategy: NoUTF8EscapingWithSuffixes
+
+storage:
+  # OTLP is a push-based protocol, Out of order samples is a common scenario.
+  tsdb:
+    out_of_order_time_window: 30m

.docker/observability/tempo-entrypoint.sh

@@ -1,8 +0,0 @@
-#!/bin/sh
-# Run as root to fix directory permissions
-chown -R 10001:10001 /var/tempo
-
-# Use su-exec (a lightweight sudo/gosu alternative, commonly used in Alpine mirroring)
-# Switch to user 10001 and execute the original command (CMD) passed to the script
-# "$@" represents all parameters passed to this script, i.e. command in docker-compose
-exec su-exec 10001:10001 /tempo "$@"

.docker/observability/tempo.yaml

@@ -18,7 +18,9 @@ distributor:
     otlp:
       protocols:
         grpc:
-          endpoint: "tempo:4317"
+          endpoint: "0.0.0.0:4317"
+        http:
+          endpoint: "0.0.0.0:4318"
 
 ingester:
   max_block_duration: 5m # cut the headblock when this much time passes. this is being set for demo purposes and should probably be left alone normally

.github/actions/setup/action.yml

@@ -52,24 +52,19 @@ runs:
         sudo apt-get install -y \
           musl-tools \
           build-essential \
-          lld \
-          libdbus-1-dev \
-          libwayland-dev \
-          libwebkit2gtk-4.1-dev \
-          libxdo-dev \
           pkg-config \
           libssl-dev
 
     - name: Install protoc
       uses: arduino/setup-protoc@v3
       with:
-        version: "31.1"
+        version: "33.1"
         repo-token: ${{ inputs.github-token }}
 
     - name: Install flatc
       uses: Nugine/setup-flatc@v1
       with:
-        version: "25.2.10"
+        version: "25.9.23"
 
     - name: Install Rust toolchain
       uses: dtolnay/rust-toolchain@stable

.github/dependabot.yml

@@ -22,8 +22,18 @@ updates:
   - package-ecosystem: "cargo" # See documentation for possible values
     directory: "/" # Location of package manifests
     schedule:
-      interval: "monthly"
+      interval: "weekly"
+      day: "monday"
+      timezone: "Asia/Shanghai"
+      time: "08:00"
     groups:
+      s3s:
+        update-types:
+          - "minor"
+          - "patch"
+        patterns:
+          - "s3s"
+          - "s3s-*"
       dependencies:
         patterns:
           - "*"

.github/workflows/audit.yml

@@ -31,6 +31,9 @@ on:
     - cron: '0 0 * * 0' # Weekly on Sunday at midnight UTC
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 env:
   CARGO_TERM_COLOR: always
 

.github/workflows/build.yml

@@ -70,6 +70,9 @@ on:
         default: true
         type: boolean
 
+permissions:
+  contents: read
+
 env:
   CARGO_TERM_COLOR: always
   RUST_BACKTRACE: 1

.github/workflows/ci.yml

@@ -59,6 +59,9 @@ on:
     - cron: "0 0 * * 0" # Weekly on Sunday at midnight UTC
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 env:
   CARGO_TERM_COLOR: always
   RUST_BACKTRACE: 1
@@ -100,6 +103,8 @@ jobs:
     runs-on: ubuntu-latest
     timeout-minutes: 60
     steps:
+      - name: Delete huge unnecessary tools folder
+        run: rm -rf /opt/hostedtoolcache
       - name: Checkout repository
         uses: actions/checkout@v5
 

.github/workflows/docker.yml

@@ -58,6 +58,10 @@ on:
         type: boolean
 
 env:
+  CONCLUSION: ${{ github.event.workflow_run.conclusion }}
+  HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
+  HEAD_SHA: ${{ github.event.workflow_run.head_sha }}
+  TRIGGERING_EVENT: ${{ github.event.workflow_run.event }}
   DOCKERHUB_USERNAME: rustfs
   CARGO_TERM_COLOR: always
   REGISTRY_DOCKERHUB: rustfs/rustfs
@@ -102,27 +106,27 @@ jobs:
 
             # Check if the triggering workflow was successful
             # If the workflow succeeded, it means ALL builds (including Linux x86_64 and aarch64) succeeded
-            if [[ "${{ github.event.workflow_run.conclusion }}" == "success" ]]; then
+            if [[ "$CONCLUSION" == "success" ]]; then
               echo "✅ Build workflow succeeded, all builds including Linux are successful"
               should_build=true
               should_push=true
             else
-              echo "❌ Build workflow failed (conclusion: ${{ github.event.workflow_run.conclusion }}), skipping Docker build"
+              echo "❌ Build workflow failed (conclusion: $CONCLUSION), skipping Docker build"
               should_build=false
             fi
 
             # Extract version info from commit message or use commit SHA
             # Use Git to generate consistent short SHA (ensures uniqueness like build.yml)
-            short_sha=$(git rev-parse --short "${{ github.event.workflow_run.head_sha }}")
+            short_sha=$(git rev-parse --short "$HEAD_SHA")
 
             # Determine build type based on triggering workflow event and ref
-            triggering_event="${{ github.event.workflow_run.event }}"
-            head_branch="${{ github.event.workflow_run.head_branch }}"
+            triggering_event="$TRIGGERING_EVENT"
+            head_branch="$HEAD_BRANCH"
 
             echo "🔍 Analyzing triggering workflow:"
             echo "   📋 Event: $triggering_event"
             echo "   🌿 Head branch: $head_branch"
-            echo "   📎 Head SHA: ${{ github.event.workflow_run.head_sha }}"
+            echo "   📎 Head SHA: $HEAD_SHA"
 
             # Check if this was triggered by a tag push
             if [[ "$triggering_event" == "push" ]]; then
@@ -158,7 +162,14 @@ jobs:
                 if [[ "$version" == *"alpha"* ]] || [[ "$version" == *"beta"* ]] || [[ "$version" == *"rc"* ]]; then
                   build_type="prerelease"
                   is_prerelease=true
-                  echo "🧪 Building Docker image for prerelease: $version"
+                  # TODO: 临时修改 - 当前允许 alpha 版本也创建 latest 标签
+                  # 等版本稳定后，需要移除下面这行，恢复原有逻辑（只有稳定版本才创建 latest）
+                  if [[ "$version" == *"alpha"* ]]; then
+                    create_latest=true
+                    echo "🧪 Building Docker image for prerelease: $version (临时允许创建 latest 标签)"
+                  else
+                    echo "🧪 Building Docker image for prerelease: $version"
+                  fi
                 else
                   build_type="release"
                   create_latest=true
@@ -174,10 +185,10 @@ jobs:
             fi
 
             echo "🔄 Build triggered by workflow_run:"
-            echo "   📋 Conclusion: ${{ github.event.workflow_run.conclusion }}"
-            echo "   🌿 Branch: ${{ github.event.workflow_run.head_branch }}"
-            echo "   📎 SHA: ${{ github.event.workflow_run.head_sha }}"
-            echo "   🎯 Event: ${{ github.event.workflow_run.event }}"
+            echo "   📋 Conclusion: $CONCLUSION"
+            echo "   🌿 Branch: $HEAD_BRANCH"
+            echo "   📎 SHA: $HEAD_SHA"
+            echo "   🎯 Event: $TRIGGERING_EVENT"
 
           elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
             # Manual trigger
@@ -204,7 +215,14 @@ jobs:
               v*alpha*|v*beta*|v*rc*|*alpha*|*beta*|*rc*)
                 build_type="prerelease"
                 is_prerelease=true
-                echo "🧪 Building with prerelease version: $input_version"
+                # TODO: 临时修改 - 当前允许 alpha 版本也创建 latest 标签
+                # 等版本稳定后，需要移除下面的 if 块，恢复原有逻辑
+                if [[ "$input_version" == *"alpha"* ]]; then
+                  create_latest=true
+                  echo "🧪 Building with prerelease version: $input_version (临时允许创建 latest 标签)"
+                else
+                  echo "🧪 Building with prerelease version: $input_version"
+                fi
                 ;;
               # Release versions (match after prereleases, more general)
               v[0-9]*|[0-9]*.*.*)
@@ -312,7 +330,9 @@ jobs:
 
           # Add channel tags for prereleases and latest for stable
           if [[ "$CREATE_LATEST" == "true" ]]; then
-            # Stable release
+            # TODO: 临时修改 - 当前 alpha 版本也会创建 latest 标签
+            # 等版本稳定后，这里的逻辑保持不变，但上游的 CREATE_LATEST 设置需要恢复
+            # Stable release (以及临时的 alpha 版本)
             TAGS="$TAGS,${{ env.REGISTRY_DOCKERHUB }}:latest"
           elif [[ "$BUILD_TYPE" == "prerelease" ]]; then
             # Prerelease channel tags (alpha, beta, rc)
@@ -409,7 +429,13 @@ jobs:
             "prerelease")
               echo "🧪 Prerelease Docker image has been built with ${VERSION} tags"
               echo "⚠️  This is a prerelease image - use with caution"
-              echo "🚫 Latest tag NOT created for prerelease"
+              # TODO: 临时修改 - alpha 版本当前会创建 latest 标签
+              # 等版本稳定后，需要恢复下面的提示信息
+              if [[ "$VERSION" == *"alpha"* ]] && [[ "$CREATE_LATEST" == "true" ]]; then
+                echo "🏷️  Latest tag has been created for alpha version (临时措施)"
+              else
+                echo "🚫 Latest tag NOT created for prerelease"
+              fi
               ;;
             *)
               echo "❌ Unexpected build type: $BUILD_TYPE"

.github/workflows/helm-package.yml

@@ -0,0 +1,78 @@
+name: Publish helm chart to artifacthub
+
+on:
+  workflow_run:
+    workflows: ["Build and Release"]
+    types: [completed]
+
+env:
+  new_version: ${{ github.event.workflow_run.head_branch }}
+
+jobs:
+  build-helm-package:
+    runs-on: ubuntu-latest
+    # Only run on successful builds triggered by tag pushes (version format: x.y.z or x.y.z-suffix)
+    if: |
+      github.event.workflow_run.conclusion == 'success' && 
+      github.event.workflow_run.event == 'push' &&
+      contains(github.event.workflow_run.head_branch, '.')
+
+    steps:
+      - name: Checkout helm chart repo
+        uses: actions/checkout@v2
+
+      - name: Replace chart appversion
+        run: |
+          set -e
+          set -x
+          old_version=$(grep "^appVersion:" helm/rustfs/Chart.yaml | awk '{print $2}')
+          sed -i "s/$old_version/$new_version/g" helm/rustfs/Chart.yaml
+          sed  -i "/^image:/,/^[^ ]/ s/tag:.*/tag: "$new_version"/" helm/rustfs/values.yaml
+
+      - name: Set up Helm
+        uses: azure/setup-helm@v4.3.0
+
+      - name: Package Helm Chart
+        run: |
+          cp helm/README.md helm/rustfs/
+          package_version=$(echo $new_version | awk -F '-' '{print $2}' | awk -F '.' '{print $NF}') 
+          helm package ./helm/rustfs --destination helm/rustfs/ --version "0.0.$package_version"
+        
+      - name: Upload helm package as artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: helm-package
+          path: helm/rustfs/*.tgz
+          retention-days: 1
+
+  publish-helm-package:
+    runs-on: ubuntu-latest
+    needs: [build-helm-package]
+
+    steps:
+      - name: Checkout helm package repo
+        uses: actions/checkout@v2
+        with:
+          repository: rustfs/helm 
+          token: ${{ secrets.RUSTFS_HELM_PACKAGE }}
+      
+      - name: Download helm package
+        uses: actions/download-artifact@v4
+        with:
+          name: helm-package
+          path: ./
+          
+      - name: Set up helm
+        uses: azure/setup-helm@v4.3.0
+        
+      - name: Generate index
+        run: helm repo index . --url https://charts.rustfs.com
+
+      - name: Push helm package and index file
+        run: |
+          git config --global user.name "${{ secrets.USERNAME }}"
+          git config --global user.email "${{ secrets.EMAIL_ADDRESS }}"
+          git status .
+          git add .
+          git commit -m "Update rustfs helm package with $new_version."
+          git push origin main

.github/workflows/issue-translator.yml

@@ -15,9 +15,13 @@
 name: "issue-translator"
 on:
   issue_comment:
-    types: [created]
+    types: [ created ]
   issues:
-    types: [opened]
+    types: [ opened ]
+
+permissions:
+  contents: read
+  issues: write
 
 jobs:
   build:

.github/workflows/performance.yml

@@ -30,6 +30,9 @@ on:
         default: "120"
         type: string
 
+permissions:
+  contents: read
+
 env:
   CARGO_TERM_COLOR: always
   RUST_BACKTRACE: 1

.gitignore

@@ -20,4 +20,7 @@ profile.json
 .docker/openobserve-otel/data
 *.zst
 .secrets
-*.go
+*.go
+*.pb
+*.svg
+deploy/logs/*.log.*

.vscode/launch.json

@@ -20,18 +20,22 @@
                 }
             },
             "env": {
-                "RUST_LOG": "rustfs=debug,ecstore=info,s3s=debug"
+                "RUST_LOG": "rustfs=debug,ecstore=info,s3s=debug,iam=debug",
+                "RUSTFS_SKIP_BACKGROUND_TASK": "on",
+                //"RUSTFS_OBS_LOG_DIRECTORY": "./deploy/logs",
+                // "RUSTFS_POLICY_PLUGIN_URL":"http://localhost:8181/v1/data/rustfs/authz/allow",
+                // "RUSTFS_POLICY_PLUGIN_AUTH_TOKEN":"your-opa-token" 
             },
             "args": [
                 "--access-key",
-                "AKEXAMPLERUSTFS",
+                "rustfsadmin",
                 "--secret-key",
-                "SKEXAMPLERUSTFS",
+                "rustfsadmin",
                 "--address",
                 "0.0.0.0:9010",
-                "--domain-name",
+                "--server-domains",
                 "127.0.0.1:9010",
-                "./target/volume/test{0...4}"
+                "./target/volume/test{1...4}"
             ],
             "cwd": "${workspaceFolder}"
         },
@@ -82,6 +86,38 @@
             "cwd": "${workspaceFolder}",
             //"stopAtEntry": false,
             //"preLaunchTask": "cargo build",
+            "env": {
+                "RUSTFS_ACCESS_KEY": "rustfsadmin",
+                "RUSTFS_SECRET_KEY": "rustfsadmin",
+                "RUSTFS_VOLUMES": "./target/volume/test{1...4}",
+                "RUSTFS_ADDRESS": ":9000",
+                "RUSTFS_CONSOLE_ENABLE": "true",
+                // "RUSTFS_OBS_TRACE_ENDPOINT": "http://127.0.0.1:4318/v1/traces", // jeager otlp http endpoint
+                // "RUSTFS_OBS_METRIC_ENDPOINT": "http://127.0.0.1:4318/v1/metrics", // default otlp http endpoint
+                // "RUSTFS_OBS_LOG_ENDPOINT": "http://127.0.0.1:4318/v1/logs", // default otlp http endpoint
+                "RUSTFS_CONSOLE_ADDRESS": "127.0.0.1:9001",
+                "RUSTFS_OBS_LOG_DIRECTORY": "./target/logs",
+            },
+            "sourceLanguages": [
+                "rust"
+            ],
+        },
+        {
+            "name": "Debug executable target/debug/test",
+            "type":  "lldb",
+            "request": "launch",
+            "program": "${workspaceFolder}/target/debug/deps/lifecycle_integration_test-5915cbfcab491b3b",
+            "args": [
+              "--skip",
+              "test_lifecycle_expiry_basic",
+              "--skip",
+              "test_lifecycle_expiry_deletemarker",
+              //"--skip",
+              //"test_lifecycle_transition_basic",
+            ],
+            "cwd": "${workspaceFolder}",
+            //"stopAtEntry": false,
+            //"preLaunchTask": "cargo build",
             "sourceLanguages": [
                 "rust"
             ],

AGENTS.md

@@ -0,0 +1,24 @@
+# Repository Guidelines
+
+## Communication Rules
+- Respond to the user in Chinese; use English in all other contexts.
+
+## Project Structure & Module Organization
+The workspace root hosts shared dependencies in `Cargo.toml`. The service binary lives under `rustfs/src/main.rs`, while reusable crates sit in `crates/` (`crypto`, `iam`, `kms`, and `e2e_test`). Local fixtures for standalone flows reside in `test_standalone/`, deployment manifests are under `deploy/`, Docker assets sit at the root, and automation lives in `scripts/`. Skim each crate’s README or module docs before contributing changes.
+
+## Build, Test, and Development Commands
+Run `cargo check --all-targets` for fast validation. Build release binaries via `cargo build --release` or the pipeline-aligned `make build`. Use `./build-rustfs.sh --dev` for iterative development and `./build-rustfs.sh --platform <target>` for cross-compiles. Prefer `make pre-commit` before pushing to cover formatting, clippy, checks, and tests.
+Always ensure `cargo fmt --all --check`, `cargo test --workspace --exclude e2e_test`, and `cargo clippy --all-targets --all-features -- -D warnings` complete successfully after each code change to keep the tree healthy and warning-free.
+
+## Coding Style & Naming Conventions
+Formatting follows the repo `rustfmt.toml` (130-column width). Use `snake_case` for items, `PascalCase` for types, and `SCREAMING_SNAKE_CASE` for constants. Avoid `unwrap()` or `expect()` outside tests; bubble errors with `Result` and crate-specific `thiserror` types. Keep async code non-blocking and offload CPU-heavy work with `tokio::task::spawn_blocking` when necessary.
+
+## Testing Guidelines
+Co-locate unit tests with their modules and give behavior-led names such as `handles_expired_token`. Integration suites belong in each crate’s `tests/` directory, while exhaustive end-to-end scenarios live in `crates/e2e_test/`. Run `cargo test --workspace --exclude e2e_test` during iteration, `cargo nextest run --all --exclude e2e_test` when available, and finish with `cargo test --all` before requesting review. Use `NO_PROXY=127.0.0.1,localhost HTTP_PROXY= HTTPS_PROXY=` for KMS e2e tests.
+When fixing bugs or adding features, include regression tests that capture the new behavior so future changes cannot silently break it.
+
+## Commit & Pull Request Guidelines
+Work on feature branches (e.g., `feat/...`) after syncing `main`. Follow Conventional Commits under 72 characters (e.g., `feat: add kms key rotation`). Each commit must compile, format cleanly, and pass `make pre-commit`. Open PRs with a concise summary, note verification commands, link relevant issues, and wait for reviewer approval.
+
+## Security & Configuration Tips
+Do not commit secrets or cloud credentials; prefer environment variables or vault tooling. Review IAM- and KMS-related changes with a second maintainer. Confirm proxy settings before running sensitive tests to avoid leaking traffic outside localhost.

CLA.md

@@ -1,39 +1,88 @@
 RustFS Individual Contributor License Agreement
 
-Thank you for your interest in contributing documentation and related software code to a project hosted or managed by RustFS. In order to clarify the intellectual property license granted with Contributions from any person or entity, RustFS must have a Contributor License Agreement (“CLA”) on file that has been signed by each Contributor, indicating agreement to the license terms below. This version of the Contributor License Agreement allows an individual to submit Contributions to the applicable project. If you are making a submission on behalf of a legal entity, then you should sign the separate Corporate Contributor License Agreement.
+Thank you for your interest in contributing documentation and related software code to a project hosted or managed by
+RustFS. In order to clarify the intellectual property license granted with Contributions from any person or entity,
+RustFS must have a Contributor License Agreement ("CLA") on file that has been signed by each Contributor, indicating
+agreement to the license terms below. This version of the Contributor License Agreement allows an individual to submit
+Contributions to the applicable project. If you are making a submission on behalf of a legal entity, then you should
+sign the separate Corporate Contributor License Agreement.
 
-You accept and agree to the following terms and conditions for Your present and future Contributions submitted to RustFS. You hereby irrevocably assign and transfer to RustFS all right, title, and interest in and to Your Contributions, including all copyrights and other intellectual property rights therein.
+You accept and agree to the following terms and conditions for Your present and future Contributions submitted to
+RustFS. You hereby irrevocably assign and transfer to RustFS all right, title, and interest in and to Your
+Contributions, including all copyrights and other intellectual property rights therein.
 
 Definitions
 
-“You” (or “Your”) shall mean the copyright owner or legal entity authorized by the copyright owner that is making this Agreement with RustFS. For legal entities, the entity making a Contribution and all other entities that control, are controlled by, or are under common control with that entity are considered to be a single Contributor. For the purposes of this definition, “control” means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
+“You” (or “Your”) shall mean the copyright owner or legal entity authorized by the copyright owner that is making this
+Agreement with RustFS. For legal entities, the entity making a Contribution and all other entities that control, are
+controlled by, or are under common control with that entity are considered to be a single Contributor. For the purposes
+of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such
+entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares,
+or (iii) beneficial ownership of such entity.
 
-“Contribution” shall mean any original work of authorship, including any modifications or additions to an existing work, that is intentionally submitted by You to RustFS for inclusion in, or documentation of, any of the products or projects owned or managed by RustFS (the “Work”), including without limitation any Work described in Schedule A. For the purposes of this definition, “submitted” means any form of electronic or written communication sent to RustFS or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, RustFS for the purpose of discussing and improving the Work.
+“Contribution” shall mean any original work of authorship, including any modifications or additions to an existing work,
+that is intentionally submitted by You to RustFS for inclusion in, or documentation of, any of the products or projects
+owned or managed by RustFS (the "Work"), including without limitation any Work described in Schedule A. For the purposes
+of this definition, "submitted" means any form of electronic or written communication sent to RustFS or its
+representatives, including but not limited to communication on electronic mailing lists, source code control systems,
+and issue tracking systems that are managed by, or on behalf of, RustFS for the purpose of discussing and improving the
+Work.
 
 Assignment of Copyright
 
-Subject to the terms and conditions of this Agreement, You hereby irrevocably assign and transfer to RustFS all right, title, and interest in and to Your Contributions, including all copyrights and other intellectual property rights therein, for the entire term of such rights, including all renewals and extensions. You agree to execute all documents and take all actions as may be reasonably necessary to vest in RustFS the ownership of Your Contributions and to assist RustFS in perfecting, maintaining, and enforcing its rights in Your Contributions.
+Subject to the terms and conditions of this Agreement, You hereby irrevocably assign and transfer to RustFS all right,
+title, and interest in and to Your Contributions, including all copyrights and other intellectual property rights
+therein, for the entire term of such rights, including all renewals and extensions. You agree to execute all documents
+and take all actions as may be reasonably necessary to vest in RustFS the ownership of Your Contributions and to assist
+RustFS in perfecting, maintaining, and enforcing its rights in Your Contributions.
 
 Grant of Patent License
 
-Subject to the terms and conditions of this Agreement, You hereby grant to RustFS and to recipients of documentation and software distributed by RustFS a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by You that are necessarily infringed by Your Contribution(s) alone or by combination of Your Contribution(s) with the Work to which such Contribution(s) was submitted. If any entity institutes patent litigation against You or any other entity (including a cross-claim or counterclaim in a lawsuit) alleging that your Contribution, or the Work to which you have contributed, constitutes direct or contributory patent infringement, then any patent licenses granted to that entity under this Agreement for that Contribution or Work shall terminate as of the date such litigation is filed.
+Subject to the terms and conditions of this Agreement, You hereby grant to RustFS and to recipients of documentation and
+software distributed by RustFS a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as
+stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the
+Work, where such license applies only to those patent claims licensable by You that are necessarily infringed by Your
+Contribution(s) alone or by combination of Your Contribution(s) with the Work to which such Contribution(s) was
+submitted. If any entity institutes patent litigation against You or any other entity (including a cross-claim or
+counterclaim in a lawsuit) alleging that your Contribution, or the Work to which you have contributed, constitutes
+direct or contributory patent infringement, then any patent licenses granted to that entity under this Agreement for
+that Contribution or Work shall terminate as of the date such litigation is filed.
 
 You represent that you are legally entitled to grant the above assignment and license.
 
-You represent that each of Your Contributions is Your original creation (see section 7 for submissions on behalf of others). You represent that Your Contribution submissions include complete details of any third-party license or other restriction (including, but not limited to, related patents and trademarks) of which you are personally aware and which are associated with any part of Your Contributions.
+You represent that each of Your Contributions is Your original creation (see section 7 for submissions on behalf of
+others). You represent that Your Contribution submissions include complete details of any third-party license or other
+restriction (including, but not limited to, related patents and trademarks) of which you are personally aware and which
+are associated with any part of Your Contributions.
 
-You are not expected to provide support for Your Contributions, except to the extent You desire to provide support. You may provide support for free, for a fee, or not at all. Unless required by applicable law or agreed to in writing, You provide Your Contributions on an “AS IS” BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON- INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE.
+You are not expected to provide support for Your Contributions, except to the extent You desire to provide support. You
+may provide support for free, for a fee, or not at all. Unless required by applicable law or agreed to in writing, You
+provide Your Contributions on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied,
+including, without limitation, any warranties or conditions of TITLE, NON- INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR
+A PARTICULAR PURPOSE.
 
-Should You wish to submit work that is not Your original creation, You may submit it to RustFS separately from any Contribution, identifying the complete details of its source and of any license or other restriction (including, but not limited to, related patents, trademarks, and license agreements) of which you are personally aware, and conspicuously marking the work as “Submitted on behalf of a third-party: [named here]”.
+Should You wish to submit work that is not Your original creation, You may submit it to RustFS separately from any
+Contribution, identifying the complete details of its source and of any license or other restriction (including, but not
+limited to, related patents, trademarks, and license agreements) of which you are personally aware, and conspicuously
+marking the work as "Submitted on behalf of a third-party: [named here]”.
 
-You agree to notify RustFS of any facts or circumstances of which you become aware that would make these representations inaccurate in any respect.
+You agree to notify RustFS of any facts or circumstances of which you become aware that would make these representations
+inaccurate in any respect.
 
 Modification of CLA
 
-RustFS reserves the right to update or modify this CLA in the future. Any updates or modifications to this CLA shall apply only to Contributions made after the effective date of the revised CLA. Contributions made prior to the update shall remain governed by the version of the CLA that was in effect at the time of submission. It is not necessary for all Contributors to re-sign the CLA when the CLA is updated or modified.
+RustFS reserves the right to update or modify this CLA in the future. Any updates or modifications to this CLA shall
+apply only to Contributions made after the effective date of the revised CLA. Contributions made prior to the update
+shall remain governed by the version of the CLA that was in effect at the time of submission. It is not necessary for
+all Contributors to re-sign the CLA when the CLA is updated or modified.
 
 Governing Law and Dispute Resolution
 
-This Agreement will be governed by and construed in accordance with the laws of the People’s Republic of China excluding that body of laws known as conflict of laws. The parties expressly agree that the United Nations Convention on Contracts for the International Sale of Goods will not apply. Any legal action or proceeding arising under this Agreement will be brought exclusively in the courts located in Beijing, China, and the parties hereby irrevocably consent to the personal jurisdiction and venue therein.
+This Agreement will be governed by and construed in accordance with the laws of the People's Republic of China excluding
+that body of laws known as conflict of laws. The parties expressly agree that the United Nations Convention on Contracts
+for the International Sale of Goods will not apply. Any legal action or proceeding arising under this Agreement will be
+brought exclusively in the courts located in Beijing, China, and the parties hereby irrevocably consent to the personal
+jurisdiction and venue therein.
 
-For your reading convenience, this Agreement is written in parallel English and Chinese sections. To the extent there is a conflict between the English and Chinese sections, the English sections shall govern.
+For your reading convenience, this Agreement is written in parallel English and Chinese sections. To the extent there is
+a conflict between the English and Chinese sections, the English sections shall govern.

CLAUDE.md

@@ -1,68 +1,275 @@
-# Claude AI Rules for RustFS Project
+# CLAUDE.md
 
-## Core Rules Reference
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
 
-This project follows the comprehensive AI coding rules defined in `.rules.md`. Please refer to that file for the complete set of development guidelines, coding standards, and best practices.
+## Project Overview
 
-## Claude-Specific Configuration
+RustFS is a high-performance distributed object storage software built with Rust, providing S3-compatible APIs and
+advanced features like data lakes, AI, and big data support. It's designed as an alternative to MinIO with better
+performance and a more business-friendly Apache 2.0 license.
 
-When using Claude for this project, ensure you:
+## Build Commands
 
-1. **Review the unified rules**: Always check `.rules.md` for the latest project guidelines
-2. **Follow branch protection**: Never attempt to commit directly to main/master branch
-3. **Use English**: All code comments, documentation, and variable names must be in English
-4. **Clean code practices**: Only make modifications you're confident about
-5. **Test thoroughly**: Ensure all changes pass formatting, linting, and testing requirements
-6. **Clean up after yourself**: Remove any temporary scripts or test files created during the session
+### Primary Build Commands
 
-## Quick Reference
+- `cargo build --release` - Build the main RustFS binary
+- `./build-rustfs.sh` - Recommended build script that handles console resources and cross-platform compilation
+- `./build-rustfs.sh --dev` - Development build with debug symbols
+- `make build` or `just build` - Use Make/Just for standardized builds
 
-### Critical Rules
-- 🚫 **NEVER commit directly to main/master branch**
-- ✅ **ALWAYS work on feature branches**
-- 📝 **ALWAYS use English for code and documentation**
-- 🧹 **ALWAYS clean up temporary files after use**
-- 🎯 **ONLY make confident, necessary modifications**
+### Platform-Specific Builds
 
-### Pre-commit Checklist
-```bash
-# Before committing, always run:
-cargo fmt --all
-cargo clippy --all-targets --all-features -- -D warnings
-cargo check --all-targets
-cargo test
-```
+- `./build-rustfs.sh --platform x86_64-unknown-linux-musl` - Build for musl target
+- `./build-rustfs.sh --platform aarch64-unknown-linux-gnu` - Build for ARM64
+- `make build-musl` or `just build-musl` - Build musl variant
+- `make build-cross-all` - Build all supported architectures
 
-### Branch Workflow
-```bash
-git checkout main
-git pull origin main
-git checkout -b feat/your-feature-name
-# Make your changes
-git add .
-git commit -m "feat: your feature description"
-git push origin feat/your-feature-name
-gh pr create
-```
+### Testing Commands
 
-## Claude-Specific Best Practices
+- `cargo test --workspace --exclude e2e_test` - Run unit tests (excluding e2e tests)
+- `cargo nextest run --all --exclude e2e_test` - Use nextest if available (faster)
+- `cargo test --all --doc` - Run documentation tests
+- `make test` or `just test` - Run full test suite
+- `make pre-commit` - Run all quality checks (fmt, clippy, check, test)
 
-1. **Task Analysis**: Always thoroughly analyze the task before starting implementation
-2. **Minimal Changes**: Make only the necessary changes to accomplish the task
-3. **Clear Communication**: Provide clear explanations of changes and their rationale
-4. **Error Prevention**: Verify code correctness before suggesting changes
-5. **Documentation**: Ensure all code changes are properly documented in English
+### End-to-End Testing
 
-## Important Notes
+- `cargo test --package e2e_test` - Run all e2e tests
+- `./scripts/run_e2e_tests.sh` - Run e2e tests via script
+- `./scripts/run_scanner_benchmarks.sh` - Run scanner performance benchmarks
 
-- This file serves as an entry point for Claude AI
-- All detailed rules and guidelines are maintained in `.rules.md`
-- Updates to coding standards should be made in `.rules.md` to ensure consistency across all AI tools
-- When in doubt, always refer to `.rules.md` for authoritative guidance
-- Claude should prioritize code quality, safety, and maintainability over speed
+### KMS-Specific Testing (with proxy bypass)
 
-## See Also
+-
+`NO_PROXY=127.0.0.1,localhost HTTP_PROXY= HTTPS_PROXY= http_proxy= https_proxy= cargo test --package e2e_test test_local_kms_end_to_end -- --nocapture --test-threads=1` -
+Run complete KMS end-to-end test
+-
+`NO_PROXY=127.0.0.1,localhost HTTP_PROXY= HTTPS_PROXY= http_proxy= https_proxy= cargo test --package e2e_test kms:: -- --nocapture --test-threads=1` -
+Run all KMS tests
+- `cargo test --package e2e_test test_local_kms_key_isolation -- --nocapture --test-threads=1` - Test KMS key isolation
+- `cargo test --package e2e_test test_local_kms_large_file -- --nocapture --test-threads=1` - Test KMS with large files
 
-- [.rules.md](./.rules.md) - Complete AI coding rules and guidelines
-- [CONTRIBUTING.md](./CONTRIBUTING.md) - Contribution guidelines
-- [README.md](./README.md) - Project overview and setup instructions
+### Code Quality
+
+- `cargo fmt --all` - Format code
+- `cargo clippy --all-targets --all-features -- -D warnings` - Lint code
+- `make pre-commit` or `just pre-commit` - Run all quality checks (fmt, clippy, check, test)
+
+### Quick Development Commands
+
+- `make help` or `just help` - Show all available commands with descriptions
+- `make help-build` - Show detailed build options and cross-compilation help
+- `make help-docker` - Show comprehensive Docker build and deployment options
+- `./scripts/dev_deploy.sh <IP>` - Deploy development build to remote server
+- `./scripts/run.sh` - Start local development server
+- `./scripts/probe.sh` - Health check and connectivity testing
+
+### Docker Build Commands
+
+- `make docker-buildx` - Build multi-architecture production images
+- `make docker-dev-local` - Build development image for local use
+- `./docker-buildx.sh --push` - Build and push production images
+
+## Architecture Overview
+
+### Core Components
+
+**Main Binary (`rustfs/`):**
+
+- Entry point at `rustfs/src/main.rs`
+- Core modules: admin, auth, config, server, storage, license management, profiling
+- HTTP server with S3-compatible APIs
+- Service state management and graceful shutdown
+- Parallel service initialization with DNS resolver, bucket metadata, and IAM
+
+**Key Crates (`crates/`):**
+
+- `ecstore` - Erasure coding storage implementation (core storage layer)
+- `iam` - Identity and Access Management
+- `kms` - Key Management Service for encryption and key handling
+- `madmin` - Management dashboard and admin API interface
+- `s3select-api` & `s3select-query` - S3 Select API and query engine
+- `config` - Configuration management with notify features
+- `crypto` - Cryptography and security features
+- `lock` - Distributed locking implementation
+- `filemeta` - File metadata management
+- `rio` - Rust I/O utilities and abstractions
+- `common` - Shared utilities and data structures
+- `protos` - Protocol buffer definitions
+- `audit-logger` - Audit logging for file operations
+- `notify` - Event notification system
+- `obs` - Observability utilities
+- `workers` - Worker thread pools and task scheduling
+- `appauth` - Application authentication and authorization
+- `ahm` - Asynchronous Hash Map for concurrent data structures
+- `mcp` - MCP server for S3 operations
+- `signer` - Client request signing utilities
+- `checksums` - Client checksum calculation utilities
+- `utils` - General utility functions and helpers
+- `zip` - ZIP file handling and compression
+- `targets` - Target-specific configurations and utilities
+
+### Build System
+
+- Cargo workspace with 25+ crates (including new KMS functionality)
+- Custom `build-rustfs.sh` script for advanced build options
+- Multi-architecture Docker builds via `docker-buildx.sh`
+- Both Make and Just task runners supported with comprehensive help
+- Cross-compilation support for multiple Linux targets
+- Automated CI/CD with GitHub Actions for testing, building, and Docker publishing
+- Performance benchmarking and audit workflows
+
+### Key Dependencies
+
+- `axum` - HTTP framework for S3 API server
+- `tokio` - Async runtime
+- `s3s` - S3 protocol implementation library
+- `datafusion` - For S3 Select query processing
+- `hyper`/`hyper-util` - HTTP client/server utilities
+- `rustls` - TLS implementation
+- `serde`/`serde_json` - Serialization
+- `tracing` - Structured logging and observability
+- `pprof` - Performance profiling with flamegraph support
+- `tikv-jemallocator` - Memory allocator for Linux GNU builds
+
+### Development Workflow
+
+- Console resources are embedded during build via `rust-embed`
+- Protocol buffers generated via custom `gproto` binary
+- E2E tests in separate crate (`e2e_test`) with comprehensive KMS testing
+- Shadow build for version/metadata embedding
+- Support for both GNU and musl libc targets
+- Development scripts in `scripts/` directory for common tasks
+- Git hooks setup available via `make setup-hooks` or `just setup-hooks`
+
+### Performance & Observability
+
+- Performance profiling available with `pprof` integration (disabled on Windows)
+- Profiling enabled via environment variables in production
+- Built-in observability with OpenTelemetry integration
+- Background services (scanner, heal) can be controlled via environment variables:
+    - `RUSTFS_ENABLE_SCANNER` (default: true)
+    - `RUSTFS_ENABLE_HEAL` (default: true)
+
+### Service Architecture
+
+- Service state management with graceful shutdown handling
+- Parallel initialization of core systems (DNS, bucket metadata, IAM)
+- Event notification system with MQTT and webhook support
+- Auto-heal and data scanner for storage integrity
+- Jemalloc allocator for Linux GNU targets for better performance
+
+## Environment Variables
+
+- `RUSTFS_ENABLE_SCANNER` - Enable/disable background data scanner (default: true)
+- `RUSTFS_ENABLE_HEAL` - Enable/disable auto-heal functionality (default: true)
+- Various profiling and observability controls
+- Build-time variables for Docker builds (RELEASE, REGISTRY, etc.)
+- Test environment configurations in `scripts/dev_rustfs.env`
+
+### KMS Environment Variables
+
+- `NO_PROXY=127.0.0.1,localhost` - Required for KMS E2E tests to bypass proxy
+- `HTTP_PROXY=` `HTTPS_PROXY=` `http_proxy=` `https_proxy=` - Clear proxy settings for local KMS testing
+
+## KMS (Key Management Service) Architecture
+
+### KMS Implementation Status
+
+- **Full KMS Integration:** Complete implementation with Local and Vault backends
+- **Automatic Configuration:** KMS auto-configures on startup with `--kms-enable` flag
+- **Encryption Support:** Full S3-compatible server-side encryption (SSE-S3, SSE-KMS, SSE-C)
+- **Admin API:** Complete KMS management via HTTP admin endpoints
+- **Production Ready:** Comprehensive testing including large files and key isolation
+
+### KMS Configuration
+
+- **Local Backend:** `--kms-backend local --kms-key-dir <path> --kms-default-key-id <id>`
+- **Vault Backend:** `--kms-backend vault --kms-vault-endpoint <url> --kms-vault-key-name <name>`
+- **Auto-startup:** KMS automatically initializes when `--kms-enable` is provided
+- **Manual Configuration:** Also supports dynamic configuration via admin API
+
+### S3 Encryption Support
+
+- **SSE-S3:** Server-side encryption with S3-managed keys (`ServerSideEncryption: AES256`)
+- **SSE-KMS:** Server-side encryption with KMS-managed keys (`ServerSideEncryption: aws:kms`)
+- **SSE-C:** Server-side encryption with customer-provided keys
+- **Response Headers:** All encryption types return correct `server_side_encryption` headers in PUT/GET responses
+
+### KMS Testing Architecture
+
+- **Comprehensive E2E Tests:** Located in `crates/e2e_test/src/kms/`
+- **Test Environments:** Automated test environment setup with temporary directories
+- **Encryption Coverage:** Tests all three encryption types (SSE-S3, SSE-KMS, SSE-C)
+- **API Coverage:** Tests all KMS admin APIs (CreateKey, DescribeKey, ListKeys, etc.)
+- **Edge Cases:** Key isolation, large file handling, error scenarios
+
+### Key Files for KMS
+
+- `crates/kms/` - Core KMS implementation with Local/Vault backends
+- `rustfs/src/main.rs` - KMS auto-initialization in `init_kms_system()`
+- `rustfs/src/storage/ecfs.rs` - SSE encryption/decryption in PUT/GET operations
+- `rustfs/src/admin/handlers/kms*.rs` - KMS admin endpoints
+- `crates/e2e_test/src/kms/` - Comprehensive KMS test suite
+- `crates/rio/src/encrypt_reader.rs` - Streaming encryption for large files
+
+## Code Style and Safety Requirements
+
+- **Language Requirements:**
+    - Communicate with me in Chinese, but **only English can be used in code files**
+    - Code comments, function names, variable names, and all text in source files must be in English only
+    - No Chinese characters, emojis, or non-ASCII characters are allowed in any source code files
+    - This includes comments, strings, documentation, and any other text within code files
+- **Safety-Critical Rules:**
+    - `unsafe_code = "deny"` enforced at workspace level
+    - Never use `unwrap()`, `expect()`, or panic-inducing code except in tests
+    - Avoid blocking I/O operations in async contexts
+    - Use proper error handling with `Result<T, E>` and `Option<T>`
+    - Follow Rust's ownership and borrowing rules strictly
+- **Performance Guidelines:**
+    - Use `cargo clippy --all-targets --all-features -- -D warnings` to catch issues
+    - Prefer `anyhow` for error handling in applications, `thiserror` for libraries
+    - Use appropriate async runtimes and avoid blocking calls
+- **Testing Standards:**
+    - All new features must include comprehensive tests
+    - Use `#[cfg(test)]` for test-only code that may use panic macros
+    - E2E tests should cover KMS integration scenarios
+
+## Common Development Tasks
+
+### Running KMS Tests Locally
+
+1. **Clear proxy settings:** KMS tests require direct localhost connections
+2. **Use serial execution:** `--test-threads=1` prevents port conflicts
+3. **Enable output:** `--nocapture` shows detailed test logs
+4. **Full command:**
+   `NO_PROXY=127.0.0.1,localhost HTTP_PROXY= HTTPS_PROXY= http_proxy= https_proxy= cargo test --package e2e_test test_local_kms_end_to_end -- --nocapture --test-threads=1`
+
+### KMS Development Workflow
+
+1. **Code changes:** Modify KMS-related code in `crates/kms/` or `rustfs/src/`
+2. **Compile:** Always run `cargo build` after changes
+3. **Test specific functionality:** Use targeted test commands for faster iteration
+4. **Full validation:** Run complete end-to-end tests before commits
+
+### Debugging KMS Issues
+
+- **Server startup:** Check that KMS auto-initializes with debug logs
+- **Encryption failures:** Verify SSE headers are correctly set in both PUT and GET responses
+- **Test failures:** Use `--nocapture` to see detailed error messages
+- **Key management:** Test admin API endpoints with proper authentication
+
+## Important Reminders
+
+- **Always compile after code changes:** Use `cargo build` to catch errors early
+- **Don't bypass tests:** All functionality must be properly tested, not worked around
+- **Use proper error handling:** Never use `unwrap()` or `expect()` in production code (except tests)
+- **Follow S3 compatibility:** Ensure all encryption types return correct HTTP response headers
+
+# important-instruction-reminders
+
+Do what has been asked; nothing more, nothing less.
+NEVER create files unless they're absolutely necessary for achieving your goal.
+ALWAYS prefer editing an existing file to creating a new one.
+NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly
+requested by the User.

Cargo.toml

@@ -15,8 +15,8 @@
 [workspace]
 members = [
     "rustfs", # Core file system implementation
-    "cli/rustfs-gui", # Graphical user interface client
     "crates/appauth", # Application authentication and authorization
+    "crates/audit", # Audit target management system with multi-target fan-out
     "crates/common", # Shared utilities and data structures
     "crates/config", # Configuration management
     "crates/crypto", # Cryptography and security features
@@ -28,8 +28,10 @@ members = [
     "crates/madmin", # Management dashboard and admin API interface
     "crates/notify", # Notification system for events
     "crates/obs", # Observability utilities
+    "crates/policy", # Policy management
     "crates/protos", # Protocol buffer definitions
     "crates/rio", # Rust I/O utilities and abstractions
+    "crates/targets", # Target-specific configurations and utilities
     "crates/s3select-api", # S3 Select API interface
     "crates/s3select-query", # S3 Select query engine
     "crates/signer", # client signer
@@ -37,8 +39,9 @@ members = [
     "crates/utils", # Utility functions and helpers
     "crates/workers", # Worker thread pools and task scheduling
     "crates/zip", # ZIP file handling and compression
-    "crates/ahm",
+    "crates/ahm", # Asynchronous Hash Map for concurrent data structures
     "crates/mcp", # MCP server for S3 operations
+    "crates/kms", # Key Management Service
 ]
 resolver = "2"
 
@@ -59,236 +62,222 @@ unsafe_code = "deny"
 [workspace.lints.clippy]
 all = "warn"
 
-[patch.crates-io]
-rustfs-utils = { path = "crates/utils" }
-rustfs-filemeta = { path = "crates/filemeta" }
-rustfs-rio = { path = "crates/rio" }
-
 [workspace.dependencies]
+# RustFS Internal Crates
+rustfs = { path = "./rustfs", version = "0.0.5" }
 rustfs-ahm = { path = "crates/ahm", version = "0.0.5" }
-rustfs-s3select-api = { path = "crates/s3select-api", version = "0.0.5" }
 rustfs-appauth = { path = "crates/appauth", version = "0.0.5" }
+rustfs-audit = { path = "crates/audit", version = "0.0.5" }
+rustfs-checksums = { path = "crates/checksums", version = "0.0.5" }
 rustfs-common = { path = "crates/common", version = "0.0.5" }
+rustfs-config = { path = "./crates/config", version = "0.0.5" }
 rustfs-crypto = { path = "crates/crypto", version = "0.0.5" }
 rustfs-ecstore = { path = "crates/ecstore", version = "0.0.5" }
+rustfs-filemeta = { path = "crates/filemeta", version = "0.0.5" }
 rustfs-iam = { path = "crates/iam", version = "0.0.5" }
+rustfs-kms = { path = "crates/kms", version = "0.0.5" }
 rustfs-lock = { path = "crates/lock", version = "0.0.5" }
 rustfs-madmin = { path = "crates/madmin", version = "0.0.5" }
+rustfs-mcp = { path = "crates/mcp", version = "0.0.5" }
+rustfs-notify = { path = "crates/notify", version = "0.0.5" }
+rustfs-obs = { path = "crates/obs", version = "0.0.5" }
 rustfs-policy = { path = "crates/policy", version = "0.0.5" }
 rustfs-protos = { path = "crates/protos", version = "0.0.5" }
-rustfs-s3select-query = { path = "crates/s3select-query", version = "0.0.5" }
-rustfs = { path = "./rustfs", version = "0.0.5" }
-rustfs-zip = { path = "./crates/zip", version = "0.0.5" }
-rustfs-config = { path = "./crates/config", version = "0.0.5" }
-rustfs-obs = { path = "crates/obs", version = "0.0.5" }
-rustfs-notify = { path = "crates/notify", version = "0.0.5" }
-rustfs-utils = { path = "crates/utils", version = "0.0.5" }
 rustfs-rio = { path = "crates/rio", version = "0.0.5" }
-rustfs-filemeta = { path = "crates/filemeta", version = "0.0.5" }
+rustfs-s3select-api = { path = "crates/s3select-api", version = "0.0.5" }
+rustfs-s3select-query = { path = "crates/s3select-query", version = "0.0.5" }
 rustfs-signer = { path = "crates/signer", version = "0.0.5" }
-rustfs-checksums = { path = "crates/checksums", version = "0.0.5" }
+rustfs-targets = { path = "crates/targets", version = "0.0.5" }
+rustfs-utils = { path = "crates/utils", version = "0.0.5" }
 rustfs-workers = { path = "crates/workers", version = "0.0.5" }
-rustfs-mcp = { path = "crates/mcp", version = "0.0.5" }
-aes-gcm = { version = "0.10.3", features = ["std"] }
-anyhow = "1.0.99"
-arc-swap = "1.7.1"
-argon2 = { version = "0.5.3", features = ["std"] }
-atoi = "2.0.0"
+rustfs-zip = { path = "./crates/zip", version = "0.0.5" }
+
+# Async Runtime and Networking
 async-channel = "2.5.0"
-async-recursion = "1.1.1"
-async-trait = "0.1.88"
 async-compression = { version = "0.4.19" }
-atomic_enum = "0.3.0"
-aws-config = { version = "1.8.4" }
-aws-sdk-s3 = "1.101.0"
-axum = "0.8.4"
-base64-simd = "0.8.0"
-base64 = "0.22.1"
-brotli = "8.0.1"
-bytes = { version = "1.10.1", features = ["serde"] }
-bytesize = "2.0.1"
-byteorder = "1.5.0"
-cfg-if = "1.0.1"
-crc-fast = "1.4.0"
-chacha20poly1305 = { version = "0.10.1" }
-chrono = { version = "0.4.41", features = ["serde"] }
-clap = { version = "4.5.44", features = ["derive", "env"] }
-const-str = { version = "0.6.4", features = ["std", "proc"] }
-crc32fast = "1.5.0"
-criterion = { version = "0.7", features = ["html_reports"] }
-dashmap = "6.1.0"
-datafusion = "46.0.1"
-derive_builder = "0.20.2"
-dioxus = { version = "0.6.3", features = ["router"] }
-dirs = "6.0.0"
-enumset = "1.1.7"
-flatbuffers = "25.2.10"
-flate2 = "1.1.2"
-flexi_logger = { version = "0.31.2", features = ["trc", "dont_minimize_extra_stacks"] }
-form_urlencoded = "1.2.1"
+async-recursion = "1.1.1"
+async-trait = "0.1.89"
+axum = "0.8.7"
+axum-extra = "0.12.2"
+axum-server = { version = "0.8.0", features = ["tls-rustls-no-provider"], default-features = false }
 futures = "0.3.31"
 futures-core = "0.3.31"
 futures-util = "0.3.31"
+hyper = { version = "1.8.1", features = ["http2", "http1", "server"] }
+hyper-rustls = { version = "0.27.7", default-features = false, features = ["native-tokio", "http1", "tls12", "logging", "http2", "ring", "webpki-roots"] }
+hyper-util = { version = "0.1.19", features = ["tokio", "server-auto", "server-graceful"] }
+http = "1.4.0"
+http-body = "1.0.1"
+reqwest = { version = "0.12.25", default-features = false, features = ["rustls-tls-webpki-roots", "charset", "http2", "system-proxy", "stream", "json", "blocking"] }
+socket2 = "0.6.1"
+tokio = { version = "1.48.0", features = ["fs", "rt-multi-thread"] }
+tokio-rustls = { version = "0.26.4", default-features = false, features = ["logging", "tls12", "ring"] }
+tokio-stream = { version = "0.1.17" }
+tokio-test = "0.4.4"
+tokio-util = { version = "0.7.17", features = ["io", "compat"] }
+tonic = { version = "0.14.2", features = ["gzip"] }
+tonic-prost = { version = "0.14.2" }
+tonic-prost-build = { version = "0.14.2" }
+tower = { version = "0.5.2", features = ["timeout"] }
+tower-http = { version = "0.6.8", features = ["cors"] }
+
+# Serialization and Data Formats
+bytes = { version = "1.11.0", features = ["serde"] }
+bytesize = "2.3.1"
+byteorder = "1.5.0"
+flatbuffers = "25.9.23"
+form_urlencoded = "1.2.2"
+prost = "0.14.1"
+quick-xml = "0.38.4"
+rmcp = { version = "0.10.0" }
+rmp = { version = "0.8.14" }
+rmp-serde = { version = "1.3.0" }
+serde = { version = "1.0.228", features = ["derive"] }
+serde_json = { version = "1.0.145", features = ["raw_value"] }
+serde_urlencoded = "0.7.1"
+schemars = "1.1.0"
+
+# Cryptography and Security
+aes-gcm = { version = "0.11.0-rc.2", features = ["rand_core"] }
+argon2 = { version = "0.6.0-rc.3", features = ["std"] }
+blake3 = { version = "1.8.2", features = ["rayon", "mmap"] }
+chacha20poly1305 = { version = "0.11.0-rc.2" }
+crc-fast = "1.6.0"
+hmac = { version = "0.13.0-rc.3" }
+jsonwebtoken = { version = "10.2.0", features = ["rust_crypto"] }
+pbkdf2 = "0.13.0-rc.3"
+rsa = { version = "0.10.0-rc.10" }
+rustls = { version = "0.23.35", features = ["ring", "logging", "std", "tls12"], default-features = false }
+rustls-pemfile = "2.2.0"
+rustls-pki-types = "1.13.1"
+sha1 = "0.11.0-rc.3"
+sha2 = "0.11.0-rc.3"
+subtle = "2.6"
+zeroize = { version = "1.8.2", features = ["derive"] }
+
+# Time and Date
+chrono = { version = "0.4.42", features = ["serde"] }
+humantime = "2.3.0"
+time = { version = "0.3.44", features = ["std", "parsing", "formatting", "macros", "serde"] }
+
+# Utilities and Tools
+anyhow = "1.0.100"
+arc-swap = "1.7.1"
+astral-tokio-tar = "0.5.6"
+atoi = "2.0.0"
+atomic_enum = "0.3.0"
+aws-config = { version = "1.8.11" }
+aws-credential-types = { version = "1.2.10" }
+aws-sdk-s3 = { version = "1.116.0", default-features = false, features = ["sigv4a", "rustls", "rt-tokio"] }
+aws-smithy-types = { version = "1.3.4" }
+base64 = "0.22.1"
+base64-simd = "0.8.0"
+brotli = "8.0.2"
+cfg-if = "1.0.4"
+clap = { version = "4.5.53", features = ["derive", "env"] }
+const-str = { version = "0.7.0", features = ["std", "proc"] }
+convert_case = "0.10.0"
+criterion = { version = "0.8", features = ["html_reports"] }
+crossbeam-queue = "0.3.12"
+datafusion = "51.0.0"
+derive_builder = "0.20.2"
+enumset = "1.1.10"
+faster-hex = "0.10.0"
+flate2 = "1.1.5"
+flexi_logger = { version = "0.31.7", features = ["trc", "dont_minimize_extra_stacks", "compress", "kv", "json"] }
 glob = "0.3.3"
-hex = "0.4.3"
+google-cloud-storage = "1.4.0"
+google-cloud-auth = "1.2.0"
+hashbrown = { version = "0.16.1", features = ["serde", "rayon"] }
+heed = { version = "0.22.0" }
 hex-simd = "0.8.0"
 highway = { version = "1.3.0" }
-hmac = "0.12.1"
-hyper = "1.6.0"
-hyper-util = { version = "0.1.16", features = [
-    "tokio",
-    "server-auto",
-    "server-graceful",
-] }
-hyper-rustls = "0.27.7"
-http = "1.3.1"
-http-body = "1.0.1"
-humantime = "2.2.0"
 ipnetwork = { version = "0.21.1", features = ["serde"] }
-jsonwebtoken = "9.3.1"
-keyring = { version = "3.6.3", features = [
-    "apple-native",
-    "windows-native",
-    "sync-secret-service",
-] }
 lazy_static = "1.5.0"
-libsystemd = { version = "0.7.2" }
-local-ip-address = "0.6.5"
+libc = "0.2.178"
+libsystemd = "0.7.2"
+local-ip-address = "0.6.6"
 lz4 = "1.28.1"
-matchit = "0.8.4"
-md-5 = "0.10.6"
+matchit = "0.9.0"
+md-5 = "0.11.0-rc.3"
+md5 = "0.8.0"
 mime_guess = "2.0.5"
+moka = { version = "0.12.11", features = ["future"] }
 netif = "0.1.6"
 nix = { version = "0.30.1", features = ["fs"] }
-nu-ansi-term = "0.50.1"
+nu-ansi-term = "0.50.3"
 num_cpus = { version = "1.17.0" }
 nvml-wrapper = "0.11.0"
-object_store = "0.11.2"
-once_cell = "1.21.3"
-opentelemetry = { version = "0.30.0" }
-opentelemetry-appender-tracing = { version = "0.30.1", features = [
-    "experimental_use_tracing_span_context",
-    "experimental_metadata_attributes",
-    "spec_unstable_logs_enabled"
-] }
-opentelemetry_sdk = { version = "0.30.0" }
-opentelemetry-stdout = { version = "0.30.0" }
-opentelemetry-otlp = { version = "0.30.0", default-features = false, features = [
-    "grpc-tonic", "gzip-tonic", "trace", "metrics", "logs", "internal-logs"
-] }
-opentelemetry-semantic-conventions = { version = "0.30.0", features = [
-    "semconv_experimental",
-] }
-parking_lot = "0.12.4"
+object_store = "0.12.4"
+parking_lot = "0.12.5"
 path-absolutize = "3.1.1"
 path-clean = "1.0.1"
-blake3 = { version = "1.8.2" }
-pbkdf2 = "0.12.2"
-percent-encoding = "2.3.1"
 pin-project-lite = "0.2.16"
-prost = "0.14.1"
 pretty_assertions = "1.4.1"
-quick-xml = "0.38.1"
-rand = "0.9.2"
-rdkafka = { version = "0.38.0", features = ["tokio"] }
-reed-solomon-simd = { version = "3.0.1" }
-regex = { version = "1.11.1" }
-reqwest = { version = "0.12.22", default-features = false, features = [
-    "rustls-tls",
-    "charset",
-    "http2",
-    "system-proxy",
-    "stream",
-    "json",
-    "blocking",
-] }
-rfd = { version = "0.15.4", default-features = false, features = [
-    "xdg-portal",
-    "tokio",
-] }
-rmcp = { version = "0.5.0" }
-rmp = "0.8.14"
-rmp-serde = "1.3.0"
-rsa = "0.9.8"
-rumqttc = { version = "0.24" }
-rust-embed = { version = "8.7.2" }
-rust-i18n = { version = "3.1.5" }
-rustfs-rsc = "2025.506.1"
-rustls = { version = "0.23.31" }
-rustls-pki-types = "1.12.0"
-rustls-pemfile = "2.2.0"
-s3s = { version = "0.12.0-minio-preview.3" }
-schemars = "1.0.4"
-serde = { version = "1.0.219", features = ["derive"] }
-serde_json = { version = "1.0.142", features = ["raw_value"] }
-serde_urlencoded = "0.7.1"
+rand = { version = "0.10.0-rc.5", features = ["serde"] }
+rayon = "1.11.0"
+reed-solomon-simd = { version = "3.1.0" }
+regex = { version = "1.12.2" }
+rumqttc = { version = "0.25.1" }
+rust-embed = { version = "8.9.0" }
+rustc-hash = { version = "2.1.1" }
+s3s = { version = "0.12.0-rc.4", features = ["minio"] }
 serial_test = "3.2.0"
-sha1 = "0.10.6"
-sha2 = "0.10.9"
-shadow-rs = { version = "1.2.1", default-features = false }
+shadow-rs = { version = "1.4.0", default-features = false }
 siphasher = "1.0.1"
 smallvec = { version = "1.15.1", features = ["serde"] }
-snafu = "0.8.6"
+smartstring = "1.0.1"
+snafu = "0.8.9"
 snap = "1.1.1"
-socket2 = "0.6.0"
+starshard = { version = "0.6.0", features = ["rayon", "async", "serde"] }
 strum = { version = "0.27.2", features = ["derive"] }
-sysinfo = "0.37.0"
-sysctl = "0.6.0"
-tempfile = "3.20.0"
+sysctl = "0.7.1"
+sysinfo = "0.37.2"
 temp-env = "0.3.6"
+tempfile = "3.23.0"
 test-case = "3.3.1"
-thiserror = "2.0.14"
-time = { version = "0.3.41", features = [
-    "std",
-    "parsing",
-    "formatting",
-    "macros",
-    "serde",
-] }
-tokio = { version = "1.47.1", features = ["fs", "rt-multi-thread"] }
-tokio-rustls = { version = "0.26.2", default-features = false }
-tokio-stream = { version = "0.1.17" }
-tokio-tar = "0.3.1"
-tokio-test = "0.4.4"
-tokio-util = { version = "0.7.16", features = ["io", "compat"] }
-tonic = { version = "0.14.1", features = ["gzip"] }
-tonic-prost = { version = "0.14.1" }
-tonic-prost-build = { version = "0.14.1" }
-tower = { version = "0.5.2", features = ["timeout"] }
-tower-http = { version = "0.6.6", features = ["cors"] }
-tracing = "0.1.41"
-tracing-appender = "0.2.3"
-tracing-core = "0.1.34"
+thiserror = "2.0.17"
+tracing = { version = "0.1.43" }
+tracing-appender = "0.2.4"
 tracing-error = "0.2.1"
-tracing-opentelemetry = "0.31.0"
-tracing-subscriber = { version = "0.3.19", features = ["env-filter", "time"] }
+tracing-opentelemetry = "0.32.0"
+tracing-subscriber = { version = "0.3.22", features = ["env-filter", "time"] }
 transform-stream = "0.3.1"
-url = "2.5.4"
+url = "2.5.7"
 urlencoding = "2.1.3"
-uuid = { version = "1.18.0", features = [
-    "v4",
-    "fast-rng",
-    "macro-diagnostics",
-] }
-wildmatch = { version = "2.4.0", features = ["serde"] }
+uuid = { version = "1.19.0", features = ["v4", "fast-rng", "macro-diagnostics"] }
+vaultrs = { version = "0.7.4" }
+walkdir = "2.5.0"
+wildmatch = { version = "2.6.1", features = ["serde"] }
 winapi = { version = "0.3.9" }
 xxhash-rust = { version = "0.8.15", features = ["xxh64", "xxh3"] }
-zip = "2.4.2"
+zip = "6.0.0"
 zstd = "0.13.3"
 
+# Observability and Metrics
+metrics = "0.24.3"
+opentelemetry = { version = "0.31.0" }
+opentelemetry-appender-tracing = { version = "0.31.1", features = ["experimental_use_tracing_span_context", "experimental_metadata_attributes", "spec_unstable_logs_enabled"] }
+opentelemetry-otlp = { version = "0.31.0", features = ["gzip-http", "reqwest-rustls"] }
+opentelemetry_sdk = { version = "0.31.0" }
+opentelemetry-semantic-conventions = { version = "0.31.0", features = ["semconv_experimental"] }
+opentelemetry-stdout = { version = "0.31.0" }
+
+# Performance Analysis and Memory Profiling
+mimalloc = "0.1"
+# Use tikv-jemallocator as memory allocator and enable performance analysis
+tikv-jemallocator = { version = "0.6", features = ["profiling", "stats", "unprefixed_malloc_on_supported_platforms", "background_threads"] }
+# Used to control and obtain statistics for jemalloc at runtime
+tikv-jemalloc-ctl = { version = "0.6", features = ["use_std", "stats", "profiling"] }
+# Used to generate pprof-compatible memory profiling data and support symbolization and flame graphs
+jemalloc_pprof = { version = "0.8.1", features = ["symbolize", "flamegraph"] }
+# Used to generate CPU performance analysis data and flame diagrams
+pprof = { version = "0.15.0", features = ["flamegraph", "protobuf-codec"] }
+
+
 
 [workspace.metadata.cargo-shear]
-ignored = ["rustfs", "rust-i18n", "rustfs-mcp"]
-
-[profile.wasm-dev]
-inherits = "dev"
-opt-level = 1
-
-[profile.server-dev]
-inherits = "dev"
-
-[profile.android-dev]
-inherits = "dev"
+ignored = ["rustfs", "rustfs-mcp", "tokio-test"]
 
 [profile.release]
 opt-level = 3

Dockerfile

@@ -1,58 +1,47 @@
-# Multi-stage build for RustFS production image
-
-# Build stage: Download and extract RustFS binary
 FROM alpine:3.22 AS build
 
-# Build arguments for platform and release
 ARG TARGETARCH
 ARG RELEASE=latest
 
-# Install minimal dependencies for downloading and extracting
 RUN apk add --no-cache ca-certificates curl unzip
-
-# Create build directory
 WORKDIR /build
 
-# Set architecture-specific variables
-RUN if [ "$TARGETARCH" = "amd64" ]; then \
-        echo "x86_64-musl" > /tmp/arch; \
-    elif [ "$TARGETARCH" = "arm64" ]; then \
-        echo "aarch64-musl" > /tmp/arch; \
+RUN set -eux; \
+    case "$TARGETARCH" in \
+      amd64)  ARCH_SUBSTR="x86_64-musl"  ;; \
+      arm64)  ARCH_SUBSTR="aarch64-musl" ;; \
+      *) echo "Unsupported TARGETARCH=$TARGETARCH" >&2; exit 1 ;; \
+    esac; \
+    if [ "$RELEASE" = "latest" ]; then \
+      TAG="$(curl -fsSL https://api.github.com/repos/rustfs/rustfs/releases \
+              | grep -o '"tag_name": "[^"]*"' | cut -d'"' -f4 | head -n 1)"; \
     else \
-        echo "unsupported" > /tmp/arch; \
-    fi
-RUN ARCH=$(cat /tmp/arch) && \
-    if [ "$ARCH" = "unsupported" ]; then \
-        echo "Unsupported architecture: $TARGETARCH" && exit 1; \
-    fi && \
-    if [ "${RELEASE}" = "latest" ]; then \
-        # For latest, download from GitHub releases using the -latest suffix
-        PACKAGE_NAME="rustfs-linux-${ARCH}-latest.zip"; \
-        # Use GitHub API to get the latest release URL
-        LATEST_RELEASE_URL=$(curl -s https://api.github.com/repos/rustfs/rustfs/releases/latest | grep -o '"browser_download_url": "[^"]*'"${PACKAGE_NAME}"'"' | cut -d'"' -f4 | head -1); \
-        if [ -z "$LATEST_RELEASE_URL" ]; then \
-            echo "Failed to find latest release for ${PACKAGE_NAME}" >&2; \
-            exit 1; \
-        fi; \
-        DOWNLOAD_URL="$LATEST_RELEASE_URL"; \
-    else \
-        # For specific versions, construct the GitHub release URL directly
-        # RELEASE is the GitHub release tag (e.g., "1.0.0-alpha.42")
-        # VERSION is the version in filename (e.g., "v1.0.0-alpha.42")
-        VERSION="v${RELEASE}"; \
-        PACKAGE_NAME="rustfs-linux-${ARCH}-${VERSION}.zip"; \
-        DOWNLOAD_URL="https://github.com/rustfs/rustfs/releases/download/${RELEASE}/${PACKAGE_NAME}"; \
-    fi && \
-    echo "Downloading ${PACKAGE_NAME} from ${DOWNLOAD_URL}" >&2 && \
-    curl -f -L "${DOWNLOAD_URL}" -o rustfs.zip && \
-    unzip rustfs.zip -d /build && \
-    chmod +x /build/rustfs && \
-    rm rustfs.zip || { echo "Failed to download or extract ${PACKAGE_NAME}" >&2; exit 1; }
+      TAG="$RELEASE"; \
+    fi; \
+    echo "Using tag: $TAG (arch pattern: $ARCH_SUBSTR)"; \
+    # Find download URL in assets list for this tag that contains arch substring and ends with .zip
+    URL="$(curl -fsSL "https://api.github.com/repos/rustfs/rustfs/releases/tags/$TAG" \
+           | grep -o "\"browser_download_url\": \"[^\"]*${ARCH_SUBSTR}[^\"]*\\.zip\"" \
+           | cut -d'"' -f4 | head -n 1)"; \
+    if [ -z "$URL" ]; then echo "Failed to locate release asset for $ARCH_SUBSTR at tag $TAG" >&2; exit 1; fi; \
+    echo "Downloading: $URL"; \
+    curl -fL "$URL" -o rustfs.zip; \
+    unzip -q rustfs.zip -d /build; \
+    # If binary is not in root directory, try to locate and move from zip to /build/rustfs
+    if [ ! -x /build/rustfs ]; then \
+      BIN_PATH="$(unzip -Z -1 rustfs.zip | grep -E '(^|/)rustfs$' | head -n 1 || true)"; \
+      if [ -n "$BIN_PATH" ]; then \
+        mkdir -p /build/.tmp && unzip -q rustfs.zip "$BIN_PATH" -d /build/.tmp && \
+        mv "/build/.tmp/$BIN_PATH" /build/rustfs; \
+      fi; \
+    fi; \
+    [ -x /build/rustfs ] || { echo "rustfs binary not found in asset" >&2; exit 1; }; \
+    chmod +x /build/rustfs; \
+    rm -rf rustfs.zip /build/.tmp || true
 
-# Runtime stage: Configure runtime environment
-FROM alpine:3.22.1
 
-# Build arguments and labels
+FROM alpine:3.22
+
 ARG RELEASE=latest
 ARG BUILD_DATE
 ARG VCS_REF
@@ -60,7 +49,7 @@ ARG VCS_REF
 LABEL name="RustFS" \
       vendor="RustFS Team" \
       maintainer="RustFS Team <dev@rustfs.com>" \
-      version="${RELEASE}" \
+      version="v${RELEASE#v}" \
       release="${RELEASE}" \
       build-date="${BUILD_DATE}" \
       vcs-ref="${VCS_REF}" \
@@ -69,43 +58,38 @@ LABEL name="RustFS" \
       url="https://rustfs.com" \
       license="Apache-2.0"
 
-# Install runtime dependencies
-RUN echo "https://dl-cdn.alpinelinux.org/alpine/v3.20/community" >> /etc/apk/repositories && \
-    apk update && \
-    apk add --no-cache ca-certificates bash gosu coreutils shadow && \
-    addgroup -g 1000 rustfs && \
-    adduser -u 1000 -G rustfs -s /bin/bash -D rustfs
+RUN apk add --no-cache ca-certificates coreutils curl
 
-# Copy CA certificates and RustFS binary from build stage
 COPY --from=build /etc/ssl/certs/ca-certificates.crt /etc/ssl/certs/
 COPY --from=build /build/rustfs /usr/bin/rustfs
-
-# Copy entry point script
 COPY entrypoint.sh /entrypoint.sh
 
-# Set permissions
-RUN chmod +x /usr/bin/rustfs /entrypoint.sh && \
+RUN chmod +x /usr/bin/rustfs /entrypoint.sh
+
+RUN addgroup -g 10001 -S rustfs && \
+    adduser -u 10001 -G rustfs -S rustfs -D && \
     mkdir -p /data /logs && \
-    chown rustfs:rustfs /data /logs && \
-    chmod 700 /data /logs
+    chown -R rustfs:rustfs /data /logs && \
+    chmod 0750 /data /logs
 
-# Environment variables (credentials should be set via environment or secrets)
-ENV RUSTFS_ADDRESS=:9000 \
-    RUSTFS_ACCESS_KEY=rustfsadmin \
-    RUSTFS_SECRET_KEY=rustfsadmin \
-    RUSTFS_CONSOLE_ENABLE=true \
-    RUSTFS_VOLUMES=/data \
-    RUST_LOG=warn \
-    RUSTFS_OBS_LOG_DIRECTORY=/logs \
-    RUSTFS_SINKS_FILE_PATH=/logs
+ENV RUSTFS_ADDRESS=":9000" \
+    RUSTFS_CONSOLE_ADDRESS=":9001" \
+    RUSTFS_ACCESS_KEY="rustfsadmin" \
+    RUSTFS_SECRET_KEY="rustfsadmin" \
+    RUSTFS_CONSOLE_ENABLE="true" \
+    RUSTFS_EXTERNAL_ADDRESS="" \
+    RUSTFS_CORS_ALLOWED_ORIGINS="*" \
+    RUSTFS_CONSOLE_CORS_ALLOWED_ORIGINS="*" \
+    RUSTFS_VOLUMES="/data" \
+    RUST_LOG="warn" \
+    RUSTFS_OBS_LOG_DIRECTORY="/logs" 
+    
+EXPOSE 9000 9001
 
-# Expose port
-EXPOSE 9000
-
-# Volumes for data and logs
 VOLUME ["/data", "/logs"]
 
-# Set entry point
-ENTRYPOINT ["/entrypoint.sh"]
-CMD ["/usr/bin/rustfs"]
+USER rustfs
 
+ENTRYPOINT ["/entrypoint.sh"]
+
+CMD ["rustfs"]

Dockerfile.source

@@ -1,80 +1,88 @@
+# syntax=docker/dockerfile:1.6
 # Multi-stage Dockerfile for RustFS - LOCAL DEVELOPMENT ONLY
 #
-# ⚠️  IMPORTANT: This Dockerfile is for local development and testing only.
-# ⚠️  It builds RustFS from source code and is NOT used in CI/CD pipelines.
-# ⚠️  CI/CD pipeline uses pre-built binaries from Dockerfile instead.
+# IMPORTANT: This Dockerfile builds RustFS from source for local development and testing.
+# CI/CD uses the production Dockerfile with prebuilt binaries instead.
 #
-# Usage for local development:
+# Example:
 #   docker build -f Dockerfile.source -t rustfs:dev-local .
 #   docker run --rm -p 9000:9000 rustfs:dev-local
 #
-# Supports cross-compilation for amd64 and arm64 architectures
+# Supports cross-compilation for amd64 and arm64 via TARGETPLATFORM.
+
 ARG TARGETPLATFORM
 ARG BUILDPLATFORM
 
+# -----------------------------
 # Build stage
-FROM --platform=$BUILDPLATFORM rust:1.88-bookworm AS builder
+# -----------------------------
+FROM rust:1.88-bookworm AS builder
 
-# Re-declare build arguments after FROM (required for multi-stage builds)
+# Re-declare args after FROM
 ARG TARGETPLATFORM
 ARG BUILDPLATFORM
 
-# Debug: Print platform information
-RUN echo "🐳 Build Info: BUILDPLATFORM=$BUILDPLATFORM, TARGETPLATFORM=$TARGETPLATFORM"
+# Debug: print platforms
+RUN echo "Build info -> BUILDPLATFORM=${BUILDPLATFORM}, TARGETPLATFORM=${TARGETPLATFORM}"
 
-# Install required build dependencies
-RUN apt-get update && apt-get install -y \
-    wget \
-    git \
+# Install build toolchain and headers
+# Use distro packages for protoc/flatc to avoid host-arch mismatch
+RUN set -eux; \
+    export DEBIAN_FRONTEND=noninteractive; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
+    build-essential \
+    ca-certificates \
     curl \
-    unzip \
-    gcc \
+    git \
     pkg-config \
     libssl-dev \
     lld \
-    && rm -rf /var/lib/apt/lists/*
+    protobuf-compiler \
+    flatbuffers-compiler; \
+    rm -rf /var/lib/apt/lists/*
 
-# Note: sccache removed for simpler builds
-
-# Install cross-compilation tools for ARM64
-RUN if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
-        apt-get update && \
-        apt-get install -y gcc-aarch64-linux-gnu && \
-        rm -rf /var/lib/apt/lists/*; \
+# Optional: cross toolchain for aarch64 (only when targeting linux/arm64)
+RUN set -eux; \
+    if [ "${TARGETPLATFORM:-linux/amd64}" = "linux/arm64" ]; then \
+    export DEBIAN_FRONTEND=noninteractive; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends gcc-aarch64-linux-gnu; \
+    rm -rf /var/lib/apt/lists/*; \
     fi
 
-# Install protoc
-RUN wget https://github.com/protocolbuffers/protobuf/releases/download/v31.1/protoc-31.1-linux-x86_64.zip \
-    && unzip protoc-31.1-linux-x86_64.zip -d protoc3 \
-    && mv protoc3/bin/* /usr/local/bin/ && chmod +x /usr/local/bin/protoc \
-    && mv protoc3/include/* /usr/local/include/ && rm -rf protoc-31.1-linux-x86_64.zip protoc3
-
-# Install flatc
-RUN wget https://github.com/google/flatbuffers/releases/download/v25.2.10/Linux.flatc.binary.g++-13.zip \
-    && unzip Linux.flatc.binary.g++-13.zip \
-    && mv flatc /usr/local/bin/ && chmod +x /usr/local/bin/flatc && rm -rf Linux.flatc.binary.g++-13.zip
-
-# Set up Rust targets based on platform
-RUN set -e && \
-    PLATFORM="${TARGETPLATFORM:-linux/amd64}" && \
-    echo "🎯 Setting up Rust target for platform: $PLATFORM" && \
-    case "$PLATFORM" in \
-        "linux/amd64") rustup target add x86_64-unknown-linux-gnu ;; \
-        "linux/arm64") rustup target add aarch64-unknown-linux-gnu ;; \
-        *) echo "❌ Unsupported platform: $PLATFORM" && exit 1 ;; \
+# Add Rust targets based on TARGETPLATFORM
+RUN set -eux; \
+    case "${TARGETPLATFORM:-linux/amd64}" in \
+    linux/amd64) rustup target add x86_64-unknown-linux-gnu ;; \
+    linux/arm64) rustup target add aarch64-unknown-linux-gnu ;; \
+    *) echo "Unsupported TARGETPLATFORM=${TARGETPLATFORM}" >&2; exit 1 ;; \
     esac
 
-# Set up environment for cross-compilation
+# Cross-compilation environment (used only when targeting aarch64)
 ENV CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER=aarch64-linux-gnu-gcc
 ENV CC_aarch64_unknown_linux_gnu=aarch64-linux-gnu-gcc
 ENV CXX_aarch64_unknown_linux_gnu=aarch64-linux-gnu-g++
 
 WORKDIR /usr/src/rustfs
 
-# Copy all source code
+# Layered copy to maximize caching:
+# 1) top-level manifests
+COPY Cargo.toml Cargo.lock ./
+# 2) workspace member manifests (adjust if workspace layout changes)
+COPY rustfs/Cargo.toml rustfs/Cargo.toml
+COPY crates/*/Cargo.toml crates/
+COPY cli/rustfs-gui/Cargo.toml cli/rustfs-gui/Cargo.toml
+
+# Pre-fetch dependencies for better caching
+RUN --mount=type=cache,target=/usr/local/cargo/registry \
+    --mount=type=cache,target=/usr/local/cargo/git \
+    cargo fetch --locked || true
+
+# 3) copy full sources (this is the main cache invalidation point)
 COPY . .
 
-# Configure cargo for optimized builds
+# Cargo build configuration for lean release artifacts
 ENV CARGO_NET_GIT_FETCH_WITH_CLI=true \
     CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse \
     CARGO_INCREMENTAL=0 \
@@ -82,75 +90,91 @@ ENV CARGO_NET_GIT_FETCH_WITH_CLI=true \
     CARGO_PROFILE_RELEASE_SPLIT_DEBUGINFO=off \
     CARGO_PROFILE_RELEASE_STRIP=symbols
 
-# Generate protobuf code
-RUN cargo run --bin gproto
+# Generate protobuf/flatbuffers code (uses protoc/flatc from distro)
+RUN --mount=type=cache,target=/usr/local/cargo/registry \
+    --mount=type=cache,target=/usr/local/cargo/git \
+    --mount=type=cache,target=/usr/src/rustfs/target \
+    cargo run --bin gproto
 
-# Build the actual application with optimizations
-RUN case "$TARGETPLATFORM" in \
-        "linux/amd64") \
-            echo "🔨 Building for amd64..." && \
-            rustup target add x86_64-unknown-linux-gnu && \
-            cargo build --release --target x86_64-unknown-linux-gnu --bin rustfs -j $(nproc) && \
-            cp target/x86_64-unknown-linux-gnu/release/rustfs /usr/local/bin/rustfs \
-            ;; \
-        "linux/arm64") \
-            echo "🔨 Building for arm64..." && \
-            rustup target add aarch64-unknown-linux-gnu && \
-            cargo build --release --target aarch64-unknown-linux-gnu --bin rustfs -j $(nproc) && \
-            cp target/aarch64-unknown-linux-gnu/release/rustfs /usr/local/bin/rustfs \
-            ;; \
-        *) \
-            echo "❌ Unsupported platform: $TARGETPLATFORM" && exit 1 \
-            ;; \
+# Build RustFS (target depends on TARGETPLATFORM)
+RUN --mount=type=cache,target=/usr/local/cargo/registry \
+    --mount=type=cache,target=/usr/local/cargo/git \
+    --mount=type=cache,target=/usr/src/rustfs/target \
+    set -eux; \
+    case "${TARGETPLATFORM:-linux/amd64}" in \
+    linux/amd64) \
+    echo "Building for x86_64-unknown-linux-gnu"; \
+    cargo build --release --locked --target x86_64-unknown-linux-gnu --bin rustfs -j "$(nproc)"; \
+    install -m 0755 target/x86_64-unknown-linux-gnu/release/rustfs /usr/local/bin/rustfs \
+    ;; \
+    linux/arm64) \
+    echo "Building for aarch64-unknown-linux-gnu"; \
+    cargo build --release --locked --target aarch64-unknown-linux-gnu --bin rustfs -j "$(nproc)"; \
+    install -m 0755 target/aarch64-unknown-linux-gnu/release/rustfs /usr/local/bin/rustfs \
+    ;; \
+    *) \
+    echo "Unsupported TARGETPLATFORM=${TARGETPLATFORM}" >&2; exit 1 \
+    ;; \
     esac
 
-# Runtime stage - Ubuntu minimal for better compatibility
+# -----------------------------
+# Runtime stage (Ubuntu minimal)
+# -----------------------------
 FROM ubuntu:22.04
 
-# Install runtime dependencies
-RUN apt-get update && apt-get install -y \
+ARG BUILD_DATE
+ARG VCS_REF
+
+LABEL name="RustFS (dev-local)" \
+    maintainer="RustFS Team" \
+    build-date="${BUILD_DATE}" \
+    vcs-ref="${VCS_REF}" \
+    description="RustFS - local development image built from source (NOT for production)."
+
+# Minimal runtime deps: certificates + tzdata + coreutils (for chroot --userspec)
+RUN set -eux; \
+    export DEBIAN_FRONTEND=noninteractive; \
+    apt-get update; \
+    apt-get install -y --no-install-recommends \
     ca-certificates \
     tzdata \
-    wget \
-    coreutils \
-    passwd \
-    && rm -rf /var/lib/apt/lists/*
+    coreutils; \
+    rm -rf /var/lib/apt/lists/*
 
-# Create rustfs user and group
-RUN groupadd -g 1000 rustfs && \
-    useradd -d /app -g rustfs -u 1000 -s /bin/bash rustfs
+# Create a conventional runtime user/group (final switch happens in entrypoint via chroot --userspec)
+RUN set -eux; \
+    groupadd -g 1000 rustfs; \
+    useradd -u 1000 -g rustfs -M -s /usr/sbin/nologin rustfs
 
 WORKDIR /app
 
-# Create data directories
-RUN mkdir -p /data/rustfs{0,1,2,3} && \
-    chown -R rustfs:rustfs /data /app
+# Prepare data/log directories with sane defaults
+RUN set -eux; \
+    mkdir -p /data /logs; \
+    chown -R rustfs:rustfs /data /logs /app; \
+    chmod 0750 /data /logs
 
-# Copy binary from builder stage
-COPY --from=builder /usr/local/bin/rustfs /app/rustfs
-RUN chmod +x /app/rustfs && chown rustfs:rustfs /app/rustfs
-
-# Copy entrypoint script
+# Copy the freshly built binary and the entrypoint
+COPY --from=builder /usr/local/bin/rustfs /usr/bin/rustfs
 COPY entrypoint.sh /entrypoint.sh
-RUN chmod +x /entrypoint.sh
+RUN chmod +x /usr/bin/rustfs /entrypoint.sh
 
-# Switch to non-root user
-USER rustfs
+# Default environment (override in docker run/compose as needed)
+ENV RUSTFS_ADDRESS=":9000" \
+    RUSTFS_ACCESS_KEY="rustfsadmin" \
+    RUSTFS_SECRET_KEY="rustfsadmin" \
+    RUSTFS_CONSOLE_ENABLE="true" \
+    RUSTFS_VOLUMES="/data" \
+    RUST_LOG="warn" \
+    RUSTFS_OBS_LOG_DIRECTORY="/logs" \
+    RUSTFS_USERNAME="rustfs" \
+    RUSTFS_GROUPNAME="rustfs" \
+    RUSTFS_UID="1000" \
+    RUSTFS_GID="1000"
 
-# Expose ports
 EXPOSE 9000
+VOLUME ["/data", "/logs"]
 
-# Environment variables
-ENV RUSTFS_ACCESS_KEY=rustfsadmin \
-    RUSTFS_SECRET_KEY=rustfsadmin \
-    RUSTFS_ADDRESS=":9000" \
-    RUSTFS_CONSOLE_ENABLE=true \
-    RUSTFS_VOLUMES=/data \
-    RUST_LOG=warn
-
-# Volume for data
-VOLUME ["/data"]
-
-# Set entrypoint and default command
+# Keep root here; entrypoint will drop privileges using chroot --userspec
 ENTRYPOINT ["/entrypoint.sh"]
-CMD ["/app/rustfs"]
+CMD ["/usr/bin/rustfs"]

Makefile

@@ -23,7 +23,7 @@ fmt-check:
 .PHONY: clippy
 clippy:
 	@echo "🔍 Running clippy checks..."
-	cargo clippy --fix --allow-dirty 
+	cargo clippy --fix --allow-dirty
 	cargo clippy --all-targets --all-features -- -D warnings
 
 .PHONY: check
@@ -34,7 +34,12 @@ check:
 .PHONY: test
 test:
 	@echo "🧪 Running tests..."
-	cargo nextest run --all --exclude e2e_test
+	@if command -v cargo-nextest >/dev/null 2>&1; then \
+		cargo nextest run --all --exclude e2e_test; \
+	else \
+		echo "ℹ️ cargo-nextest not found; falling back to 'cargo test'"; \
+		cargo test --workspace --exclude e2e_test -- --nocapture; \
+	fi
 	cargo test --all --doc
 
 .PHONY: pre-commit
@@ -210,7 +215,9 @@ docker-build-production:
 docker-build-source:
 	@echo "🏗️ Building single-architecture source Docker image..."
 	@echo "💡 Consider using 'make docker-dev-local' for multi-arch support"
-	$(DOCKER_CLI) build -f $(DOCKERFILE_SOURCE) -t rustfs:source .
+	DOCKER_BUILDKIT=1 $(DOCKER_CLI) build \
+		--build-arg BUILDKIT_INLINE_CACHE=1 \
+		-f $(DOCKERFILE_SOURCE) -t rustfs:source .
 
 # ========================================================================================
 # Development Environment

README.md

@@ -1,6 +1,6 @@
 [![RustFS](https://rustfs.com/images/rustfs-github.png)](https://rustfs.com)
 
-<p align="center">RustFS is a high-performance distributed object storage software built using Rust</p>
+<p align="center">RustFS is a high-performance, distributed object storage system built in Rust.</p>
 
 <p align="center">
   <a href="https://github.com/rustfs/rustfs/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/rustfs/rustfs/actions/workflows/ci.yml/badge.svg" /></a>
@@ -11,7 +11,7 @@
 </p>
 
 <p align="center">
-  <a href="https://docs.rustfs.com/introduction.html">Getting Started</a>
+  <a href="https://docs.rustfs.com/installation/">Getting Started</a>
   · <a href="https://docs.rustfs.com/">Docs</a>
   · <a href="https://github.com/rustfs/rustfs/issues">Bug reports</a>
   · <a href="https://github.com/rustfs/rustfs/discussions">Discussions</a>
@@ -19,114 +19,150 @@
 
 <p align="center">
 English | <a href="https://github.com/rustfs/rustfs/blob/main/README_ZH.md">简体中文</a> |
-  <!-- Keep these links. Translations will automatically update with the README. -->
   <a href="https://readme-i18n.com/rustfs/rustfs?lang=de">Deutsch</a> |
   <a href="https://readme-i18n.com/rustfs/rustfs?lang=es">Español</a> |
   <a href="https://readme-i18n.com/rustfs/rustfs?lang=fr">français</a> |
   <a href="https://readme-i18n.com/rustfs/rustfs?lang=ja">日本語</a> |
   <a href="https://readme-i18n.com/rustfs/rustfs?lang=ko">한국어</a> |
-  <a href="https://readme-i18n.com/rustfs/rustfs?lang=pt">Português</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=pt">Portuguese</a> |
   <a href="https://readme-i18n.com/rustfs/rustfs?lang=ru">Русский</a>
 </p>
 
-RustFS is a high-performance distributed object storage software built using Rust, one of the most popular languages worldwide. Along with MinIO, it shares a range of advantages such as simplicity, S3 compatibility, open-source nature, support for data lakes, AI, and big data. Furthermore, it has a better and more user-friendly open-source license in comparison to other storage systems, being constructed under the Apache license. As Rust serves as its foundation, RustFS provides faster speed and safer distributed features for high-performance object storage.
+RustFS is a high-performance, distributed object storage system built in Rust—one of the most loved programming languages worldwide. RustFS combines the simplicity of MinIO with the memory safety and raw performance of Rust. It offers full S3 compatibility, is completely open-source, and is optimized for data lakes, AI, and big data workloads.
 
-> ⚠️ **RustFS is under rapid development. Do NOT use in production environments!**
+Unlike other storage systems, RustFS is released under the permissible Apache 2.0 license, avoiding the restrictions of AGPL. With Rust as its foundation, RustFS delivers superior speed and secure distributed features for next-generation object storage.
 
-## Features
+## Feature & Status
 
-- **High Performance**: Built with Rust, ensuring speed and efficiency.
-- **Distributed Architecture**: Scalable and fault-tolerant design for large-scale deployments.
-- **S3 Compatibility**: Seamless integration with existing S3-compatible applications.
-- **Data Lake Support**: Optimized for big data and AI workloads.
-- **Open Source**: Licensed under Apache 2.0, encouraging community contributions and transparency.
-- **User-Friendly**: Designed with simplicity in mind, making it easy to deploy and manage.
+- **High Performance**: Built with Rust to ensure maximum speed and resource efficiency.
+- **Distributed Architecture**: Scalable and fault-tolerant design suitable for large-scale deployments.
+- **S3 Compatibility**: Seamless integration with existing S3-compatible applications and tools.
+- **Data Lake Support**: Optimized for high-throughput big data and AI workloads.
+- **Open Source**: Licensed under Apache 2.0, encouraging unrestricted community contributions and commercial usage.
+- **User-Friendly**: Designed with simplicity in mind for easy deployment and management.
 
-## RustFS vs MinIO
+| Feature | Status | Feature | Status |
+| :--- | :--- | :--- | :--- |
+| **S3 Core Features** | ✅ Available | **Bitrot Protection** | ✅ Available |
+| **Upload / Download** | ✅ Available | **Single Node Mode** | ✅ Available |
+| **Versioning** | ✅ Available |  **Bucket Replication** | ⚠️ Partial Support |
+| **Logging** | ✅ Available |  **Lifecycle Management** | 🚧 Under Testing |
+| **Event Notifications** | ✅ Available |  **Distributed Mode** | 🚧 Under Testing |
+| **K8s Helm Charts** | ✅ Available |  **OPA (Open Policy Agent)** | 🚧 Under Testing |
 
-Stress test server parameters
 
-|  Type  |  parameter   | Remark |
-| - | - | - |
-|CPU | 2 Core | Intel Xeon(Sapphire Rapids) Platinum 8475B , 2.7/3.2 GHz|   |
-|Memory| 4GB |     |
-|Network | 15Gbp |      |
-|Driver  | 40GB x 4 |   IOPS 3800 / Driver |
+
+
+## RustFS vs MinIO Performance
+
+**Stress Test Environment:**
+
+| Type    | Parameter | Remark                                                   |
+|---------|-----------|----------------------------------------------------------|
+| CPU     | 2 Core    | Intel Xeon (Sapphire Rapids) Platinum 8475B, 2.7/3.2 GHz |
+| Memory  | 4GB       |                                                          |
+| Network | 15Gbps    |                                                          |
+| Drive   | 40GB x 4  | IOPS 3800 / Drive                                        |
 
 <https://github.com/user-attachments/assets/2e4979b5-260c-4f2c-ac12-c87fd558072a>
 
-### RustFS vs Other object storage
+### RustFS vs Other Object Storage
 
-| RustFS | Other object storage|
-| - | - |
-| Powerful Console | Simple and useless Console |
-| Developed based on Rust language, memory is safer | Developed in Go or C, with potential issues like memory GC/leaks |
-| Does not report logs to third-party countries  | Reporting logs to other third countries may violate national security laws |
-| Licensed under Apache, more business-friendly  | AGPL V3 License and other License, polluted open source and License traps, infringement of intellectual property rights |
-| Comprehensive S3 support, works with domestic and international cloud providers  | Full support for S3, but no local cloud vendor support |
-| Rust-based development, strong support for secure and innovative devices  | Poor support for edge gateways and secure innovative devices|
-| Stable commercial prices, free community support | High pricing, with costs up to $250,000 for 1PiB |
-| No risk | Intellectual property risks and risks of prohibited uses |
+| Feature | RustFS | Other Object Storage |
+| :--- | :--- | :--- |
+| **Console Experience** | **Powerful Console**<br>Comprehensive management interface. | **Basic / Limited Console**<br>Often overly simple or lacking critical features. |
+| **Language & Safety** | **Rust-based**<br>Memory safety by design. | **Go or C-based**<br>Potential for memory GC pauses or leaks. |
+| **Data Sovereignty** | **No Telemetry / Full Compliance**<br>Guards against unauthorized cross-border data egress. Compliant with GDPR (EU/UK), CCPA (US), and APPI (Japan). | **Potential Risk**<br>Possible legal exposure and unwanted data telemetry. |
+| **Licensing** | **Permissive Apache 2.0**<br>Business-friendly, no "poison pill" clauses. | **Restrictive AGPL v3**<br>Risk of license traps and intellectual property pollution. |
+| **Compatibility** | **100% S3 Compatible**<br>Works with any cloud provider or client, anywhere. | **Variable Compatibility**<br>May lack support for local cloud vendors or specific APIs. |
+| **Edge & IoT** | **Strong Edge Support**<br>Ideal for secure, innovative edge devices. | **Weak Edge Support**<br>Often too heavy for edge gateways. |
+| **Risk Profile** | **Enterprise Risk Mitigation**<br>Clear IP rights and safe for commercial use. | **Legal Risks**<br>Intellectual property ambiguity and usage restrictions. |
 
 ## Quickstart
 
 To get started with RustFS, follow these steps:
 
-1. **One-click installation script (Option 1)​​**
-
-   ```bash
-   curl -O  https://rustfs.com/install_rustfs.sh && bash install_rustfs.sh
-   ```
-
-2. **Docker Quick Start (Option 2)​​**
+### 1. One-click Installation (Option 1)
 
   ```bash
-   # Latest stable release
-   docker run -d -p 9000:9000 -v /data:/data rustfs/rustfs:latest
+  curl -O https://rustfs.com/install_rustfs.sh && bash install_rustfs.sh
+````
 
-   # Development version (main branch)
-   docker run -d -p 9000:9000 -v /data:/data rustfs/rustfs:main-latest
+### 2\. Docker Quick Start (Option 2)
 
-   # Specific version
-   docker run -d -p 9000:9000 -v /data:/data rustfs/rustfs:v1.0.0
-   ```
+The RustFS container runs as a non-root user `rustfs` (UID `10001`). If you run Docker with `-v` to mount a host directory, please ensure the host directory owner is set to `10001`, otherwise you will encounter permission denied errors.
 
-3. **Build from Source (Option 3) - Advanced Users**
+```bash
+ # Create data and logs directories
+ mkdir -p data logs
 
-   For developers who want to build RustFS Docker images from source with multi-architecture support:
+ # Change the owner of these directories
+ chown -R 10001:10001 data logs
 
-   ```bash
-   # Build multi-architecture images locally
-   ./docker-buildx.sh --build-arg RELEASE=latest
+ # Using latest version
+ docker run -d -p 9000:9000 -p 9001:9001 -v $(pwd)/data:/data -v $(pwd)/logs:/logs rustfs/rustfs:latest
 
-   # Build and push to registry
-   ./docker-buildx.sh --push
+ # Using specific version
+ docker run -d -p 9000:9000 -p 9001:9001 -v $(pwd)/data:/data -v $(pwd)/logs:/logs rustfs/rustfs:1.0.0.alpha.68
+```
 
-   # Build specific version
-   ./docker-buildx.sh --release v1.0.0 --push
+You can also use Docker Compose. Using the `docker-compose.yml` file in the root directory:
 
-   # Build for custom registry
-   ./docker-buildx.sh --registry your-registry.com --namespace yourname --push
-   ```
+```bash
+docker compose --profile observability up -d
+```
 
-   The `docker-buildx.sh` script supports:
-   - **Multi-architecture builds**: `linux/amd64`, `linux/arm64`
-   - **Automatic version detection**: Uses git tags or commit hashes
-   - **Registry flexibility**: Supports Docker Hub, GitHub Container Registry, etc.
-   - **Build optimization**: Includes caching and parallel builds
+**NOTE**: We recommend reviewing the `docker-compose.yaml` file before running. It defines several services including Grafana, Prometheus, and Jaeger, which are helpful for RustFS observability. If you wish to start Redis or Nginx containers, you can specify the corresponding profiles.
 
-   You can also use Make targets for convenience:
+### 3\. Build from Source (Option 3) - Advanced Users
 
-   ```bash
-   make docker-buildx                    # Build locally
-   make docker-buildx-push               # Build and push
-   make docker-buildx-version VERSION=v1.0.0  # Build specific version
-   make help-docker                      # Show all Docker-related commands
-   ```
+For developers who want to build RustFS Docker images from source with multi-architecture support:
 
-4. **Access the Console**: Open your web browser and navigate to `http://localhost:9000` to access the RustFS console, default username and password is `rustfsadmin` .
-5. **Create a Bucket**: Use the console to create a new bucket for your objects.
-6. **Upload Objects**: You can upload files directly through the console or use S3-compatible APIs to interact with your RustFS instance.
+```bash
+# Build multi-architecture images locally
+./docker-buildx.sh --build-arg RELEASE=latest
+
+# Build and push to registry
+./docker-buildx.sh --push
+
+# Build specific version
+./docker-buildx.sh --release v1.0.0 --push
+
+# Build for custom registry
+./docker-buildx.sh --registry your-registry.com --namespace yourname --push
+```
+
+The `docker-buildx.sh` script supports:
+\- **Multi-architecture builds**: `linux/amd64`, `linux/arm64`
+\- **Automatic version detection**: Uses git tags or commit hashes
+\- **Registry flexibility**: Supports Docker Hub, GitHub Container Registry, etc.
+\- **Build optimization**: Includes caching and parallel builds
+
+You can also use Make targets for convenience:
+
+```bash
+make docker-buildx                    # Build locally
+make docker-buildx-push               # Build and push
+make docker-buildx-version VERSION=v1.0.0  # Build specific version
+make help-docker                      # Show all Docker-related commands
+```
+
+> **Heads-up (macOS cross-compilation)**: macOS keeps the default `ulimit -n` at 256, so `cargo zigbuild` or `./build-rustfs.sh --platform ...` may fail with `ProcessFdQuotaExceeded` when targeting Linux. The build script attempts to raise the limit automatically, but if you still see the warning, run `ulimit -n 4096` (or higher) in your shell before building.
+
+### 4\. Build with Helm Chart (Option 4) - Cloud Native
+
+Follow the instructions in the [Helm Chart README](https://charts.rustfs.com/) to install RustFS on a Kubernetes cluster.
+
+-----
+
+### Accessing RustFS
+
+5.  **Access the Console**: Open your web browser and navigate to `http://localhost:9000` to access the RustFS console.
+      * Default credentials: `rustfsadmin` / `rustfsadmin`
+6.  **Create a Bucket**: Use the console to create a new bucket for your objects.
+7.  **Upload Objects**: You can upload files directly through the console or use S3-compatible APIs/clients to interact with your RustFS instance.
+
+**NOTE**: To access the RustFS instance via `https`, please refer to the [TLS Configuration Docs](https://docs.rustfs.com/integration/tls-configured.html).
 
 ## Documentation
 
@@ -134,36 +170,47 @@ For detailed documentation, including configuration options, API references, and
 
 ## Getting Help
 
-If you have any questions or need assistance, you can:
+If you have any questions or need assistance:
 
-- Check the [FAQ](https://github.com/rustfs/rustfs/discussions/categories/q-a) for common issues and solutions.
-- Join our [GitHub Discussions](https://github.com/rustfs/rustfs/discussions) to ask questions and share your experiences.
-- Open an issue on our [GitHub Issues](https://github.com/rustfs/rustfs/issues) page for bug reports or feature requests.
+  - Check the [FAQ](https://github.com/rustfs/rustfs/discussions/categories/q-a) for common issues and solutions.
+  - Join our [GitHub Discussions](https://github.com/rustfs/rustfs/discussions) to ask questions and share your experiences.
+  - Open an issue on our [GitHub Issues](https://github.com/rustfs/rustfs/issues) page for bug reports or feature requests.
 
 ## Links
 
-- [Documentation](https://docs.rustfs.com) - The manual you should read
-- [Changelog](https://github.com/rustfs/rustfs/releases) - What we broke and fixed
-- [GitHub Discussions](https://github.com/rustfs/rustfs/discussions) - Where the community lives
+  - [Documentation](https://docs.rustfs.com) - The manual you should read
+  - [Changelog](https://github.com/rustfs/rustfs/releases) - What we broke and fixed
+  - [GitHub Discussions](https://github.com/rustfs/rustfs/discussions) - Where the community lives
 
 ## Contact
 
-- **Bugs**: [GitHub Issues](https://github.com/rustfs/rustfs/issues)
-- **Business**: <hello@rustfs.com>
-- **Jobs**: <jobs@rustfs.com>
-- **General Discussion**: [GitHub Discussions](https://github.com/rustfs/rustfs/discussions)
-- **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)
+  - **Bugs**: [GitHub Issues](https://github.com/rustfs/rustfs/issues)
+  - **Business**: [hello@rustfs.com](mailto:hello@rustfs.com)
+  - **Jobs**: [jobs@rustfs.com](mailto:jobs@rustfs.com)
+  - **General Discussion**: [GitHub Discussions](https://github.com/rustfs/rustfs/discussions)
+  - **Contributing**: [CONTRIBUTING.md](CONTRIBUTING.md)
 
 ## Contributors
 
 RustFS is a community-driven project, and we appreciate all contributions. Check out the [Contributors](https://github.com/rustfs/rustfs/graphs/contributors) page to see the amazing people who have helped make RustFS better.
 
 <a href="https://github.com/rustfs/rustfs/graphs/contributors">
-  <img src="https://opencollective.com/rustfs/contributors.svg?width=890&limit=500&button=false" />
+<img src="https://opencollective.com/rustfs/contributors.svg?width=890&limit=500&button=false" alt="Contributors" />
 </a>
 
+## Github Trending Top
+
+🚀 RustFS is beloved by open-source enthusiasts and enterprise users worldwide, often appearing on the GitHub Trending top charts.
+
+<a href="https://trendshift.io/repositories/14181" target="_blank"><img src="https://raw.githubusercontent.com/rustfs/rustfs/refs/heads/main/docs/rustfs-trending.jpg" alt="rustfs%2Frustfs | Trendshift" /></a>
+
+## Star History
+
+[![Star History Chart](https://api.star-history.com/svg?repos=rustfs/rustfs&type=date&legend=top-left)](https://www.star-history.com/#rustfs/rustfs&type=date&legend=top-left)
+
 ## License
 
 [Apache 2.0](https://opensource.org/licenses/Apache-2.0)
 
 **RustFS** is a trademark of RustFS, Inc. All other trademarks are the property of their respective owners.
+

README_ZH.md

@@ -1,119 +1,219 @@
 [![RustFS](https://rustfs.com/images/rustfs-github.png)](https://rustfs.com)
 
-<p align="center">RustFS 是一个使用 Rust 构建的高性能分布式对象存储软件</p >
+<p align="center">RustFS 是一个基于 Rust 构建的高性能分布式对象存储系统。</p>
 
 <p align="center">
   <a href="https://github.com/rustfs/rustfs/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/rustfs/rustfs/actions/workflows/ci.yml/badge.svg" /></a>
-  <a href="https://github.com/rustfs/rustfs/actions/workflows/docker.yml"><img alt="Build and Push Docker Images" src="https://github.com/rustfs/rustfs/actions/workflows/docker.yml/badge.svg" /></a>
-  <img alt="GitHub commit activity" src="https://img.shields.io/github/commit-activity/m/rustfs/rustfs"/>
-  <img alt="Github Last Commit" src="https://img.shields.io/github/last-commit/rustfs/rustfs"/>
+  <a href="https://github.com/rustfs/rustfs/actions/workflows/docker.yml"><img alt="构建并推送 Docker 镜像" src="https://github.com/rustfs/rustfs/actions/workflows/docker.yml/badge.svg" /></a>
+  <img alt="GitHub 提交活跃度" src="https://img.shields.io/github/commit-activity/m/rustfs/rustfs"/>
+  <img alt="Github 最新提交" src="https://img.shields.io/github/last-commit/rustfs/rustfs"/>
   <a href="https://hellogithub.com/repository/rustfs/rustfs" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=b95bcb72bdc340b68f16fdf6790b7d5b&claim_uid=MsbvjYeLDKAH457&theme=small" alt="Featured｜HelloGitHub" /></a>
-</p >
+</p>
 
 <p align="center">
-  <a href="https://docs.rustfs.com/zh/introduction.html">快速开始</a >
-  · <a href="https://docs.rustfs.com/zh/">文档</a >
-  · <a href="https://github.com/rustfs/rustfs/issues">问题报告</a >
-  · <a href="https://github.com/rustfs/rustfs/discussions">讨论</a >
-</p >
+  <a href="https://docs.rustfs.com/installation/">快速开始</a>
+  · <a href="https://docs.rustfs.com/">文档</a>
+  · <a href="https://github.com/rustfs/rustfs/issues">报告 Bug</a>
+  · <a href="https://github.com/rustfs/rustfs/discussions">社区讨论</a>
+</p>
 
 <p align="center">
-<a href="https://github.com/rustfs/rustfs/blob/main/README.md">English</a > | 简体中文
-</p >
+  <a href="https://github.com/rustfs/rustfs/blob/main/README.md">English</a> | 简体中文 |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=de">Deutsch</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=es">Español</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=fr">français</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=ja">日本語</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=ko">한국어</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=pt">Portuguese</a> |
+  <a href="https://readme-i18n.com/rustfs/rustfs?lang=ru">Русский</a>
+</p>
 
-RustFS 是一个使用 Rust（全球最受欢迎的编程语言之一）构建的高性能分布式对象存储软件。与 MinIO 一样，它具有简单性、S3 兼容性、开源特性以及对数据湖、AI 和大数据的支持等一系列优势。此外，与其他存储系统相比，它采用 Apache 许可证构建，拥有更好、更用户友好的开源许可证。由于以 Rust 为基础，RustFS 为高性能对象存储提供了更快的速度和更安全的分布式功能。
+RustFS 是一个基于 Rust 构建的高性能分布式对象存储系统。Rust 是全球最受开发者喜爱的编程语言之一，RustFS 完美结合了 MinIO 的简洁性与 Rust 的内存安全及高性能优势。它提供完整的 S3 兼容性，完全开源，并专为数据湖、人工智能（AI）和大数据负载进行了优化。
 
-## 特性
+与其他存储系统不同，RustFS 采用更宽松、商业友好的 Apache 2.0 许可证，避免了 AGPL 协议的限制。以 Rust 为基石，RustFS 为下一代对象存储提供了更快的速度和更安全的分布式特性。
 
-- **高性能**：使用 Rust 构建，确保速度和效率。
+## 特征和功能状态
+
+- **高性能**：基于 Rust 构建，确保极致的速度和资源效率。
 - **分布式架构**：可扩展且容错的设计，适用于大规模部署。
-- **S3 兼容性**：与现有 S3 兼容应用程序无缝集成。
-- **数据湖支持**：针对大数据和 AI 工作负载进行了优化。
-- **开源**：采用 Apache 2.0 许可证，鼓励社区贡献和透明度。
-- **用户友好**：设计简单，易于部署和管理。
+- **S3 兼容性**：与现有的 S3 兼容应用和工具无缝集成。
+- **数据湖支持**：专为高吞吐量的大数据和 AI 工作负载优化。
+- **完全开源**：采用 Apache 2.0 许可证，鼓励社区贡献和商业使用。
+- **简单易用**：设计简洁，易于部署和管理。
 
-## RustFS vs MinIO
 
-压力测试服务器参数
+| 功能 | 状态 |   功能 | 状态 | 
+| :--- | :--- | :--- | :--- |
+| **S3 核心功能** | ✅ 可用 |    **Bitrot (防数据腐烂)** | ✅ 可用 |
+| **上传 / 下载** | ✅ 可用 |     **单机模式** | ✅ 可用 |
+| **版本控制** | ✅ 可用 | **存储桶复制** | ⚠️ 部分可用 |
+| **日志功能** | ✅ 可用 |  **生命周期管理** | 🚧 测试中 |
+| **事件通知** | ✅ 可用 |  **分布式模式** | 🚧 测试中 |
+| **K8s Helm Chart** | ✅ 可用 |  **OPA (策略引擎)** | 🚧 测试中 |
 
-|  类型  |  参数   | 备注 |
-| - | - | - |
-|CPU | 2 核心 | Intel Xeon(Sapphire Rapids) Platinum 8475B , 2.7/3.2 GHz|   |
-|内存| 4GB |     |
-|网络 | 15Gbp |      |
-|驱动器  | 40GB x 4 |   IOPS 3800 / 驱动器 |
+
+
+
+## RustFS vs MinIO 性能对比
+
+**压力测试环境参数：**
+
+| 类型    | 参数 | 备注                                                   |
+|---------|-----------|----------------------------------------------------------|
+| CPU     | 2 核    | Intel Xeon (Sapphire Rapids) Platinum 8475B , 2.7/3.2 GHz |
+| 内存  | 4GB       |                                                          |
+| 网络 | 15Gbps     |                                                          |
+| 硬盘  | 40GB x 4  | IOPS 3800 / Drive                                       |
 
 <https://github.com/user-attachments/assets/2e4979b5-260c-4f2c-ac12-c87fd558072a>
 
 ### RustFS vs 其他对象存储
 
-| RustFS | 其他对象存储|
-| - | - |
-| 强大的控制台 | 简单且无用的控制台 |
-| 基于 Rust 语言开发，内存更安全 | 使用 Go 或 C 开发，存在内存 GC/泄漏等潜在问题 |
-| 不向第三方国家报告日志  | 向其他第三方国家报告日志可能违反国家安全法律 |
-| 采用 Apache 许可证，对商业更友好  | AGPL V3 许可证等其他许可证，污染开源和许可证陷阱，侵犯知识产权 |
-| 全面的 S3 支持，适用于国内外云提供商  | 完全支持 S3，但不支持本地云厂商 |
-| 基于 Rust 开发，对安全和创新设备有强大支持  | 对边缘网关和安全创新设备支持较差|
-| 稳定的商业价格，免费社区支持 | 高昂的定价，1PiB 成本高达 $250,000 |
-| 无风险 | 知识产权风险和禁止使用的风险 |
+| 特性 | RustFS | 其他对象存储 |
+| :--- | :--- | :--- |
+| **控制台体验** | **功能强大的控制台**<br>提供全面的管理界面。 | **基础/简陋的控制台**<br>通常功能过于简单或缺失关键特性。 |
+| **语言与安全** | **基于 Rust 开发**<br>天生的内存安全。 | **基于 Go 或 C 开发**<br>存在内存 GC 停顿或内存泄漏的潜在风险。 |
+| **数据主权** | **无遥测 / 完全合规**<br>防止未经授权的数据跨境传输。完全符合 GDPR (欧盟/英国)、CCPA (美国) 和 APPI (日本) 等法规。 | **潜在风险**<br>可能存在法律风险和隐蔽的数据遥测（Telemetry）。 |
+| **开源协议** | **宽松的 Apache 2.0**<br>商业友好，无“毒丸”条款。 | **受限的 AGPL v3**<br>存在许可证陷阱和知识产权污染的风险。 |
+| **兼容性** | **100% S3 兼容**<br>适用于任何云提供商和客户端，随处运行。 | **兼容性不一**<br>虽然支持 S3，但可能缺乏对本地云厂商或特定 API 的支持。 |
+| **边缘与 IoT** | **强大的边缘支持**<br>非常适合安全、创新的边缘设备。 | **边缘支持较弱**<br>对于边缘网关来说通常过于沉重。 |
+| **成本** | **稳定且免费**<br>免费社区支持，稳定的商业定价。 | **高昂成本**<br>1PiB 的成本可能高达 250,000 美元。 |
+| **风险控制** | **企业级风险规避**<br>清晰的知识产权，商业使用安全无忧。 | **法律风险**<br>知识产权归属模糊及使用限制风险。 |
 
 ## 快速开始
 
-要开始使用 RustFS，请按照以下步骤操作：
+请按照以下步骤快速上手 RustFS：
 
-1. **一键脚本快速启动 (方案一)**
-
-   ```bash
-   curl -O  https://rustfs.com/install_rustfs.sh && bash install_rustfs.sh
-   ```
-
-2. **Docker快速启动（方案二）**
+### 1. 一键安装脚本 (选项 1)
 
   ```bash
-   docker run -d -p 9000:9000  -v /data:/data rustfs/rustfs
-   ```
+  curl -O https://rustfs.com/install_rustfs.sh && bash install_rustfs.sh
+````
 
-3. **访问控制台**：打开 Web 浏览器并导航到 `http://localhost:9000` 以访问 RustFS 控制台，默认的用户名和密码是 `rustfsadmin` 。
-4. **创建存储桶**：使用控制台为您的对象创建新的存储桶。
-5. **上传对象**：您可以直接通过控制台上传文件，或使用 S3 兼容的 API 与您的 RustFS 实例交互。
+### 2\. Docker 快速启动 (选项 2)
+
+RustFS 容器以非 root 用户 `rustfs` (UID `10001`) 运行。如果您使用 Docker 的 `-v` 参数挂载宿主机目录，请务必确保宿主机目录的所有者已更改为 `1000`，否则会遇到权限拒绝错误。
+
+```bash
+ # 创建数据和日志目录
+ mkdir -p data logs
+
+ # 更改这两个目录的所有者
+ chown -R 10001:10001 data logs
+
+ # 使用最新版本运行
+ docker run -d -p 9000:9000 -p 9001:9001 -v $(pwd)/data:/data -v $(pwd)/logs:/logs rustfs/rustfs:latest
+
+ # 使用指定版本运行
+ docker run -d -p 9000:9000 -p 9001:9001 -v $(pwd)/data:/data -v $(pwd)/logs:/logs rustfs/rustfs:1.0.0.alpha.68
+```
+
+您也可以使用 Docker Compose。使用根目录下的 `docker-compose.yml` 文件：
+
+```bash
+docker compose --profile observability up -d
+```
+
+**注意**: 我们建议您在运行前查看 `docker-compose.yaml` 文件。该文件定义了包括 Grafana、Prometheus 和 Jaeger 在内的多个服务，有助于 RustFS 的可观测性监控。如果您还想启动 Redis 或 Nginx 容器，可以指定相应的 profile。
+
+### 3\. 源码编译 (选项 3) - 进阶用户
+
+适用于希望从源码构建支持多架构 RustFS Docker 镜像的开发者：
+
+```bash
+# 在本地构建多架构镜像
+./docker-buildx.sh --build-arg RELEASE=latest
+
+# 构建并推送到仓库
+./docker-buildx.sh --push
+
+# 构建指定版本
+./docker-buildx.sh --release v1.0.0 --push
+
+# 构建并推送到自定义仓库
+./docker-buildx.sh --registry your-registry.com --namespace yourname --push
+```
+
+`docker-buildx.sh` 脚本支持：
+\- **多架构构建**: `linux/amd64`, `linux/arm64`
+\- **自动版本检测**: 使用 git tags 或 commit hash
+\- **灵活的仓库支持**: 支持 Docker Hub, GitHub Container Registry 等
+\- **构建优化**: 包含缓存和并行构建
+
+为了方便起见，您也可以使用 Make 命令：
+
+```bash
+make docker-buildx                    # 本地构建
+make docker-buildx-push               # 构建并推送
+make docker-buildx-version VERSION=v1.0.0  # 构建指定版本
+make help-docker                      # 显示所有 Docker 相关命令
+```
+
+> **注意 (macOS 交叉编译)**: macOS 默认的 `ulimit -n` 限制为 256，因此在使用 `cargo zigbuild` 或 `./build-rustfs.sh --platform ...` 交叉编译 Linux 版本时，可能会因 `ProcessFdQuotaExceeded` 失败。构建脚本会尝试自动提高限制，但如果您仍然看到警告，请在构建前在终端运行 `ulimit -n 4096` (或更高)。
+
+### 4\. 使用 Helm Chart 安装 (选项 4) - 云原生环境
+
+请按照 [Helm Chart README](https://charts.rustfs.com) 上的说明在 Kubernetes 集群上安装 RustFS。
+
+-----
+
+### 访问 RustFS
+
+5.  **访问控制台**: 打开浏览器并访问 `http://localhost:9000` 进入 RustFS 控制台。
+      * 默认账号/密码: `rustfsadmin` / `rustfsadmin`
+6.  **创建存储桶**: 使用控制台为您​​的对象创建一个新的存储桶 (Bucket)。
+7.  **上传对象**: 您可以直接通过控制台上传文件，或使用 S3 兼容的 API/客户端与您的 RustFS 实例进行交互。
+
+**注意**: 如果您希望通过 `https` 访问 RustFS 实例，请参考 [TLS 配置文档](https://docs.rustfs.com/integration/tls-configured.html)。
 
 ## 文档
 
-有关详细文档，包括配置选项、API 参考和高级用法，请访问我们的[文档](https://docs.rustfs.com)。
+有关详细文档，包括配置选项、API 参考和高级用法，请访问我们的 [官方文档](https://docs.rustfs.com)。
 
 ## 获取帮助
 
-如果您有任何问题或需要帮助，您可以：
+如果您有任何问题或需要帮助：
 
-- 查看[常见问题解答](https://github.com/rustfs/rustfs/discussions/categories/q-a)以获取常见问题和解决方案。
-- 加入我们的 [GitHub 讨论](https://github.com/rustfs/rustfs/discussions)来提问和分享您的经验。
-- 在我们的 [GitHub Issues](https://github.com/rustfs/rustfs/issues) 页面上开启问题，报告错误或功能请求。
+  - 查看 [FAQ](https://github.com/rustfs/rustfs/discussions/categories/q-a) 寻找常见问题和解决方案。
+  - 加入我们的 [GitHub Discussions](https://github.com/rustfs/rustfs/discussions) 提问并分享您的经验。
+  - 在我们的 [GitHub Issues](https://github.com/rustfs/rustfs/issues) 页面提交 Bug 报告或功能请求。
 
 ## 链接
 
-- [文档](https://docs.rustfs.com) - 您应该阅读的手册
-- [更新日志](https://docs.rustfs.com/changelog) - 我们破坏和修复的内容
-- [GitHub 讨论](https://github.com/rustfs/rustfs/discussions) - 社区所在地
+  - [官方文档](https://docs.rustfs.com) - 必读手册
+  - [更新日志](https://github.com/rustfs/rustfs/releases) - 版本变更记录
+  - [社区讨论](https://github.com/rustfs/rustfs/discussions) - 社区交流地
 
-## 联系
+## 联系方式
 
-- **错误报告**：[GitHub Issues](https://github.com/rustfs/rustfs/issues)
-- **商务合作**：<hello@rustfs.com>
-- **招聘**：<jobs@rustfs.com>
-- **一般讨论**：[GitHub 讨论](https://github.com/rustfs/rustfs/discussions)
-- **贡献**：[CONTRIBUTING.md](CONTRIBUTING.md)
+  - **Bug 反馈**: [GitHub Issues](https://github.com/rustfs/rustfs/issues)
+  - **商务合作**: [hello@rustfs.com](mailto:hello@rustfs.com)
+  - **工作机会**: [jobs@rustfs.com](mailto:jobs@rustfs.com)
+  - **一般讨论**: [GitHub Discussions](https://github.com/rustfs/rustfs/discussions)
+  - **贡献指南**: [CONTRIBUTING.md](https://www.google.com/search?q=CONTRIBUTING.md)
 
 ## 贡献者
 
-RustFS 是一个社区驱动的项目，我们感谢所有的贡献。查看[贡献者](https://github.com/rustfs/rustfs/graphs/contributors)页面，了解帮助 RustFS 变得更好的杰出人员。
+RustFS 是一个社区驱动的项目，我们感谢所有的贡献。请查看 [贡献者](https://github.com/rustfs/rustfs/graphs/contributors) 页面，看看那些让 RustFS 变得更好的了不起的人们。
 
 <a href="https://github.com/rustfs/rustfs/graphs/contributors">
-  <img src="https://opencollective.com/rustfs/contributors.svg?width=890&limit=500&button=false" />
-</a >
+<img src="https://opencollective.com/rustfs/contributors.svg?width=890&limit=500&button=false" alt="Contributors" />
+</a>
+
+## Github Trending Top
+
+🚀 RustFS 深受全球开源爱好者和企业用户的喜爱，经常荣登 GitHub Trending 榜单。
+
+<a href="https://trendshift.io/repositories/14181" target="_blank"><img src="https://raw.githubusercontent.com/rustfs/rustfs/refs/heads/main/docs/rustfs-trending.jpg" alt="rustfs%2Frustfs | Trendshift" /></a>
+
+## Star 历史
+
+[![Star History Chart](https://api.star-history.com/svg?repos=rustfs/rustfs&type=date&legend=top-left)](https://www.star-history.com/#rustfs/rustfs&type=date&legend=top-left)
+
 
 ## 许可证
 
 [Apache 2.0](https://opensource.org/licenses/Apache-2.0)
 
 **RustFS** 是 RustFS, Inc. 的商标。所有其他商标均为其各自所有者的财产。
+

build-rustfs.sh

@@ -163,6 +163,35 @@ print_message() {
     echo -e "${color}${message}${NC}"
 }
 
+# Prevent zig/ld from hitting macOS file descriptor defaults during linking
+ensure_file_descriptor_limit() {
+    local required_limit=4096
+    local current_limit
+    current_limit=$(ulimit -Sn 2>/dev/null || echo "")
+
+    if [ -z "$current_limit" ] || [ "$current_limit" = "unlimited" ]; then
+        return
+    fi
+
+    if (( current_limit >= required_limit )); then
+        return
+    fi
+
+    local hard_limit target_limit
+    hard_limit=$(ulimit -Hn 2>/dev/null || echo "")
+    target_limit=$required_limit
+
+    if [ -n "$hard_limit" ] && [ "$hard_limit" != "unlimited" ] && (( hard_limit < required_limit )); then
+        target_limit=$hard_limit
+    fi
+
+    if ulimit -Sn "$target_limit" 2>/dev/null; then
+        print_message $YELLOW "🔧 Increased open file limit from $current_limit to $target_limit to avoid ProcessFdQuotaExceeded"
+    else
+        print_message $YELLOW "⚠️ Unable to raise ulimit -n automatically (current: $current_limit, needed: $required_limit). Please run 'ulimit -n $required_limit' manually before building."
+    fi
+}
+
 # Get version from git
 get_version() {
     if git describe --abbrev=0 --tags >/dev/null 2>&1; then
@@ -570,10 +599,11 @@ main() {
         fi
     fi
 
+    ensure_file_descriptor_limit
+
     # Start build process
     build_rustfs
 }
 
 # Run main function
 main
-

cli/rustfs-gui/Cargo.toml

@@ -1,46 +0,0 @@
-# Copyright 2024 RustFS Team
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-
-[package]
-name = "rustfs-gui"
-edition.workspace = true
-license.workspace = true
-repository.workspace = true
-rust-version.workspace = true
-version.workspace = true
-
-[dependencies]
-chrono = { workspace = true }
-dioxus = { workspace = true, features = ["router"] }
-dirs = { workspace = true }
-hex = { workspace = true }
-keyring = { workspace = true }
-rfd = { workspace = true }
-rust-embed = { workspace = true, features = ["interpolate-folder-path"] }
-rust-i18n = { workspace = true }
-serde = { workspace = true }
-serde_json = { workspace = true }
-sha2 = { workspace = true }
-tokio = { workspace = true, features = ["io-util", "net", "process", "sync"] }
-tracing-subscriber = { workspace = true, features = ["fmt", "env-filter", "tracing-log", "time", "local-time", "json"] }
-tracing-appender = { workspace = true }
-
-[features]
-default = ["desktop"]
-web = ["dioxus/web"]
-desktop = ["dioxus/desktop"]
-mobile = ["dioxus/mobile"]
-
-[lints]
-workspace = true

cli/rustfs-gui/Dioxus.toml

@@ -1,52 +0,0 @@
-[application]
-
-# App (Project) Name
-name = "rustfs-gui"
-
-# The static resource path
-asset_dir = "public"
-
-[web.app]
-
-# HTML title tag content
-title = "rustfs-gui"
-
-# include `assets` in web platform
-[web.resource]
-
-# Additional CSS style files
-style = []
-
-# Additional JavaScript files
-script = []
-
-[web.resource.dev]
-
-# Javascript code file
-# serve: [dev-server] only
-script = []
-
-[bundle]
-identifier = "com.rustfs.cli.gui"
-
-publisher = "RustFsGUI"
-
-category = "Utility"
-
-copyright = "Copyright 2025 rustfs.com"
-
-icon = [
-    "assets/icons/icon.icns",
-    "assets/icons/icon.ico",
-    "assets/icons/icon.png",
-    "assets/icons/rustfs-icon.png",
-]
-#[bundle.macos]
-#provider_short_name = "RustFs"
-[bundle.windows]
-tsp = true
-icon_path = "assets/icons/icon.ico"
-allow_downgrades = true
-[bundle.windows.webview_install_mode]
-[bundle.windows.webview_install_mode.EmbedBootstrapper]
-silent = true

cli/rustfs-gui/README.md

@@ -1,34 +0,0 @@
-## Rustfs GUI
-
-### Tailwind
-
-1. Install npm: https://docs.npmjs.com/downloading-and-installing-node-js-and-npm
-2. Install the Tailwind CSS CLI: https://tailwindcss.com/docs/installation
-3. Run the following command in the root of the project to start the Tailwind CSS compiler:
-
-```bash
-npx tailwindcss -i ./input.css -o ./assets/tailwind.css --watch
-```
-
-### Dioxus CLI
-
-#### Install the stable version (recommended)
-
-```shell
-cargo install dioxus-cli
-```
-
-### Serving Your App
-
-Run the following command in the root of your project to start developing with the default platform:
-
-```bash
-dx serve
-```
-
-To run for a different platform, use the `--platform platform` flag. E.g.
-
-```bash
-dx serve --platform desktop
-```
-

cli/rustfs-gui/assets/js/sts.js

@@ -1,48 +0,0 @@
-/**
- * Copyright 2024 RustFS Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-window.switchTab = function (tabId) {
-    // Hide everything
-    document.querySelectorAll('.tab-content').forEach(content => {
-        content.classList.add('hidden');
-    });
-
-    // Reset all label styles
-    document.querySelectorAll('.tab-btn').forEach(btn => {
-        btn.classList.remove('border-b-2', 'border-black');
-        btn.classList.add('text-gray-500');
-    });
-
-    // Displays the selected content
-    const activeContent = document.getElementById(tabId);
-    if (activeContent) {
-        activeContent.classList.remove('hidden');
-    }
-
-    // Updates the selected label style
-    const activeBtn = document.querySelector(`[data-tab="${tabId}"]`);
-    if (activeBtn) {
-        activeBtn.classList.add('border-b-2', 'border-black');
-        activeBtn.classList.remove('text-gray-500');
-    }
-};
-
-window.togglePassword = function (button) {
-    const input = button.parentElement.querySelector('input[type="password"], input[type="text"]');
-    if (input) {
-        input.type = input.type === 'password' ? 'text' : 'password';
-    }
-};

cli/rustfs-gui/assets/rustfs-logo.svg

@@ -1,15 +0,0 @@
-<svg width="1558" height="260" viewBox="0 0 1558 260" fill="none" xmlns="http://www.w3.org/2000/svg">
-<g clip-path="url(#clip0_0_3)">
-<path d="M1288.5 112.905H1159.75V58.4404H1262L1270 0L1074 0V260H1159.75V162.997H1296.95L1288.5 112.905Z" fill="#0196D0"/>
-<path d="M1058.62 58.4404V0H789V58.4404H881.133V260H966.885V58.4404H1058.62Z" fill="#0196D0"/>
-<path d="M521 179.102V0L454.973 15V161C454.973 181.124 452.084 193.146 443.5 202C434.916 211.257 419.318 214.5 400.5 214.5C381.022 214.5 366.744 210.854 357.5 202C348.916 193.548 346.357 175.721 346.357 156V0L280 15V175.48C280 208.08 290.234 229.412 309.712 241.486C329.19 253.56 358.903 260 400.5 260C440.447 260 470.159 253.56 490.297 241.486C510.766 229.412 521 208.483 521 179.102Z" fill="#0196D0"/>
-<path d="M172.84 84.2813C172.84 97.7982 168.249 107.737 158.41 113.303C149.883 118.471 137.092 121.254 120.693 122.049V162.997C129.876 163.792 138.076 166.177 144.307 176.514L184.647 260H265L225.316 180.489C213.181 155.046 201.374 149.48 178.744 143.517C212.197 138.349 241.386 118.471 241.386 73.1499C241.386 53.2722 233.843 30.2141 218.756 17.8899C203.998 5.56575 183.991 0 159.394 0H120.693V48.5015H127.58C142.23 48.5015 153.6 51.4169 161.689 57.2477C169.233 62.8135 172.84 71.5596 172.84 84.2813ZM120.693 122.049C119.163 122.049 117.741 122.049 116.43 122.049H68.5457V48.5015H120.693V0H0V260H70.5137V162.997H110.526C113.806 162.997 117.741 162.997 120.693 162.997V122.049Z" fill="#0196D0"/>
-<path d="M774 179.297C774 160.829 766.671 144.669 752.013 131.972C738.127 119.66 712.025 110.169 673.708 103.5C662.136 101.191 651.722 99.6523 643.235 97.3437C586.532 84.6467 594.632 52.7118 650.564 52.7118C680.651 52.7118 709.582 61.946 738.127 66.9478C742.37 67.7174 743.913 68.1021 744.298 68.1021L750.47 12.697C720.383 3.46282 684.895 0 654.036 0C616.619 0 587.689 6.54088 567.245 19.2379C546.801 31.9349 536 57.7137 536 82.3382C536 103.5 543.715 119.66 559.916 131.972C575.731 143.515 604.276 152.749 645.55 160.059C658.279 162.368 668.694 163.907 676.794 166.215C685.023 168.524 691.066 170.704 694.924 172.756C702.253 176.604 706.11 182.375 706.11 188.531C706.11 196.611 701.481 202.767 692.224 207C664.836 220.081 587.689 212.001 556.83 198.15L543.715 247.784C547.186 248.169 552.972 249.323 559.916 250.477C616.619 259.327 690.681 270.869 741.212 238.935C762.814 225.468 774 206.23 774 179.297Z" fill="#0196D0"/>
-<path d="M1558 179.568C1558 160.383 1550.42 144.268 1535.67 131.99C1521.32 119.968 1494.34 110.631 1454.74 103.981C1442.38 101.679 1432.01 99.3764 1422.84 97.8416C1422.44 97.8416 1422.04 97.8416 1422.04 97.4579V112.422L1361.04 75.2038L1422.04 38.3692V52.9496C1424.7 52.9496 1427.49 52.9496 1430.41 52.9496C1461.51 52.9496 1491.42 62.5419 1521.32 67.5299C1525.31 67.9136 1526.9 67.9136 1527.3 67.9136L1533.68 12.6619C1502.98 3.83692 1465.9 0 1434 0C1395.33 0 1365.43 6.52277 1345.09 19.5683C1323.16 32.6139 1312 57.9376 1312 82.8776C1312 103.981 1320.37 120.096 1336.72 131.607C1353.46 143.885 1382.97 153.093 1425.23 160.383C1434 161.535 1441.18 162.686 1447.56 164.22L1448.36 150.791L1507.36 190.312L1445.57 224.844L1445.96 212.949C1409.68 215.635 1357.45 209.112 1333.53 197.985L1320.37 247.482C1323.56 248.249 1329.54 248.633 1336.72 250.551C1395.33 259.376 1471.88 270.887 1524.11 238.657C1546.84 225.611 1558 205.659 1558 179.568Z" fill="#0196D0"/>
-</g>
-<defs>
-<clipPath id="clip0_0_3">
-<rect width="1558" height="260" fill="white"/>
-</clipPath>
-</defs>
-</svg>

cli/rustfs-gui/assets/styling/navbar.css

@@ -1,33 +0,0 @@
-/**
- * Copyright 2024 RustFS Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-#navbar {
-    display: flex;
-    flex-direction: row;
-}
-
-#navbar a {
-    color: #ffffff;
-    margin-right: 20px;
-    text-decoration: none;
-    transition: color 0.2s ease;
-}
-
-#navbar a:hover {
-    cursor: pointer;
-    color: #ffffff;
-/ / #91a4d2;
-}

cli/rustfs-gui/assets/tailwind.css

@@ -1,972 +0,0 @@
-/**
- * Copyright 2024 RustFS Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-*, ::before, ::after {
-  --tw-border-spacing-x: 0;
-  --tw-border-spacing-y: 0;
-  --tw-translate-x: 0;
-  --tw-translate-y: 0;
-  --tw-rotate: 0;
-  --tw-skew-x: 0;
-  --tw-skew-y: 0;
-  --tw-scale-x: 1;
-  --tw-scale-y: 1;
-  --tw-pan-x:  ;
-  --tw-pan-y:  ;
-  --tw-pinch-zoom:  ;
-  --tw-scroll-snap-strictness: proximity;
-  --tw-gradient-from-position:  ;
-  --tw-gradient-via-position:  ;
-  --tw-gradient-to-position:  ;
-  --tw-ordinal:  ;
-  --tw-slashed-zero:  ;
-  --tw-numeric-figure:  ;
-  --tw-numeric-spacing:  ;
-  --tw-numeric-fraction:  ;
-  --tw-ring-inset:  ;
-  --tw-ring-offset-width: 0px;
-  --tw-ring-offset-color: #fff;
-  --tw-ring-color: rgb(59 130 246 / 0.5);
-  --tw-ring-offset-shadow: 0 0 #0000;
-  --tw-ring-shadow: 0 0 #0000;
-  --tw-shadow: 0 0 #0000;
-  --tw-shadow-colored: 0 0 #0000;
-  --tw-blur:  ;
-  --tw-brightness:  ;
-  --tw-contrast:  ;
-  --tw-grayscale:  ;
-  --tw-hue-rotate:  ;
-  --tw-invert:  ;
-  --tw-saturate:  ;
-  --tw-sepia:  ;
-  --tw-drop-shadow:  ;
-  --tw-backdrop-blur:  ;
-  --tw-backdrop-brightness:  ;
-  --tw-backdrop-contrast:  ;
-  --tw-backdrop-grayscale:  ;
-  --tw-backdrop-hue-rotate:  ;
-  --tw-backdrop-invert:  ;
-  --tw-backdrop-opacity:  ;
-  --tw-backdrop-saturate:  ;
-  --tw-backdrop-sepia:  ;
-  --tw-contain-size:  ;
-  --tw-contain-layout:  ;
-  --tw-contain-paint:  ;
-  --tw-contain-style:  ;
-}
-
-::backdrop {
-  --tw-border-spacing-x: 0;
-  --tw-border-spacing-y: 0;
-  --tw-translate-x: 0;
-  --tw-translate-y: 0;
-  --tw-rotate: 0;
-  --tw-skew-x: 0;
-  --tw-skew-y: 0;
-  --tw-scale-x: 1;
-  --tw-scale-y: 1;
-  --tw-pan-x:  ;
-  --tw-pan-y:  ;
-  --tw-pinch-zoom:  ;
-  --tw-scroll-snap-strictness: proximity;
-  --tw-gradient-from-position:  ;
-  --tw-gradient-via-position:  ;
-  --tw-gradient-to-position:  ;
-  --tw-ordinal:  ;
-  --tw-slashed-zero:  ;
-  --tw-numeric-figure:  ;
-  --tw-numeric-spacing:  ;
-  --tw-numeric-fraction:  ;
-  --tw-ring-inset:  ;
-  --tw-ring-offset-width: 0px;
-  --tw-ring-offset-color: #fff;
-  --tw-ring-color: rgb(59 130 246 / 0.5);
-  --tw-ring-offset-shadow: 0 0 #0000;
-  --tw-ring-shadow: 0 0 #0000;
-  --tw-shadow: 0 0 #0000;
-  --tw-shadow-colored: 0 0 #0000;
-  --tw-blur:  ;
-  --tw-brightness:  ;
-  --tw-contrast:  ;
-  --tw-grayscale:  ;
-  --tw-hue-rotate:  ;
-  --tw-invert:  ;
-  --tw-saturate:  ;
-  --tw-sepia:  ;
-  --tw-drop-shadow:  ;
-  --tw-backdrop-blur:  ;
-  --tw-backdrop-brightness:  ;
-  --tw-backdrop-contrast:  ;
-  --tw-backdrop-grayscale:  ;
-  --tw-backdrop-hue-rotate:  ;
-  --tw-backdrop-invert:  ;
-  --tw-backdrop-opacity:  ;
-  --tw-backdrop-saturate:  ;
-  --tw-backdrop-sepia:  ;
-  --tw-contain-size:  ;
-  --tw-contain-layout:  ;
-  --tw-contain-paint:  ;
-  --tw-contain-style:  ;
-}
-
-/*
-! tailwindcss v3.4.17 | MIT License | https://tailwindcss.com
-*/
-
-/*
-1. Prevent padding and border from affecting element width. (https://github.com/mozdevs/cssremedy/issues/4)
-2. Allow adding a border to an element by just adding a border-width. (https://github.com/tailwindcss/tailwindcss/pull/116)
-*/
-
-*,
-::before,
-::after {
-  box-sizing: border-box;
-  /* 1 */
-  border-width: 0;
-  /* 2 */
-  border-style: solid;
-  /* 2 */
-  border-color: #e5e7eb;
-  /* 2 */
-}
-
-::before,
-::after {
-  --tw-content: '';
-}
-
-/*
-1. Use a consistent sensible line-height in all browsers.
-2. Prevent adjustments of font size after orientation changes in iOS.
-3. Use a more readable tab size.
-4. Use the user's configured `sans` font-family by default.
-5. Use the user's configured `sans` font-feature-settings by default.
-6. Use the user's configured `sans` font-variation-settings by default.
-7. Disable tap highlights on iOS
-*/
-
-html,
-:host {
-  line-height: 1.5;
-  /* 1 */
-  -webkit-text-size-adjust: 100%;
-  /* 2 */
-  -moz-tab-size: 4;
-  /* 3 */
-  -o-tab-size: 4;
-     tab-size: 4;
-  /* 3 */
-  font-family: ui-sans-serif, system-ui, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji";
-  /* 4 */
-  font-feature-settings: normal;
-  /* 5 */
-  font-variation-settings: normal;
-  /* 6 */
-  -webkit-tap-highlight-color: transparent;
-  /* 7 */
-}
-
-/*
-1. Remove the margin in all browsers.
-2. Inherit line-height from `html` so users can set them as a class directly on the `html` element.
-*/
-
-body {
-  margin: 0;
-  /* 1 */
-  line-height: inherit;
-  /* 2 */
-}
-
-/*
-1. Add the correct height in Firefox.
-2. Correct the inheritance of border color in Firefox. (https://bugzilla.mozilla.org/show_bug.cgi?id=190655)
-3. Ensure horizontal rules are visible by default.
-*/
-
-hr {
-  height: 0;
-  /* 1 */
-  color: inherit;
-  /* 2 */
-  border-top-width: 1px;
-  /* 3 */
-}
-
-/*
-Add the correct text decoration in Chrome, Edge, and Safari.
-*/
-
-abbr:where([title]) {
-  -webkit-text-decoration: underline dotted;
-          text-decoration: underline dotted;
-}
-
-/*
-Remove the default font size and weight for headings.
-*/
-
-h1,
-h2,
-h3,
-h4,
-h5,
-h6 {
-  font-size: inherit;
-  font-weight: inherit;
-}
-
-/*
-Reset links to optimize for opt-in styling instead of opt-out.
-*/
-
-a {
-  color: inherit;
-  text-decoration: inherit;
-}
-
-/*
-Add the correct font weight in Edge and Safari.
-*/
-
-b,
-strong {
-  font-weight: bolder;
-}
-
-/*
-1. Use the user's configured `mono` font-family by default.
-2. Use the user's configured `mono` font-feature-settings by default.
-3. Use the user's configured `mono` font-variation-settings by default.
-4. Correct the odd `em` font sizing in all browsers.
-*/
-
-code,
-kbd,
-samp,
-pre {
-  font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;
-  /* 1 */
-  font-feature-settings: normal;
-  /* 2 */
-  font-variation-settings: normal;
-  /* 3 */
-  font-size: 1em;
-  /* 4 */
-}
-
-/*
-Add the correct font size in all browsers.
-*/
-
-small {
-  font-size: 80%;
-}
-
-/*
-Prevent `sub` and `sup` elements from affecting the line height in all browsers.
-*/
-
-sub,
-sup {
-  font-size: 75%;
-  line-height: 0;
-  position: relative;
-  vertical-align: baseline;
-}
-
-sub {
-  bottom: -0.25em;
-}
-
-sup {
-  top: -0.5em;
-}
-
-/*
-1. Remove text indentation from table contents in Chrome and Safari. (https://bugs.chromium.org/p/chromium/issues/detail?id=999088, https://bugs.webkit.org/show_bug.cgi?id=201297)
-2. Correct table border color inheritance in all Chrome and Safari. (https://bugs.chromium.org/p/chromium/issues/detail?id=935729, https://bugs.webkit.org/show_bug.cgi?id=195016)
-3. Remove gaps between table borders by default.
-*/
-
-table {
-  text-indent: 0;
-  /* 1 */
-  border-color: inherit;
-  /* 2 */
-  border-collapse: collapse;
-  /* 3 */
-}
-
-/*
-1. Change the font styles in all browsers.
-2. Remove the margin in Firefox and Safari.
-3. Remove default padding in all browsers.
-*/
-
-button,
-input,
-optgroup,
-select,
-textarea {
-  font-family: inherit;
-  /* 1 */
-  font-feature-settings: inherit;
-  /* 1 */
-  font-variation-settings: inherit;
-  /* 1 */
-  font-size: 100%;
-  /* 1 */
-  font-weight: inherit;
-  /* 1 */
-  line-height: inherit;
-  /* 1 */
-  letter-spacing: inherit;
-  /* 1 */
-  color: inherit;
-  /* 1 */
-  margin: 0;
-  /* 2 */
-  padding: 0;
-  /* 3 */
-}
-
-/*
-Remove the inheritance of text transform in Edge and Firefox.
-*/
-
-button,
-select {
-  text-transform: none;
-}
-
-/*
-1. Correct the inability to style clickable types in iOS and Safari.
-2. Remove default button styles.
-*/
-
-button,
-input:where([type='button']),
-input:where([type='reset']),
-input:where([type='submit']) {
-  -webkit-appearance: button;
-  /* 1 */
-  background-color: transparent;
-  /* 2 */
-  background-image: none;
-  /* 2 */
-}
-
-/*
-Use the modern Firefox focus style for all focusable elements.
-*/
-
-:-moz-focusring {
-  outline: auto;
-}
-
-/*
-Remove the additional `:invalid` styles in Firefox. (https://github.com/mozilla/gecko-dev/blob/2f9eacd9d3d995c937b4251a5557d95d494c9be1/layout/style/res/forms.css#L728-L737)
-*/
-
-:-moz-ui-invalid {
-  box-shadow: none;
-}
-
-/*
-Add the correct vertical alignment in Chrome and Firefox.
-*/
-
-progress {
-  vertical-align: baseline;
-}
-
-/*
-Correct the cursor style of increment and decrement buttons in Safari.
-*/
-
-::-webkit-inner-spin-button,
-::-webkit-outer-spin-button {
-  height: auto;
-}
-
-/*
-1. Correct the odd appearance in Chrome and Safari.
-2. Correct the outline style in Safari.
-*/
-
-[type='search'] {
-  -webkit-appearance: textfield;
-  /* 1 */
-  outline-offset: -2px;
-  /* 2 */
-}
-
-/*
-Remove the inner padding in Chrome and Safari on macOS.
-*/
-
-::-webkit-search-decoration {
-  -webkit-appearance: none;
-}
-
-/*
-1. Correct the inability to style clickable types in iOS and Safari.
-2. Change font properties to `inherit` in Safari.
-*/
-
-::-webkit-file-upload-button {
-  -webkit-appearance: button;
-  /* 1 */
-  font: inherit;
-  /* 2 */
-}
-
-/*
-Add the correct display in Chrome and Safari.
-*/
-
-summary {
-  display: list-item;
-}
-
-/*
-Removes the default spacing and border for appropriate elements.
-*/
-
-blockquote,
-dl,
-dd,
-h1,
-h2,
-h3,
-h4,
-h5,
-h6,
-hr,
-figure,
-p,
-pre {
-  margin: 0;
-}
-
-fieldset {
-  margin: 0;
-  padding: 0;
-}
-
-legend {
-  padding: 0;
-}
-
-ol,
-ul,
-menu {
-  list-style: none;
-  margin: 0;
-  padding: 0;
-}
-
-/*
-Reset default styling for dialogs.
-*/
-
-dialog {
-  padding: 0;
-}
-
-/*
-Prevent resizing textareas horizontally by default.
-*/
-
-textarea {
-  resize: vertical;
-}
-
-/*
-1. Reset the default placeholder opacity in Firefox. (https://github.com/tailwindlabs/tailwindcss/issues/3300)
-2. Set the default placeholder color to the user's configured gray 400 color.
-*/
-
-input::-moz-placeholder, textarea::-moz-placeholder {
-  opacity: 1;
-  /* 1 */
-  color: #9ca3af;
-  /* 2 */
-}
-
-input::placeholder,
-textarea::placeholder {
-  opacity: 1;
-  /* 1 */
-  color: #9ca3af;
-  /* 2 */
-}
-
-/*
-Set the default cursor for buttons.
-*/
-
-button,
-[role="button"] {
-  cursor: pointer;
-}
-
-/*
-Make sure disabled buttons don't get the pointer cursor.
-*/
-
-:disabled {
-  cursor: default;
-}
-
-/*
-1. Make replaced elements `display: block` by default. (https://github.com/mozdevs/cssremedy/issues/14)
-2. Add `vertical-align: middle` to align replaced elements more sensibly by default. (https://github.com/jensimmons/cssremedy/issues/14#issuecomment-634934210)
-   This can trigger a poorly considered lint error in some tools but is included by design.
-*/
-
-img,
-svg,
-video,
-canvas,
-audio,
-iframe,
-embed,
-object {
-  display: block;
-  /* 1 */
-  vertical-align: middle;
-  /* 2 */
-}
-
-/*
-Constrain images and videos to the parent width and preserve their intrinsic aspect ratio. (https://github.com/mozdevs/cssremedy/issues/14)
-*/
-
-img,
-video {
-  max-width: 100%;
-  height: auto;
-}
-
-/* Make elements with the HTML hidden attribute stay hidden by default */
-
-[hidden]:where(:not([hidden="until-found"])) {
-  display: none;
-}
-
-.static {
-  position: static;
-}
-
-.absolute {
-  position: absolute;
-}
-
-.relative {
-  position: relative;
-}
-
-.right-2 {
-  right: 0.5rem;
-}
-
-.right-6 {
-  right: 1.5rem;
-}
-
-.top-1\/2 {
-  top: 50%;
-}
-
-.top-4 {
-  top: 1rem;
-}
-
-.z-10 {
-  z-index: 10;
-}
-
-.mb-2 {
-  margin-bottom: 0.5rem;
-}
-
-.mb-4 {
-  margin-bottom: 1rem;
-}
-
-.mb-6 {
-  margin-bottom: 1.5rem;
-}
-
-.mb-8 {
-  margin-bottom: 2rem;
-}
-
-.ml-2 {
-  margin-left: 0.5rem;
-}
-
-.flex {
-  display: flex;
-}
-
-.hidden {
-  display: none;
-}
-
-.h-16 {
-  height: 4rem;
-}
-
-.h-24 {
-  height: 6rem;
-}
-
-.h-4 {
-  height: 1rem;
-}
-
-.h-5 {
-  height: 1.25rem;
-}
-
-.h-6 {
-  height: 1.5rem;
-}
-
-.min-h-screen {
-  min-height: 100vh;
-}
-
-.w-16 {
-  width: 4rem;
-}
-
-.w-20 {
-  width: 5rem;
-}
-
-.w-24 {
-  width: 6rem;
-}
-
-.w-4 {
-  width: 1rem;
-}
-
-.w-48 {
-  width: 12rem;
-}
-
-.w-5 {
-  width: 1.25rem;
-}
-
-.w-6 {
-  width: 1.5rem;
-}
-
-.w-full {
-  width: 100%;
-}
-
-.flex-1 {
-  flex: 1 1 0%;
-}
-
-.-translate-y-1\/2 {
-  --tw-translate-y: -50%;
-  transform: translate(var(--tw-translate-x), var(--tw-translate-y)) rotate(var(--tw-rotate)) skewX(var(--tw-skew-x)) skewY(var(--tw-skew-y)) scaleX(var(--tw-scale-x)) scaleY(var(--tw-scale-y));
-}
-
-.transform {
-  transform: translate(var(--tw-translate-x), var(--tw-translate-y)) rotate(var(--tw-rotate)) skewX(var(--tw-skew-x)) skewY(var(--tw-skew-y)) scaleX(var(--tw-scale-x)) scaleY(var(--tw-scale-y));
-}
-
-@keyframes spin {
-  to {
-    transform: rotate(360deg);
-  }
-}
-
-.animate-spin {
-  animation: spin 1s linear infinite;
-}
-
-.flex-col {
-  flex-direction: column;
-}
-
-.items-center {
-  align-items: center;
-}
-
-.justify-center {
-  justify-content: center;
-}
-
-.space-x-2 > :not([hidden]) ~ :not([hidden]) {
-  --tw-space-x-reverse: 0;
-  margin-right: calc(0.5rem * var(--tw-space-x-reverse));
-  margin-left: calc(0.5rem * calc(1 - var(--tw-space-x-reverse)));
-}
-
-.space-x-4 > :not([hidden]) ~ :not([hidden]) {
-  --tw-space-x-reverse: 0;
-  margin-right: calc(1rem * var(--tw-space-x-reverse));
-  margin-left: calc(1rem * calc(1 - var(--tw-space-x-reverse)));
-}
-
-.space-x-8 > :not([hidden]) ~ :not([hidden]) {
-  --tw-space-x-reverse: 0;
-  margin-right: calc(2rem * var(--tw-space-x-reverse));
-  margin-left: calc(2rem * calc(1 - var(--tw-space-x-reverse)));
-}
-
-.space-y-4 > :not([hidden]) ~ :not([hidden]) {
-  --tw-space-y-reverse: 0;
-  margin-top: calc(1rem * calc(1 - var(--tw-space-y-reverse)));
-  margin-bottom: calc(1rem * var(--tw-space-y-reverse));
-}
-
-.space-y-6 > :not([hidden]) ~ :not([hidden]) {
-  --tw-space-y-reverse: 0;
-  margin-top: calc(1.5rem * calc(1 - var(--tw-space-y-reverse)));
-  margin-bottom: calc(1.5rem * var(--tw-space-y-reverse));
-}
-
-.rounded {
-  border-radius: 0.25rem;
-}
-
-.rounded-full {
-  border-radius: 9999px;
-}
-
-.rounded-lg {
-  border-radius: 0.5rem;
-}
-
-.rounded-md {
-  border-radius: 0.375rem;
-}
-
-.border {
-  border-width: 1px;
-}
-
-.border-b {
-  border-bottom-width: 1px;
-}
-
-.border-b-2 {
-  border-bottom-width: 2px;
-}
-
-.border-black {
-  --tw-border-opacity: 1;
-  border-color: rgb(0 0 0 / var(--tw-border-opacity, 1));
-}
-
-.border-gray-200 {
-  --tw-border-opacity: 1;
-  border-color: rgb(229 231 235 / var(--tw-border-opacity, 1));
-}
-
-.bg-\[\#111827\] {
-  --tw-bg-opacity: 1;
-  background-color: rgb(17 24 39 / var(--tw-bg-opacity, 1));
-}
-
-.bg-gray-100 {
-  --tw-bg-opacity: 1;
-  background-color: rgb(243 244 246 / var(--tw-bg-opacity, 1));
-}
-
-.bg-gray-900 {
-  --tw-bg-opacity: 1;
-  background-color: rgb(17 24 39 / var(--tw-bg-opacity, 1));
-}
-
-.bg-red-500 {
-  --tw-bg-opacity: 1;
-  background-color: rgb(239 68 68 / var(--tw-bg-opacity, 1));
-}
-
-.bg-white {
-  --tw-bg-opacity: 1;
-  background-color: rgb(255 255 255 / var(--tw-bg-opacity, 1));
-}
-
-.p-2 {
-  padding: 0.5rem;
-}
-
-.p-4 {
-  padding: 1rem;
-}
-
-.p-8 {
-  padding: 2rem;
-}
-
-.px-1 {
-  padding-left: 0.25rem;
-  padding-right: 0.25rem;
-}
-
-.px-3 {
-  padding-left: 0.75rem;
-  padding-right: 0.75rem;
-}
-
-.px-4 {
-  padding-left: 1rem;
-  padding-right: 1rem;
-}
-
-.py-0\.5 {
-  padding-top: 0.125rem;
-  padding-bottom: 0.125rem;
-}
-
-.py-2 {
-  padding-top: 0.5rem;
-  padding-bottom: 0.5rem;
-}
-
-.py-4 {
-  padding-top: 1rem;
-  padding-bottom: 1rem;
-}
-
-.py-6 {
-  padding-top: 1.5rem;
-  padding-bottom: 1.5rem;
-}
-
-.pr-10 {
-  padding-right: 2.5rem;
-}
-
-.text-2xl {
-  font-size: 1.5rem;
-  line-height: 2rem;
-}
-
-.text-base {
-  font-size: 1rem;
-  line-height: 1.5rem;
-}
-
-.text-sm {
-  font-size: 0.875rem;
-  line-height: 1.25rem;
-}
-
-.font-medium {
-  font-weight: 500;
-}
-
-.font-semibold {
-  font-weight: 600;
-}
-
-.text-blue-500 {
-  --tw-text-opacity: 1;
-  color: rgb(59 130 246 / var(--tw-text-opacity, 1));
-}
-
-.text-blue-600 {
-  --tw-text-opacity: 1;
-  color: rgb(37 99 235 / var(--tw-text-opacity, 1));
-}
-
-.text-gray-400 {
-  --tw-text-opacity: 1;
-  color: rgb(156 163 175 / var(--tw-text-opacity, 1));
-}
-
-.text-gray-500 {
-  --tw-text-opacity: 1;
-  color: rgb(107 114 128 / var(--tw-text-opacity, 1));
-}
-
-.text-gray-600 {
-  --tw-text-opacity: 1;
-  color: rgb(75 85 99 / var(--tw-text-opacity, 1));
-}
-
-.text-white {
-  --tw-text-opacity: 1;
-  color: rgb(255 255 255 / var(--tw-text-opacity, 1));
-}
-
-.opacity-25 {
-  opacity: 0.25;
-}
-
-.opacity-75 {
-  opacity: 0.75;
-}
-
-.filter {
-  filter: var(--tw-blur) var(--tw-brightness) var(--tw-contrast) var(--tw-grayscale) var(--tw-hue-rotate) var(--tw-invert) var(--tw-saturate) var(--tw-sepia) var(--tw-drop-shadow);
-}
-
-.hover\:bg-\[\#1f2937\]:hover {
-  --tw-bg-opacity: 1;
-  background-color: rgb(31 41 55 / var(--tw-bg-opacity, 1));
-}
-
-.hover\:bg-gray-100:hover {
-  --tw-bg-opacity: 1;
-  background-color: rgb(243 244 246 / var(--tw-bg-opacity, 1));
-}
-
-.hover\:bg-red-600:hover {
-  --tw-bg-opacity: 1;
-  background-color: rgb(220 38 38 / var(--tw-bg-opacity, 1));
-}
-
-.hover\:text-gray-700:hover {
-  --tw-text-opacity: 1;
-  color: rgb(55 65 81 / var(--tw-text-opacity, 1));
-}
-
-.hover\:text-gray-900:hover {
-  --tw-text-opacity: 1;
-  color: rgb(17 24 39 / var(--tw-text-opacity, 1));
-}
-
-.focus\:outline-none:focus {
-  outline: 2px solid transparent;
-  outline-offset: 2px;
-}
-
-.focus\:ring-2:focus {
-  --tw-ring-offset-shadow: var(--tw-ring-inset) 0 0 0 var(--tw-ring-offset-width) var(--tw-ring-offset-color);
-  --tw-ring-shadow: var(--tw-ring-inset) 0 0 0 calc(2px + var(--tw-ring-offset-width)) var(--tw-ring-color);
-  box-shadow: var(--tw-ring-offset-shadow), var(--tw-ring-shadow), var(--tw-shadow, 0 0 #0000);
-}
-
-.focus\:ring-blue-500:focus {
-  --tw-ring-opacity: 1;
-  --tw-ring-color: rgb(59 130 246 / var(--tw-ring-opacity, 1));
-}

cli/rustfs-gui/embedded-rustfs/README.md

@@ -1 +0,0 @@
-rustfs bin path, do not delete

cli/rustfs-gui/input.css

@@ -1,19 +0,0 @@
-/**
- * Copyright 2024 RustFS Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-@tailwind base;
-@tailwind components;
-@tailwind utilities;

cli/rustfs-gui/src/components/home.rs

@@ -1,330 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::components::navbar::LoadingSpinner;
-use crate::route::Route;
-use crate::utils::{RustFSConfig, ServiceManager};
-use chrono::Datelike;
-use dioxus::logger::tracing::debug;
-use dioxus::prelude::*;
-use std::time::Duration;
-
-const HEADER_LOGO: Asset = asset!("/assets/rustfs-logo.svg");
-const TAILWIND_CSS: Asset = asset!("/assets/tailwind.css");
-
-/// Define the state of the service
-#[derive(PartialEq, Debug, Clone)]
-enum ServiceState {
-    Start,
-    Stop,
-}
-
-/// Define the Home component
-/// The Home component is the main component of the application
-/// It is responsible for starting and stopping the service
-/// It also displays the service status and provides a button to toggle the service
-/// The Home component also displays the footer of the application
-/// The footer contains links to the official site, documentation, GitHub, and license
-/// The footer also displays the version of the application
-/// The Home component also contains a button to change the theme of the application
-/// The Home component also contains a button to go to the settings page
-#[component]
-pub fn Home() -> Element {
-    #[allow(clippy::redundant_closure)]
-    let service = use_signal(|| ServiceManager::new());
-    let conf = RustFSConfig::load().unwrap_or_else(|e| {
-        ServiceManager::show_error(&format!("load config failed: {e}"));
-        RustFSConfig::default()
-    });
-
-    debug!("loaded configurations: {:?}", conf);
-    let config = use_signal(|| conf.clone());
-
-    use dioxus_router::prelude::Link;
-    use document::{Meta, Stylesheet, Title};
-    let mut service_state = use_signal(|| ServiceState::Start);
-    // Create a periodic check on the effect of the service status
-    use_effect(move || {
-        spawn(async move {
-            loop {
-                if let Some(pid) = ServiceManager::check_service_status().await {
-                    debug!("service_running true pid: {:?}", pid);
-                    service_state.set(ServiceState::Stop);
-                } else {
-                    debug!("service_running true pid: 0");
-                    service_state.set(ServiceState::Start);
-                }
-                tokio::time::sleep(Duration::from_secs(2)).await;
-            }
-        });
-    });
-    debug!("project start service_state: {:?}", service_state.read());
-    // Use 'use_signal' to manage service status
-    let mut loading = use_signal(|| false);
-    let mut start_service = move |_| {
-        let service = service;
-        let config = config.read().clone();
-        let mut service_state = service_state;
-        // set the loading status
-        loading.set(true);
-        debug!("stop loading_state: {:?}", loading.read());
-        spawn(async move {
-            match service.read().start(config).await {
-                Ok(result) => {
-                    if result.success {
-                        let duration = result.end_time - result.start_time;
-                        debug!("The service starts successfully and takes a long time:{}ms", duration.num_milliseconds());
-                        service_state.set(ServiceState::Stop);
-                    } else {
-                        ServiceManager::show_error(&result.message);
-                        service_state.set(ServiceState::Start);
-                    }
-                }
-                Err(e) => {
-                    ServiceManager::show_error(&format!("start service failed: {e}"));
-                }
-            }
-            // Only set loading to false when it's actually done
-            loading.set(false);
-            debug!("start loading_state: {:?}", loading.read());
-        });
-    };
-
-    let mut stop_service = move |_| {
-        let service = service;
-        let mut service_state = service_state;
-        // set the loading status
-        loading.set(true);
-        spawn(async move {
-            match service.read().stop().await {
-                Ok(result) => {
-                    if result.success {
-                        let duration = result.end_time - result.start_time;
-                        debug!("The service stops successfully and takes a long time:{}ms", duration.num_milliseconds());
-                        service_state.set(ServiceState::Start);
-                    } else {
-                        ServiceManager::show_error(&result.message);
-                    }
-                }
-                Err(e) => {
-                    ServiceManager::show_error(&format!("stop service failed: {e}"));
-                }
-            }
-            debug!("service_state: {:?}", service_state.read());
-            // Only set loading to false when it's actually done
-            loading.set(false);
-            debug!("stop loading_state: {:?}", loading.read());
-        });
-    };
-
-    // Toggle the state when the button is clicked
-    let toggle_service = {
-        let mut service_state = service_state;
-        debug!("toggle_service service_state: {:?}", service_state.read());
-        move |_| {
-            if service_state.read().eq(&ServiceState::Stop) {
-                // If the service status is started, you need to run a command to stop the service
-                stop_service(());
-                service_state.set(ServiceState::Start);
-            } else {
-                start_service(());
-                service_state.set(ServiceState::Stop);
-            }
-        }
-    };
-
-    // Define dynamic styles based on state
-    let button_class = if service_state.read().eq(&ServiceState::Start) {
-        "bg-[#111827] hover:bg-[#1f2937] text-white px-4 py-2 rounded-md flex items-center space-x-2"
-    } else {
-        "bg-red-500 hover:bg-red-600 text-white px-4 py-2 rounded-md flex items-center space-x-2"
-    };
-
-    rsx! {
-        // The Stylesheet component inserts a style link into the head of the document
-        Stylesheet {href: TAILWIND_CSS,}
-        Title { "RustFS APP" }
-        Meta {
-            name: "description",
-            // TODO: translate to english
-            content: "RustFS is developed in the popular and secure Rust language, compatible with S3 protocol. Suitable for all scenarios including AI/ML and massive data storage, big data, internet, industrial and secure storage. Nearly free to use. Follows Apache 2 license, supports domestic security devices and systems.",
-        }
-        div { class: "min-h-screen flex flex-col items-center bg-white",
-            div { class: "absolute top-4 right-6 flex space-x-2",
-                // change theme
-                button { class: "p-2 hover:bg-gray-100 rounded-lg", ChangeThemeButton {} }
-                // setting button
-                Link {
-                    class: "p-2 hover:bg-gray-100 rounded-lg",
-                    to: Route::SettingViews {},
-                    SettingButton {}
-                }
-            }
-            main { class: "flex-1 flex flex-col items-center justify-center space-y-6 p-4",
-                div { class: "w-24 h-24 bg-gray-900 rounded-full flex items-center justify-center",
-                    img { alt: "Logo", class: "w-16 h-16", src: HEADER_LOGO }
-                }
-                div { class: "text-gray-600",
-                    "Service is running on "
-                    span { class: "text-blue-600", " 127.0.0.1:9000 " }
-                }
-                LoadingSpinner {
-                    loading: loading.read().to_owned(),
-                    text: "processing...",
-                }
-                button { class: button_class, onclick: toggle_service,
-                    svg {
-                        class: "h-4 w-4",
-                        fill: "none",
-                        stroke: "currentColor",
-                        view_box: "0 0 24 24",
-                        xmlns: "http://www.w3.org/2000/svg",
-                        if service_state.read().eq(&ServiceState::Start) {
-                            path {
-                                d: "M14.752 11.168l-3.197-2.132A1 1 0 0010 9.87v4.263a1 1 0 001.555.832l3.197-2.132a1 1 0 000-1.664z",
-                                stroke_linecap: "round",
-                                stroke_linejoin: "round",
-                                stroke_width: "2",
-                            }
-                            path {
-                                d: "M21 12a9 9 0 11-18 0 9 9 0 0118 0z",
-                                stroke_linecap: "round",
-                                stroke_linejoin: "round",
-                                stroke_width: "2",
-                            }
-                        } else {
-                            path {
-                                stroke_linecap: "round",
-                                stroke_linejoin: "round",
-                                stroke_width: "2",
-                                d: "M21 12a9 9 0 11-18 0 9 9 0 0118 0z",
-                            }
-                            path {
-                                stroke_linecap: "round",
-                                stroke_linejoin: "round",
-                                stroke_width: "2",
-                                d: "M9 10h6v4H9z",
-                            }
-                        }
-                    }
-                    span { id: "serviceStatus",
-                        if service_state.read().eq(&ServiceState::Start) {
-                            "Start service"
-                        } else {
-                            "Stop service"
-                        }
-                    }
-                }
-            }
-            Footer { version: "v1.0.0".to_string() }
-        }
-    }
-}
-
-#[component]
-pub fn Footer(version: String) -> Element {
-    let now = chrono::Local::now();
-    let year = now.naive_local().year();
-    rsx! {
-        footer { class: "w-full py-6 flex flex-col items-center space-y-4 mb-6",
-            nav { class: "flex space-x-4 text-gray-600",
-                a { class: "hover:text-gray-900", href: "https://rustfs.com", "Official Site" }
-                a {
-                    class: "hover:text-gray-900",
-                    href: "https://rustfs.com/docs",
-                    "Documentation"
-                }
-                a {
-                    class: "hover:text-gray-900",
-                    href: "https://github.com/rustfs/rustfs",
-                    "GitHub"
-                }
-                a {
-                    class: "hover:text-gray-900",
-                    href: "https://rustfs.com/docs/license/",
-                    "License"
-                }
-                a { class: "hover:text-gray-900", href: "#", "Sponsors" }
-            }
-            div { class: "text-gray-500 text-sm", " © rustfs.com {year}, All rights reserved." }
-            div { class: "text-gray-400 text-sm mb-8", " version {version} " }
-        }
-    }
-}
-
-#[component]
-pub fn GoBackButtons() -> Element {
-    rsx! {
-        button {
-            class: "p-2 hover:bg-gray-100 rounded-lg",
-            "onclick": "window.history.back()",
-            "Back to the Past"
-        }
-    }
-}
-
-#[component]
-pub fn GoForwardButtons() -> Element {
-    rsx! {
-        button {
-            class: "p-2 hover:bg-gray-100 rounded-lg",
-            "onclick": "window.history.forward()",
-            "Back to the Future"
-        }
-    }
-}
-
-#[component]
-pub fn ChangeThemeButton() -> Element {
-    rsx! {
-        svg {
-            class: "h-6 w-6 text-gray-600",
-            fill: "none",
-            stroke: "currentColor",
-            view_box: "0 0 24 24",
-            xmlns: "http://www.w3.org/2000/svg",
-            path {
-                d: "M9 3v2m6-2v2M9 19v2m6-2v2M5 9H3m2 6H3m18-6h-2m2 6h-2M7 19h10a2 2 0 002-2V7a2 2 0 00-2-2H7a2 2 0 00-2 2v10a2 2 0 002 2zM9 9h6v6H9V9z",
-                stroke_linecap: "round",
-                stroke_linejoin: "round",
-                stroke_width: "2",
-            }
-        }
-    }
-}
-
-#[component]
-pub fn SettingButton() -> Element {
-    rsx! {
-        svg {
-            class: "h-6 w-6 text-gray-600",
-            fill: "none",
-            stroke: "currentColor",
-            view_box: "0 0 24 24",
-            xmlns: "http://www.w3.org/2000/svg",
-            path {
-                d: "M10.325 4.317c.426-1.756 2.924-1.756 3.35 0a1.724 1.724 0 002.573 1.066c1.543-.94 3.31.826 2.37 2.37a1.724 1.724 0 001.065 2.572c1.756.426 1.756 2.924 0 3.35a1.724 1.724 0 00-1.066 2.573c.94 1.543-.826 3.31-2.37 2.37a1.724 1.724 0 00-2.572 1.065c-.426 1.756-2.924 1.756-3.35 0a1.724 1.724 0 00-2.573-1.066c-1.543.94-3.31-.826-2.37-2.37a1.724 1.724 0 00-1.065-2.572c-1.756-.426-1.756-2.924 0-3.35a1.724 1.724 0 001.066-2.573c-.94-1.543.826-3.31 2.37-2.37.996.608 2.296.07 2.572-1.065z",
-                stroke_linecap: "round",
-                stroke_linejoin: "round",
-                stroke_width: "2",
-            }
-            path {
-                d: "M15 12a3 3 0 11-6 0 3 3 0 016 0z",
-                stroke_linecap: "round",
-                stroke_linejoin: "round",
-                stroke_width: "2",
-            }
-        }
-    }
-}

cli/rustfs-gui/src/components/mod.rs

@@ -1,20 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-mod home;
-pub use home::Home;
-mod navbar;
-pub use navbar::Navbar;
-mod setting;
-pub use setting::Setting;

cli/rustfs-gui/src/components/navbar.rs

@@ -1,74 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::route::Route;
-use dioxus::logger::tracing::debug;
-use dioxus::prelude::*;
-
-const NAVBAR_CSS: Asset = asset!("/assets/styling/navbar.css");
-
-#[component]
-pub fn Navbar() -> Element {
-    rsx! {
-        document::Link { rel: "stylesheet", href: NAVBAR_CSS }
-
-        div { id: "navbar", class: "hidden", style: "display: none;",
-            Link { to: Route::HomeViews {}, "Home" }
-            Link { to: Route::SettingViews {}, "Setting" }
-        }
-
-        Outlet::<Route> {}
-    }
-}
-
-#[derive(Props, PartialEq, Debug, Clone)]
-pub struct LoadingSpinnerProps {
-    #[props(default = true)]
-    loading: bool,
-    #[props(default = "Processing...")]
-    text: &'static str,
-}
-
-#[component]
-pub fn LoadingSpinner(props: LoadingSpinnerProps) -> Element {
-    debug!("loading: {}", props.loading);
-    if !props.loading {
-        debug!("LoadingSpinner false loading: {}", props.loading);
-        return rsx! {};
-    }
-    rsx! {
-        div { class: "flex items-center justify-center z-10",
-            svg {
-                class: "animate-spin h-5 w-5 text-blue-500",
-                xmlns: "http://www.w3.org/2000/svg",
-                fill: "none",
-                view_box: "0 0 24 24",
-                circle {
-                    class: "opacity-25",
-                    cx: "12",
-                    cy: "12",
-                    r: "10",
-                    stroke: "currentColor",
-                    stroke_width: "4",
-                }
-                path {
-                    class: "opacity-75",
-                    fill: "currentColor",
-                    d: "M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4zm2 5.291A7.962 7.962 0 014 12H0c0 3.042 1.135 5.824 3 7.938l3-2.647z",
-                }
-            }
-            span { class: "ml-2 text-gray-600", "{props.text}" }
-        }
-    }
-}

cli/rustfs-gui/src/components/setting.rs

@@ -1,216 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::components::navbar::LoadingSpinner;
-use dioxus::logger::tracing::{debug, error};
-use dioxus::prelude::*;
-
-const SETTINGS_JS: Asset = asset!("/assets/js/sts.js");
-const TAILWIND_CSS: Asset = asset!("/assets/tailwind.css");
-#[component]
-pub fn Setting() -> Element {
-    use crate::utils::{RustFSConfig, ServiceManager};
-    use document::{Meta, Script, Stylesheet, Title};
-
-    #[allow(clippy::redundant_closure)]
-    let service = use_signal(|| ServiceManager::new());
-    let conf = RustFSConfig::load().unwrap_or_else(|e| {
-        error!("load config error: {}", e);
-        RustFSConfig::default_config()
-    });
-    debug!("conf address: {:?}", conf.clone().address);
-
-    let config = use_signal(|| conf.clone());
-    let address_state = use_signal(|| conf.address.to_string());
-    let mut host_state = use_signal(|| conf.host.to_string());
-    let mut port_state = use_signal(|| conf.port.to_string());
-    let mut access_key_state = use_signal(|| conf.access_key.to_string());
-    let mut secret_key_state = use_signal(|| conf.secret_key.to_string());
-    let mut volume_name_state = use_signal(|| conf.volume_name.to_string());
-    let loading = use_signal(|| false);
-
-    let save_and_restart = {
-        let host_state = host_state;
-        let port_state = port_state;
-        let access_key_state = access_key_state;
-        let secret_key_state = secret_key_state;
-        let volume_name_state = volume_name_state;
-        let mut loading = loading;
-        debug!("save_and_restart access_key:{}", access_key_state.read());
-        move |_| {
-            // set the loading status
-            loading.set(true);
-            let mut config = config;
-            config.write().address = format!("{}:{}", host_state.read(), port_state.read());
-            config.write().host = host_state.read().to_string();
-            config.write().port = port_state.read().to_string();
-            config.write().access_key = access_key_state.read().to_string();
-            config.write().secret_key = secret_key_state.read().to_string();
-            config.write().volume_name = volume_name_state.read().to_string();
-            // restart service
-            let service = service;
-            let config = config.read().clone();
-            spawn(async move {
-                if let Err(e) = service.read().restart(config).await {
-                    ServiceManager::show_error(&format!("Failed to send restart command: {e}"));
-                }
-                // reset the status when you're done
-                loading.set(false);
-            });
-        }
-    };
-
-    rsx! {
-        Title { "Settings - RustFS App" }
-        Meta { name: "description", content: "Settings - RustFS App." }
-        // The Stylesheet component inserts a style link into the head of the document
-        Stylesheet { href: TAILWIND_CSS }
-        Script { src: SETTINGS_JS }
-        div { class: "bg-white p-8",
-            h1 { class: "text-2xl font-semibold mb-6", "Settings" }
-            div { class: "border-b border-gray-200 mb-6",
-                nav { class: "flex space-x-8",
-                    button {
-                        class: "tab-btn px-1 py-4 text-sm font-medium border-b-2 border-black",
-                        "data-tab": "service",
-                        "onclick": "switchTab('service')",
-                        "Service "
-                    }
-                    button {
-                        class: "tab-btn px-1 py-4 text-sm font-medium text-gray-500 hover:text-gray-700",
-                        "data-tab": "user",
-                        "onclick": "switchTab('user')",
-                        "User "
-                    }
-                    button {
-                        class: "tab-btn px-1 py-4 text-sm font-medium text-gray-500 hover:text-gray-700 hidden",
-                        "data-tab": "logs",
-                        "onclick": "switchTab('logs')",
-                        "Logs "
-                    }
-                }
-            }
-            div { id: "tabContent",
-                div { class: "tab-content", id: "service",
-                    div { class: "mb-8",
-                        h2 { class: "text-base font-medium mb-2", "Service address" }
-                        p { class: "text-gray-600 mb-4",
-                            " The service address is the IP address and port number of the service. the default address is "
-                            code { class: "bg-gray-100 px-1 py-0.5 rounded", {address_state} }
-                            ". "
-                        }
-                        div { class: "flex space-x-2",
-                            input {
-                                class: "border rounded px-3 py-2 w-48 focus:outline-none focus:ring-2 focus:ring-blue-500",
-                                r#type: "text",
-                                value: host_state,
-                                oninput: move |evt| host_state.set(evt.value().clone()),
-                            }
-                            span { class: "flex items-center", ":" }
-                            input {
-                                class: "border rounded px-3 py-2 w-20 focus:outline-none focus:ring-2 focus:ring-blue-500",
-                                r#type: "text",
-                                value: port_state,
-                                oninput: move |evt| port_state.set(evt.value().clone()),
-                            }
-                        }
-                    }
-                    div { class: "mb-8",
-                        h2 { class: "text-base font-medium mb-2", "Storage path" }
-                        p { class: "text-gray-600 mb-4",
-                            "Update the storage path of the service. the default path is {volume_name_state}."
-                        }
-                        input {
-                            class: "border rounded px-3 py-2 w-full focus:outline-none focus:ring-2 focus:ring-blue-500",
-                            r#type: "text",
-                            value: volume_name_state,
-                            oninput: move |evt| volume_name_state.set(evt.value().clone()),
-                        }
-                    }
-                }
-                div { class: "tab-content hidden", id: "user",
-                    div { class: "mb-8",
-                        h2 { class: "text-base font-medium mb-2", "User" }
-                        p { class: "text-gray-600 mb-4",
-                            "The user is the owner of the service. the default user is "
-                            code { class: "bg-gray-100 px-1 py-0.5 rounded", {access_key_state} }
-                        }
-                        input {
-                            class: "border rounded px-3 py-2 w-full focus:outline-none focus:ring-2 focus:ring-blue-500",
-                            r#type: "text",
-                            value: access_key_state,
-                            oninput: move |evt| access_key_state.set(evt.value().clone()),
-                        }
-                    }
-                    div { class: "mb-8",
-                        h2 { class: "text-base font-medium mb-2", "Password" }
-                        p { class: "text-gray-600 mb-4",
-                            "The password is the password of the user. the default password is "
-                            code { class: "bg-gray-100 px-1 py-0.5 rounded", {secret_key_state} }
-                        }
-                        div { class: "relative",
-                            input {
-                                class: "border rounded px-3 py-2 w-full pr-10 focus:outline-none focus:ring-2 focus:ring-blue-500",
-                                r#type: "password",
-                                value: secret_key_state,
-                                oninput: move |evt| secret_key_state.set(evt.value().clone()),
-                            }
-                            button {
-                                class: "absolute right-2 top-1/2 transform -translate-y-1/2 text-gray-500 hover:text-gray-700",
-                                "onclick": "togglePassword(this)",
-                                svg {
-                                    class: "h-5 w-5",
-                                    fill: "currentColor",
-                                    view_box: "0 0 20 20",
-                                    xmlns: "http://www.w3.org/2000/svg",
-                                    path { d: "M10 12a2 2 0 100-4 2 2 0 000 4z" }
-                                    path {
-                                        clip_rule: "evenodd",
-                                        d: "M.458 10C1.732 5.943 5.522 3 10 3s8.268 2.943 9.542 7c-1.274 4.057-5.064 7-9.542 7S1.732 14.057.458 10zM14 10a4 4 0 11-8 0 4 4 0 018 0z",
-                                        fill_rule: "evenodd",
-                                    }
-                                }
-                            }
-                        }
-                    }
-                }
-                div { class: "tab-content hidden", id: "logs",
-                    div { class: "mb-8",
-                        h2 { class: "text-base font-medium mb-2", "Logs storage path" }
-                        p { class: "text-gray-600 mb-4",
-                            "The logs storage path is the path where the logs are stored. the default path is /var/log/rustfs. "
-                        }
-                        input {
-                            class: "border rounded px-3 py-2 w-full focus:outline-none focus:ring-2 focus:ring-blue-500",
-                            r#type: "text",
-                            value: "/var/logs/rustfs",
-                        }
-                    }
-                }
-            }
-            div { class: "flex space-x-4",
-                button {
-                    class: "bg-[#111827] text-white px-4 py-2 rounded hover:bg-[#1f2937]",
-                    onclick: save_and_restart,
-                    " Save and restart "
-                }
-                GoBackButton { "Back" }
-            }
-            LoadingSpinner {
-                loading: loading.read().to_owned(),
-                text: "Service processing...",
-            }
-        }
-    }
-}

cli/rustfs-gui/src/route/router.rs

@@ -1,28 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::components::Navbar;
-use crate::views::{HomeViews, SettingViews};
-use dioxus::prelude::*;
-
-/// The router for the application
-#[derive(Debug, Clone, Routable, PartialEq)]
-#[rustfmt::skip]
-pub enum Route {
-    #[layout(Navbar)]
-    #[route("/")]
-    HomeViews {},
-    #[route("/settings")]
-    SettingViews {},
-}

cli/rustfs-gui/src/utils/config.rs

@@ -1,564 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use keyring::Entry;
-use serde::{Deserialize, Serialize};
-use std::error::Error;
-
-/// Configuration for the RustFS service
-///
-/// # Fields
-/// * `address` - The address of the RustFS service
-/// * `host` - The host of the RustFS service
-/// * `port` - The port of the RustFS service
-/// * `access_key` - The access key of the RustFS service
-/// * `secret_key` - The secret key of the RustFS service
-/// * `domain_name` - The domain name of the RustFS service
-/// * `volume_name` - The volume name of the RustFS service
-/// * `console_address` - The console address of the RustFS service
-///
-/// # Example
-/// ```
-/// let config = RustFSConfig {
-///    address: "127.0.0.1:9000".to_string(),
-///    host: "127.0.0.1".to_string(),
-///    port: "9000".to_string(),
-///    access_key: "rustfsadmin".to_string(),
-///    secret_key: "rustfsadmin".to_string(),
-///    domain_name: "demo.rustfs.com".to_string(),
-///    volume_name: "data".to_string(),
-///    console_address: "127.0.0.1:9001".to_string(),
-/// };
-/// println!("{:?}", config);
-/// assert_eq!(config.address, "127.0.0.1:9000");
-/// ```
-#[derive(Debug, Clone, Default, Deserialize, Serialize, Ord, PartialOrd, Eq, PartialEq)]
-pub struct RustFSConfig {
-    pub address: String,
-    pub host: String,
-    pub port: String,
-    pub access_key: String,
-    pub secret_key: String,
-    pub domain_name: String,
-    pub volume_name: String,
-    pub console_address: String,
-}
-
-impl RustFSConfig {
-    /// keyring the name of the service
-    const SERVICE_NAME: &'static str = "rustfs-service";
-    /// keyring the key of the service
-    const SERVICE_KEY: &'static str = "rustfs_key";
-    /// default domain name
-    const DEFAULT_DOMAIN_NAME_VALUE: &'static str = "demo.rustfs.com";
-    /// default address value
-    const DEFAULT_ADDRESS_VALUE: &'static str = "127.0.0.1:9000";
-    /// default port value
-    const DEFAULT_PORT_VALUE: &'static str = "9000";
-    /// default host value
-    const DEFAULT_HOST_VALUE: &'static str = "127.0.0.1";
-    /// default access key value
-    const DEFAULT_ACCESS_KEY_VALUE: &'static str = "rustfsadmin";
-    /// default secret key value
-    const DEFAULT_SECRET_KEY_VALUE: &'static str = "rustfsadmin";
-    /// default console address value
-    const DEFAULT_CONSOLE_ADDRESS_VALUE: &'static str = "127.0.0.1:9001";
-
-    /// get the default volume_name
-    ///
-    /// # Returns
-    /// * The default volume name
-    ///
-    /// # Example
-    /// ```
-    /// let volume_name = RustFSConfig::default_volume_name();
-    /// ```
-    pub fn default_volume_name() -> String {
-        dirs::home_dir()
-            .map(|home| home.join("rustfs").join("data"))
-            .and_then(|path| path.to_str().map(String::from))
-            .unwrap_or_else(|| "data".to_string())
-    }
-
-    /// create a default configuration
-    ///
-    /// # Returns
-    /// * The default configuration
-    ///
-    /// # Example
-    /// ```
-    /// let config = RustFSConfig::default_config();
-    /// println!("{:?}", config);
-    /// assert_eq!(config.address, "127.0.0.1:9000");
-    /// ```
-    pub fn default_config() -> Self {
-        Self {
-            address: Self::DEFAULT_ADDRESS_VALUE.to_string(),
-            host: Self::DEFAULT_HOST_VALUE.to_string(),
-            port: Self::DEFAULT_PORT_VALUE.to_string(),
-            access_key: Self::DEFAULT_ACCESS_KEY_VALUE.to_string(),
-            secret_key: Self::DEFAULT_SECRET_KEY_VALUE.to_string(),
-            domain_name: Self::DEFAULT_DOMAIN_NAME_VALUE.to_string(),
-            volume_name: Self::default_volume_name(),
-            console_address: Self::DEFAULT_CONSOLE_ADDRESS_VALUE.to_string(),
-        }
-    }
-
-    /// Load the configuration from the keyring
-    ///
-    /// # Errors
-    /// * If the configuration cannot be loaded from the keyring
-    /// * If the configuration cannot be deserialized
-    /// * If the address cannot be extracted from the configuration
-    ///
-    /// # Example
-    /// ```
-    /// let config = RustFSConfig::load().unwrap();
-    /// println!("{:?}", config);
-    /// assert_eq!(config.address, "127.0.0.1:9000");
-    /// ```
-    pub fn load() -> Result<Self, Box<dyn Error>> {
-        let mut config = Self::default_config();
-
-        // Try to get the configuration of the storage from the keyring
-        let entry = Entry::new(Self::SERVICE_NAME, Self::SERVICE_KEY)?;
-        if let Ok(stored_json) = entry.get_password() {
-            if let Ok(stored_config) = serde_json::from_str::<RustFSConfig>(&stored_json) {
-                // update fields that are not empty and non default
-                if !stored_config.address.is_empty() && stored_config.address != Self::DEFAULT_ADDRESS_VALUE {
-                    config.address = stored_config.address;
-                    let (host, port) = Self::extract_host_port(config.address.as_str())
-                        .ok_or_else(|| format!("Unable to extract host and port from address '{}'", config.address))?;
-                    config.host = host.to_string();
-                    config.port = port.to_string();
-                }
-                if !stored_config.access_key.is_empty() && stored_config.access_key != Self::DEFAULT_ACCESS_KEY_VALUE {
-                    config.access_key = stored_config.access_key;
-                }
-                if !stored_config.secret_key.is_empty() && stored_config.secret_key != Self::DEFAULT_SECRET_KEY_VALUE {
-                    config.secret_key = stored_config.secret_key;
-                }
-                if !stored_config.domain_name.is_empty() && stored_config.domain_name != Self::DEFAULT_DOMAIN_NAME_VALUE {
-                    config.domain_name = stored_config.domain_name;
-                }
-                // The stored volume_name is updated only if it is not empty and different from the default
-                if !stored_config.volume_name.is_empty() && stored_config.volume_name != Self::default_volume_name() {
-                    config.volume_name = stored_config.volume_name;
-                }
-                if !stored_config.console_address.is_empty()
-                    && stored_config.console_address != Self::DEFAULT_CONSOLE_ADDRESS_VALUE
-                {
-                    config.console_address = stored_config.console_address;
-                }
-            }
-        }
-
-        Ok(config)
-    }
-
-    /// Auxiliary method: Extract the host and port from the address string
-    /// # Arguments
-    /// * `address` - The address string
-    ///
-    /// # Returns
-    /// * `Some((host, port))` - The host and port
-    ///
-    /// # Errors
-    /// * If the address is not in the form 'host:port'
-    /// * If the port is not a valid u16
-    ///
-    /// # Example
-    /// ```
-    /// let (host, port) = RustFSConfig::extract_host_port("127.0.0.1:9000").unwrap();
-    /// assert_eq!(host, "127.0.0.1");
-    /// assert_eq!(port, 9000);
-    /// ```
-    pub fn extract_host_port(address: &str) -> Option<(&str, u16)> {
-        let parts: Vec<&str> = address.split(':').collect();
-        if parts.len() == 2 {
-            if let Ok(port) = parts[1].parse::<u16>() {
-                return Some((parts[0], port));
-            }
-        }
-        None
-    }
-
-    /// save the configuration to keyring
-    ///
-    /// # Errors
-    /// * If the configuration cannot be serialized
-    /// * If the configuration cannot be saved to the keyring
-    ///
-    /// # Example
-    /// ```
-    /// let config = RustFSConfig::default_config();
-    /// config.save().unwrap();
-    /// ```
-    pub fn save(&self) -> Result<(), Box<dyn Error>> {
-        let entry = Entry::new(Self::SERVICE_NAME, Self::SERVICE_KEY)?;
-        let json = serde_json::to_string(self)?;
-        entry.set_password(&json)?;
-        Ok(())
-    }
-
-    /// Clear the stored configuration from the system keyring
-    ///
-    /// # Returns
-    /// `Ok(())` if the configuration was successfully cleared, or an error if the operation failed.
-    ///
-    /// # Example
-    /// ```
-    /// RustFSConfig::clear().unwrap();
-    /// ```
-    #[allow(dead_code)]
-    pub fn clear() -> Result<(), Box<dyn Error>> {
-        let entry = Entry::new(Self::SERVICE_NAME, Self::SERVICE_KEY)?;
-        entry.delete_credential()?;
-        Ok(())
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_rustfs_config_default() {
-        let config = RustFSConfig::default();
-        assert!(config.address.is_empty());
-        assert!(config.host.is_empty());
-        assert!(config.port.is_empty());
-        assert!(config.access_key.is_empty());
-        assert!(config.secret_key.is_empty());
-        assert!(config.domain_name.is_empty());
-        assert!(config.volume_name.is_empty());
-        assert!(config.console_address.is_empty());
-    }
-
-    #[test]
-    fn test_rustfs_config_creation() {
-        let config = RustFSConfig {
-            address: "192.168.1.100:9000".to_string(),
-            host: "192.168.1.100".to_string(),
-            port: "9000".to_string(),
-            access_key: "testuser".to_string(),
-            secret_key: "testpass".to_string(),
-            domain_name: "test.rustfs.com".to_string(),
-            volume_name: "/data/rustfs".to_string(),
-            console_address: "192.168.1.100:9001".to_string(),
-        };
-
-        assert_eq!(config.address, "192.168.1.100:9000");
-        assert_eq!(config.host, "192.168.1.100");
-        assert_eq!(config.port, "9000");
-        assert_eq!(config.access_key, "testuser");
-        assert_eq!(config.secret_key, "testpass");
-        assert_eq!(config.domain_name, "test.rustfs.com");
-        assert_eq!(config.volume_name, "/data/rustfs");
-        assert_eq!(config.console_address, "192.168.1.100:9001");
-    }
-
-    #[test]
-    fn test_default_volume_name() {
-        let volume_name = RustFSConfig::default_volume_name();
-        assert!(!volume_name.is_empty());
-        // Should either be the home directory path or fallback to "data"
-        assert!(volume_name.contains("rustfs") || volume_name == "data");
-    }
-
-    #[test]
-    fn test_default_config() {
-        let config = RustFSConfig::default_config();
-        assert_eq!(config.address, RustFSConfig::DEFAULT_ADDRESS_VALUE);
-        assert_eq!(config.host, RustFSConfig::DEFAULT_HOST_VALUE);
-        assert_eq!(config.port, RustFSConfig::DEFAULT_PORT_VALUE);
-        assert_eq!(config.access_key, RustFSConfig::DEFAULT_ACCESS_KEY_VALUE);
-        assert_eq!(config.secret_key, RustFSConfig::DEFAULT_SECRET_KEY_VALUE);
-        assert_eq!(config.domain_name, RustFSConfig::DEFAULT_DOMAIN_NAME_VALUE);
-        assert_eq!(config.console_address, RustFSConfig::DEFAULT_CONSOLE_ADDRESS_VALUE);
-        assert!(!config.volume_name.is_empty());
-    }
-
-    #[test]
-    fn test_extract_host_port_valid() {
-        let test_cases = vec![
-            ("127.0.0.1:9000", Some(("127.0.0.1", 9000))),
-            ("localhost:8080", Some(("localhost", 8080))),
-            ("192.168.1.100:3000", Some(("192.168.1.100", 3000))),
-            ("0.0.0.0:80", Some(("0.0.0.0", 80))),
-            ("example.com:443", Some(("example.com", 443))),
-        ];
-
-        for (input, expected) in test_cases {
-            let result = RustFSConfig::extract_host_port(input);
-            assert_eq!(result, expected, "Failed for input: {input}");
-        }
-    }
-
-    #[test]
-    fn test_extract_host_port_invalid() {
-        let invalid_cases = vec![
-            "127.0.0.1",            // Missing port
-            "127.0.0.1:",           // Empty port
-            "127.0.0.1:abc",        // Invalid port
-            "127.0.0.1:99999",      // Port out of range
-            "",                     // Empty string
-            "127.0.0.1:9000:extra", // Too many parts
-            "invalid",              // No colon
-        ];
-
-        for input in invalid_cases {
-            let result = RustFSConfig::extract_host_port(input);
-            assert_eq!(result, None, "Should be None for input: {input}");
-        }
-
-        // Special case: empty host but valid port should still work
-        let result = RustFSConfig::extract_host_port(":9000");
-        assert_eq!(result, Some(("", 9000)));
-    }
-
-    #[test]
-    fn test_extract_host_port_edge_cases() {
-        // Test edge cases for port numbers
-        assert_eq!(RustFSConfig::extract_host_port("host:0"), Some(("host", 0)));
-        assert_eq!(RustFSConfig::extract_host_port("host:65535"), Some(("host", 65535)));
-        assert_eq!(RustFSConfig::extract_host_port("host:65536"), None); // Out of range
-    }
-
-    #[test]
-    fn test_serialization() {
-        let config = RustFSConfig {
-            address: "127.0.0.1:9000".to_string(),
-            host: "127.0.0.1".to_string(),
-            port: "9000".to_string(),
-            access_key: "admin".to_string(),
-            secret_key: "password".to_string(),
-            domain_name: "test.com".to_string(),
-            volume_name: "/data".to_string(),
-            console_address: "127.0.0.1:9001".to_string(),
-        };
-
-        let json = serde_json::to_string(&config).unwrap();
-        assert!(json.contains("127.0.0.1:9000"));
-        assert!(json.contains("admin"));
-        assert!(json.contains("test.com"));
-    }
-
-    #[test]
-    fn test_deserialization() {
-        let json = r#"{
-            "address": "192.168.1.100:9000",
-            "host": "192.168.1.100",
-            "port": "9000",
-            "access_key": "testuser",
-            "secret_key": "testpass",
-            "domain_name": "example.com",
-            "volume_name": "/opt/data",
-            "console_address": "192.168.1.100:9001"
-        }"#;
-
-        let config: RustFSConfig = serde_json::from_str(json).unwrap();
-        assert_eq!(config.address, "192.168.1.100:9000");
-        assert_eq!(config.host, "192.168.1.100");
-        assert_eq!(config.port, "9000");
-        assert_eq!(config.access_key, "testuser");
-        assert_eq!(config.secret_key, "testpass");
-        assert_eq!(config.domain_name, "example.com");
-        assert_eq!(config.volume_name, "/opt/data");
-        assert_eq!(config.console_address, "192.168.1.100:9001");
-    }
-
-    #[test]
-    fn test_serialization_deserialization_roundtrip() {
-        let original_config = RustFSConfig {
-            address: "10.0.0.1:8080".to_string(),
-            host: "10.0.0.1".to_string(),
-            port: "8080".to_string(),
-            access_key: "roundtrip_user".to_string(),
-            secret_key: "roundtrip_pass".to_string(),
-            domain_name: "roundtrip.test".to_string(),
-            volume_name: "/tmp/roundtrip".to_string(),
-            console_address: "10.0.0.1:8081".to_string(),
-        };
-
-        let json = serde_json::to_string(&original_config).unwrap();
-        let deserialized_config: RustFSConfig = serde_json::from_str(&json).unwrap();
-
-        assert_eq!(original_config, deserialized_config);
-    }
-
-    #[test]
-    fn test_config_ordering() {
-        let config1 = RustFSConfig {
-            address: "127.0.0.1:9000".to_string(),
-            host: "127.0.0.1".to_string(),
-            port: "9000".to_string(),
-            access_key: "admin".to_string(),
-            secret_key: "password".to_string(),
-            domain_name: "test.com".to_string(),
-            volume_name: "/data".to_string(),
-            console_address: "127.0.0.1:9001".to_string(),
-        };
-
-        let config2 = RustFSConfig {
-            address: "127.0.0.1:9000".to_string(),
-            host: "127.0.0.1".to_string(),
-            port: "9000".to_string(),
-            access_key: "admin".to_string(),
-            secret_key: "password".to_string(),
-            domain_name: "test.com".to_string(),
-            volume_name: "/data".to_string(),
-            console_address: "127.0.0.1:9001".to_string(),
-        };
-
-        let config3 = RustFSConfig {
-            address: "127.0.0.1:9001".to_string(), // Different port
-            host: "127.0.0.1".to_string(),
-            port: "9001".to_string(),
-            access_key: "admin".to_string(),
-            secret_key: "password".to_string(),
-            domain_name: "test.com".to_string(),
-            volume_name: "/data".to_string(),
-            console_address: "127.0.0.1:9002".to_string(),
-        };
-
-        assert_eq!(config1, config2);
-        assert_ne!(config1, config3);
-        assert!(config1 < config3); // Lexicographic ordering
-    }
-
-    #[test]
-    fn test_clone() {
-        let original = RustFSConfig::default_config();
-        let cloned = original.clone();
-
-        assert_eq!(original, cloned);
-        assert_eq!(original.address, cloned.address);
-        assert_eq!(original.access_key, cloned.access_key);
-    }
-
-    #[test]
-    fn test_debug_format() {
-        let config = RustFSConfig::default_config();
-        let debug_str = format!("{config:?}");
-
-        assert!(debug_str.contains("RustFSConfig"));
-        assert!(debug_str.contains("address"));
-        assert!(debug_str.contains("127.0.0.1:9000"));
-    }
-
-    #[test]
-    fn test_constants() {
-        assert_eq!(RustFSConfig::SERVICE_NAME, "rustfs-service");
-        assert_eq!(RustFSConfig::SERVICE_KEY, "rustfs_key");
-        assert_eq!(RustFSConfig::DEFAULT_DOMAIN_NAME_VALUE, "demo.rustfs.com");
-        assert_eq!(RustFSConfig::DEFAULT_ADDRESS_VALUE, "127.0.0.1:9000");
-        assert_eq!(RustFSConfig::DEFAULT_PORT_VALUE, "9000");
-        assert_eq!(RustFSConfig::DEFAULT_HOST_VALUE, "127.0.0.1");
-        assert_eq!(RustFSConfig::DEFAULT_ACCESS_KEY_VALUE, "rustfsadmin");
-        assert_eq!(RustFSConfig::DEFAULT_SECRET_KEY_VALUE, "rustfsadmin");
-        assert_eq!(RustFSConfig::DEFAULT_CONSOLE_ADDRESS_VALUE, "127.0.0.1:9001");
-    }
-
-    #[test]
-    fn test_empty_strings() {
-        let config = RustFSConfig {
-            address: "".to_string(),
-            host: "".to_string(),
-            port: "".to_string(),
-            access_key: "".to_string(),
-            secret_key: "".to_string(),
-            domain_name: "".to_string(),
-            volume_name: "".to_string(),
-            console_address: "".to_string(),
-        };
-
-        assert!(config.address.is_empty());
-        assert!(config.host.is_empty());
-        assert!(config.port.is_empty());
-        assert!(config.access_key.is_empty());
-        assert!(config.secret_key.is_empty());
-        assert!(config.domain_name.is_empty());
-        assert!(config.volume_name.is_empty());
-        assert!(config.console_address.is_empty());
-    }
-
-    #[test]
-    fn test_very_long_strings() {
-        let long_string = "a".repeat(1000);
-        let config = RustFSConfig {
-            address: format!("{long_string}:9000"),
-            host: long_string.clone(),
-            port: "9000".to_string(),
-            access_key: long_string.clone(),
-            secret_key: long_string.clone(),
-            domain_name: format!("{long_string}.com"),
-            volume_name: format!("/data/{long_string}"),
-            console_address: format!("{long_string}:9001"),
-        };
-
-        assert_eq!(config.host.len(), 1000);
-        assert_eq!(config.access_key.len(), 1000);
-        assert_eq!(config.secret_key.len(), 1000);
-    }
-
-    #[test]
-    fn test_special_characters() {
-        let config = RustFSConfig {
-            address: "127.0.0.1:9000".to_string(),
-            host: "127.0.0.1".to_string(),
-            port: "9000".to_string(),
-            access_key: "user@domain.com".to_string(),
-            secret_key: "p@ssw0rd!#$%".to_string(),
-            domain_name: "test-domain.example.com".to_string(),
-            volume_name: "/data/rust-fs/storage".to_string(),
-            console_address: "127.0.0.1:9001".to_string(),
-        };
-
-        assert!(config.access_key.contains("@"));
-        assert!(config.secret_key.contains("!#$%"));
-        assert!(config.domain_name.contains("-"));
-        assert!(config.volume_name.contains("/"));
-    }
-
-    #[test]
-    fn test_unicode_strings() {
-        let config = RustFSConfig {
-            address: "127.0.0.1:9000".to_string(),
-            host: "127.0.0.1".to_string(),
-            port: "9000".to_string(),
-            access_key: "username".to_string(),
-            secret_key: "password123".to_string(),
-            domain_name: "test.com".to_string(),
-            volume_name: "/data/storage".to_string(),
-            console_address: "127.0.0.1:9001".to_string(),
-        };
-
-        assert_eq!(config.access_key, "username");
-        assert_eq!(config.secret_key, "password123");
-        assert_eq!(config.domain_name, "test.com");
-        assert_eq!(config.volume_name, "/data/storage");
-    }
-
-    #[test]
-    fn test_memory_efficiency() {
-        // Test that the structure doesn't use excessive memory
-        assert!(std::mem::size_of::<RustFSConfig>() < 1000);
-    }
-
-    // Note: Keyring-related tests (load, save, clear) are not included here
-    // because they require actual keyring access and would be integration tests
-    // rather than unit tests. They should be tested separately in an integration
-    // test environment where keyring access can be properly mocked or controlled.
-}

cli/rustfs-gui/src/utils/helper.rs

@@ -1,899 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::utils::RustFSConfig;
-use dioxus::logger::tracing::{debug, error, info};
-use rust_embed::RustEmbed;
-use sha2::{Digest, Sha256};
-use std::error::Error;
-use std::path::{Path, PathBuf};
-use std::process::Command as StdCommand;
-use std::sync::LazyLock;
-use std::time::Duration;
-use tokio::fs;
-use tokio::fs::File;
-use tokio::io::AsyncWriteExt;
-use tokio::net::TcpStream;
-use tokio::sync::{Mutex, mpsc};
-
-#[derive(RustEmbed)]
-#[folder = "$CARGO_MANIFEST_DIR/embedded-rustfs/"]
-struct Asset;
-
-// Use `LazyLock` to cache the checksum of embedded resources
-static RUSTFS_HASH: LazyLock<Mutex<String>> = LazyLock::new(|| {
-    let rustfs_file = if cfg!(windows) { "rustfs.exe" } else { "rustfs" };
-    let rustfs_data = Asset::get(rustfs_file).expect("RustFs binary not embedded");
-    let hash = hex::encode(Sha256::digest(&rustfs_data.data));
-    Mutex::new(hash)
-});
-
-/// Service command
-/// This enum represents the commands that can be sent to the service manager
-/// to start, stop, or restart the service
-/// The `Start` variant contains the configuration for the service
-/// The `Restart` variant contains the configuration for the service
-///
-/// # Example
-/// ```
-/// let config = RustFSConfig {
-///    address: "127.0.0.1:9000".to_string(),
-///    host: "127.0.0.1".to_string(),
-///    port: "9000".to_string(),
-///    access_key: "rustfsadmin".to_string(),
-///    secret_key: "rustfsadmin".to_string(),
-///    domain_name: "demo.rustfs.com".to_string(),
-///    volume_name: "data".to_string(),
-///    console_address: "127.0.0.1:9001".to_string(),
-/// };
-///
-/// let command = ServiceCommand::Start(config);
-/// println!("{:?}", command);
-///
-/// assert_eq!(command, ServiceCommand::Start(config));
-/// ```
-pub enum ServiceCommand {
-    Start(RustFSConfig),
-    Stop,
-    Restart(RustFSConfig),
-}
-
-/// Service operation result
-/// This struct represents the result of a service operation
-/// It contains information about the success of the operation,
-///
-/// # Example
-/// ```
-/// use chrono::Local;
-///
-/// let result = ServiceOperationResult {
-///     success: true,
-///     start_time: chrono::Local::now(),
-///     end_time: chrono::Local::now(),
-///     message: "Service started successfully".to_string(),
-/// };
-///
-/// println!("{:?}", result);
-/// assert_eq!(result.success, true);
-/// ```
-#[derive(Debug)]
-pub struct ServiceOperationResult {
-    pub success: bool,
-    pub start_time: chrono::DateTime<chrono::Local>,
-    pub end_time: chrono::DateTime<chrono::Local>,
-    pub message: String,
-}
-
-/// Service manager
-/// This struct represents a service manager that can be used to start, stop, or restart a service
-/// It contains a command sender that can be used to send commands to the service manager
-///
-/// # Example
-/// ```
-/// let service_manager = ServiceManager::new();
-/// println!("{:?}", service_manager);
-/// ```
-#[derive(Debug, Clone)]
-pub struct ServiceManager {
-    command_tx: mpsc::Sender<ServiceCommand>,
-    // process: Arc<Mutex<Option<Child>>>,
-    // pid: Arc<Mutex<Option<u32>>>,                     // Add PID storage
-    // current_config: Arc<Mutex<Option<RustFSConfig>>>, // Add configuration storage
-}
-
-impl ServiceManager {
-    /// check if the service is running and return a pid
-    /// This function is platform dependent
-    /// On Unix systems, it uses the `ps` command to check for the service
-    /// On Windows systems, it uses the `wmic` command to check for the service
-    ///
-    /// # Example
-    /// ```
-    /// let pid = check_service_status().await;
-    /// println!("{:?}", pid);
-    /// ```
-    pub async fn check_service_status() -> Option<u32> {
-        #[cfg(unix)]
-        {
-            // use the ps command on a unix system
-            if let Ok(output) = StdCommand::new("ps").arg("-ef").output() {
-                let output_str = String::from_utf8_lossy(&output.stdout);
-                for line in output_str.lines() {
-                    // match contains `rustfs/bin/rustfs` of the line
-                    if line.contains("rustfs/bin/rustfs") && !line.contains("grep") {
-                        if let Some(pid_str) = line.split_whitespace().nth(1) {
-                            if let Ok(pid) = pid_str.parse::<u32>() {
-                                return Some(pid);
-                            }
-                        }
-                    }
-                }
-            }
-        }
-
-        #[cfg(windows)]
-        {
-            if let Ok(output) = StdCommand::new("wmic")
-                .arg("process")
-                .arg("where")
-                .arg("caption='rustfs.exe'")
-                .arg("get")
-                .arg("processid")
-                .output()
-            {
-                let output_str = String::from_utf8_lossy(&output.stdout);
-                for line in output_str.lines() {
-                    if let Ok(pid) = line.trim().parse::<u32>() {
-                        return Some(pid);
-                    }
-                }
-            }
-        }
-
-        None
-    }
-
-    /// Prepare the service
-    /// This function downloads the service executable if it doesn't exist
-    /// It also creates the necessary directories for the service
-    ///
-    /// # Example
-    /// ```
-    /// let executable_path = prepare_service().await;
-    /// println!("{:?}", executable_path);
-    /// ```
-    async fn prepare_service() -> Result<PathBuf, Box<dyn Error>> {
-        // get the user directory
-        let home_dir = dirs::home_dir().ok_or("Unable to get user directory")?;
-        let rustfs_dir = home_dir.join("rustfs");
-        let bin_dir = rustfs_dir.join("bin");
-        let data_dir = rustfs_dir.join("data");
-        let logs_dir = rustfs_dir.join("logs");
-
-        // create the necessary directories
-        for dir in [&bin_dir, &data_dir, &logs_dir] {
-            if !dir.exists() {
-                tokio::fs::create_dir_all(dir).await?;
-            }
-        }
-
-        let rustfs_file = if cfg!(windows) { "rustfs.exe" } else { "rustfs" };
-        let executable_path = bin_dir.join(rustfs_file);
-        let hash_path = bin_dir.join("embedded_rustfs.sha256");
-
-        if executable_path.exists() && hash_path.exists() {
-            let cached_hash = fs::read_to_string(&hash_path).await?;
-            let expected_hash = RUSTFS_HASH.lock().await;
-            if cached_hash == *expected_hash {
-                println!("Use cached rustfs: {executable_path:?}");
-                return Ok(executable_path);
-            }
-        }
-
-        // Extract and write files
-        let rustfs_data = Asset::get(rustfs_file).expect("RustFS binary not embedded");
-        let mut file = File::create(&executable_path).await?;
-        file.write_all(&rustfs_data.data).await?;
-        let expected_hash = hex::encode(Sha256::digest(&rustfs_data.data));
-        fs::write(&hash_path, expected_hash).await?;
-
-        // set execution permissions on unix systems
-        #[cfg(unix)]
-        {
-            use std::os::unix::fs::PermissionsExt;
-            let mut perms = std::fs::metadata(&executable_path)?.permissions();
-            perms.set_mode(0o755);
-            std::fs::set_permissions(&executable_path, perms)?;
-        }
-
-        Ok(executable_path)
-    }
-
-    /// Helper function: Extracts the port from the address string
-    ///
-    /// # Example
-    /// ```
-    /// let address = "127.0.0.1:9000";
-    /// let port = extract_port(address);
-    /// println!("{:?}", port);
-    /// ```
-    fn extract_port(address: &str) -> Option<u16> {
-        address.split(':').nth(1)?.parse().ok()
-    }
-
-    /// Create a new instance of the service manager
-    ///
-    /// # Example
-    /// ```
-    /// let service_manager = ServiceManager::new();
-    /// println!("{:?}", service_manager);
-    /// ```
-    pub(crate) fn new() -> Self {
-        let (command_tx, mut command_rx) = mpsc::channel(10);
-        // Start the control loop
-        tokio::spawn(async move {
-            while let Some(cmd) = command_rx.recv().await {
-                match cmd {
-                    ServiceCommand::Start(config) => {
-                        if let Err(e) = Self::start_service(&config).await {
-                            Self::show_error(&format!("Failed to start service: {e}"));
-                        }
-                    }
-                    ServiceCommand::Stop => {
-                        if let Err(e) = Self::stop_service().await {
-                            Self::show_error(&format!("Failed to stop service: {e}"));
-                        }
-                    }
-                    ServiceCommand::Restart(config) => {
-                        if Self::check_service_status().await.is_some() {
-                            if let Err(e) = Self::stop_service().await {
-                                Self::show_error(&format!("Failed to restart service: {e}"));
-                                continue;
-                            }
-                        }
-                        if let Err(e) = Self::start_service(&config).await {
-                            Self::show_error(&format!("Failed to restart service: {e}"));
-                        }
-                    }
-                }
-            }
-        });
-
-        ServiceManager { command_tx }
-    }
-
-    /// Start the service
-    /// This function starts the service with the given configuration
-    ///
-    /// # Example
-    /// ```
-    /// let config = RustFSConfig {
-    ///    address: "127.0.0.1:9000".to_string(),
-    ///    host: "127.0.0.1".to_string(),
-    ///    port: "9000".to_string(),
-    ///    access_key: "rustfsadmin".to_string(),
-    ///    secret_key: "rustfsadmin".to_string(),
-    ///    domain_name: "demo.rustfs.com".to_string(),
-    ///    volume_name: "data".to_string(),
-    ///    console_address: "127.0.0.1:9001".to_string(),
-    /// };
-    ///
-    /// let result = start_service(&config).await;
-    /// println!("{:?}", result);
-    /// ```
-    async fn start_service(config: &RustFSConfig) -> Result<(), Box<dyn Error>> {
-        // Check if the service is already running
-        if let Some(existing_pid) = Self::check_service_status().await {
-            return Err(format!("Service is already running, PID: {existing_pid}").into());
-        }
-
-        // Prepare the service program
-        let executable_path = Self::prepare_service().await?;
-        // Check the data catalog
-        let volume_name_path = Path::new(&config.volume_name);
-        if !volume_name_path.exists() {
-            tokio::fs::create_dir_all(&config.volume_name).await?;
-        }
-
-        // Extract the port from the configuration
-        let main_port = Self::extract_port(&config.address).ok_or("Unable to parse main service port")?;
-        let console_port = Self::extract_port(&config.console_address).ok_or("Unable to parse console port")?;
-
-        let host = config.address.split(':').next().ok_or("Unable to parse host address")?;
-
-        // Check the port
-        let ports = vec![main_port, console_port];
-        for port in ports {
-            if Self::is_port_in_use(host, port).await {
-                return Err(format!("Port {port} is already in use").into());
-            }
-        }
-
-        // Start the service
-        let mut child = tokio::process::Command::new(executable_path)
-            .arg("--address")
-            .arg(&config.address)
-            .arg("--access-key")
-            .arg(&config.access_key)
-            .arg("--secret-key")
-            .arg(&config.secret_key)
-            .arg("--console-address")
-            .arg(&config.console_address)
-            .arg(config.volume_name.clone())
-            .spawn()?;
-
-        let process_pid = child.id().unwrap();
-        // Wait for the service to start
-        tokio::time::sleep(Duration::from_secs(2)).await;
-
-        // Check if the service started successfully
-        if Self::is_port_in_use(host, main_port).await {
-            Self::show_info(&format!("Service started successfully! Process ID: {process_pid}"));
-
-            Ok(())
-        } else {
-            child.kill().await?;
-            Err("Service failed to start".into())
-        }
-    }
-
-    /// Stop the service
-    /// This function stops the service
-    ///
-    /// # Example
-    /// ```
-    /// let result = stop_service().await;
-    /// println!("{:?}", result);
-    /// ```
-    async fn stop_service() -> Result<(), Box<dyn Error>> {
-        let existing_pid = Self::check_service_status().await;
-        debug!("existing_pid: {:?}", existing_pid);
-        if let Some(service_pid) = existing_pid {
-            // An attempt was made to terminate the process
-            #[cfg(unix)]
-            {
-                StdCommand::new("kill").arg("-9").arg(service_pid.to_string()).output()?;
-            }
-
-            #[cfg(windows)]
-            {
-                StdCommand::new("taskkill")
-                    .arg("/F")
-                    .arg("/PID")
-                    .arg(service_pid.to_string())
-                    .output()?;
-            }
-
-            // Verify that the service is indeed stopped
-            tokio::time::sleep(Duration::from_secs(1)).await;
-            if Self::check_service_status().await.is_some() {
-                return Err("Service failed to stop".into());
-            }
-            Self::show_info("Service stopped successfully");
-
-            Ok(())
-        } else {
-            Err("Service is not running".into())
-        }
-    }
-
-    /// Check if the port is in use
-    /// This function checks if the given port is in use on the given host
-    ///
-    /// # Example
-    /// ```
-    /// let host = "127.0.0.1";
-    /// let port = 9000;
-    /// let result = is_port_in_use(host, port).await;
-    /// println!("{:?}", result);
-    /// ```
-    async fn is_port_in_use(host: &str, port: u16) -> bool {
-        TcpStream::connect(format!("{host}:{port}")).await.is_ok()
-    }
-
-    /// Show an error message
-    /// This function shows an error message dialog
-    ///
-    /// # Example
-    /// ```
-    /// show_error("This is an error message");
-    /// ```
-    pub(crate) fn show_error(message: &str) {
-        rfd::MessageDialog::new()
-            .set_title("Error")
-            .set_description(message)
-            .set_level(rfd::MessageLevel::Error)
-            .show();
-    }
-
-    /// Show an information message
-    /// This function shows an information message dialog
-    ///
-    /// # Example
-    /// ```
-    /// show_info("This is an information message");
-    /// ```
-    pub(crate) fn show_info(message: &str) {
-        rfd::MessageDialog::new()
-            .set_title("Success")
-            .set_description(message)
-            .set_level(rfd::MessageLevel::Info)
-            .show();
-    }
-
-    /// Start the service
-    /// This function sends a `Start` command to the service manager
-    ///
-    /// # Example
-    /// ```
-    /// let config = RustFSConfig {
-    ///    address: "127.0.0.1:9000".to_string(),
-    ///    host: "127.0.0.1".to_string(),
-    ///    port: "9000".to_string(),
-    ///    access_key: "rustfsadmin".to_string(),
-    ///    secret_key: "rustfsadmin".to_string(),
-    ///    domain_name: "demo.rustfs.com".to_string(),
-    ///    volume_name: "data".to_string(),
-    ///    console_address: "127.0.0.1:9001".to_string(),
-    /// };
-    ///
-    /// let service_manager = ServiceManager::new();
-    /// let result = service_manager.start(config).await;
-    /// println!("{:?}", result);
-    /// ```
-    ///
-    /// # Errors
-    /// This function returns an error if the service fails to start
-    ///
-    /// # Panics
-    /// This function panics if the port number is invalid
-    ///
-    /// # Safety
-    /// This function is not marked as unsafe
-    ///
-    /// # Performance
-    /// This function is not optimized for performance
-    ///
-    /// # Design
-    /// This function is designed to be simple and easy to use
-    ///
-    /// # Security
-    /// This function does not have any security implications
-    pub async fn start(&self, config: RustFSConfig) -> Result<ServiceOperationResult, Box<dyn Error>> {
-        let start_time = chrono::Local::now();
-        self.command_tx.send(ServiceCommand::Start(config.clone())).await?;
-
-        let host = &config.host;
-        let port = config.port.parse::<u16>().expect("Invalid port number");
-        // wait for the service to actually start
-        let mut retries = 0;
-        while retries < 30 {
-            // wait up to 30 seconds
-            if Self::check_service_status().await.is_some() && Self::is_port_in_use(host, port).await {
-                let end_time = chrono::Local::now();
-                return Ok(ServiceOperationResult {
-                    success: true,
-                    start_time,
-                    end_time,
-                    message: "Service started successfully".to_string(),
-                });
-            }
-            tokio::time::sleep(Duration::from_secs(1)).await;
-            retries += 1;
-        }
-
-        Err("Service start timeout".into())
-    }
-
-    /// Stop the service
-    /// This function sends a `Stop` command to the service manager
-    ///
-    /// # Example
-    /// ```
-    /// let service_manager = ServiceManager::new();
-    /// let result = service_manager.stop().await;
-    /// println!("{:?}", result);
-    /// ```
-    ///
-    /// # Errors
-    /// This function returns an error if the service fails to stop
-    ///
-    /// # Panics
-    /// This function panics if the port number is invalid
-    ///
-    /// # Safety
-    /// This function is not marked as unsafe
-    ///
-    /// # Performance
-    /// This function is not optimized for performance
-    ///
-    /// # Design
-    /// This function is designed to be simple and easy to use
-    ///
-    /// # Security
-    /// This function does not have any security implications
-    pub async fn stop(&self) -> Result<ServiceOperationResult, Box<dyn Error>> {
-        let start_time = chrono::Local::now();
-        self.command_tx.send(ServiceCommand::Stop).await?;
-
-        // Wait for the service to actually stop
-        let mut retries = 0;
-        while retries < 15 {
-            // Wait up to 15 seconds
-            if Self::check_service_status().await.is_none() {
-                let end_time = chrono::Local::now();
-                return Ok(ServiceOperationResult {
-                    success: true,
-                    start_time,
-                    end_time,
-                    message: "Service stopped successfully".to_string(),
-                });
-            }
-            tokio::time::sleep(Duration::from_secs(1)).await;
-            retries += 1;
-        }
-
-        Err("Service stop timeout".into())
-    }
-
-    /// Restart the service
-    /// This function sends a `Restart` command to the service manager
-    ///
-    /// # Example
-    /// ```
-    /// let config = RustFSConfig {
-    ///    address: "127.0.0.1:9000".to_string(),
-    ///    host: "127.0.0.1".to_string(),
-    ///    port: "9000".to_string(),
-    ///    access_key: "rustfsadmin".to_string(),
-    ///    secret_key: "rustfsadmin".to_string(),
-    ///    domain_name: "demo.rustfs.com".to_string(),
-    ///    volume_name: "data".to_string(),
-    ///    console_address: "127.0.0.1:9001".to_string(),
-    /// };
-    ///
-    /// let service_manager = ServiceManager::new();
-    /// let result = service_manager.restart(config).await;
-    /// println!("{:?}", result);
-    /// ```
-    ///
-    /// # Errors
-    /// This function returns an error if the service fails to restart
-    ///
-    /// # Panics
-    /// This function panics if the port number is invalid
-    ///
-    /// # Safety
-    /// This function is not marked as unsafe
-    ///
-    /// # Performance
-    /// This function is not optimized for performance
-    ///
-    /// # Design
-    /// This function is designed to be simple and easy to use
-    ///
-    /// # Security
-    /// This function does not have any security implications
-    pub async fn restart(&self, config: RustFSConfig) -> Result<ServiceOperationResult, Box<dyn Error>> {
-        let start_time = chrono::Local::now();
-        self.command_tx.send(ServiceCommand::Restart(config.clone())).await?;
-
-        let host = &config.host;
-        let port = config.port.parse::<u16>().expect("Invalid port number");
-
-        // wait for the service to restart
-        let mut retries = 0;
-        while retries < 45 {
-            // Longer waiting time is given as both the stop and start processes are involved
-            if Self::check_service_status().await.is_some() && Self::is_port_in_use(host, port).await {
-                match config.save() {
-                    Ok(_) => info!("save config success"),
-                    Err(e) => {
-                        error!("save config error: {}", e);
-                        self.command_tx.send(ServiceCommand::Stop).await?;
-                        Self::show_error("Failed to save configuration");
-                        return Err("Failed to save configuration".into());
-                    }
-                }
-                let end_time = chrono::Local::now();
-                return Ok(ServiceOperationResult {
-                    success: true,
-                    start_time,
-                    end_time,
-                    message: "Service restarted successfully".to_string(),
-                });
-            }
-            tokio::time::sleep(Duration::from_secs(1)).await;
-            retries += 1;
-        }
-        Err("Service restart timeout".into())
-    }
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::time::Duration;
-
-    #[test]
-    fn test_service_command_creation() {
-        let config = RustFSConfig::default_config();
-
-        let start_cmd = ServiceCommand::Start(config.clone());
-        let stop_cmd = ServiceCommand::Stop;
-        let restart_cmd = ServiceCommand::Restart(config);
-
-        // Test that commands can be created
-        match start_cmd {
-            ServiceCommand::Start(_) => {}
-            _ => panic!("Expected Start command"),
-        }
-
-        match stop_cmd {
-            ServiceCommand::Stop => {}
-            _ => panic!("Expected Stop command"),
-        }
-
-        match restart_cmd {
-            ServiceCommand::Restart(_) => {}
-            _ => panic!("Expected Restart command"),
-        }
-    }
-
-    #[test]
-    fn test_service_operation_result_creation() {
-        let start_time = chrono::Local::now();
-        let end_time = chrono::Local::now();
-
-        let success_result = ServiceOperationResult {
-            success: true,
-            start_time,
-            end_time,
-            message: "Operation successful".to_string(),
-        };
-
-        let failure_result = ServiceOperationResult {
-            success: false,
-            start_time,
-            end_time,
-            message: "Operation failed".to_string(),
-        };
-
-        assert!(success_result.success);
-        assert_eq!(success_result.message, "Operation successful");
-
-        assert!(!failure_result.success);
-        assert_eq!(failure_result.message, "Operation failed");
-    }
-
-    #[test]
-    fn test_service_operation_result_debug() {
-        let result = ServiceOperationResult {
-            success: true,
-            start_time: chrono::Local::now(),
-            end_time: chrono::Local::now(),
-            message: "Test message".to_string(),
-        };
-
-        let debug_str = format!("{result:?}");
-        assert!(debug_str.contains("ServiceOperationResult"));
-        assert!(debug_str.contains("success: true"));
-        assert!(debug_str.contains("Test message"));
-    }
-
-    #[test]
-    fn test_service_manager_creation() {
-        // Test ServiceManager creation in a tokio runtime
-        let rt = tokio::runtime::Runtime::new().unwrap();
-        rt.block_on(async {
-            let service_manager = ServiceManager::new();
-
-            // Test that ServiceManager can be created and cloned
-            let cloned_manager = service_manager.clone();
-
-            // Both should be valid (we can't test much more without async runtime)
-            assert!(format!("{service_manager:?}").contains("ServiceManager"));
-            assert!(format!("{cloned_manager:?}").contains("ServiceManager"));
-        });
-    }
-
-    #[test]
-    fn test_extract_port_valid() {
-        let test_cases = vec![
-            ("127.0.0.1:9000", Some(9000)),
-            ("localhost:8080", Some(8080)),
-            ("192.168.1.100:3000", Some(3000)),
-            ("0.0.0.0:80", Some(80)),
-            ("example.com:443", Some(443)),
-            ("host:65535", Some(65535)),
-            ("host:1", Some(1)),
-        ];
-
-        for (input, expected) in test_cases {
-            let result = ServiceManager::extract_port(input);
-            assert_eq!(result, expected, "Failed for input: {input}");
-        }
-    }
-
-    #[test]
-    fn test_extract_port_invalid() {
-        let invalid_cases = vec![
-            "127.0.0.1",       // Missing port
-            "127.0.0.1:",      // Empty port
-            "127.0.0.1:abc",   // Invalid port
-            "127.0.0.1:99999", // Port out of range
-            "",                // Empty string
-            "invalid",         // No colon
-            "host:-1",         // Negative port
-            "host:0.5",        // Decimal port
-        ];
-
-        for input in invalid_cases {
-            let result = ServiceManager::extract_port(input);
-            assert_eq!(result, None, "Should be None for input: {input}");
-        }
-
-        // Special case: empty host but valid port should still work
-        assert_eq!(ServiceManager::extract_port(":9000"), Some(9000));
-
-        // Special case: multiple colons - extract_port takes the second part
-        // For "127.0.0.1:9000:extra", it takes "9000" which is valid
-        assert_eq!(ServiceManager::extract_port("127.0.0.1:9000:extra"), Some(9000));
-    }
-
-    #[test]
-    fn test_extract_port_edge_cases() {
-        // Test edge cases for port numbers
-        assert_eq!(ServiceManager::extract_port("host:0"), Some(0));
-        assert_eq!(ServiceManager::extract_port("host:65535"), Some(65535));
-        assert_eq!(ServiceManager::extract_port("host:65536"), None); // Out of range
-        // IPv6-like address - extract_port takes the second part after split(':')
-        // For "::1:8080", split(':') gives ["", "", "1", "8080"], nth(1) gives ""
-        assert_eq!(ServiceManager::extract_port("::1:8080"), None); // Second part is empty
-        // For "[::1]:8080", split(':') gives ["[", "", "1]", "8080"], nth(1) gives ""
-        assert_eq!(ServiceManager::extract_port("[::1]:8080"), None); // Second part is empty
-    }
-
-    #[test]
-    fn test_show_error() {
-        // Test that show_error function exists and can be called
-        // We can't actually test the dialog in a test environment
-        // so we just verify the function signature
-    }
-
-    #[test]
-    fn test_show_info() {
-        // Test that show_info function exists and can be called
-        // We can't actually test the dialog in a test environment
-        // so we just verify the function signature
-    }
-
-    #[test]
-    fn test_service_operation_result_timing() {
-        let start_time = chrono::Local::now();
-        std::thread::sleep(Duration::from_millis(10)); // Small delay
-        let end_time = chrono::Local::now();
-
-        let result = ServiceOperationResult {
-            success: true,
-            start_time,
-            end_time,
-            message: "Timing test".to_string(),
-        };
-
-        // End time should be after start time
-        assert!(result.end_time >= result.start_time);
-    }
-
-    #[test]
-    fn test_service_operation_result_with_unicode() {
-        let result = ServiceOperationResult {
-            success: true,
-            start_time: chrono::Local::now(),
-            end_time: chrono::Local::now(),
-            message: "Operation successful 🎉".to_string(),
-        };
-
-        assert_eq!(result.message, "Operation successful 🎉");
-        assert!(result.success);
-    }
-
-    #[test]
-    fn test_service_operation_result_with_long_message() {
-        let long_message = "A".repeat(10000);
-        let result = ServiceOperationResult {
-            success: false,
-            start_time: chrono::Local::now(),
-            end_time: chrono::Local::now(),
-            message: long_message.clone(),
-        };
-
-        assert_eq!(result.message.len(), 10000);
-        assert_eq!(result.message, long_message);
-        assert!(!result.success);
-    }
-
-    #[test]
-    fn test_service_command_with_different_configs() {
-        let config1 = RustFSConfig {
-            address: "127.0.0.1:9000".to_string(),
-            host: "127.0.0.1".to_string(),
-            port: "9000".to_string(),
-            access_key: "admin1".to_string(),
-            secret_key: "pass1".to_string(),
-            domain_name: "test1.com".to_string(),
-            volume_name: "/data1".to_string(),
-            console_address: "127.0.0.1:9001".to_string(),
-        };
-
-        let config2 = RustFSConfig {
-            address: "192.168.1.100:8080".to_string(),
-            host: "192.168.1.100".to_string(),
-            port: "8080".to_string(),
-            access_key: "admin2".to_string(),
-            secret_key: "pass2".to_string(),
-            domain_name: "test2.com".to_string(),
-            volume_name: "/data2".to_string(),
-            console_address: "192.168.1.100:8081".to_string(),
-        };
-
-        let start_cmd1 = ServiceCommand::Start(config1);
-        let restart_cmd2 = ServiceCommand::Restart(config2);
-
-        // Test that different configs can be used
-        match start_cmd1 {
-            ServiceCommand::Start(config) => {
-                assert_eq!(config.address, "127.0.0.1:9000");
-                assert_eq!(config.access_key, "admin1");
-            }
-            _ => panic!("Expected Start command"),
-        }
-
-        match restart_cmd2 {
-            ServiceCommand::Restart(config) => {
-                assert_eq!(config.address, "192.168.1.100:8080");
-                assert_eq!(config.access_key, "admin2");
-            }
-            _ => panic!("Expected Restart command"),
-        }
-    }
-
-    #[test]
-    fn test_memory_efficiency() {
-        // Test that structures don't use excessive memory
-        assert!(std::mem::size_of::<ServiceCommand>() < 2000);
-        assert!(std::mem::size_of::<ServiceOperationResult>() < 1000);
-        assert!(std::mem::size_of::<ServiceManager>() < 1000);
-    }
-
-    // Note: The following methods are not tested here because they require:
-    // - Async runtime (tokio)
-    // - File system access
-    // - Network access
-    // - Process management
-    // - External dependencies (embedded assets)
-    //
-    // These should be tested in integration tests:
-    // - check_service_status()
-    // - prepare_service()
-    // - start_service()
-    // - stop_service()
-    // - is_port_in_use()
-    // - ServiceManager::start()
-    // - ServiceManager::stop()
-    // - ServiceManager::restart()
-    //
-    // The RUSTFS_HASH lazy_static is also not tested here as it depends
-    // on embedded assets that may not be available in unit test environment.
-}

cli/rustfs-gui/src/utils/logger.rs

@@ -1,300 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use dioxus::logger::tracing::debug;
-use tracing_appender::non_blocking::WorkerGuard;
-use tracing_appender::rolling::{RollingFileAppender, Rotation};
-use tracing_subscriber::fmt;
-use tracing_subscriber::layer::SubscriberExt;
-use tracing_subscriber::util::SubscriberInitExt;
-
-/// Initialize the logger with a rolling file appender
-/// that rotates log files daily
-pub fn init_logger() -> WorkerGuard {
-    // configuring rolling logs rolling by day
-    let home_dir = dirs::home_dir().expect("Unable to get user directory");
-    let rustfs_dir = home_dir.join("rustfs");
-    let logs_dir = rustfs_dir.join("logs");
-    let file_appender = RollingFileAppender::builder()
-        .rotation(Rotation::DAILY) // rotate log files once every hour
-        .filename_prefix("rustfs-cli") // log file names will be prefixed with `myapp.`
-        .filename_suffix("log") // log file names will be suffixed with `.log`
-        .build(logs_dir) // try to build an appender that stores log files in `/ var/ log`
-        .expect("initializing rolling file appender failed");
-    // non-blocking writer for improved performance
-    let (non_blocking_file, worker_guard) = tracing_appender::non_blocking(file_appender);
-
-    // console output layer
-    let console_layer = fmt::layer()
-        .with_writer(std::io::stdout)
-        .with_ansi(true)
-        .with_line_number(true); // enable colors in the console
-
-    // file output layer
-    let file_layer = fmt::layer()
-        .with_writer(non_blocking_file)
-        .with_ansi(false)
-        .with_thread_names(true)
-        .with_target(true)
-        .with_thread_ids(true)
-        .with_level(true)
-        .with_line_number(true); // disable colors in the file
-
-    // Combine all tiers and initialize global subscribers
-    tracing_subscriber::registry()
-        .with(console_layer)
-        .with(file_layer)
-        .with(tracing_subscriber::EnvFilter::new("info")) // filter the log level by environment variables
-        .init();
-    debug!("Logger initialized");
-    worker_guard
-}
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-    use std::sync::Once;
-
-    static INIT: Once = Once::new();
-
-    // Helper function to ensure logger is only initialized once in tests
-    fn ensure_logger_init() {
-        INIT.call_once(|| {
-            // Initialize a simple test logger to avoid conflicts
-            let _ = tracing_subscriber::fmt().with_test_writer().try_init();
-        });
-    }
-
-    #[test]
-    fn test_logger_initialization_components() {
-        ensure_logger_init();
-
-        // Test that we can create the components used in init_logger
-        // without actually initializing the global logger again
-
-        // Test home directory access
-        let home_dir_result = dirs::home_dir();
-        assert!(home_dir_result.is_some(), "Should be able to get home directory");
-
-        let home_dir = home_dir_result.unwrap();
-        let rustfs_dir = home_dir.join("rustfs");
-        let logs_dir = rustfs_dir.join("logs");
-
-        // Test path construction
-        assert!(rustfs_dir.to_string_lossy().contains("rustfs"));
-        assert!(logs_dir.to_string_lossy().contains("logs"));
-    }
-
-    #[test]
-    fn test_rolling_file_appender_builder() {
-        ensure_logger_init();
-
-        // Test that we can create a RollingFileAppender builder
-        let builder = RollingFileAppender::builder()
-            .rotation(Rotation::DAILY)
-            .filename_prefix("test-rustfs-cli")
-            .filename_suffix("log");
-
-        // We can't actually build it without creating directories,
-        // but we can verify the builder pattern works
-        let debug_str = format!("{builder:?}");
-        // The actual debug format might be different, so just check it's not empty
-        assert!(!debug_str.is_empty());
-        // Check that it contains some expected parts
-        assert!(debug_str.contains("Builder") || debug_str.contains("builder") || debug_str.contains("RollingFileAppender"));
-    }
-
-    #[test]
-    fn test_rotation_types() {
-        ensure_logger_init();
-
-        // Test different rotation types
-        let daily = Rotation::DAILY;
-        let hourly = Rotation::HOURLY;
-        let minutely = Rotation::MINUTELY;
-        let never = Rotation::NEVER;
-
-        // Test that rotation types can be created and formatted
-        assert!(!format!("{daily:?}").is_empty());
-        assert!(!format!("{hourly:?}").is_empty());
-        assert!(!format!("{minutely:?}").is_empty());
-        assert!(!format!("{never:?}").is_empty());
-    }
-
-    #[test]
-    fn test_fmt_layer_configuration() {
-        ensure_logger_init();
-
-        // Test that we can create fmt layers with different configurations
-        // We can't actually test the layers directly due to type complexity,
-        // but we can test that the configuration values are correct
-
-        // Test console layer settings
-        let console_ansi = true;
-        let console_line_number = true;
-        assert!(console_ansi);
-        assert!(console_line_number);
-
-        // Test file layer settings
-        let file_ansi = false;
-        let file_thread_names = true;
-        let file_target = true;
-        let file_thread_ids = true;
-        let file_level = true;
-        let file_line_number = true;
-
-        assert!(!file_ansi);
-        assert!(file_thread_names);
-        assert!(file_target);
-        assert!(file_thread_ids);
-        assert!(file_level);
-        assert!(file_line_number);
-    }
-
-    #[test]
-    fn test_env_filter_creation() {
-        ensure_logger_init();
-
-        // Test that EnvFilter can be created with different levels
-        let info_filter = tracing_subscriber::EnvFilter::new("info");
-        let debug_filter = tracing_subscriber::EnvFilter::new("debug");
-        let warn_filter = tracing_subscriber::EnvFilter::new("warn");
-        let error_filter = tracing_subscriber::EnvFilter::new("error");
-
-        // Test that filters can be created
-        assert!(!format!("{info_filter:?}").is_empty());
-        assert!(!format!("{debug_filter:?}").is_empty());
-        assert!(!format!("{warn_filter:?}").is_empty());
-        assert!(!format!("{error_filter:?}").is_empty());
-    }
-
-    #[test]
-    fn test_path_construction() {
-        ensure_logger_init();
-
-        // Test path construction logic used in init_logger
-        if let Some(home_dir) = dirs::home_dir() {
-            let rustfs_dir = home_dir.join("rustfs");
-            let logs_dir = rustfs_dir.join("logs");
-
-            // Test that paths are constructed correctly
-            assert!(rustfs_dir.ends_with("rustfs"));
-            assert!(logs_dir.ends_with("logs"));
-            assert!(logs_dir.parent().unwrap().ends_with("rustfs"));
-
-            // Test path string representation
-            let rustfs_str = rustfs_dir.to_string_lossy();
-            let logs_str = logs_dir.to_string_lossy();
-
-            assert!(rustfs_str.contains("rustfs"));
-            assert!(logs_str.contains("rustfs"));
-            assert!(logs_str.contains("logs"));
-        }
-    }
-
-    #[test]
-    fn test_filename_patterns() {
-        ensure_logger_init();
-
-        // Test the filename patterns used in the logger
-        let prefix = "rustfs-cli";
-        let suffix = "log";
-
-        assert_eq!(prefix, "rustfs-cli");
-        assert_eq!(suffix, "log");
-
-        // Test that these would create valid filenames
-        let sample_filename = format!("{prefix}.2024-01-01.{suffix}");
-        assert_eq!(sample_filename, "rustfs-cli.2024-01-01.log");
-    }
-
-    #[test]
-    fn test_worker_guard_type() {
-        ensure_logger_init();
-
-        // Test that WorkerGuard type exists and can be referenced
-        // We can't actually create one without the full setup, but we can test the type
-        let guard_size = std::mem::size_of::<WorkerGuard>();
-        assert!(guard_size > 0, "WorkerGuard should have non-zero size");
-    }
-
-    #[test]
-    fn test_logger_configuration_constants() {
-        ensure_logger_init();
-
-        // Test the configuration values used in the logger
-        let default_log_level = "info";
-        let filename_prefix = "rustfs-cli";
-        let filename_suffix = "log";
-        let rotation = Rotation::DAILY;
-
-        assert_eq!(default_log_level, "info");
-        assert_eq!(filename_prefix, "rustfs-cli");
-        assert_eq!(filename_suffix, "log");
-        assert!(matches!(rotation, Rotation::DAILY));
-    }
-
-    #[test]
-    fn test_directory_names() {
-        ensure_logger_init();
-
-        // Test the directory names used in the logger setup
-        let rustfs_dir_name = "rustfs";
-        let logs_dir_name = "logs";
-
-        assert_eq!(rustfs_dir_name, "rustfs");
-        assert_eq!(logs_dir_name, "logs");
-
-        // Test path joining
-        let combined = format!("{rustfs_dir_name}/{logs_dir_name}");
-        assert_eq!(combined, "rustfs/logs");
-    }
-
-    #[test]
-    fn test_layer_settings() {
-        ensure_logger_init();
-
-        // Test the boolean settings used in layer configuration
-        let console_ansi = true;
-        let console_line_number = true;
-        let file_ansi = false;
-        let file_thread_names = true;
-        let file_target = true;
-        let file_thread_ids = true;
-        let file_level = true;
-        let file_line_number = true;
-
-        // Verify the settings
-        assert!(console_ansi);
-        assert!(console_line_number);
-        assert!(!file_ansi);
-        assert!(file_thread_names);
-        assert!(file_target);
-        assert!(file_thread_ids);
-        assert!(file_level);
-        assert!(file_line_number);
-    }
-
-    // Note: The actual init_logger() function is not tested here because:
-    // 1. It initializes a global tracing subscriber which can only be done once
-    // 2. It requires file system access to create directories
-    // 3. It has side effects that would interfere with other tests
-    // 4. It returns a WorkerGuard that needs to be kept alive
-    //
-    // This function should be tested in integration tests where:
-    // - File system access can be properly controlled
-    // - The global state can be managed
-    // - The actual logging behavior can be verified
-    // - The WorkerGuard lifecycle can be properly managed
-}

cli/rustfs-gui/src/views/app.rs

@@ -1,38 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::route::Route;
-use dioxus::logger::tracing::info;
-use dioxus::prelude::*;
-
-const FAVICON: Asset = asset!("/assets/favicon.ico");
-const TAILWIND_CSS: Asset = asset!("/assets/tailwind.css");
-
-/// The main application component
-/// This is the root component of the application
-/// It contains the global resources and the router
-/// for the application
-#[component]
-pub fn App() -> Element {
-    // Build cool things ✌️
-    use document::{Link, Title};
-    info!("App rendered");
-    rsx! {
-        // Global app resources
-        Link { rel: "icon", href: FAVICON }
-        Link { rel: "stylesheet", href: TAILWIND_CSS }
-        Title { "RustFS" }
-        Router::<Route> {}
-    }
-}

cli/rustfs-gui/src/views/home.rs

@@ -1,23 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::components::Home;
-use dioxus::prelude::*;
-
-#[component]
-pub fn HomeViews() -> Element {
-    rsx! {
-        Home {}
-    }
-}

cli/rustfs-gui/src/views/setting.rs

@@ -1,23 +0,0 @@
-// Copyright 2024 RustFS Team
-//
-// Licensed under the Apache License, Version 2.0 (the "License");
-// you may not use this file except in compliance with the License.
-// You may obtain a copy of the License at
-//
-//     http://www.apache.org/licenses/LICENSE-2.0
-//
-// Unless required by applicable law or agreed to in writing, software
-// distributed under the License is distributed on an "AS IS" BASIS,
-// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-// See the License for the specific language governing permissions and
-// limitations under the License.
-
-use crate::components::Setting;
-use dioxus::prelude::*;
-
-#[component]
-pub fn SettingViews() -> Element {
-    rsx! {
-        Setting {}
-    }
-}

cli/rustfs-gui/tailwind.config.js

@@ -1,24 +0,0 @@
-/**
- * Copyright 2024 RustFS Team
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-module.exports = {
-    mode: "all",
-    content: ["./src/**/*.{rs,html,css}", "./dist/**/*.html"],
-    theme: {
-        extend: {},
-    },
-    plugins: [],
-};

crates/ahm/Cargo.toml

@@ -13,6 +13,7 @@ keywords = ["RustFS", "AHM", "health-management", "scanner", "Minio"]
 categories = ["web-programming", "development-tools", "filesystem"]
 
 [dependencies]
+rustfs-config = { workspace = true }
 rustfs-ecstore = { workspace = true }
 rustfs-common = { workspace = true }
 rustfs-filemeta = { workspace = true }
@@ -22,21 +23,23 @@ tokio = { workspace = true, features = ["full"] }
 tokio-util = { workspace = true }
 tracing = { workspace = true }
 serde = { workspace = true, features = ["derive"] }
+time = { workspace = true }
 serde_json = { workspace = true }
 thiserror = { workspace = true }
 uuid = { workspace = true, features = ["v4", "serde"] }
 anyhow = { workspace = true }
 async-trait = { workspace = true }
 futures = { workspace = true }
-url = { workspace = true }
-rustfs-lock = { workspace = true }
 s3s = { workspace = true }
-lazy_static = { workspace = true }
 chrono = { workspace = true }
+rand = { workspace = true }
+reqwest = { workspace = true }
+tempfile = { workspace = true }
+walkdir = { workspace = true }
 
 [dev-dependencies]
 serde_json = { workspace = true }
-serial_test = "3.2.0"
+serial_test = { workspace = true }
 tracing-subscriber = { workspace = true }
-walkdir = "2.5.0"
 tempfile = { workspace = true }
+heed = { workspace = true }

crates/ahm/src/error.rs

@@ -14,10 +14,12 @@
 
 use thiserror::Error;
 
-/// RustFS AHM/Heal/Scanner 统一错误类型
+/// Custom error type for AHM operations
+/// This enum defines various error variants that can occur during
+/// the execution of AHM-related tasks, such as I/O errors, storage errors,
+/// configuration errors, and specific errors related to healing operations.
 #[derive(Debug, Error)]
 pub enum Error {
-    // 通用
     #[error("I/O error: {0}")]
     Io(#[from] std::io::Error),
 
@@ -39,14 +41,26 @@ pub enum Error {
     #[error(transparent)]
     Anyhow(#[from] anyhow::Error),
 
-    // Scanner相关
+    // Scanner
     #[error("Scanner error: {0}")]
     Scanner(String),
 
     #[error("Metrics error: {0}")]
     Metrics(String),
 
-    // Heal相关
+    #[error("Serialization error: {0}")]
+    Serialization(String),
+
+    #[error("IO error: {0}")]
+    IO(String),
+
+    #[error("Not found: {0}")]
+    NotFound(String),
+
+    #[error("Invalid checkpoint: {0}")]
+    InvalidCheckpoint(String),
+
+    // Heal
     #[error("Heal task not found: {task_id}")]
     TaskNotFound { task_id: String },
 
@@ -75,9 +89,13 @@ pub enum Error {
     ProgressTrackingFailed { message: String },
 }
 
+/// A specialized Result type for AHM operations
+///This type is a convenient alias for results returned by functions in the AHM crate,
+/// using the custom Error type defined above.
 pub type Result<T, E = Error> = std::result::Result<T, E>;
 
 impl Error {
+    /// Create an Other error from any error type
     pub fn other<E>(error: E) -> Self
     where
         E: Into<Box<dyn std::error::Error + Send + Sync>>,
@@ -86,7 +104,6 @@ impl Error {
     }
 }
 
-// 可选：实现与 std::io::Error 的互转
 impl From<Error> for std::io::Error {
     fn from(err: Error) -> Self {
         std::io::Error::other(err)

crates/ahm/src/heal/channel.rs

@@ -12,18 +12,19 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::Result;
 use crate::heal::{
     manager::HealManager,
     task::{HealOptions, HealPriority, HealRequest, HealType},
+    utils,
 };
-
+use crate::{Error, Result};
 use rustfs_common::heal_channel::{
     HealChannelCommand, HealChannelPriority, HealChannelReceiver, HealChannelRequest, HealChannelResponse, HealScanMode,
+    publish_heal_response,
 };
 use std::sync::Arc;
 use tokio::sync::mpsc;
-use tracing::{error, info};
+use tracing::{debug, error, info};
 
 /// Heal channel processor
 pub struct HealChannelProcessor {
@@ -60,7 +61,7 @@ impl HealChannelProcessor {
                             }
                         }
                         None => {
-                            info!("Heal channel receiver closed, stopping processor");
+                            debug!("Heal channel receiver closed, stopping processor");
                             break;
                         }
                     }
@@ -89,7 +90,12 @@ impl HealChannelProcessor {
 
     /// Process start request
     async fn process_start_request(&self, request: HealChannelRequest) -> Result<()> {
-        info!("Processing heal start request: {} for bucket: {}", request.id, request.bucket);
+        info!(
+            "Processing heal start request: {} for bucket: {}/{}",
+            request.id,
+            request.bucket,
+            request.object_prefix.as_deref().unwrap_or("")
+        );
 
         // Convert channel request to heal request
         let heal_request = self.convert_to_heal_request(request.clone())?;
@@ -99,7 +105,6 @@ impl HealChannelProcessor {
             Ok(task_id) => {
                 info!("Successfully submitted heal request: {} as task: {}", request.id, task_id);
 
-                // Send success response
                 let response = HealChannelResponse {
                     request_id: request.id,
                     success: true,
@@ -107,9 +112,7 @@ impl HealChannelProcessor {
                     error: None,
                 };
 
-                if let Err(e) = self.response_sender.send(response) {
-                    error!("Failed to send heal response: {}", e);
-                }
+                self.publish_response(response);
             }
             Err(e) => {
                 error!("Failed to submit heal request: {} - {}", request.id, e);
@@ -122,9 +125,7 @@ impl HealChannelProcessor {
                     error: Some(e.to_string()),
                 };
 
-                if let Err(e) = self.response_sender.send(response) {
-                    error!("Failed to send heal error response: {}", e);
-                }
+                self.publish_response(response);
             }
         }
 
@@ -144,9 +145,7 @@ impl HealChannelProcessor {
             error: None,
         };
 
-        if let Err(e) = self.response_sender.send(response) {
-            error!("Failed to send query response: {}", e);
-        }
+        self.publish_response(response);
 
         Ok(())
     }
@@ -164,9 +163,7 @@ impl HealChannelProcessor {
             error: None,
         };
 
-        if let Err(e) = self.response_sender.send(response) {
-            error!("Failed to send cancel response: {}", e);
-        }
+        self.publish_response(response);
 
         Ok(())
     }
@@ -174,9 +171,12 @@ impl HealChannelProcessor {
     /// Convert channel request to heal request
     fn convert_to_heal_request(&self, request: HealChannelRequest) -> Result<HealRequest> {
         let heal_type = if let Some(disk_id) = &request.disk {
+            let set_disk_id = utils::normalize_set_disk_id(disk_id).ok_or_else(|| Error::InvalidHealType {
+                heal_type: format!("erasure-set({disk_id})"),
+            })?;
             HealType::ErasureSet {
                 buckets: vec![],
-                set_disk_id: disk_id.clone(),
+                set_disk_id,
             }
         } else if let Some(prefix) = &request.object_prefix {
             if !prefix.is_empty() {
@@ -226,8 +226,340 @@ impl HealChannelProcessor {
         Ok(HealRequest::new(heal_type, options, priority))
     }
 
+    fn publish_response(&self, response: HealChannelResponse) {
+        // Try to send to local channel first, but don't block broadcast on failure
+        if let Err(e) = self.response_sender.send(response.clone()) {
+            error!("Failed to enqueue heal response locally: {}", e);
+        }
+        // Always attempt to broadcast, even if local send failed
+        // Use the original response for broadcast; local send uses a clone
+        if let Err(e) = publish_heal_response(response) {
+            error!("Failed to broadcast heal response: {}", e);
+        }
+    }
+
     /// Get response sender for external use
     pub fn get_response_sender(&self) -> mpsc::UnboundedSender<HealChannelResponse> {
         self.response_sender.clone()
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::heal::storage::HealStorageAPI;
+    use rustfs_common::heal_channel::{HealChannelPriority, HealChannelRequest, HealScanMode};
+    use std::sync::Arc;
+
+    // Mock storage for testing
+    struct MockStorage;
+    #[async_trait::async_trait]
+    impl HealStorageAPI for MockStorage {
+        async fn get_object_meta(
+            &self,
+            _bucket: &str,
+            _object: &str,
+        ) -> crate::Result<Option<rustfs_ecstore::store_api::ObjectInfo>> {
+            Ok(None)
+        }
+        async fn get_object_data(&self, _bucket: &str, _object: &str) -> crate::Result<Option<Vec<u8>>> {
+            Ok(None)
+        }
+        async fn put_object_data(&self, _bucket: &str, _object: &str, _data: &[u8]) -> crate::Result<()> {
+            Ok(())
+        }
+        async fn delete_object(&self, _bucket: &str, _object: &str) -> crate::Result<()> {
+            Ok(())
+        }
+        async fn verify_object_integrity(&self, _bucket: &str, _object: &str) -> crate::Result<bool> {
+            Ok(true)
+        }
+        async fn ec_decode_rebuild(&self, _bucket: &str, _object: &str) -> crate::Result<Vec<u8>> {
+            Ok(vec![])
+        }
+        async fn get_disk_status(
+            &self,
+            _endpoint: &rustfs_ecstore::disk::endpoint::Endpoint,
+        ) -> crate::Result<crate::heal::storage::DiskStatus> {
+            Ok(crate::heal::storage::DiskStatus::Ok)
+        }
+        async fn format_disk(&self, _endpoint: &rustfs_ecstore::disk::endpoint::Endpoint) -> crate::Result<()> {
+            Ok(())
+        }
+        async fn get_bucket_info(&self, _bucket: &str) -> crate::Result<Option<rustfs_ecstore::store_api::BucketInfo>> {
+            Ok(None)
+        }
+        async fn heal_bucket_metadata(&self, _bucket: &str) -> crate::Result<()> {
+            Ok(())
+        }
+        async fn list_buckets(&self) -> crate::Result<Vec<rustfs_ecstore::store_api::BucketInfo>> {
+            Ok(vec![])
+        }
+        async fn object_exists(&self, _bucket: &str, _object: &str) -> crate::Result<bool> {
+            Ok(false)
+        }
+        async fn get_object_size(&self, _bucket: &str, _object: &str) -> crate::Result<Option<u64>> {
+            Ok(None)
+        }
+        async fn get_object_checksum(&self, _bucket: &str, _object: &str) -> crate::Result<Option<String>> {
+            Ok(None)
+        }
+        async fn heal_object(
+            &self,
+            _bucket: &str,
+            _object: &str,
+            _version_id: Option<&str>,
+            _opts: &rustfs_common::heal_channel::HealOpts,
+        ) -> crate::Result<(rustfs_madmin::heal_commands::HealResultItem, Option<crate::Error>)> {
+            Ok((rustfs_madmin::heal_commands::HealResultItem::default(), None))
+        }
+        async fn heal_bucket(
+            &self,
+            _bucket: &str,
+            _opts: &rustfs_common::heal_channel::HealOpts,
+        ) -> crate::Result<rustfs_madmin::heal_commands::HealResultItem> {
+            Ok(rustfs_madmin::heal_commands::HealResultItem::default())
+        }
+        async fn heal_format(
+            &self,
+            _dry_run: bool,
+        ) -> crate::Result<(rustfs_madmin::heal_commands::HealResultItem, Option<crate::Error>)> {
+            Ok((rustfs_madmin::heal_commands::HealResultItem::default(), None))
+        }
+        async fn list_objects_for_heal(&self, _bucket: &str, _prefix: &str) -> crate::Result<Vec<String>> {
+            Ok(vec![])
+        }
+        async fn list_objects_for_heal_page(
+            &self,
+            _bucket: &str,
+            _prefix: &str,
+            _continuation_token: Option<&str>,
+        ) -> crate::Result<(Vec<String>, Option<String>, bool)> {
+            Ok((vec![], None, false))
+        }
+        async fn get_disk_for_resume(&self, _set_disk_id: &str) -> crate::Result<rustfs_ecstore::disk::DiskStore> {
+            Err(crate::Error::other("Not implemented in mock"))
+        }
+    }
+
+    fn create_test_heal_manager() -> Arc<HealManager> {
+        let storage: Arc<dyn HealStorageAPI> = Arc::new(MockStorage);
+        Arc::new(HealManager::new(storage, None))
+    }
+
+    #[test]
+    fn test_heal_channel_processor_new() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        // Verify processor is created successfully
+        let _sender = processor.get_response_sender();
+        // If we can get the sender, processor was created correctly
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_bucket() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let channel_request = HealChannelRequest {
+            id: "test-id".to_string(),
+            bucket: "test-bucket".to_string(),
+            object_prefix: None,
+            disk: None,
+            priority: HealChannelPriority::Normal,
+            scan_mode: None,
+            remove_corrupted: None,
+            recreate_missing: None,
+            update_parity: None,
+            recursive: None,
+            dry_run: None,
+            timeout_seconds: None,
+            pool_index: None,
+            set_index: None,
+            force_start: false,
+        };
+
+        let heal_request = processor.convert_to_heal_request(channel_request).unwrap();
+        assert!(matches!(heal_request.heal_type, HealType::Bucket { .. }));
+        assert_eq!(heal_request.priority, HealPriority::Normal);
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_object() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let channel_request = HealChannelRequest {
+            id: "test-id".to_string(),
+            bucket: "test-bucket".to_string(),
+            object_prefix: Some("test-object".to_string()),
+            disk: None,
+            priority: HealChannelPriority::High,
+            scan_mode: Some(HealScanMode::Deep),
+            remove_corrupted: Some(true),
+            recreate_missing: Some(true),
+            update_parity: Some(true),
+            recursive: Some(false),
+            dry_run: Some(false),
+            timeout_seconds: Some(300),
+            pool_index: Some(0),
+            set_index: Some(1),
+            force_start: false,
+        };
+
+        let heal_request = processor.convert_to_heal_request(channel_request).unwrap();
+        assert!(matches!(heal_request.heal_type, HealType::Object { .. }));
+        assert_eq!(heal_request.priority, HealPriority::High);
+        assert_eq!(heal_request.options.scan_mode, HealScanMode::Deep);
+        assert!(heal_request.options.remove_corrupted);
+        assert!(heal_request.options.recreate_missing);
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_erasure_set() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let channel_request = HealChannelRequest {
+            id: "test-id".to_string(),
+            bucket: "test-bucket".to_string(),
+            object_prefix: None,
+            disk: Some("pool_0_set_1".to_string()),
+            priority: HealChannelPriority::Critical,
+            scan_mode: None,
+            remove_corrupted: None,
+            recreate_missing: None,
+            update_parity: None,
+            recursive: None,
+            dry_run: None,
+            timeout_seconds: None,
+            pool_index: None,
+            set_index: None,
+            force_start: false,
+        };
+
+        let heal_request = processor.convert_to_heal_request(channel_request).unwrap();
+        assert!(matches!(heal_request.heal_type, HealType::ErasureSet { .. }));
+        assert_eq!(heal_request.priority, HealPriority::Urgent);
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_invalid_disk_id() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let channel_request = HealChannelRequest {
+            id: "test-id".to_string(),
+            bucket: "test-bucket".to_string(),
+            object_prefix: None,
+            disk: Some("invalid-disk-id".to_string()),
+            priority: HealChannelPriority::Normal,
+            scan_mode: None,
+            remove_corrupted: None,
+            recreate_missing: None,
+            update_parity: None,
+            recursive: None,
+            dry_run: None,
+            timeout_seconds: None,
+            pool_index: None,
+            set_index: None,
+            force_start: false,
+        };
+
+        let result = processor.convert_to_heal_request(channel_request);
+        assert!(result.is_err());
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_priority_mapping() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let priorities = vec![
+            (HealChannelPriority::Low, HealPriority::Low),
+            (HealChannelPriority::Normal, HealPriority::Normal),
+            (HealChannelPriority::High, HealPriority::High),
+            (HealChannelPriority::Critical, HealPriority::Urgent),
+        ];
+
+        for (channel_priority, expected_heal_priority) in priorities {
+            let channel_request = HealChannelRequest {
+                id: "test-id".to_string(),
+                bucket: "test-bucket".to_string(),
+                object_prefix: None,
+                disk: None,
+                priority: channel_priority,
+                scan_mode: None,
+                remove_corrupted: None,
+                recreate_missing: None,
+                update_parity: None,
+                recursive: None,
+                dry_run: None,
+                timeout_seconds: None,
+                pool_index: None,
+                set_index: None,
+                force_start: false,
+            };
+
+            let heal_request = processor.convert_to_heal_request(channel_request).unwrap();
+            assert_eq!(heal_request.priority, expected_heal_priority);
+        }
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_force_start() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let channel_request = HealChannelRequest {
+            id: "test-id".to_string(),
+            bucket: "test-bucket".to_string(),
+            object_prefix: None,
+            disk: None,
+            priority: HealChannelPriority::Normal,
+            scan_mode: None,
+            remove_corrupted: Some(false),
+            recreate_missing: Some(false),
+            update_parity: Some(false),
+            recursive: None,
+            dry_run: None,
+            timeout_seconds: None,
+            pool_index: None,
+            set_index: None,
+            force_start: true, // Should override the above false values
+        };
+
+        let heal_request = processor.convert_to_heal_request(channel_request).unwrap();
+        assert!(heal_request.options.remove_corrupted);
+        assert!(heal_request.options.recreate_missing);
+        assert!(heal_request.options.update_parity);
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_heal_request_empty_object_prefix() {
+        let heal_manager = create_test_heal_manager();
+        let processor = HealChannelProcessor::new(heal_manager);
+
+        let channel_request = HealChannelRequest {
+            id: "test-id".to_string(),
+            bucket: "test-bucket".to_string(),
+            object_prefix: Some("".to_string()), // Empty prefix should be treated as bucket heal
+            disk: None,
+            priority: HealChannelPriority::Normal,
+            scan_mode: None,
+            remove_corrupted: None,
+            recreate_missing: None,
+            update_parity: None,
+            recursive: None,
+            dry_run: None,
+            timeout_seconds: None,
+            pool_index: None,
+            set_index: None,
+            force_start: false,
+        };
+
+        let heal_request = processor.convert_to_heal_request(channel_request).unwrap();
+        assert!(matches!(heal_request.heal_type, HealType::Bucket { .. }));
+    }
+}

crates/ahm/src/heal/erasure_healer.rs

@@ -12,12 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
 use crate::heal::{
     progress::HealProgress,
     resume::{CheckpointManager, ResumeManager, ResumeUtils},
     storage::HealStorageAPI,
 };
+use crate::{Error, Result};
 use futures::future::join_all;
 use rustfs_common::heal_channel::{HealOpts, HealScanMode};
 use rustfs_ecstore::disk::DiskStore;
@@ -49,14 +49,15 @@ impl ErasureSetHealer {
     }
 
     /// execute erasure set heal with resume
+    #[tracing::instrument(skip(self, buckets), fields(set_disk_id = %set_disk_id, bucket_count = buckets.len()))]
     pub async fn heal_erasure_set(&self, buckets: &[String], set_disk_id: &str) -> Result<()> {
-        info!("Starting erasure set heal for {} buckets on set disk {}", buckets.len(), set_disk_id);
+        info!("Starting erasure set heal");
 
         // 1. generate or get task id
         let task_id = self.get_or_create_task_id(set_disk_id).await?;
 
         // 2. initialize or resume resume state
-        let (resume_manager, checkpoint_manager) = self.initialize_resume_state(&task_id, buckets).await?;
+        let (resume_manager, checkpoint_manager) = self.initialize_resume_state(&task_id, set_disk_id, buckets).await?;
 
         // 3. execute heal with resume
         let result = self
@@ -77,25 +78,38 @@ impl ErasureSetHealer {
     }
 
     /// get or create task id
-    async fn get_or_create_task_id(&self, _set_disk_id: &str) -> Result<String> {
+    async fn get_or_create_task_id(&self, set_disk_id: &str) -> Result<String> {
         // check if there are resumable tasks
         let resumable_tasks = ResumeUtils::get_resumable_tasks(&self.disk).await?;
 
         for task_id in resumable_tasks {
-            if ResumeUtils::can_resume_task(&self.disk, &task_id).await {
-                info!("Found resumable task: {}", task_id);
-                return Ok(task_id);
+            match ResumeManager::load_from_disk(self.disk.clone(), &task_id).await {
+                Ok(manager) => {
+                    let state = manager.get_state().await;
+                    if state.set_disk_id == set_disk_id && ResumeUtils::can_resume_task(&self.disk, &task_id).await {
+                        info!("Found resumable task: {} for set {}", task_id, set_disk_id);
+                        return Ok(task_id);
+                    }
+                }
+                Err(e) => {
+                    warn!("Failed to load resume state for task {}: {}", task_id, e);
+                }
             }
         }
 
         // create new task id
-        let task_id = ResumeUtils::generate_task_id();
+        let task_id = format!("{}_{}", set_disk_id, ResumeUtils::generate_task_id());
         info!("Created new heal task: {}", task_id);
         Ok(task_id)
     }
 
     /// initialize or resume resume state
-    async fn initialize_resume_state(&self, task_id: &str, buckets: &[String]) -> Result<(ResumeManager, CheckpointManager)> {
+    async fn initialize_resume_state(
+        &self,
+        task_id: &str,
+        set_disk_id: &str,
+        buckets: &[String],
+    ) -> Result<(ResumeManager, CheckpointManager)> {
         // check if resume state exists
         if ResumeManager::has_resume_state(&self.disk, task_id).await {
             info!("Loading existing resume state for task: {}", task_id);
@@ -111,8 +125,14 @@ impl ErasureSetHealer {
         } else {
             info!("Creating new resume state for task: {}", task_id);
 
-            let resume_manager =
-                ResumeManager::new(self.disk.clone(), task_id.to_string(), "erasure_set".to_string(), buckets.to_vec()).await?;
+            let resume_manager = ResumeManager::new(
+                self.disk.clone(),
+                task_id.to_string(),
+                "erasure_set".to_string(),
+                set_disk_id.to_string(),
+                buckets.to_vec(),
+            )
+            .await?;
 
             let checkpoint_manager = CheckpointManager::new(self.disk.clone(), task_id.to_string()).await?;
 
@@ -162,6 +182,7 @@ impl ErasureSetHealer {
             let bucket_result = self
                 .heal_bucket_with_resume(
                     bucket,
+                    bucket_idx,
                     &mut current_object_index,
                     &mut processed_objects,
                     &mut successful_objects,
@@ -182,7 +203,7 @@ impl ErasureSetHealer {
 
             // check cancel status
             if self.cancel_token.is_cancelled() {
-                info!("Heal task cancelled");
+                warn!("Heal task cancelled");
                 return Err(Error::TaskCancelled);
             }
 
@@ -211,9 +232,11 @@ impl ErasureSetHealer {
 
     /// heal single bucket with resume
     #[allow(clippy::too_many_arguments)]
+    #[tracing::instrument(skip(self, current_object_index, processed_objects, successful_objects, failed_objects, _skipped_objects, resume_manager, checkpoint_manager), fields(bucket = %bucket, bucket_index = bucket_index))]
     async fn heal_bucket_with_resume(
         &self,
         bucket: &str,
+        bucket_index: usize,
         current_object_index: &mut usize,
         processed_objects: &mut u64,
         successful_objects: &mut u64,
@@ -222,7 +245,7 @@ impl ErasureSetHealer {
         resume_manager: &ResumeManager,
         checkpoint_manager: &CheckpointManager,
     ) -> Result<()> {
-        info!("Starting heal for bucket: {} from object index {}", bucket, current_object_index);
+        info!(target: "rustfs:ahm:heal_bucket_with_resume" ,"Starting heal for bucket from object index {}", current_object_index);
 
         // 1. get bucket info
         let _bucket_info = match self.storage.get_bucket_info(bucket).await? {
@@ -233,59 +256,114 @@ impl ErasureSetHealer {
             }
         };
 
-        // 2. get objects to heal
-        let objects = self.storage.list_objects_for_heal(bucket, "").await?;
+        // 2. process objects with pagination to avoid loading all objects into memory
+        let mut continuation_token: Option<String> = None;
+        let mut global_obj_idx = 0usize;
 
-        // 3. continue from checkpoint
-        for (obj_idx, object) in objects.iter().enumerate().skip(*current_object_index) {
-            // check if already processed
-            if checkpoint_manager.get_checkpoint().await.processed_objects.contains(object) {
-                continue;
-            }
-
-            // update current object
-            resume_manager
-                .set_current_item(Some(bucket.to_string()), Some(object.clone()))
+        loop {
+            // Get one page of objects
+            let (objects, next_token, is_truncated) = self
+                .storage
+                .list_objects_for_heal_page(bucket, "", continuation_token.as_deref())
                 .await?;
 
-            // heal object
-            let heal_opts = HealOpts {
-                scan_mode: HealScanMode::Normal,
-                remove: true,
-                recreate: true,
-                ..Default::default()
-            };
+            // Process objects in this page
+            for object in objects {
+                // Skip objects before the checkpoint
+                if global_obj_idx < *current_object_index {
+                    global_obj_idx += 1;
+                    continue;
+                }
 
-            match self.storage.heal_object(bucket, object, None, &heal_opts).await {
-                Ok((_result, None)) => {
-                    *successful_objects += 1;
+                // check if already processed
+                if checkpoint_manager.get_checkpoint().await.processed_objects.contains(&object) {
+                    global_obj_idx += 1;
+                    continue;
+                }
+
+                // update current object
+                resume_manager
+                    .set_current_item(Some(bucket.to_string()), Some(object.clone()))
+                    .await?;
+
+                // Check if object still exists before attempting heal
+                let object_exists = match self.storage.object_exists(bucket, &object).await {
+                    Ok(exists) => exists,
+                    Err(e) => {
+                        warn!("Failed to check existence of {}/{}: {}, marking as failed", bucket, object, e);
+                        *failed_objects += 1;
+                        checkpoint_manager.add_failed_object(object.clone()).await?;
+                        global_obj_idx += 1;
+                        *current_object_index = global_obj_idx;
+                        continue;
+                    }
+                };
+
+                if !object_exists {
+                    info!(
+                        target: "rustfs:ahm:heal_bucket_with_resume" ,"Object {}/{} no longer exists, skipping heal (likely deleted intentionally)",
+                        bucket, object
+                    );
                     checkpoint_manager.add_processed_object(object.clone()).await?;
-                    info!("Successfully healed object {}/{}", bucket, object);
+                    *successful_objects += 1; // Treat as successful - object is gone as intended
+                    global_obj_idx += 1;
+                    *current_object_index = global_obj_idx;
+                    continue;
                 }
-                Ok((_, Some(err))) => {
-                    *failed_objects += 1;
-                    checkpoint_manager.add_failed_object(object.clone()).await?;
-                    warn!("Failed to heal object {}/{}: {}", bucket, object, err);
+
+                // heal object
+                let heal_opts = HealOpts {
+                    scan_mode: HealScanMode::Normal,
+                    remove: true,
+                    recreate: true, // Keep recreate enabled for legitimate heal scenarios
+                    ..Default::default()
+                };
+
+                match self.storage.heal_object(bucket, &object, None, &heal_opts).await {
+                    Ok((_result, None)) => {
+                        *successful_objects += 1;
+                        checkpoint_manager.add_processed_object(object.clone()).await?;
+                        info!("Successfully healed object {}/{}", bucket, object);
+                    }
+                    Ok((_, Some(err))) => {
+                        *failed_objects += 1;
+                        checkpoint_manager.add_failed_object(object.clone()).await?;
+                        warn!("Failed to heal object {}/{}: {}", bucket, object, err);
+                    }
+                    Err(err) => {
+                        *failed_objects += 1;
+                        checkpoint_manager.add_failed_object(object.clone()).await?;
+                        warn!("Error healing object {}/{}: {}", bucket, object, err);
+                    }
                 }
-                Err(err) => {
-                    *failed_objects += 1;
-                    checkpoint_manager.add_failed_object(object.clone()).await?;
-                    warn!("Error healing object {}/{}: {}", bucket, object, err);
+
+                *processed_objects += 1;
+                global_obj_idx += 1;
+                *current_object_index = global_obj_idx;
+
+                // check cancel status
+                if self.cancel_token.is_cancelled() {
+                    info!("Heal task cancelled during object processing");
+                    return Err(Error::TaskCancelled);
+                }
+
+                // save checkpoint periodically
+                if global_obj_idx % 100 == 0 {
+                    checkpoint_manager
+                        .update_position(bucket_index, *current_object_index)
+                        .await?;
                 }
             }
 
-            *processed_objects += 1;
-            *current_object_index = obj_idx + 1;
-
-            // check cancel status
-            if self.cancel_token.is_cancelled() {
-                info!("Heal task cancelled during object processing");
-                return Err(Error::TaskCancelled);
+            // Check if there are more pages
+            if !is_truncated {
+                break;
             }
 
-            // save checkpoint periodically
-            if obj_idx % 100 == 0 {
-                checkpoint_manager.update_position(0, *current_object_index).await?;
+            continuation_token = next_token;
+            if continuation_token.is_none() {
+                warn!("List is truncated but no continuation token provided for {}", bucket);
+                break;
             }
         }
 
@@ -316,7 +394,10 @@ impl ErasureSetHealer {
             let cancel_token = self.cancel_token.clone();
 
             async move {
-                let _permit = semaphore.acquire().await.unwrap();
+                let _permit = semaphore
+                    .acquire()
+                    .await
+                    .map_err(|e| Error::other(format!("Failed to acquire semaphore for bucket heal: {e}")))?;
 
                 if cancel_token.is_cancelled() {
                     return Err(Error::TaskCancelled);
@@ -348,16 +429,12 @@ impl ErasureSetHealer {
             }
         };
 
-        // 2. get objects to heal
-        let objects = storage.list_objects_for_heal(bucket, "").await?;
+        // 2. process objects with pagination to avoid loading all objects into memory
+        let mut continuation_token: Option<String> = None;
+        let mut total_scanned = 0u64;
+        let mut total_success = 0u64;
+        let mut total_failed = 0u64;
 
-        // 3. update progress
-        {
-            let mut p = progress.write().await;
-            p.objects_scanned += objects.len() as u64;
-        }
-
-        // 4. heal objects concurrently
         let heal_opts = HealOpts {
             scan_mode: HealScanMode::Normal,
             remove: true,   // remove corrupted data
@@ -365,27 +442,65 @@ impl ErasureSetHealer {
             ..Default::default()
         };
 
-        let object_results = Self::heal_objects_concurrently(storage, bucket, &objects, &heal_opts, progress).await;
+        loop {
+            // Get one page of objects
+            let (objects, next_token, is_truncated) = storage
+                .list_objects_for_heal_page(bucket, "", continuation_token.as_deref())
+                .await?;
 
-        // 5. count results
-        let (success_count, failure_count) = object_results
-            .into_iter()
-            .fold((0, 0), |(success, failure), result| match result {
-                Ok(_) => (success + 1, failure),
-                Err(_) => (success, failure + 1),
-            });
+            let page_count = objects.len() as u64;
+            total_scanned += page_count;
 
-        // 6. update progress
+            // 3. update progress
+            {
+                let mut p = progress.write().await;
+                p.objects_scanned = total_scanned;
+            }
+
+            // 4. heal objects concurrently for this page
+            let object_results = Self::heal_objects_concurrently(storage, bucket, &objects, &heal_opts, progress).await;
+
+            // 5. count results for this page
+            let (success_count, failure_count) =
+                object_results
+                    .into_iter()
+                    .fold((0, 0), |(success, failure), result| match result {
+                        Ok(_) => (success + 1, failure),
+                        Err(_) => (success, failure + 1),
+                    });
+
+            total_success += success_count;
+            total_failed += failure_count;
+
+            // 6. update progress
+            {
+                let mut p = progress.write().await;
+                p.objects_healed = total_success;
+                p.objects_failed = total_failed;
+                p.set_current_object(Some(format!("processing bucket: {bucket} (page)")));
+            }
+
+            // Check if there are more pages
+            if !is_truncated {
+                break;
+            }
+
+            continuation_token = next_token;
+            if continuation_token.is_none() {
+                warn!("List is truncated but no continuation token provided for {}", bucket);
+                break;
+            }
+        }
+
+        // 7. final progress update
         {
             let mut p = progress.write().await;
-            p.objects_healed += success_count;
-            p.objects_failed += failure_count;
             p.set_current_object(Some(format!("completed bucket: {bucket}")));
         }
 
         info!(
-            "Completed heal for bucket {}: {} success, {} failures",
-            bucket, success_count, failure_count
+            "Completed heal for bucket {}: {} success, {} failures (total scanned: {})",
+            bucket, total_success, total_failed, total_scanned
         );
 
         Ok(())
@@ -411,7 +526,10 @@ impl ErasureSetHealer {
             let semaphore = semaphore.clone();
 
             async move {
-                let _permit = semaphore.acquire().await.unwrap();
+                let _permit = semaphore
+                    .acquire()
+                    .await
+                    .map_err(|e| Error::other(format!("Failed to acquire semaphore for object heal: {e}")))?;
 
                 match storage.heal_object(&bucket, &object, None, &heal_opts).await {
                     Ok((_result, None)) => {

crates/ahm/src/heal/event.rs

@@ -12,7 +12,8 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::heal::task::{HealOptions, HealPriority, HealRequest, HealType};
+use crate::heal::{HealOptions, HealPriority, HealRequest, HealType};
+use crate::{Error, Result};
 use rustfs_ecstore::disk::endpoint::Endpoint;
 use serde::{Deserialize, Serialize};
 use std::time::SystemTime;
@@ -104,7 +105,7 @@ pub enum HealEvent {
 
 impl HealEvent {
     /// Convert HealEvent to HealRequest
-    pub fn to_heal_request(&self) -> HealRequest {
+    pub fn to_heal_request(&self) -> Result<HealRequest> {
         match self {
             HealEvent::ObjectCorruption {
                 bucket,
@@ -112,7 +113,7 @@ impl HealEvent {
                 version_id,
                 severity,
                 ..
-            } => HealRequest::new(
+            } => Ok(HealRequest::new(
                 HealType::Object {
                     bucket: bucket.clone(),
                     object: object.clone(),
@@ -120,13 +121,13 @@ impl HealEvent {
                 },
                 HealOptions::default(),
                 Self::severity_to_priority(severity),
-            ),
+            )),
             HealEvent::ObjectMissing {
                 bucket,
                 object,
                 version_id,
                 ..
-            } => HealRequest::new(
+            } => Ok(HealRequest::new(
                 HealType::Object {
                     bucket: bucket.clone(),
                     object: object.clone(),
@@ -134,34 +135,38 @@ impl HealEvent {
                 },
                 HealOptions::default(),
                 HealPriority::High,
-            ),
-            HealEvent::MetadataCorruption { bucket, object, .. } => HealRequest::new(
+            )),
+            HealEvent::MetadataCorruption { bucket, object, .. } => Ok(HealRequest::new(
                 HealType::Metadata {
                     bucket: bucket.clone(),
                     object: object.clone(),
                 },
                 HealOptions::default(),
                 HealPriority::High,
-            ),
+            )),
             HealEvent::DiskStatusChange { endpoint, .. } => {
                 // Convert disk status change to erasure set heal
                 // Note: This requires access to storage to get bucket list, which is not available here
                 // The actual bucket list will need to be provided by the caller or retrieved differently
-                HealRequest::new(
+                let set_disk_id = crate::heal::utils::format_set_disk_id_from_i32(endpoint.pool_idx, endpoint.set_idx)
+                    .ok_or_else(|| Error::InvalidHealType {
+                        heal_type: format!("erasure-set(pool={}, set={})", endpoint.pool_idx, endpoint.set_idx),
+                    })?;
+                Ok(HealRequest::new(
                     HealType::ErasureSet {
                         buckets: vec![], // Empty bucket list - caller should populate this
-                        set_disk_id: format!("{}_{}", endpoint.pool_idx, endpoint.set_idx),
+                        set_disk_id,
                     },
                     HealOptions::default(),
                     HealPriority::High,
-                )
+                ))
             }
             HealEvent::ECDecodeFailure {
                 bucket,
                 object,
                 version_id,
                 ..
-            } => HealRequest::new(
+            } => Ok(HealRequest::new(
                 HealType::ECDecode {
                     bucket: bucket.clone(),
                     object: object.clone(),
@@ -169,13 +174,13 @@ impl HealEvent {
                 },
                 HealOptions::default(),
                 HealPriority::Urgent,
-            ),
+            )),
             HealEvent::ChecksumMismatch {
                 bucket,
                 object,
                 version_id,
                 ..
-            } => HealRequest::new(
+            } => Ok(HealRequest::new(
                 HealType::Object {
                     bucket: bucket.clone(),
                     object: object.clone(),
@@ -183,17 +188,19 @@ impl HealEvent {
                 },
                 HealOptions::default(),
                 HealPriority::High,
-            ),
-            HealEvent::BucketMetadataCorruption { bucket, .. } => {
-                HealRequest::new(HealType::Bucket { bucket: bucket.clone() }, HealOptions::default(), HealPriority::High)
-            }
-            HealEvent::MRFMetadataCorruption { meta_path, .. } => HealRequest::new(
+            )),
+            HealEvent::BucketMetadataCorruption { bucket, .. } => Ok(HealRequest::new(
+                HealType::Bucket { bucket: bucket.clone() },
+                HealOptions::default(),
+                HealPriority::High,
+            )),
+            HealEvent::MRFMetadataCorruption { meta_path, .. } => Ok(HealRequest::new(
                 HealType::MRF {
                     meta_path: meta_path.clone(),
                 },
                 HealOptions::default(),
                 HealPriority::High,
-            ),
+            )),
         }
     }
 
@@ -357,3 +364,319 @@ impl Default for HealEventHandler {
         Self::new(1000)
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::heal::task::{HealPriority, HealType};
+
+    #[test]
+    fn test_heal_event_object_corruption_to_request() {
+        let event = HealEvent::ObjectCorruption {
+            bucket: "test-bucket".to_string(),
+            object: "test-object".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::Object { .. }));
+        assert_eq!(request.priority, HealPriority::High);
+    }
+
+    #[test]
+    fn test_heal_event_object_missing_to_request() {
+        let event = HealEvent::ObjectMissing {
+            bucket: "test-bucket".to_string(),
+            object: "test-object".to_string(),
+            version_id: Some("v1".to_string()),
+            expected_locations: vec![0, 1],
+            available_locations: vec![2, 3],
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::Object { .. }));
+        assert_eq!(request.priority, HealPriority::High);
+    }
+
+    #[test]
+    fn test_heal_event_metadata_corruption_to_request() {
+        let event = HealEvent::MetadataCorruption {
+            bucket: "test-bucket".to_string(),
+            object: "test-object".to_string(),
+            corruption_type: CorruptionType::MetadataCorruption,
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::Metadata { .. }));
+        assert_eq!(request.priority, HealPriority::High);
+    }
+
+    #[test]
+    fn test_heal_event_ec_decode_failure_to_request() {
+        let event = HealEvent::ECDecodeFailure {
+            bucket: "test-bucket".to_string(),
+            object: "test-object".to_string(),
+            version_id: None,
+            missing_shards: vec![0, 1],
+            available_shards: vec![2, 3, 4],
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::ECDecode { .. }));
+        assert_eq!(request.priority, HealPriority::Urgent);
+    }
+
+    #[test]
+    fn test_heal_event_checksum_mismatch_to_request() {
+        let event = HealEvent::ChecksumMismatch {
+            bucket: "test-bucket".to_string(),
+            object: "test-object".to_string(),
+            version_id: None,
+            expected_checksum: "abc123".to_string(),
+            actual_checksum: "def456".to_string(),
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::Object { .. }));
+        assert_eq!(request.priority, HealPriority::High);
+    }
+
+    #[test]
+    fn test_heal_event_bucket_metadata_corruption_to_request() {
+        let event = HealEvent::BucketMetadataCorruption {
+            bucket: "test-bucket".to_string(),
+            corruption_type: CorruptionType::MetadataCorruption,
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::Bucket { .. }));
+        assert_eq!(request.priority, HealPriority::High);
+    }
+
+    #[test]
+    fn test_heal_event_mrf_metadata_corruption_to_request() {
+        let event = HealEvent::MRFMetadataCorruption {
+            meta_path: "test-bucket/test-object".to_string(),
+            corruption_type: CorruptionType::MetadataCorruption,
+        };
+
+        let request = event.to_heal_request().unwrap();
+        assert!(matches!(request.heal_type, HealType::MRF { .. }));
+        assert_eq!(request.priority, HealPriority::High);
+    }
+
+    #[test]
+    fn test_heal_event_severity_to_priority() {
+        let event_low = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::Low,
+        };
+        let request = event_low.to_heal_request().unwrap();
+        assert_eq!(request.priority, HealPriority::Low);
+
+        let event_medium = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::Medium,
+        };
+        let request = event_medium.to_heal_request().unwrap();
+        assert_eq!(request.priority, HealPriority::Normal);
+
+        let event_high = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+        let request = event_high.to_heal_request().unwrap();
+        assert_eq!(request.priority, HealPriority::High);
+
+        let event_critical = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::Critical,
+        };
+        let request = event_critical.to_heal_request().unwrap();
+        assert_eq!(request.priority, HealPriority::Urgent);
+    }
+
+    #[test]
+    fn test_heal_event_description() {
+        let event = HealEvent::ObjectCorruption {
+            bucket: "test-bucket".to_string(),
+            object: "test-object".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+
+        let desc = event.description();
+        assert!(desc.contains("Object corruption detected"));
+        assert!(desc.contains("test-bucket/test-object"));
+        assert!(desc.contains("DataCorruption"));
+    }
+
+    #[test]
+    fn test_heal_event_severity() {
+        let event = HealEvent::ECDecodeFailure {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            missing_shards: vec![],
+            available_shards: vec![],
+        };
+        assert_eq!(event.severity(), Severity::Critical);
+
+        let event = HealEvent::ObjectMissing {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            expected_locations: vec![],
+            available_locations: vec![],
+        };
+        assert_eq!(event.severity(), Severity::High);
+    }
+
+    #[test]
+    fn test_heal_event_handler_new() {
+        let handler = HealEventHandler::new(10);
+        assert_eq!(handler.event_count(), 0);
+        assert_eq!(handler.max_events, 10);
+    }
+
+    #[test]
+    fn test_heal_event_handler_default() {
+        let handler = HealEventHandler::default();
+        assert_eq!(handler.max_events, 1000);
+    }
+
+    #[test]
+    fn test_heal_event_handler_add_event() {
+        let mut handler = HealEventHandler::new(3);
+        let event = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+
+        handler.add_event(event.clone());
+        assert_eq!(handler.event_count(), 1);
+
+        handler.add_event(event.clone());
+        handler.add_event(event.clone());
+        assert_eq!(handler.event_count(), 3);
+    }
+
+    #[test]
+    fn test_heal_event_handler_max_events() {
+        let mut handler = HealEventHandler::new(2);
+        let event = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+
+        handler.add_event(event.clone());
+        handler.add_event(event.clone());
+        handler.add_event(event.clone()); // Should remove oldest
+
+        assert_eq!(handler.event_count(), 2);
+    }
+
+    #[test]
+    fn test_heal_event_handler_get_events() {
+        let mut handler = HealEventHandler::new(10);
+        let event = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+
+        handler.add_event(event.clone());
+        handler.add_event(event.clone());
+
+        let events = handler.get_events();
+        assert_eq!(events.len(), 2);
+    }
+
+    #[test]
+    fn test_heal_event_handler_clear_events() {
+        let mut handler = HealEventHandler::new(10);
+        let event = HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        };
+
+        handler.add_event(event);
+        assert_eq!(handler.event_count(), 1);
+
+        handler.clear_events();
+        assert_eq!(handler.event_count(), 0);
+    }
+
+    #[test]
+    fn test_heal_event_handler_filter_by_severity() {
+        let mut handler = HealEventHandler::new(10);
+        handler.add_event(HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::Low,
+        });
+        handler.add_event(HealEvent::ECDecodeFailure {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            missing_shards: vec![],
+            available_shards: vec![],
+        });
+
+        let high_severity = handler.filter_by_severity(Severity::High);
+        assert_eq!(high_severity.len(), 1); // Only ECDecodeFailure is Critical >= High
+    }
+
+    #[test]
+    fn test_heal_event_handler_filter_by_type() {
+        let mut handler = HealEventHandler::new(10);
+        handler.add_event(HealEvent::ObjectCorruption {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            corruption_type: CorruptionType::DataCorruption,
+            severity: Severity::High,
+        });
+        handler.add_event(HealEvent::ObjectMissing {
+            bucket: "test".to_string(),
+            object: "test".to_string(),
+            version_id: None,
+            expected_locations: vec![],
+            available_locations: vec![],
+        });
+
+        let corruption_events = handler.filter_by_type("ObjectCorruption");
+        assert_eq!(corruption_events.len(), 1);
+
+        let missing_events = handler.filter_by_type("ObjectMissing");
+        assert_eq!(missing_events.len(), 1);
+    }
+}

crates/ahm/src/heal/manager.rs

@@ -12,17 +12,17 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
 use crate::heal::{
     progress::{HealProgress, HealStatistics},
     storage::HealStorageAPI,
     task::{HealOptions, HealPriority, HealRequest, HealTask, HealTaskStatus, HealType},
 };
+use crate::{Error, Result};
 use rustfs_ecstore::disk::DiskAPI;
 use rustfs_ecstore::disk::error::DiskError;
 use rustfs_ecstore::global::GLOBAL_LOCAL_DISK_MAP;
 use std::{
-    collections::{HashMap, VecDeque},
+    collections::{BinaryHeap, HashMap, HashSet},
     sync::Arc,
     time::{Duration, SystemTime},
 };
@@ -31,7 +31,152 @@ use tokio::{
     time::interval,
 };
 use tokio_util::sync::CancellationToken;
-use tracing::{error, info, warn};
+use tracing::{debug, error, info, warn};
+
+/// Priority queue wrapper for heal requests
+/// Uses BinaryHeap for priority-based ordering while maintaining FIFO for same-priority items
+#[derive(Debug)]
+struct PriorityHealQueue {
+    /// Heap of (priority, sequence, request) tuples
+    heap: BinaryHeap<PriorityQueueItem>,
+    /// Sequence counter for FIFO ordering within same priority
+    sequence: u64,
+    /// Set of request keys to prevent duplicates
+    dedup_keys: HashSet<String>,
+}
+
+/// Wrapper for heap items to implement proper ordering
+#[derive(Debug)]
+struct PriorityQueueItem {
+    priority: HealPriority,
+    sequence: u64,
+    request: HealRequest,
+}
+
+impl Eq for PriorityQueueItem {}
+
+impl PartialEq for PriorityQueueItem {
+    fn eq(&self, other: &Self) -> bool {
+        self.priority == other.priority && self.sequence == other.sequence
+    }
+}
+
+impl Ord for PriorityQueueItem {
+    fn cmp(&self, other: &Self) -> std::cmp::Ordering {
+        // First compare by priority (higher priority first)
+        match self.priority.cmp(&other.priority) {
+            std::cmp::Ordering::Equal => {
+                // If priorities are equal, use sequence for FIFO (lower sequence first)
+                other.sequence.cmp(&self.sequence)
+            }
+            ordering => ordering,
+        }
+    }
+}
+
+impl PartialOrd for PriorityQueueItem {
+    fn partial_cmp(&self, other: &Self) -> Option<std::cmp::Ordering> {
+        Some(self.cmp(other))
+    }
+}
+
+impl PriorityHealQueue {
+    fn new() -> Self {
+        Self {
+            heap: BinaryHeap::new(),
+            sequence: 0,
+            dedup_keys: HashSet::new(),
+        }
+    }
+
+    fn len(&self) -> usize {
+        self.heap.len()
+    }
+
+    fn is_empty(&self) -> bool {
+        self.heap.is_empty()
+    }
+
+    fn push(&mut self, request: HealRequest) -> bool {
+        let key = Self::make_dedup_key(&request);
+
+        // Check for duplicates
+        if self.dedup_keys.contains(&key) {
+            return false; // Duplicate request, don't add
+        }
+
+        self.dedup_keys.insert(key);
+        self.sequence += 1;
+        self.heap.push(PriorityQueueItem {
+            priority: request.priority,
+            sequence: self.sequence,
+            request,
+        });
+        true
+    }
+
+    /// Get statistics about queue contents by priority
+    fn get_priority_stats(&self) -> HashMap<HealPriority, usize> {
+        let mut stats = HashMap::new();
+        for item in &self.heap {
+            *stats.entry(item.priority).or_insert(0) += 1;
+        }
+        stats
+    }
+
+    fn pop(&mut self) -> Option<HealRequest> {
+        self.heap.pop().map(|item| {
+            let key = Self::make_dedup_key(&item.request);
+            self.dedup_keys.remove(&key);
+            item.request
+        })
+    }
+
+    /// Create a deduplication key from a heal request
+    fn make_dedup_key(request: &HealRequest) -> String {
+        match &request.heal_type {
+            HealType::Object {
+                bucket,
+                object,
+                version_id,
+            } => {
+                format!("object:{}:{}:{}", bucket, object, version_id.as_deref().unwrap_or(""))
+            }
+            HealType::Bucket { bucket } => {
+                format!("bucket:{bucket}")
+            }
+            HealType::ErasureSet { set_disk_id, .. } => {
+                format!("erasure_set:{set_disk_id}")
+            }
+            HealType::Metadata { bucket, object } => {
+                format!("metadata:{bucket}:{object}")
+            }
+            HealType::MRF { meta_path } => {
+                format!("mrf:{meta_path}")
+            }
+            HealType::ECDecode {
+                bucket,
+                object,
+                version_id,
+            } => {
+                format!("ecdecode:{}:{}:{}", bucket, object, version_id.as_deref().unwrap_or(""))
+            }
+        }
+    }
+
+    /// Check if a request with the same key already exists in the queue
+    #[allow(dead_code)]
+    fn contains_key(&self, request: &HealRequest) -> bool {
+        let key = Self::make_dedup_key(request);
+        self.dedup_keys.contains(&key)
+    }
+
+    /// Check if an erasure set heal request for a specific set_disk_id exists
+    fn contains_erasure_set(&self, set_disk_id: &str) -> bool {
+        let key = format!("erasure_set:{set_disk_id}");
+        self.dedup_keys.contains(&key)
+    }
+}
 
 /// Heal config
 #[derive(Debug, Clone)]
@@ -50,12 +195,28 @@ pub struct HealConfig {
 
 impl Default for HealConfig {
     fn default() -> Self {
+        let queue_size: usize =
+            rustfs_utils::get_env_usize(rustfs_config::ENV_HEAL_QUEUE_SIZE, rustfs_config::DEFAULT_HEAL_QUEUE_SIZE);
+        let heal_interval = Duration::from_secs(rustfs_utils::get_env_u64(
+            rustfs_config::ENV_HEAL_INTERVAL_SECS,
+            rustfs_config::DEFAULT_HEAL_INTERVAL_SECS,
+        ));
+        let enable_auto_heal =
+            rustfs_utils::get_env_bool(rustfs_config::ENV_HEAL_AUTO_HEAL_ENABLE, rustfs_config::DEFAULT_HEAL_AUTO_HEAL_ENABLE);
+        let task_timeout = Duration::from_secs(rustfs_utils::get_env_u64(
+            rustfs_config::ENV_HEAL_TASK_TIMEOUT_SECS,
+            rustfs_config::DEFAULT_HEAL_TASK_TIMEOUT_SECS,
+        ));
+        let max_concurrent_heals = rustfs_utils::get_env_usize(
+            rustfs_config::ENV_HEAL_MAX_CONCURRENT_HEALS,
+            rustfs_config::DEFAULT_HEAL_MAX_CONCURRENT_HEALS,
+        );
         Self {
-            enable_auto_heal: true,
-            heal_interval: Duration::from_secs(10), // 10 seconds
-            max_concurrent_heals: 4,
-            task_timeout: Duration::from_secs(300), // 5 minutes
-            queue_size: 1000,
+            enable_auto_heal,
+            heal_interval,        // 10 seconds
+            max_concurrent_heals, // max 4,
+            task_timeout,         // 5 minutes
+            queue_size,
         }
     }
 }
@@ -85,8 +246,8 @@ pub struct HealManager {
     state: Arc<RwLock<HealState>>,
     /// Active heal tasks
     active_heals: Arc<Mutex<HashMap<String, Arc<HealTask>>>>,
-    /// Heal queue
-    heal_queue: Arc<Mutex<VecDeque<HealRequest>>>,
+    /// Heal queue (priority-based)
+    heal_queue: Arc<Mutex<PriorityHealQueue>>,
     /// Storage layer interface
     storage: Arc<dyn HealStorageAPI>,
     /// Cancel token
@@ -103,7 +264,7 @@ impl HealManager {
             config: Arc::new(RwLock::new(config)),
             state: Arc::new(RwLock::new(HealState::default())),
             active_heals: Arc::new(Mutex::new(HashMap::new())),
-            heal_queue: Arc::new(Mutex::new(VecDeque::new())),
+            heal_queue: Arc::new(Mutex::new(PriorityHealQueue::new())),
             storage,
             cancel_token: CancellationToken::new(),
             statistics: Arc::new(RwLock::new(HealStatistics::new())),
@@ -125,7 +286,7 @@ impl HealManager {
         // start scheduler
         self.start_scheduler().await?;
 
-        // start auto disk scanner
+        // start auto disk scanner to heal unformatted disks
         self.start_auto_disk_scanner().await?;
 
         info!("HealManager started successfully");
@@ -161,17 +322,54 @@ impl HealManager {
         let config = self.config.read().await;
         let mut queue = self.heal_queue.lock().await;
 
-        if queue.len() >= config.queue_size {
+        let queue_len = queue.len();
+        let queue_capacity = config.queue_size;
+
+        if queue_len >= queue_capacity {
             return Err(Error::ConfigurationError {
-                message: "Heal queue is full".to_string(),
+                message: format!("Heal queue is full ({queue_len}/{queue_capacity})"),
             });
         }
 
+        // Warn when queue is getting full (>80% capacity)
+        let capacity_threshold = (queue_capacity as f64 * 0.8) as usize;
+        if queue_len >= capacity_threshold {
+            warn!(
+                "Heal queue is {}% full ({}/{}). Consider increasing queue size or processing capacity.",
+                (queue_len * 100) / queue_capacity,
+                queue_len,
+                queue_capacity
+            );
+        }
+
         let request_id = request.id.clone();
-        queue.push_back(request);
+        let priority = request.priority;
+
+        // Try to push the request; if it's a duplicate, still return the request_id
+        let is_new = queue.push(request);
+
+        // Log queue statistics periodically (when adding high/urgent priority items)
+        if matches!(priority, HealPriority::High | HealPriority::Urgent) {
+            let stats = queue.get_priority_stats();
+            info!(
+                "Heal queue stats after adding {:?} priority request: total={}, urgent={}, high={}, normal={}, low={}",
+                priority,
+                queue_len + 1,
+                stats.get(&HealPriority::Urgent).unwrap_or(&0),
+                stats.get(&HealPriority::High).unwrap_or(&0),
+                stats.get(&HealPriority::Normal).unwrap_or(&0),
+                stats.get(&HealPriority::Low).unwrap_or(&0)
+            );
+        }
+
         drop(queue);
 
-        info!("Submitted heal request: {}", request_id);
+        if is_new {
+            info!("Submitted heal request: {} with priority: {:?}", request_id, priority);
+        } else {
+            info!("Heal request already queued (duplicate): {}", request_id);
+        }
+
         Ok(request_id)
     }
 
@@ -220,7 +418,12 @@ impl HealManager {
 
     /// Get statistics
     pub async fn get_statistics(&self) -> HealStatistics {
-        self.statistics.read().await.clone()
+        let stats = self.statistics.read().await.clone();
+        debug!(
+            "HealManager stats snapshot: total_tasks={}, successful_tasks={}, failed_tasks={}, running_tasks={}",
+            stats.total_tasks, stats.successful_tasks, stats.failed_tasks, stats.running_tasks
+        );
+        stats
     }
 
     /// Get active task count
@@ -271,13 +474,18 @@ impl HealManager {
         let cancel_token = self.cancel_token.clone();
         let storage = self.storage.clone();
 
+        info!(
+            "start_auto_disk_scanner: Starting auto disk scanner with interval: {:?}",
+            config.read().await.heal_interval
+        );
+
         tokio::spawn(async move {
             let mut interval = interval(config.read().await.heal_interval);
 
             loop {
                 tokio::select! {
                     _ = cancel_token.cancelled() => {
-                        info!("Auto disk scanner received shutdown signal");
+                        info!("start_auto_disk_scanner: Auto disk scanner received shutdown signal");
                         break;
                     }
                     _ = interval.tick() => {
@@ -296,6 +504,7 @@ impl HealManager {
                         }
 
                         if endpoints.is_empty() {
+                            info!("start_auto_disk_scanner: No endpoints need healing");
                             continue;
                         }
 
@@ -303,45 +512,58 @@ impl HealManager {
                         let buckets = match storage.list_buckets().await {
                             Ok(buckets) => buckets.iter().map(|b| b.name.clone()).collect::<Vec<String>>(),
                             Err(e) => {
-                                error!("Failed to get bucket list for auto healing: {}", e);
+                                error!("start_auto_disk_scanner: Failed to get bucket list for auto healing: {}", e);
                                 continue;
                             }
                         };
 
                         // Create erasure set heal requests for each endpoint
                         for ep in endpoints {
+                            let Some(set_disk_id) =
+                                crate::heal::utils::format_set_disk_id_from_i32(ep.pool_idx, ep.set_idx)
+                            else {
+                                warn!("start_auto_disk_scanner: Skipping endpoint {} without valid pool/set index", ep);
+                                continue;
+                            };
                             // skip if already queued or healing
+                            // Use consistent lock order: queue first, then active_heals to avoid deadlock
                             let mut skip = false;
                             {
                                 let queue = heal_queue.lock().await;
-                                if queue.iter().any(|req| matches!(&req.heal_type, crate::heal::task::HealType::ErasureSet { set_disk_id, .. } if set_disk_id == &format!("{}_{}", ep.pool_idx, ep.set_idx))) {
+                                if queue.contains_erasure_set(&set_disk_id) {
                                     skip = true;
                                 }
                             }
                             if !skip {
                                 let active = active_heals.lock().await;
-                                if active.values().any(|task| matches!(&task.heal_type, crate::heal::task::HealType::ErasureSet { set_disk_id, .. } if set_disk_id == &format!("{}_{}", ep.pool_idx, ep.set_idx))) {
+                                if active.values().any(|task| {
+                                    matches!(
+                                        &task.heal_type,
+                                        crate::heal::task::HealType::ErasureSet { set_disk_id: active_id, .. }
+                                        if active_id == &set_disk_id
+                                    )
+                                }) {
                                     skip = true;
                                 }
                             }
 
                             if skip {
+                                info!("start_auto_disk_scanner: Skipping auto erasure set heal for endpoint: {} (set_disk_id: {}) because it is already queued or healing", ep, set_disk_id);
                                 continue;
                             }
 
                             // enqueue erasure set heal request for this disk
-                            let set_disk_id = format!("pool_{}_set_{}", ep.pool_idx, ep.set_idx);
                             let req = HealRequest::new(
                                 HealType::ErasureSet {
                                     buckets: buckets.clone(),
-                                    set_disk_id: set_disk_id.clone()
+                                    set_disk_id: set_disk_id.clone(),
                                 },
                                 HealOptions::default(),
                                 HealPriority::Normal,
                             );
                             let mut queue = heal_queue.lock().await;
-                            queue.push_back(req);
-                            info!("Enqueued auto erasure set heal for endpoint: {} (set_disk_id: {})", ep, set_disk_id);
+                            queue.push(req);
+                            info!("start_auto_disk_scanner: Enqueued auto erasure set heal for endpoint: {} (set_disk_id: {})", ep, set_disk_id);
                         }
                     }
                 }
@@ -351,8 +573,9 @@ impl HealManager {
     }
 
     /// Process heal queue
+    /// Processes multiple tasks per cycle when capacity allows and queue has high-priority items
     async fn process_heal_queue(
-        heal_queue: &Arc<Mutex<VecDeque<HealRequest>>>,
+        heal_queue: &Arc<Mutex<PriorityHealQueue>>,
         active_heals: &Arc<Mutex<HashMap<String, Arc<HealTask>>>>,
         config: &Arc<RwLock<HealConfig>>,
         statistics: &Arc<RwLock<HealStatistics>>,
@@ -361,51 +584,83 @@ impl HealManager {
         let config = config.read().await;
         let mut active_heals_guard = active_heals.lock().await;
 
-        // check if new heal tasks can be started
-        if active_heals_guard.len() >= config.max_concurrent_heals {
+        // Check if new heal tasks can be started
+        let active_count = active_heals_guard.len();
+        if active_count >= config.max_concurrent_heals {
             return;
         }
 
+        // Calculate how many tasks we can start this cycle
+        let available_slots = config.max_concurrent_heals - active_count;
+
         let mut queue = heal_queue.lock().await;
-        if let Some(request) = queue.pop_front() {
-            let task = Arc::new(HealTask::from_request(request, storage.clone()));
-            let task_id = task.id.clone();
-            active_heals_guard.insert(task_id.clone(), task.clone());
-            drop(active_heals_guard);
-            let active_heals_clone = active_heals.clone();
-            let statistics_clone = statistics.clone();
+        let queue_len = queue.len();
 
-            // start heal task
-            tokio::spawn(async move {
-                info!("Starting heal task: {}", task_id);
-                let result = task.execute().await;
-                match result {
-                    Ok(_) => {
-                        info!("Heal task completed successfully: {}", task_id);
-                    }
-                    Err(e) => {
-                        error!("Heal task failed: {} - {}", task_id, e);
-                    }
-                }
-                let mut active_heals_guard = active_heals_clone.lock().await;
-                if let Some(completed_task) = active_heals_guard.remove(&task_id) {
-                    // update statistics
-                    let mut stats = statistics_clone.write().await;
-                    match completed_task.get_status().await {
-                        HealTaskStatus::Completed => {
-                            stats.update_task_completion(true);
+        if queue_len == 0 {
+            return;
+        }
+
+        // Process multiple tasks if:
+        // 1. We have available slots
+        // 2. Queue is not empty
+        // Prioritize urgent/high priority tasks by processing up to 2 tasks per cycle if available
+        let tasks_to_process = if queue_len > 0 {
+            std::cmp::min(available_slots, std::cmp::min(2, queue_len))
+        } else {
+            0
+        };
+
+        for _ in 0..tasks_to_process {
+            if let Some(request) = queue.pop() {
+                let task_priority = request.priority;
+                let task = Arc::new(HealTask::from_request(request, storage.clone()));
+                let task_id = task.id.clone();
+                active_heals_guard.insert(task_id.clone(), task.clone());
+                let active_heals_clone = active_heals.clone();
+                let statistics_clone = statistics.clone();
+
+                // start heal task
+                tokio::spawn(async move {
+                    info!("Starting heal task: {} with priority: {:?}", task_id, task_priority);
+                    let result = task.execute().await;
+                    match result {
+                        Ok(_) => {
+                            info!("Heal task completed successfully: {}", task_id);
                         }
-                        _ => {
-                            stats.update_task_completion(false);
+                        Err(e) => {
+                            error!("Heal task failed: {} - {}", task_id, e);
                         }
                     }
-                    stats.update_running_tasks(active_heals_guard.len() as u64);
-                }
-            });
+                    let mut active_heals_guard = active_heals_clone.lock().await;
+                    if let Some(completed_task) = active_heals_guard.remove(&task_id) {
+                        // update statistics
+                        let mut stats = statistics_clone.write().await;
+                        match completed_task.get_status().await {
+                            HealTaskStatus::Completed => {
+                                stats.update_task_completion(true);
+                            }
+                            _ => {
+                                stats.update_task_completion(false);
+                            }
+                        }
+                        stats.update_running_tasks(active_heals_guard.len() as u64);
+                    }
+                });
+            } else {
+                break;
+            }
+        }
 
-            // update statistics
-            let mut stats = statistics.write().await;
-            stats.total_tasks += 1;
+        // Update statistics for all started tasks
+        let mut stats = statistics.write().await;
+        stats.total_tasks += tasks_to_process as u64;
+
+        // Log queue status if items remain
+        if !queue.is_empty() {
+            let remaining = queue.len();
+            if remaining > 10 {
+                info!("Heal queue has {} pending requests, {} tasks active", remaining, active_heals_guard.len());
+            }
         }
     }
 }
@@ -420,3 +675,333 @@ impl std::fmt::Debug for HealManager {
             .finish()
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::heal::task::{HealOptions, HealPriority, HealRequest, HealType};
+
+    #[test]
+    fn test_priority_queue_ordering() {
+        let mut queue = PriorityHealQueue::new();
+
+        // Add requests with different priorities
+        let low_req = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket1".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Low,
+        );
+
+        let normal_req = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket2".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let high_req = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket3".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::High,
+        );
+
+        let urgent_req = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket4".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Urgent,
+        );
+
+        // Add in random order: low, high, normal, urgent
+        assert!(queue.push(low_req));
+        assert!(queue.push(high_req));
+        assert!(queue.push(normal_req));
+        assert!(queue.push(urgent_req));
+
+        assert_eq!(queue.len(), 4);
+
+        // Should pop in priority order: urgent, high, normal, low
+        let popped1 = queue.pop().unwrap();
+        assert_eq!(popped1.priority, HealPriority::Urgent);
+
+        let popped2 = queue.pop().unwrap();
+        assert_eq!(popped2.priority, HealPriority::High);
+
+        let popped3 = queue.pop().unwrap();
+        assert_eq!(popped3.priority, HealPriority::Normal);
+
+        let popped4 = queue.pop().unwrap();
+        assert_eq!(popped4.priority, HealPriority::Low);
+
+        assert_eq!(queue.len(), 0);
+    }
+
+    #[test]
+    fn test_priority_queue_fifo_same_priority() {
+        let mut queue = PriorityHealQueue::new();
+
+        // Add multiple requests with same priority
+        let req1 = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket1".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let req2 = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket2".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let req3 = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket3".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let id1 = req1.id.clone();
+        let id2 = req2.id.clone();
+        let id3 = req3.id.clone();
+
+        assert!(queue.push(req1));
+        assert!(queue.push(req2));
+        assert!(queue.push(req3));
+
+        // Should maintain FIFO order for same priority
+        let popped1 = queue.pop().unwrap();
+        assert_eq!(popped1.id, id1);
+
+        let popped2 = queue.pop().unwrap();
+        assert_eq!(popped2.id, id2);
+
+        let popped3 = queue.pop().unwrap();
+        assert_eq!(popped3.id, id3);
+    }
+
+    #[test]
+    fn test_priority_queue_deduplication() {
+        let mut queue = PriorityHealQueue::new();
+
+        let req1 = HealRequest::new(
+            HealType::Object {
+                bucket: "bucket1".to_string(),
+                object: "object1".to_string(),
+                version_id: None,
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let req2 = HealRequest::new(
+            HealType::Object {
+                bucket: "bucket1".to_string(),
+                object: "object1".to_string(),
+                version_id: None,
+            },
+            HealOptions::default(),
+            HealPriority::High,
+        );
+
+        // First request should be added
+        assert!(queue.push(req1));
+        assert_eq!(queue.len(), 1);
+
+        // Second request with same object should be rejected (duplicate)
+        assert!(!queue.push(req2));
+        assert_eq!(queue.len(), 1);
+    }
+
+    #[test]
+    fn test_priority_queue_contains_erasure_set() {
+        let mut queue = PriorityHealQueue::new();
+
+        let req = HealRequest::new(
+            HealType::ErasureSet {
+                buckets: vec!["bucket1".to_string()],
+                set_disk_id: "pool_0_set_1".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        assert!(queue.push(req));
+        assert!(queue.contains_erasure_set("pool_0_set_1"));
+        assert!(!queue.contains_erasure_set("pool_0_set_2"));
+    }
+
+    #[test]
+    fn test_priority_queue_dedup_key_generation() {
+        // Test different heal types generate different keys
+        let obj_req = HealRequest::new(
+            HealType::Object {
+                bucket: "bucket1".to_string(),
+                object: "object1".to_string(),
+                version_id: None,
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let bucket_req = HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket1".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let erasure_req = HealRequest::new(
+            HealType::ErasureSet {
+                buckets: vec!["bucket1".to_string()],
+                set_disk_id: "pool_0_set_1".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        );
+
+        let obj_key = PriorityHealQueue::make_dedup_key(&obj_req);
+        let bucket_key = PriorityHealQueue::make_dedup_key(&bucket_req);
+        let erasure_key = PriorityHealQueue::make_dedup_key(&erasure_req);
+
+        // All keys should be different
+        assert_ne!(obj_key, bucket_key);
+        assert_ne!(obj_key, erasure_key);
+        assert_ne!(bucket_key, erasure_key);
+
+        assert!(obj_key.starts_with("object:"));
+        assert!(bucket_key.starts_with("bucket:"));
+        assert!(erasure_key.starts_with("erasure_set:"));
+    }
+
+    #[test]
+    fn test_priority_queue_mixed_priorities_and_types() {
+        let mut queue = PriorityHealQueue::new();
+
+        // Add various requests
+        let requests = vec![
+            (
+                HealType::Object {
+                    bucket: "b1".to_string(),
+                    object: "o1".to_string(),
+                    version_id: None,
+                },
+                HealPriority::Low,
+            ),
+            (
+                HealType::Bucket {
+                    bucket: "b2".to_string(),
+                },
+                HealPriority::Urgent,
+            ),
+            (
+                HealType::ErasureSet {
+                    buckets: vec!["b3".to_string()],
+                    set_disk_id: "pool_0_set_1".to_string(),
+                },
+                HealPriority::Normal,
+            ),
+            (
+                HealType::Object {
+                    bucket: "b4".to_string(),
+                    object: "o4".to_string(),
+                    version_id: None,
+                },
+                HealPriority::High,
+            ),
+        ];
+
+        for (heal_type, priority) in requests {
+            let req = HealRequest::new(heal_type, HealOptions::default(), priority);
+            queue.push(req);
+        }
+
+        assert_eq!(queue.len(), 4);
+
+        // Check they come out in priority order
+        let priorities: Vec<HealPriority> = (0..4).filter_map(|_| queue.pop().map(|r| r.priority)).collect();
+
+        assert_eq!(
+            priorities,
+            vec![
+                HealPriority::Urgent,
+                HealPriority::High,
+                HealPriority::Normal,
+                HealPriority::Low,
+            ]
+        );
+    }
+
+    #[test]
+    fn test_priority_queue_stats() {
+        let mut queue = PriorityHealQueue::new();
+
+        // Add requests with different priorities
+        for _ in 0..3 {
+            queue.push(HealRequest::new(
+                HealType::Bucket {
+                    bucket: format!("bucket-low-{}", queue.len()),
+                },
+                HealOptions::default(),
+                HealPriority::Low,
+            ));
+        }
+
+        for _ in 0..2 {
+            queue.push(HealRequest::new(
+                HealType::Bucket {
+                    bucket: format!("bucket-normal-{}", queue.len()),
+                },
+                HealOptions::default(),
+                HealPriority::Normal,
+            ));
+        }
+
+        queue.push(HealRequest::new(
+            HealType::Bucket {
+                bucket: "bucket-high".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::High,
+        ));
+
+        let stats = queue.get_priority_stats();
+
+        assert_eq!(*stats.get(&HealPriority::Low).unwrap_or(&0), 3);
+        assert_eq!(*stats.get(&HealPriority::Normal).unwrap_or(&0), 2);
+        assert_eq!(*stats.get(&HealPriority::High).unwrap_or(&0), 1);
+        assert_eq!(*stats.get(&HealPriority::Urgent).unwrap_or(&0), 0);
+    }
+
+    #[test]
+    fn test_priority_queue_is_empty() {
+        let mut queue = PriorityHealQueue::new();
+
+        assert!(queue.is_empty());
+
+        queue.push(HealRequest::new(
+            HealType::Bucket {
+                bucket: "test".to_string(),
+            },
+            HealOptions::default(),
+            HealPriority::Normal,
+        ));
+
+        assert!(!queue.is_empty());
+
+        queue.pop();
+
+        assert!(queue.is_empty());
+    }
+}

crates/ahm/src/heal/mod.rs

@@ -20,6 +20,7 @@ pub mod progress;
 pub mod resume;
 pub mod storage;
 pub mod task;
+pub mod utils;
 
 pub use erasure_healer::ErasureSetHealer;
 pub use manager::HealManager;

crates/ahm/src/heal/progress.rs

@@ -146,3 +146,244 @@ impl HealStatistics {
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_heal_progress_new() {
+        let progress = HealProgress::new();
+        assert_eq!(progress.objects_scanned, 0);
+        assert_eq!(progress.objects_healed, 0);
+        assert_eq!(progress.objects_failed, 0);
+        assert_eq!(progress.bytes_processed, 0);
+        assert_eq!(progress.progress_percentage, 0.0);
+        assert!(progress.start_time.is_some());
+        assert!(progress.last_update_time.is_some());
+        assert!(progress.current_object.is_none());
+    }
+
+    #[test]
+    fn test_heal_progress_update_progress() {
+        let mut progress = HealProgress::new();
+        progress.update_progress(10, 8, 2, 1024);
+
+        assert_eq!(progress.objects_scanned, 10);
+        assert_eq!(progress.objects_healed, 8);
+        assert_eq!(progress.objects_failed, 2);
+        assert_eq!(progress.bytes_processed, 1024);
+        // Progress percentage should be calculated based on healed/total
+        // total = scanned + healed + failed = 10 + 8 + 2 = 20
+        // healed/total = 8/20 = 0.4 = 40%
+        assert!((progress.progress_percentage - 40.0).abs() < 0.001);
+        assert!(progress.last_update_time.is_some());
+    }
+
+    #[test]
+    fn test_heal_progress_update_progress_zero_total() {
+        let mut progress = HealProgress::new();
+        progress.update_progress(0, 0, 0, 0);
+
+        assert_eq!(progress.progress_percentage, 0.0);
+    }
+
+    #[test]
+    fn test_heal_progress_update_progress_all_healed() {
+        let mut progress = HealProgress::new();
+        // When scanned=0, healed=10, failed=0: total=10, progress = 10/10 = 100%
+        progress.update_progress(0, 10, 0, 2048);
+
+        // All healed, should be 100%
+        assert!((progress.progress_percentage - 100.0).abs() < 0.001);
+    }
+
+    #[test]
+    fn test_heal_progress_set_current_object() {
+        let mut progress = HealProgress::new();
+        let initial_time = progress.last_update_time;
+
+        // Small delay to ensure time difference
+        std::thread::sleep(std::time::Duration::from_millis(10));
+
+        progress.set_current_object(Some("test-bucket/test-object".to_string()));
+
+        assert_eq!(progress.current_object, Some("test-bucket/test-object".to_string()));
+        assert!(progress.last_update_time.is_some());
+        // last_update_time should be updated
+        assert_ne!(progress.last_update_time, initial_time);
+    }
+
+    #[test]
+    fn test_heal_progress_set_current_object_none() {
+        let mut progress = HealProgress::new();
+        progress.set_current_object(Some("test".to_string()));
+        progress.set_current_object(None);
+
+        assert!(progress.current_object.is_none());
+    }
+
+    #[test]
+    fn test_heal_progress_is_completed_by_percentage() {
+        let mut progress = HealProgress::new();
+        progress.update_progress(10, 10, 0, 1024);
+
+        assert!(progress.is_completed());
+    }
+
+    #[test]
+    fn test_heal_progress_is_completed_by_processed() {
+        let mut progress = HealProgress::new();
+        progress.objects_scanned = 10;
+        progress.objects_healed = 8;
+        progress.objects_failed = 2;
+        // healed + failed = 8 + 2 = 10 >= scanned = 10
+        assert!(progress.is_completed());
+    }
+
+    #[test]
+    fn test_heal_progress_is_not_completed() {
+        let mut progress = HealProgress::new();
+        progress.objects_scanned = 10;
+        progress.objects_healed = 5;
+        progress.objects_failed = 2;
+        // healed + failed = 5 + 2 = 7 < scanned = 10
+        assert!(!progress.is_completed());
+    }
+
+    #[test]
+    fn test_heal_progress_get_success_rate() {
+        let mut progress = HealProgress::new();
+        progress.objects_healed = 8;
+        progress.objects_failed = 2;
+
+        // success_rate = 8 / (8 + 2) * 100 = 80%
+        assert!((progress.get_success_rate() - 80.0).abs() < 0.001);
+    }
+
+    #[test]
+    fn test_heal_progress_get_success_rate_zero_total() {
+        let progress = HealProgress::new();
+        // No healed or failed objects
+        assert_eq!(progress.get_success_rate(), 0.0);
+    }
+
+    #[test]
+    fn test_heal_progress_get_success_rate_all_success() {
+        let mut progress = HealProgress::new();
+        progress.objects_healed = 10;
+        progress.objects_failed = 0;
+
+        assert!((progress.get_success_rate() - 100.0).abs() < 0.001);
+    }
+
+    #[test]
+    fn test_heal_statistics_new() {
+        let stats = HealStatistics::new();
+        assert_eq!(stats.total_tasks, 0);
+        assert_eq!(stats.successful_tasks, 0);
+        assert_eq!(stats.failed_tasks, 0);
+        assert_eq!(stats.running_tasks, 0);
+        assert_eq!(stats.total_objects_healed, 0);
+        assert_eq!(stats.total_bytes_healed, 0);
+    }
+
+    #[test]
+    fn test_heal_statistics_default() {
+        let stats = HealStatistics::default();
+        assert_eq!(stats.total_tasks, 0);
+        assert_eq!(stats.successful_tasks, 0);
+        assert_eq!(stats.failed_tasks, 0);
+    }
+
+    #[test]
+    fn test_heal_statistics_update_task_completion_success() {
+        let mut stats = HealStatistics::new();
+        let initial_time = stats.last_update_time;
+
+        std::thread::sleep(std::time::Duration::from_millis(10));
+        stats.update_task_completion(true);
+
+        assert_eq!(stats.successful_tasks, 1);
+        assert_eq!(stats.failed_tasks, 0);
+        assert!(stats.last_update_time > initial_time);
+    }
+
+    #[test]
+    fn test_heal_statistics_update_task_completion_failure() {
+        let mut stats = HealStatistics::new();
+        stats.update_task_completion(false);
+
+        assert_eq!(stats.successful_tasks, 0);
+        assert_eq!(stats.failed_tasks, 1);
+    }
+
+    #[test]
+    fn test_heal_statistics_update_running_tasks() {
+        let mut stats = HealStatistics::new();
+        let initial_time = stats.last_update_time;
+
+        std::thread::sleep(std::time::Duration::from_millis(10));
+        stats.update_running_tasks(5);
+
+        assert_eq!(stats.running_tasks, 5);
+        assert!(stats.last_update_time > initial_time);
+    }
+
+    #[test]
+    fn test_heal_statistics_add_healed_objects() {
+        let mut stats = HealStatistics::new();
+        let initial_time = stats.last_update_time;
+
+        std::thread::sleep(std::time::Duration::from_millis(10));
+        stats.add_healed_objects(10, 10240);
+
+        assert_eq!(stats.total_objects_healed, 10);
+        assert_eq!(stats.total_bytes_healed, 10240);
+        assert!(stats.last_update_time > initial_time);
+    }
+
+    #[test]
+    fn test_heal_statistics_add_healed_objects_accumulative() {
+        let mut stats = HealStatistics::new();
+        stats.add_healed_objects(5, 5120);
+        stats.add_healed_objects(3, 3072);
+
+        assert_eq!(stats.total_objects_healed, 8);
+        assert_eq!(stats.total_bytes_healed, 8192);
+    }
+
+    #[test]
+    fn test_heal_statistics_get_success_rate() {
+        let mut stats = HealStatistics::new();
+        stats.successful_tasks = 8;
+        stats.failed_tasks = 2;
+
+        // success_rate = 8 / (8 + 2) * 100 = 80%
+        assert!((stats.get_success_rate() - 80.0).abs() < 0.001);
+    }
+
+    #[test]
+    fn test_heal_statistics_get_success_rate_zero_total() {
+        let stats = HealStatistics::new();
+        assert_eq!(stats.get_success_rate(), 0.0);
+    }
+
+    #[test]
+    fn test_heal_statistics_get_success_rate_all_success() {
+        let mut stats = HealStatistics::new();
+        stats.successful_tasks = 10;
+        stats.failed_tasks = 0;
+
+        assert!((stats.get_success_rate() - 100.0).abs() < 0.001);
+    }
+
+    #[test]
+    fn test_heal_statistics_get_success_rate_all_failure() {
+        let mut stats = HealStatistics::new();
+        stats.successful_tasks = 0;
+        stats.failed_tasks = 5;
+
+        assert_eq!(stats.get_success_rate(), 0.0);
+    }
+}

crates/ahm/src/heal/resume.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
+use crate::{Error, Result};
 use rustfs_ecstore::disk::{BUCKET_META_PREFIX, DiskAPI, DiskStore, RUSTFS_META_BUCKET};
 use serde::{Deserialize, Serialize};
 use std::path::Path;
@@ -27,6 +27,12 @@ const RESUME_STATE_FILE: &str = "ahm_resume_state.json";
 const RESUME_PROGRESS_FILE: &str = "ahm_progress.json";
 const RESUME_CHECKPOINT_FILE: &str = "ahm_checkpoint.json";
 
+/// Helper function to convert Path to &str, returning an error if conversion fails
+fn path_to_str(path: &Path) -> Result<&str> {
+    path.to_str()
+        .ok_or_else(|| Error::other(format!("Invalid UTF-8 path: {path:?}")))
+}
+
 /// resume state
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct ResumeState {
@@ -34,6 +40,9 @@ pub struct ResumeState {
     pub task_id: String,
     /// task type
     pub task_type: String,
+    /// set disk identifier (for erasure set tasks)
+    #[serde(default)]
+    pub set_disk_id: String,
     /// start time
     pub start_time: u64,
     /// last update time
@@ -67,12 +76,13 @@ pub struct ResumeState {
 }
 
 impl ResumeState {
-    pub fn new(task_id: String, task_type: String, buckets: Vec<String>) -> Self {
+    pub fn new(task_id: String, task_type: String, set_disk_id: String, buckets: Vec<String>) -> Self {
         Self {
             task_id,
             task_type,
-            start_time: SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs(),
-            last_update: SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs(),
+            set_disk_id,
+            start_time: SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs(),
+            last_update: SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs(),
             completed: false,
             total_objects: 0,
             processed_objects: 0,
@@ -94,13 +104,13 @@ impl ResumeState {
         self.successful_objects = successful;
         self.failed_objects = failed;
         self.skipped_objects = skipped;
-        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn set_current_item(&mut self, bucket: Option<String>, object: Option<String>) {
         self.current_bucket = bucket;
         self.current_object = object;
-        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn complete_bucket(&mut self, bucket: &str) {
@@ -110,22 +120,22 @@ impl ResumeState {
         if let Some(pos) = self.pending_buckets.iter().position(|b| b == bucket) {
             self.pending_buckets.remove(pos);
         }
-        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn mark_completed(&mut self) {
         self.completed = true;
-        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn set_error(&mut self, error: String) {
         self.error_message = Some(error);
-        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn increment_retry(&mut self) {
         self.retry_count += 1;
-        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.last_update = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn can_retry(&self) -> bool {
@@ -156,8 +166,14 @@ pub struct ResumeManager {
 
 impl ResumeManager {
     /// create new resume manager
-    pub async fn new(disk: DiskStore, task_id: String, task_type: String, buckets: Vec<String>) -> Result<Self> {
-        let state = ResumeState::new(task_id, task_type, buckets);
+    pub async fn new(
+        disk: DiskStore,
+        task_id: String,
+        task_type: String,
+        set_disk_id: String,
+        buckets: Vec<String>,
+    ) -> Result<Self> {
+        let state = ResumeState::new(task_id, task_type, set_disk_id, buckets);
         let manager = Self {
             disk,
             state: Arc::new(RwLock::new(state)),
@@ -184,8 +200,11 @@ impl ResumeManager {
     /// check if resume state exists
     pub async fn has_resume_state(disk: &DiskStore, task_id: &str) -> bool {
         let file_path = Path::new(BUCKET_META_PREFIX).join(format!("{task_id}_{RESUME_STATE_FILE}"));
-        match disk.read_all(RUSTFS_META_BUCKET, file_path.to_str().unwrap()).await {
-            Ok(data) => !data.is_empty(),
+        match path_to_str(&file_path) {
+            Ok(path_str) => match disk.read_all(RUSTFS_META_BUCKET, path_str).await {
+                Ok(data) => !data.is_empty(),
+                Err(_) => false,
+            },
             Err(_) => false,
         }
     }
@@ -254,18 +273,15 @@ impl ResumeManager {
         let checkpoint_file = Path::new(BUCKET_META_PREFIX).join(format!("{task_id}_{RESUME_CHECKPOINT_FILE}"));
 
         // ignore delete errors, files may not exist
-        let _ = self
-            .disk
-            .delete(RUSTFS_META_BUCKET, state_file.to_str().unwrap(), Default::default())
-            .await;
-        let _ = self
-            .disk
-            .delete(RUSTFS_META_BUCKET, progress_file.to_str().unwrap(), Default::default())
-            .await;
-        let _ = self
-            .disk
-            .delete(RUSTFS_META_BUCKET, checkpoint_file.to_str().unwrap(), Default::default())
-            .await;
+        if let Ok(path_str) = path_to_str(&state_file) {
+            let _ = self.disk.delete(RUSTFS_META_BUCKET, path_str, Default::default()).await;
+        }
+        if let Ok(path_str) = path_to_str(&progress_file) {
+            let _ = self.disk.delete(RUSTFS_META_BUCKET, path_str, Default::default()).await;
+        }
+        if let Ok(path_str) = path_to_str(&checkpoint_file) {
+            let _ = self.disk.delete(RUSTFS_META_BUCKET, path_str, Default::default()).await;
+        }
 
         info!("Cleaned up resume state for task: {}", task_id);
         Ok(())
@@ -280,8 +296,9 @@ impl ResumeManager {
 
         let file_path = Path::new(BUCKET_META_PREFIX).join(format!("{}_{}", state.task_id, RESUME_STATE_FILE));
 
+        let path_str = path_to_str(&file_path)?;
         self.disk
-            .write_all(RUSTFS_META_BUCKET, file_path.to_str().unwrap(), state_data.into())
+            .write_all(RUSTFS_META_BUCKET, path_str, state_data.into())
             .await
             .map_err(|e| Error::TaskExecutionFailed {
                 message: format!("Failed to save resume state: {e}"),
@@ -295,7 +312,8 @@ impl ResumeManager {
     async fn read_state_file(disk: &DiskStore, task_id: &str) -> Result<Vec<u8>> {
         let file_path = Path::new(BUCKET_META_PREFIX).join(format!("{task_id}_{RESUME_STATE_FILE}"));
 
-        disk.read_all(RUSTFS_META_BUCKET, file_path.to_str().unwrap())
+        let path_str = path_to_str(&file_path)?;
+        disk.read_all(RUSTFS_META_BUCKET, path_str)
             .await
             .map(|bytes| bytes.to_vec())
             .map_err(|e| Error::TaskExecutionFailed {
@@ -327,7 +345,7 @@ impl ResumeCheckpoint {
     pub fn new(task_id: String) -> Self {
         Self {
             task_id,
-            checkpoint_time: SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs(),
+            checkpoint_time: SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs(),
             current_bucket_index: 0,
             current_object_index: 0,
             processed_objects: Vec::new(),
@@ -339,7 +357,7 @@ impl ResumeCheckpoint {
     pub fn update_position(&mut self, bucket_index: usize, object_index: usize) {
         self.current_bucket_index = bucket_index;
         self.current_object_index = object_index;
-        self.checkpoint_time = SystemTime::now().duration_since(UNIX_EPOCH).unwrap().as_secs();
+        self.checkpoint_time = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs();
     }
 
     pub fn add_processed_object(&mut self, object: String) {
@@ -397,8 +415,11 @@ impl CheckpointManager {
     /// check if checkpoint exists
     pub async fn has_checkpoint(disk: &DiskStore, task_id: &str) -> bool {
         let file_path = Path::new(BUCKET_META_PREFIX).join(format!("{task_id}_{RESUME_CHECKPOINT_FILE}"));
-        match disk.read_all(RUSTFS_META_BUCKET, file_path.to_str().unwrap()).await {
-            Ok(data) => !data.is_empty(),
+        match path_to_str(&file_path) {
+            Ok(path_str) => match disk.read_all(RUSTFS_META_BUCKET, path_str).await {
+                Ok(data) => !data.is_empty(),
+                Err(_) => false,
+            },
             Err(_) => false,
         }
     }
@@ -446,10 +467,9 @@ impl CheckpointManager {
         let task_id = &checkpoint.task_id;
 
         let checkpoint_file = Path::new(BUCKET_META_PREFIX).join(format!("{task_id}_{RESUME_CHECKPOINT_FILE}"));
-        let _ = self
-            .disk
-            .delete(RUSTFS_META_BUCKET, checkpoint_file.to_str().unwrap(), Default::default())
-            .await;
+        if let Ok(path_str) = path_to_str(&checkpoint_file) {
+            let _ = self.disk.delete(RUSTFS_META_BUCKET, path_str, Default::default()).await;
+        }
 
         info!("Cleaned up checkpoint for task: {}", task_id);
         Ok(())
@@ -464,8 +484,9 @@ impl CheckpointManager {
 
         let file_path = Path::new(BUCKET_META_PREFIX).join(format!("{}_{}", checkpoint.task_id, RESUME_CHECKPOINT_FILE));
 
+        let path_str = path_to_str(&file_path)?;
         self.disk
-            .write_all(RUSTFS_META_BUCKET, file_path.to_str().unwrap(), checkpoint_data.into())
+            .write_all(RUSTFS_META_BUCKET, path_str, checkpoint_data.into())
             .await
             .map_err(|e| Error::TaskExecutionFailed {
                 message: format!("Failed to save checkpoint: {e}"),
@@ -479,7 +500,8 @@ impl CheckpointManager {
     async fn read_checkpoint_file(disk: &DiskStore, task_id: &str) -> Result<Vec<u8>> {
         let file_path = Path::new(BUCKET_META_PREFIX).join(format!("{task_id}_{RESUME_CHECKPOINT_FILE}"));
 
-        disk.read_all(RUSTFS_META_BUCKET, file_path.to_str().unwrap())
+        let path_str = path_to_str(&file_path)?;
+        disk.read_all(RUSTFS_META_BUCKET, path_str)
             .await
             .map(|bytes| bytes.to_vec())
             .map_err(|e| Error::TaskExecutionFailed {
@@ -562,7 +584,7 @@ mod tests {
     async fn test_resume_state_creation() {
         let task_id = ResumeUtils::generate_task_id();
         let buckets = vec!["bucket1".to_string(), "bucket2".to_string()];
-        let state = ResumeState::new(task_id.clone(), "erasure_set".to_string(), buckets);
+        let state = ResumeState::new(task_id.clone(), "erasure_set".to_string(), "pool_0_set_0".to_string(), buckets);
 
         assert_eq!(state.task_id, task_id);
         assert_eq!(state.task_type, "erasure_set");
@@ -575,7 +597,7 @@ mod tests {
     async fn test_resume_state_progress() {
         let task_id = ResumeUtils::generate_task_id();
         let buckets = vec!["bucket1".to_string()];
-        let mut state = ResumeState::new(task_id, "erasure_set".to_string(), buckets);
+        let mut state = ResumeState::new(task_id, "erasure_set".to_string(), "pool_0_set_0".to_string(), buckets);
 
         state.update_progress(10, 8, 1, 1);
         assert_eq!(state.processed_objects, 10);
@@ -595,7 +617,7 @@ mod tests {
     async fn test_resume_state_bucket_completion() {
         let task_id = ResumeUtils::generate_task_id();
         let buckets = vec!["bucket1".to_string(), "bucket2".to_string()];
-        let mut state = ResumeState::new(task_id, "erasure_set".to_string(), buckets);
+        let mut state = ResumeState::new(task_id, "erasure_set".to_string(), "pool_0_set_0".to_string(), buckets);
 
         assert_eq!(state.pending_buckets.len(), 2);
         assert_eq!(state.completed_buckets.len(), 0);
@@ -650,6 +672,7 @@ mod tests {
             let state = ResumeState::new(
                 task_id.clone(),
                 "erasure_set".to_string(),
+                "pool_0_set_0".to_string(),
                 vec!["bucket1".to_string(), "bucket2".to_string()],
             );
 

crates/ahm/src/heal/storage.rs

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
+use crate::{Error, Result};
 use async_trait::async_trait;
 use rustfs_common::heal_channel::{HealOpts, HealScanMode};
 use rustfs_ecstore::{
@@ -107,9 +107,21 @@ pub trait HealStorageAPI: Send + Sync {
     /// Heal format using ecstore
     async fn heal_format(&self, dry_run: bool) -> Result<(HealResultItem, Option<Error>)>;
 
-    /// List objects for healing
+    /// List objects for healing (returns all objects, may use significant memory for large buckets)
+    ///
+    /// WARNING: This method loads all objects into memory at once. For buckets with many objects,
+    /// consider using `list_objects_for_heal_page` instead to process objects in pages.
     async fn list_objects_for_heal(&self, bucket: &str, prefix: &str) -> Result<Vec<String>>;
 
+    /// List objects for healing with pagination (returns one page and continuation token)
+    /// Returns (objects, next_continuation_token, is_truncated)
+    async fn list_objects_for_heal_page(
+        &self,
+        bucket: &str,
+        prefix: &str,
+        continuation_token: Option<&str>,
+    ) -> Result<(Vec<String>, Option<String>, bool)>;
+
     /// Get disk for resume functionality
     async fn get_disk_for_resume(&self, set_disk_id: &str) -> Result<DiskStore>;
 }
@@ -179,7 +191,9 @@ impl HealStorageAPI for ECStoreHealStorage {
                             "Object data exceeds cap ({} bytes), aborting full read to prevent OOM: {}/{}",
                             MAX_READ_BYTES, bucket, object
                         );
-                        return Ok(None);
+                        return Err(Error::other(format!(
+                            "Object too large: {n_read} bytes (max: {MAX_READ_BYTES} bytes) for {bucket}/{object}"
+                        )));
                     }
                 }
                 Err(e) => {
@@ -394,10 +408,19 @@ impl HealStorageAPI for ECStoreHealStorage {
     async fn object_exists(&self, bucket: &str, object: &str) -> Result<bool> {
         debug!("Checking object exists: {}/{}", bucket, object);
 
-        match self.get_object_meta(bucket, object).await {
-            Ok(Some(_)) => Ok(true),
-            Ok(None) => Ok(false),
-            Err(_) => Ok(false),
+        // Use get_object_info for efficient existence check without heavy heal operations
+        match self.ecstore.get_object_info(bucket, object, &Default::default()).await {
+            Ok(_) => Ok(true), // Object exists
+            Err(e) => {
+                // Map ObjectNotFound to false, other errors must be propagated!
+                if matches!(e, rustfs_ecstore::error::StorageError::ObjectNotFound(_, _)) {
+                    debug!("Object not found: {}/{}", bucket, object);
+                    Ok(false)
+                } else {
+                    error!("Error checking object existence {}/{}: {}", bucket, object, e);
+                    Err(Error::other(e))
+                }
+            }
         }
     }
 
@@ -482,45 +505,74 @@ impl HealStorageAPI for ECStoreHealStorage {
 
     async fn list_objects_for_heal(&self, bucket: &str, prefix: &str) -> Result<Vec<String>> {
         debug!("Listing objects for heal: {}/{}", bucket, prefix);
+        warn!(
+            "list_objects_for_heal loads all objects into memory. For large buckets, consider using list_objects_for_heal_page instead."
+        );
 
-        // Use list_objects_v2 to get objects
-        match self
-            .ecstore
-            .clone()
-            .list_objects_v2(bucket, prefix, None, None, 1000, false, None)
-            .await
-        {
-            Ok(list_info) => {
-                let objects: Vec<String> = list_info.objects.into_iter().map(|obj| obj.name).collect();
-                info!("Found {} objects for heal in {}/{}", objects.len(), bucket, prefix);
-                Ok(objects)
+        let mut all_objects = Vec::new();
+        let mut continuation_token: Option<String> = None;
+
+        loop {
+            let (page_objects, next_token, is_truncated) = self
+                .list_objects_for_heal_page(bucket, prefix, continuation_token.as_deref())
+                .await?;
+
+            all_objects.extend(page_objects);
+
+            if !is_truncated {
+                break;
             }
-            Err(e) => {
-                error!("Failed to list objects for heal: {}/{} - {}", bucket, prefix, e);
-                Err(Error::other(e))
+
+            continuation_token = next_token;
+            if continuation_token.is_none() {
+                warn!("List is truncated but no continuation token provided for {}/{}", bucket, prefix);
+                break;
             }
         }
+
+        info!("Found {} objects for heal in {}/{}", all_objects.len(), bucket, prefix);
+        Ok(all_objects)
+    }
+
+    async fn list_objects_for_heal_page(
+        &self,
+        bucket: &str,
+        prefix: &str,
+        continuation_token: Option<&str>,
+    ) -> Result<(Vec<String>, Option<String>, bool)> {
+        debug!("Listing objects for heal (page): {}/{}", bucket, prefix);
+
+        const MAX_KEYS: i32 = 1000;
+        let continuation_token_opt = continuation_token.map(|s| s.to_string());
+
+        // Use list_objects_v2 to get objects with pagination
+        let list_info = match self
+            .ecstore
+            .clone()
+            .list_objects_v2(bucket, prefix, continuation_token_opt, None, MAX_KEYS, false, None, false)
+            .await
+        {
+            Ok(info) => info,
+            Err(e) => {
+                error!("Failed to list objects for heal: {}/{} - {}", bucket, prefix, e);
+                return Err(Error::other(e));
+            }
+        };
+
+        // Collect objects from this page
+        let page_objects: Vec<String> = list_info.objects.into_iter().map(|obj| obj.name).collect();
+        let page_count = page_objects.len();
+
+        debug!("Listed {} objects (page) for heal in {}/{}", page_count, bucket, prefix);
+
+        Ok((page_objects, list_info.next_continuation_token, list_info.is_truncated))
     }
 
     async fn get_disk_for_resume(&self, set_disk_id: &str) -> Result<DiskStore> {
         debug!("Getting disk for resume: {}", set_disk_id);
 
         // Parse set_disk_id to extract pool and set indices
-        // Format: "pool_{pool_idx}_set_{set_idx}"
-        let parts: Vec<&str> = set_disk_id.split('_').collect();
-        if parts.len() != 4 || parts[0] != "pool" || parts[2] != "set" {
-            return Err(Error::TaskExecutionFailed {
-                message: format!("Invalid set_disk_id format: {set_disk_id}"),
-            });
-        }
-
-        let pool_idx: usize = parts[1].parse().map_err(|_| Error::TaskExecutionFailed {
-            message: format!("Invalid pool index in set_disk_id: {set_disk_id}"),
-        })?;
-
-        let set_idx: usize = parts[3].parse().map_err(|_| Error::TaskExecutionFailed {
-            message: format!("Invalid set index in set_disk_id: {set_disk_id}"),
-        })?;
+        let (pool_idx, set_idx) = crate::heal::utils::parse_set_disk_id(set_disk_id)?;
 
         // Get the first available disk from the set
         let disks = self

crates/ahm/src/heal/task.rs

@@ -12,13 +12,15 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use crate::error::{Error, Result};
-use crate::heal::ErasureSetHealer;
-use crate::heal::{progress::HealProgress, storage::HealStorageAPI};
+use crate::heal::{ErasureSetHealer, progress::HealProgress, storage::HealStorageAPI};
+use crate::{Error, Result};
 use rustfs_common::heal_channel::{HealOpts, HealScanMode};
 use serde::{Deserialize, Serialize};
-use std::sync::Arc;
-use std::time::{Duration, SystemTime};
+use std::{
+    future::Future,
+    sync::Arc,
+    time::{Duration, Instant, SystemTime},
+};
 use tokio::sync::RwLock;
 use tracing::{error, info, warn};
 use uuid::Uuid;
@@ -49,11 +51,12 @@ pub enum HealType {
 }
 
 /// Heal priority
-#[derive(Debug, Clone, PartialEq, Eq, PartialOrd, Ord, Serialize, Deserialize)]
+#[derive(Debug, Default, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Serialize, Deserialize)]
 pub enum HealPriority {
     /// Low priority
     Low = 0,
     /// Normal priority
+    #[default]
     Normal = 1,
     /// High priority
     High = 2,
@@ -61,12 +64,6 @@ pub enum HealPriority {
     Urgent = 3,
 }
 
-impl Default for HealPriority {
-    fn default() -> Self {
-        Self::Normal
-    }
-}
-
 /// Heal options
 #[derive(Debug, Clone, Serialize, Deserialize)]
 pub struct HealOptions {
@@ -200,6 +197,8 @@ pub struct HealTask {
     pub started_at: Arc<RwLock<Option<SystemTime>>>,
     /// Completed time
     pub completed_at: Arc<RwLock<Option<SystemTime>>>,
+    /// Task start instant for timeout calculation (monotonic)
+    task_start_instant: Arc<RwLock<Option<Instant>>>,
     /// Cancel token
     pub cancel_token: tokio_util::sync::CancellationToken,
     /// Storage layer interface
@@ -217,23 +216,77 @@ impl HealTask {
             created_at: request.created_at,
             started_at: Arc::new(RwLock::new(None)),
             completed_at: Arc::new(RwLock::new(None)),
+            task_start_instant: Arc::new(RwLock::new(None)),
             cancel_token: tokio_util::sync::CancellationToken::new(),
             storage,
         }
     }
 
+    async fn remaining_timeout(&self) -> Result<Option<Duration>> {
+        if let Some(total) = self.options.timeout {
+            let start_instant = { *self.task_start_instant.read().await };
+            if let Some(started_at) = start_instant {
+                let elapsed = started_at.elapsed();
+                if elapsed >= total {
+                    return Err(Error::TaskTimeout);
+                }
+                return Ok(Some(total - elapsed));
+            }
+            Ok(Some(total))
+        } else {
+            Ok(None)
+        }
+    }
+
+    async fn check_control_flags(&self) -> Result<()> {
+        if self.cancel_token.is_cancelled() {
+            return Err(Error::TaskCancelled);
+        }
+        // Only interested in propagating an error if the timeout has expired;
+        // the actual Duration value is not needed here
+        let _ = self.remaining_timeout().await?;
+        Ok(())
+    }
+
+    async fn await_with_control<F, T>(&self, fut: F) -> Result<T>
+    where
+        F: Future<Output = Result<T>> + Send,
+        T: Send,
+    {
+        let cancel_token = self.cancel_token.clone();
+        if let Some(remaining) = self.remaining_timeout().await? {
+            if remaining.is_zero() {
+                return Err(Error::TaskTimeout);
+            }
+            let mut fut = Box::pin(fut);
+            tokio::select! {
+                _ = cancel_token.cancelled() => Err(Error::TaskCancelled),
+                _ = tokio::time::sleep(remaining) => Err(Error::TaskTimeout),
+                result = &mut fut => result,
+            }
+        } else {
+            tokio::select! {
+                _ = cancel_token.cancelled() => Err(Error::TaskCancelled),
+                result = fut => result,
+            }
+        }
+    }
+
+    #[tracing::instrument(skip(self), fields(task_id = %self.id, heal_type = ?self.heal_type))]
     pub async fn execute(&self) -> Result<()> {
-        // update status to running
+        // update status and timestamps atomically to avoid race conditions
+        let now = SystemTime::now();
+        let start_instant = Instant::now();
         {
             let mut status = self.status.write().await;
-            *status = HealTaskStatus::Running;
-        }
-        {
             let mut started_at = self.started_at.write().await;
-            *started_at = Some(SystemTime::now());
+            let mut task_start_instant = self.task_start_instant.write().await;
+            *status = HealTaskStatus::Running;
+            *started_at = Some(now);
+            *task_start_instant = Some(start_instant);
         }
 
-        info!("Starting heal task: {} with type: {:?}", self.id, self.heal_type);
+        info!("Task started");
 
         let result = match &self.heal_type {
             HealType::Object {
@@ -263,7 +316,17 @@ impl HealTask {
             Ok(_) => {
                 let mut status = self.status.write().await;
                 *status = HealTaskStatus::Completed;
-                info!("Heal task completed successfully: {}", self.id);
+                info!("Task completed successfully");
+            }
+            Err(Error::TaskCancelled) => {
+                let mut status = self.status.write().await;
+                *status = HealTaskStatus::Cancelled;
+                info!("Heal task was cancelled: {}", self.id);
+            }
+            Err(Error::TaskTimeout) => {
+                let mut status = self.status.write().await;
+                *status = HealTaskStatus::Timeout;
+                warn!("Heal task timed out: {}", self.id);
             }
             Err(e) => {
                 let mut status = self.status.write().await;
@@ -292,19 +355,21 @@ impl HealTask {
     }
 
     // specific heal implementation method
+    #[tracing::instrument(skip(self), fields(bucket = %bucket, object = %object, version_id = ?version_id))]
     async fn heal_object(&self, bucket: &str, object: &str, version_id: Option<&str>) -> Result<()> {
-        info!("Healing object: {}/{}", bucket, object);
+        info!("Starting object heal workflow");
 
         // update progress
         {
             let mut progress = self.progress.write().await;
             progress.set_current_object(Some(format!("{bucket}/{object}")));
-            progress.update_progress(0, 4, 0, 0); // 开始heal，总共4个步骤
+            progress.update_progress(0, 4, 0, 0);
         }
 
         // Step 1: Check if object exists and get metadata
-        info!("Step 1: Checking object existence and metadata");
-        let object_exists = self.storage.object_exists(bucket, object).await?;
+        warn!("Step 1: Checking object existence and metadata");
+        self.check_control_flags().await?;
+        let object_exists = self.await_with_control(self.storage.object_exists(bucket, object)).await?;
         if !object_exists {
             warn!("Object does not exist: {}/{}", bucket, object);
             if self.options.recreate_missing {
@@ -336,16 +401,34 @@ impl HealTask {
             set: self.options.set_index,
         };
 
-        match self.storage.heal_object(bucket, object, version_id, &heal_opts).await {
+        let heal_result = self
+            .await_with_control(self.storage.heal_object(bucket, object, version_id, &heal_opts))
+            .await;
+
+        match heal_result {
             Ok((result, error)) => {
                 if let Some(e) = error {
+                    // Check if this is a "File not found" error during delete operations
+                    let error_msg = format!("{e}");
+                    if error_msg.contains("File not found") || error_msg.contains("not found") {
+                        info!(
+                            "Object {}/{} not found during heal - likely deleted intentionally, treating as successful",
+                            bucket, object
+                        );
+                        {
+                            let mut progress = self.progress.write().await;
+                            progress.update_progress(3, 3, 0, 0);
+                        }
+                        return Ok(());
+                    }
+
                     error!("Heal operation failed: {}/{} - {}", bucket, object, e);
 
                     // If heal failed and remove_corrupted is enabled, delete the corrupted object
                     if self.options.remove_corrupted {
-                        warn!("Removing corrupted object: {}/{}", bucket, object);
+                        info!("Removing corrupted object: {}/{}", bucket, object);
                         if !self.options.dry_run {
-                            self.storage.delete_object(bucket, object).await?;
+                            self.await_with_control(self.storage.delete_object(bucket, object)).await?;
                             info!("Successfully deleted corrupted object: {}/{}", bucket, object);
                         } else {
                             info!("Dry run mode - would delete corrupted object: {}/{}", bucket, object);
@@ -366,11 +449,9 @@ impl HealTask {
                 info!("Step 3: Verifying heal result");
                 let object_size = result.object_size as u64;
                 info!(
-                    "Heal completed successfully: {}/{} ({} bytes, {} drives healed)",
-                    bucket,
-                    object,
-                    object_size,
-                    result.after.drives.len()
+                    object_size = object_size,
+                    drives_healed = result.after.drives.len(),
+                    "Heal completed successfully"
                 );
 
                 {
@@ -379,14 +460,30 @@ impl HealTask {
                 }
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
+                // Check if this is a "File not found" error during delete operations
+                let error_msg = format!("{e}");
+                if error_msg.contains("File not found") || error_msg.contains("not found") {
+                    info!(
+                        "Object {}/{} not found during heal - likely deleted intentionally, treating as successful",
+                        bucket, object
+                    );
+                    {
+                        let mut progress = self.progress.write().await;
+                        progress.update_progress(3, 3, 0, 0);
+                    }
+                    return Ok(());
+                }
+
                 error!("Heal operation failed: {}/{} - {}", bucket, object, e);
 
                 // If heal failed and remove_corrupted is enabled, delete the corrupted object
                 if self.options.remove_corrupted {
-                    warn!("Removing corrupted object: {}/{}", bucket, object);
+                    info!("Removing corrupted object: {}/{}", bucket, object);
                     if !self.options.dry_run {
-                        self.storage.delete_object(bucket, object).await?;
+                        self.await_with_control(self.storage.delete_object(bucket, object)).await?;
                         info!("Successfully deleted corrupted object: {}/{}", bucket, object);
                     } else {
                         info!("Dry run mode - would delete corrupted object: {}/{}", bucket, object);
@@ -422,7 +519,10 @@ impl HealTask {
             set: None,
         };
 
-        match self.storage.heal_object(bucket, object, version_id, &heal_opts).await {
+        match self
+            .await_with_control(self.storage.heal_object(bucket, object, version_id, &heal_opts))
+            .await
+        {
             Ok((result, error)) => {
                 if let Some(e) = error {
                     error!("Failed to recreate missing object: {}/{} - {}", bucket, object, e);
@@ -440,6 +540,8 @@ impl HealTask {
                 }
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
                 error!("Failed to recreate missing object: {}/{} - {}", bucket, object, e);
                 Err(Error::TaskExecutionFailed {
@@ -461,7 +563,8 @@ impl HealTask {
 
         // Step 1: Check if bucket exists
         info!("Step 1: Checking bucket existence");
-        let bucket_exists = self.storage.get_bucket_info(bucket).await?.is_some();
+        self.check_control_flags().await?;
+        let bucket_exists = self.await_with_control(self.storage.get_bucket_info(bucket)).await?.is_some();
         if !bucket_exists {
             warn!("Bucket does not exist: {}", bucket);
             return Err(Error::TaskExecutionFailed {
@@ -488,7 +591,9 @@ impl HealTask {
             set: self.options.set_index,
         };
 
-        match self.storage.heal_bucket(bucket, &heal_opts).await {
+        let heal_result = self.await_with_control(self.storage.heal_bucket(bucket, &heal_opts)).await;
+
+        match heal_result {
             Ok(result) => {
                 info!("Bucket heal completed successfully: {} ({} drives)", bucket, result.after.drives.len());
 
@@ -498,6 +603,8 @@ impl HealTask {
                 }
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
                 error!("Bucket heal failed: {} - {}", bucket, e);
                 {
@@ -523,7 +630,8 @@ impl HealTask {
 
         // Step 1: Check if object exists
         info!("Step 1: Checking object existence");
-        let object_exists = self.storage.object_exists(bucket, object).await?;
+        self.check_control_flags().await?;
+        let object_exists = self.await_with_control(self.storage.object_exists(bucket, object)).await?;
         if !object_exists {
             warn!("Object does not exist: {}/{}", bucket, object);
             return Err(Error::TaskExecutionFailed {
@@ -550,7 +658,11 @@ impl HealTask {
             set: self.options.set_index,
         };
 
-        match self.storage.heal_object(bucket, object, None, &heal_opts).await {
+        let heal_result = self
+            .await_with_control(self.storage.heal_object(bucket, object, None, &heal_opts))
+            .await;
+
+        match heal_result {
             Ok((result, error)) => {
                 if let Some(e) = error {
                     error!("Metadata heal failed: {}/{} - {}", bucket, object, e);
@@ -576,6 +688,8 @@ impl HealTask {
                 }
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
                 error!("Metadata heal failed: {}/{} - {}", bucket, object, e);
                 {
@@ -624,7 +738,11 @@ impl HealTask {
             set: None,
         };
 
-        match self.storage.heal_object(bucket, &object, None, &heal_opts).await {
+        let heal_result = self
+            .await_with_control(self.storage.heal_object(bucket, &object, None, &heal_opts))
+            .await;
+
+        match heal_result {
             Ok((result, error)) => {
                 if let Some(e) = error {
                     error!("MRF heal failed: {} - {}", meta_path, e);
@@ -645,6 +763,8 @@ impl HealTask {
                 }
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
                 error!("MRF heal failed: {} - {}", meta_path, e);
                 {
@@ -670,7 +790,8 @@ impl HealTask {
 
         // Step 1: Check if object exists
         info!("Step 1: Checking object existence");
-        let object_exists = self.storage.object_exists(bucket, object).await?;
+        self.check_control_flags().await?;
+        let object_exists = self.await_with_control(self.storage.object_exists(bucket, object)).await?;
         if !object_exists {
             warn!("Object does not exist: {}/{}", bucket, object);
             return Err(Error::TaskExecutionFailed {
@@ -697,7 +818,11 @@ impl HealTask {
             set: None,
         };
 
-        match self.storage.heal_object(bucket, object, version_id, &heal_opts).await {
+        let heal_result = self
+            .await_with_control(self.storage.heal_object(bucket, object, version_id, &heal_opts))
+            .await;
+
+        match heal_result {
             Ok((result, error)) => {
                 if let Some(e) = error {
                     error!("EC decode heal failed: {}/{} - {}", bucket, object, e);
@@ -725,6 +850,8 @@ impl HealTask {
                 }
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
                 error!("EC decode heal failed: {}/{} - {}", bucket, object, e);
                 {
@@ -750,7 +877,7 @@ impl HealTask {
 
         let buckets = if buckets.is_empty() {
             info!("No buckets specified, listing all buckets");
-            let bucket_infos = self.storage.list_buckets().await?;
+            let bucket_infos = self.await_with_control(self.storage.list_buckets()).await?;
             bucket_infos.into_iter().map(|info| info.name).collect()
         } else {
             buckets
@@ -758,7 +885,9 @@ impl HealTask {
 
         // Step 1: Perform disk format heal using ecstore
         info!("Step 1: Performing disk format heal using ecstore");
-        match self.storage.heal_format(self.options.dry_run).await {
+        let format_result = self.await_with_control(self.storage.heal_format(self.options.dry_run)).await;
+
+        match format_result {
             Ok((result, error)) => {
                 if let Some(e) = error {
                     error!("Disk format heal failed: {} - {}", set_disk_id, e);
@@ -777,6 +906,8 @@ impl HealTask {
                     result.after.drives.len()
                 );
             }
+            Err(Error::TaskCancelled) => return Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => return Err(Error::TaskTimeout),
             Err(e) => {
                 error!("Disk format heal failed: {} - {}", set_disk_id, e);
                 {
@@ -796,7 +927,9 @@ impl HealTask {
 
         // Step 2: Get disk for resume functionality
         info!("Step 2: Getting disk for resume functionality");
-        let disk = self.storage.get_disk_for_resume(&set_disk_id).await?;
+        let disk = self
+            .await_with_control(self.storage.get_disk_for_resume(&set_disk_id))
+            .await?;
 
         {
             let mut progress = self.progress.write().await;
@@ -804,9 +937,18 @@ impl HealTask {
         }
 
         // Step 3: Heal bucket structure
+        // Check control flags before each iteration to ensure timely cancellation.
+        // Each heal_bucket call may handle timeout/cancellation internally, see its implementation for details.
         for bucket in buckets.iter() {
+            // Check control flags before starting each bucket heal
+            self.check_control_flags().await?;
+            // heal_bucket internally uses await_with_control for timeout/cancellation handling
             if let Err(err) = self.heal_bucket(bucket).await {
-                info!("{}", err.to_string());
+                // Check if error is due to cancellation or timeout
+                if matches!(err, Error::TaskCancelled | Error::TaskTimeout) {
+                    return Err(err);
+                }
+                info!("Bucket heal failed: {}", err.to_string());
             }
         }
 
@@ -833,6 +975,8 @@ impl HealTask {
                 info!("Erasure set heal completed successfully: {} ({} buckets)", set_disk_id, buckets.len());
                 Ok(())
             }
+            Err(Error::TaskCancelled) => Err(Error::TaskCancelled),
+            Err(Error::TaskTimeout) => Err(Error::TaskTimeout),
             Err(e) => {
                 error!("Erasure set heal failed: {} - {}", set_disk_id, e);
                 Err(Error::TaskExecutionFailed {

crates/ahm/src/heal/utils.rs

@@ -0,0 +1,110 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::{Error, Result};
+
+/// Prefix for pool index in set disk identifiers.
+const POOL_PREFIX: &str = "pool";
+/// Prefix for set index in set disk identifiers.
+const SET_PREFIX: &str = "set";
+
+/// Format a set disk identifier using unsigned indices.
+pub fn format_set_disk_id(pool_idx: usize, set_idx: usize) -> String {
+    format!("{POOL_PREFIX}_{pool_idx}_{SET_PREFIX}_{set_idx}")
+}
+
+/// Format a set disk identifier from signed indices.
+pub fn format_set_disk_id_from_i32(pool_idx: i32, set_idx: i32) -> Option<String> {
+    if pool_idx < 0 || set_idx < 0 {
+        None
+    } else {
+        Some(format_set_disk_id(pool_idx as usize, set_idx as usize))
+    }
+}
+
+/// Normalise external set disk identifiers into the canonical format.
+pub fn normalize_set_disk_id(raw: &str) -> Option<String> {
+    if raw.starts_with(&format!("{POOL_PREFIX}_")) {
+        Some(raw.to_string())
+    } else {
+        parse_compact_set_disk_id(raw).map(|(pool, set)| format_set_disk_id(pool, set))
+    }
+}
+
+/// Parse a canonical set disk identifier into pool/set indices.
+pub fn parse_set_disk_id(raw: &str) -> Result<(usize, usize)> {
+    let parts: Vec<&str> = raw.split('_').collect();
+    if parts.len() != 4 || parts[0] != POOL_PREFIX || parts[2] != SET_PREFIX {
+        return Err(Error::TaskExecutionFailed {
+            message: format!("Invalid set_disk_id format: {raw}"),
+        });
+    }
+
+    let pool_idx = parts[1].parse::<usize>().map_err(|_| Error::TaskExecutionFailed {
+        message: format!("Invalid pool index in set_disk_id: {raw}"),
+    })?;
+    let set_idx = parts[3].parse::<usize>().map_err(|_| Error::TaskExecutionFailed {
+        message: format!("Invalid set index in set_disk_id: {raw}"),
+    })?;
+    Ok((pool_idx, set_idx))
+}
+
+fn parse_compact_set_disk_id(raw: &str) -> Option<(usize, usize)> {
+    let (pool, set) = raw.split_once('_')?;
+    let pool_idx = pool.parse::<usize>().ok()?;
+    let set_idx = set.parse::<usize>().ok()?;
+    Some((pool_idx, set_idx))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn format_from_unsigned_indices() {
+        assert_eq!(format_set_disk_id(1, 2), "pool_1_set_2");
+    }
+
+    #[test]
+    fn format_from_signed_indices() {
+        assert_eq!(format_set_disk_id_from_i32(3, 4), Some("pool_3_set_4".into()));
+        assert_eq!(format_set_disk_id_from_i32(-1, 4), None);
+    }
+
+    #[test]
+    fn normalize_compact_identifier() {
+        assert_eq!(normalize_set_disk_id("3_5"), Some("pool_3_set_5".to_string()));
+    }
+
+    #[test]
+    fn normalize_prefixed_identifier() {
+        assert_eq!(normalize_set_disk_id("pool_7_set_1"), Some("pool_7_set_1".to_string()));
+    }
+
+    #[test]
+    fn normalize_invalid_identifier() {
+        assert_eq!(normalize_set_disk_id("invalid"), None);
+    }
+
+    #[test]
+    fn parse_prefixed_identifier() {
+        assert_eq!(parse_set_disk_id("pool_9_set_3").unwrap(), (9, 3));
+    }
+
+    #[test]
+    fn parse_invalid_identifier() {
+        assert!(parse_set_disk_id("bad").is_err());
+        assert!(parse_set_disk_id("pool_X_set_1").is_err());
+    }
+}

crates/ahm/src/lib.rs

@@ -12,17 +12,16 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::sync::{Arc, OnceLock};
-use tokio_util::sync::CancellationToken;
-use tracing::{error, info};
-
-pub mod error;
+mod error;
 pub mod heal;
 pub mod scanner;
 
 pub use error::{Error, Result};
 pub use heal::{HealManager, HealOptions, HealPriority, HealRequest, HealType, channel::HealChannelProcessor};
 pub use scanner::Scanner;
+use std::sync::{Arc, OnceLock};
+use tokio_util::sync::CancellationToken;
+use tracing::{error, info};
 
 // Global cancellation token for AHM services (scanner and other background tasks)
 static GLOBAL_AHM_SERVICES_CANCEL_TOKEN: OnceLock<CancellationToken> = OnceLock::new();

crates/ahm/src/scanner/checkpoint.rs

@@ -0,0 +1,326 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::scanner::node_scanner::ScanProgress;
+use crate::{Error, Result};
+use serde::{Deserialize, Serialize};
+use std::{
+    path::{Path, PathBuf},
+    time::{Duration, SystemTime},
+};
+use tokio::sync::RwLock;
+use tracing::{debug, error, info, warn};
+
+#[derive(Debug, Serialize, Deserialize, Clone)]
+pub struct CheckpointData {
+    pub version: u32,
+    pub timestamp: SystemTime,
+    pub progress: ScanProgress,
+    pub node_id: String,
+    pub checksum: u64,
+}
+
+impl CheckpointData {
+    pub fn new(progress: ScanProgress, node_id: String) -> Self {
+        let mut checkpoint = Self {
+            version: 1,
+            timestamp: SystemTime::now(),
+            progress,
+            node_id,
+            checksum: 0,
+        };
+
+        checkpoint.checksum = checkpoint.calculate_checksum();
+        checkpoint
+    }
+
+    fn calculate_checksum(&self) -> u64 {
+        use std::collections::hash_map::DefaultHasher;
+        use std::hash::{Hash, Hasher};
+
+        let mut hasher = DefaultHasher::new();
+        self.version.hash(&mut hasher);
+        self.node_id.hash(&mut hasher);
+        self.progress.current_cycle.hash(&mut hasher);
+        self.progress.current_disk_index.hash(&mut hasher);
+
+        if let Some(ref bucket) = self.progress.current_bucket {
+            bucket.hash(&mut hasher);
+        }
+
+        if let Some(ref key) = self.progress.last_scan_key {
+            key.hash(&mut hasher);
+        }
+
+        hasher.finish()
+    }
+
+    pub fn verify_integrity(&self) -> bool {
+        let calculated_checksum = self.calculate_checksum();
+        self.checksum == calculated_checksum
+    }
+}
+
+pub struct CheckpointManager {
+    checkpoint_file: PathBuf,
+    backup_file: PathBuf,
+    temp_file: PathBuf,
+    save_interval: Duration,
+    last_save: RwLock<SystemTime>,
+    node_id: String,
+}
+
+impl CheckpointManager {
+    pub fn new(node_id: &str, data_dir: &Path) -> Self {
+        if !data_dir.exists() {
+            if let Err(e) = std::fs::create_dir_all(data_dir) {
+                error!("create data dir failed {:?}: {}", data_dir, e);
+            }
+        }
+
+        let checkpoint_file = data_dir.join(format!("scanner_checkpoint_{node_id}.json"));
+        let backup_file = data_dir.join(format!("scanner_checkpoint_{node_id}.backup"));
+        let temp_file = data_dir.join(format!("scanner_checkpoint_{node_id}.tmp"));
+
+        Self {
+            checkpoint_file,
+            backup_file,
+            temp_file,
+            save_interval: Duration::from_secs(30), // 30s
+            last_save: RwLock::new(SystemTime::UNIX_EPOCH),
+            node_id: node_id.to_string(),
+        }
+    }
+
+    pub async fn save_checkpoint(&self, progress: &ScanProgress) -> Result<()> {
+        let now = SystemTime::now();
+        let last_save = *self.last_save.read().await;
+
+        if now.duration_since(last_save).unwrap_or(Duration::ZERO) < self.save_interval {
+            return Ok(());
+        }
+
+        let checkpoint_data = CheckpointData::new(progress.clone(), self.node_id.clone());
+
+        let json_data = serde_json::to_string_pretty(&checkpoint_data)
+            .map_err(|e| Error::Serialization(format!("serialize checkpoint failed: {e}")))?;
+
+        tokio::fs::write(&self.temp_file, json_data)
+            .await
+            .map_err(|e| Error::IO(format!("write temp checkpoint file failed: {e}")))?;
+
+        if self.checkpoint_file.exists() {
+            tokio::fs::copy(&self.checkpoint_file, &self.backup_file)
+                .await
+                .map_err(|e| Error::IO(format!("backup checkpoint file failed: {e}")))?;
+        }
+
+        tokio::fs::rename(&self.temp_file, &self.checkpoint_file)
+            .await
+            .map_err(|e| Error::IO(format!("replace checkpoint file failed: {e}")))?;
+
+        *self.last_save.write().await = now;
+
+        debug!(
+            "save checkpoint to {:?}, cycle: {}, disk index: {}",
+            self.checkpoint_file, checkpoint_data.progress.current_cycle, checkpoint_data.progress.current_disk_index
+        );
+
+        Ok(())
+    }
+
+    pub async fn load_checkpoint(&self) -> Result<Option<ScanProgress>> {
+        // first try main checkpoint file
+        match self.load_checkpoint_from_file(&self.checkpoint_file).await {
+            Ok(checkpoint) => {
+                info!(
+                    "restore scan progress from main checkpoint file: cycle={}, disk index={}, last scan key={:?}",
+                    checkpoint.current_cycle, checkpoint.current_disk_index, checkpoint.last_scan_key
+                );
+                Ok(Some(checkpoint))
+            }
+            Err(e) => {
+                warn!("main checkpoint file is corrupted or not exists: {}", e);
+
+                // try backup file
+                match self.load_checkpoint_from_file(&self.backup_file).await {
+                    Ok(checkpoint) => {
+                        warn!(
+                            "restore scan progress from backup file: cycle={}, disk index={}",
+                            checkpoint.current_cycle, checkpoint.current_disk_index
+                        );
+
+                        // copy backup file to main checkpoint file
+                        if let Err(copy_err) = tokio::fs::copy(&self.backup_file, &self.checkpoint_file).await {
+                            warn!("restore main checkpoint file failed: {}", copy_err);
+                        }
+
+                        Ok(Some(checkpoint))
+                    }
+                    Err(backup_e) => {
+                        warn!("backup file is corrupted or not exists: {}", backup_e);
+                        info!("cannot restore scan progress, will start fresh scan");
+                        Ok(None)
+                    }
+                }
+            }
+        }
+    }
+
+    /// load checkpoint from file
+    async fn load_checkpoint_from_file(&self, file_path: &Path) -> Result<ScanProgress> {
+        if !file_path.exists() {
+            return Err(Error::NotFound(format!("checkpoint file not exists: {file_path:?}")));
+        }
+
+        // read file content
+        let content = tokio::fs::read_to_string(file_path)
+            .await
+            .map_err(|e| Error::IO(format!("read checkpoint file failed: {e}")))?;
+
+        // deserialize
+        let checkpoint_data: CheckpointData =
+            serde_json::from_str(&content).map_err(|e| Error::Serialization(format!("deserialize checkpoint failed: {e}")))?;
+
+        // validate checkpoint data
+        self.validate_checkpoint(&checkpoint_data)?;
+
+        Ok(checkpoint_data.progress)
+    }
+
+    /// validate checkpoint data
+    fn validate_checkpoint(&self, checkpoint: &CheckpointData) -> Result<()> {
+        // validate data integrity
+        if !checkpoint.verify_integrity() {
+            return Err(Error::InvalidCheckpoint(
+                "checkpoint data verification failed, may be corrupted".to_string(),
+            ));
+        }
+
+        // validate node id match
+        if checkpoint.node_id != self.node_id {
+            return Err(Error::InvalidCheckpoint(format!(
+                "checkpoint node id not match: expected {}, actual {}",
+                self.node_id, checkpoint.node_id
+            )));
+        }
+
+        let now = SystemTime::now();
+        let checkpoint_age = now.duration_since(checkpoint.timestamp).unwrap_or(Duration::MAX);
+
+        // checkpoint is too old (more than 24 hours), may be data expired
+        if checkpoint_age > Duration::from_secs(24 * 3600) {
+            return Err(Error::InvalidCheckpoint(format!("checkpoint data is too old: {checkpoint_age:?}")));
+        }
+
+        // validate version compatibility
+        if checkpoint.version > 1 {
+            return Err(Error::InvalidCheckpoint(format!(
+                "unsupported checkpoint version: {}",
+                checkpoint.version
+            )));
+        }
+
+        Ok(())
+    }
+
+    /// clean checkpoint file
+    ///
+    /// called when scanner stops or resets
+    pub async fn cleanup_checkpoint(&self) -> Result<()> {
+        // delete main file
+        if self.checkpoint_file.exists() {
+            tokio::fs::remove_file(&self.checkpoint_file)
+                .await
+                .map_err(|e| Error::IO(format!("delete main checkpoint file failed: {e}")))?;
+        }
+
+        // delete backup file
+        if self.backup_file.exists() {
+            tokio::fs::remove_file(&self.backup_file)
+                .await
+                .map_err(|e| Error::IO(format!("delete backup checkpoint file failed: {e}")))?;
+        }
+
+        // delete temp file
+        if self.temp_file.exists() {
+            tokio::fs::remove_file(&self.temp_file)
+                .await
+                .map_err(|e| Error::IO(format!("delete temp checkpoint file failed: {e}")))?;
+        }
+
+        info!("cleaned up all checkpoint files");
+        Ok(())
+    }
+
+    /// get checkpoint file info
+    pub async fn get_checkpoint_info(&self) -> Result<Option<CheckpointInfo>> {
+        if !self.checkpoint_file.exists() {
+            return Ok(None);
+        }
+
+        let metadata = tokio::fs::metadata(&self.checkpoint_file)
+            .await
+            .map_err(|e| Error::IO(format!("get checkpoint file metadata failed: {e}")))?;
+
+        let content = tokio::fs::read_to_string(&self.checkpoint_file)
+            .await
+            .map_err(|e| Error::IO(format!("read checkpoint file failed: {e}")))?;
+
+        let checkpoint_data: CheckpointData =
+            serde_json::from_str(&content).map_err(|e| Error::Serialization(format!("deserialize checkpoint failed: {e}")))?;
+
+        Ok(Some(CheckpointInfo {
+            file_size: metadata.len(),
+            last_modified: metadata.modified().unwrap_or(SystemTime::UNIX_EPOCH),
+            checkpoint_timestamp: checkpoint_data.timestamp,
+            current_cycle: checkpoint_data.progress.current_cycle,
+            current_disk_index: checkpoint_data.progress.current_disk_index,
+            completed_disks_count: checkpoint_data.progress.completed_disks.len(),
+            is_valid: checkpoint_data.verify_integrity(),
+        }))
+    }
+
+    /// force save checkpoint (ignore time interval limit)
+    pub async fn force_save_checkpoint(&self, progress: &ScanProgress) -> Result<()> {
+        // temporarily reset last save time, force save
+        *self.last_save.write().await = SystemTime::UNIX_EPOCH;
+        self.save_checkpoint(progress).await
+    }
+
+    /// set save interval
+    pub async fn set_save_interval(&mut self, interval: Duration) {
+        self.save_interval = interval;
+        info!("checkpoint save interval set to: {:?}", interval);
+    }
+}
+
+/// checkpoint info
+#[derive(Debug, Clone)]
+pub struct CheckpointInfo {
+    /// file size
+    pub file_size: u64,
+    /// file last modified time
+    pub last_modified: SystemTime,
+    /// checkpoint creation time
+    pub checkpoint_timestamp: SystemTime,
+    /// current scan cycle
+    pub current_cycle: u64,
+    /// current disk index
+    pub current_disk_index: usize,
+    /// completed disks count
+    pub completed_disks_count: usize,
+    /// checkpoint is valid
+    pub is_valid: bool,
+}

crates/ahm/src/scanner/histogram.rs

@@ -12,13 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use serde::{Deserialize, Serialize};
 use std::{
     collections::HashMap,
     sync::atomic::{AtomicU64, Ordering},
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tracing::info;
 
 /// Scanner metrics

crates/ahm/src/scanner/io_monitor.rs

@@ -0,0 +1,555 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::Result;
+use crate::scanner::LoadLevel;
+use serde::{Deserialize, Serialize};
+use std::{
+    collections::VecDeque,
+    sync::{
+        Arc,
+        atomic::{AtomicU64, Ordering},
+    },
+    time::{Duration, SystemTime},
+};
+use tokio::sync::RwLock;
+use tokio_util::sync::CancellationToken;
+use tracing::{debug, error, info, warn};
+
+/// IO monitor config   
+#[derive(Debug, Clone)]
+pub struct IOMonitorConfig {
+    /// monitor interval
+    pub monitor_interval: Duration,
+    /// history data retention time
+    pub history_retention: Duration,
+    /// load evaluation window size
+    pub load_window_size: usize,
+    /// whether to enable actual system monitoring
+    pub enable_system_monitoring: bool,
+    /// disk path list (for monitoring specific disks)
+    pub disk_paths: Vec<String>,
+}
+
+impl Default for IOMonitorConfig {
+    fn default() -> Self {
+        Self {
+            monitor_interval: Duration::from_secs(1),    // 1 second monitor interval
+            history_retention: Duration::from_secs(300), // keep 5 minutes history
+            load_window_size: 30,                        // 30 sample points sliding window
+            enable_system_monitoring: false,             // default use simulated data
+            disk_paths: Vec::new(),
+        }
+    }
+}
+
+/// IO monitor metrics
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct IOMetrics {
+    /// timestamp
+    pub timestamp: SystemTime,
+    /// disk IOPS (read + write)
+    pub iops: u64,
+    /// read IOPS
+    pub read_iops: u64,
+    /// write IOPS
+    pub write_iops: u64,
+    /// disk queue depth
+    pub queue_depth: u64,
+    /// average latency (milliseconds)
+    pub avg_latency: u64,
+    /// read latency (milliseconds)
+    pub read_latency: u64,
+    /// write latency (milliseconds)
+    pub write_latency: u64,
+    /// CPU usage (0-100)
+    pub cpu_usage: u8,
+    /// memory usage (0-100)
+    pub memory_usage: u8,
+    /// disk usage (0-100)
+    pub disk_utilization: u8,
+    /// network IO (Mbps)
+    pub network_io: u64,
+}
+
+impl Default for IOMetrics {
+    fn default() -> Self {
+        Self {
+            timestamp: SystemTime::now(),
+            iops: 0,
+            read_iops: 0,
+            write_iops: 0,
+            queue_depth: 0,
+            avg_latency: 0,
+            read_latency: 0,
+            write_latency: 0,
+            cpu_usage: 0,
+            memory_usage: 0,
+            disk_utilization: 0,
+            network_io: 0,
+        }
+    }
+}
+
+/// load level stats
+#[derive(Debug, Clone, Default)]
+pub struct LoadLevelStats {
+    /// low load duration (seconds)
+    pub low_load_duration: u64,
+    /// medium load duration (seconds)
+    pub medium_load_duration: u64,
+    /// high load duration (seconds)
+    pub high_load_duration: u64,
+    /// critical load duration (seconds)
+    pub critical_load_duration: u64,
+    /// load transitions
+    pub load_transitions: u64,
+}
+
+/// advanced IO monitor
+pub struct AdvancedIOMonitor {
+    /// config
+    config: Arc<RwLock<IOMonitorConfig>>,
+    /// current metrics
+    current_metrics: Arc<RwLock<IOMetrics>>,
+    /// history metrics (sliding window)
+    history_metrics: Arc<RwLock<VecDeque<IOMetrics>>>,
+    /// current load level
+    current_load_level: Arc<RwLock<LoadLevel>>,
+    /// load level history
+    load_level_history: Arc<RwLock<VecDeque<(SystemTime, LoadLevel)>>>,
+    /// load level stats
+    load_stats: Arc<RwLock<LoadLevelStats>>,
+    /// business IO metrics (updated by external)
+    business_metrics: Arc<BusinessIOMetrics>,
+    /// cancel token
+    cancel_token: CancellationToken,
+}
+
+/// business IO metrics
+pub struct BusinessIOMetrics {
+    /// business request latency (milliseconds)
+    pub request_latency: AtomicU64,
+    /// business request QPS
+    pub request_qps: AtomicU64,
+    /// business error rate (0-10000, 0.00%-100.00%)
+    pub error_rate: AtomicU64,
+    /// active connections
+    pub active_connections: AtomicU64,
+    /// last update time
+    pub last_update: Arc<RwLock<SystemTime>>,
+}
+
+impl Default for BusinessIOMetrics {
+    fn default() -> Self {
+        Self {
+            request_latency: AtomicU64::new(0),
+            request_qps: AtomicU64::new(0),
+            error_rate: AtomicU64::new(0),
+            active_connections: AtomicU64::new(0),
+            last_update: Arc::new(RwLock::new(SystemTime::UNIX_EPOCH)),
+        }
+    }
+}
+
+impl AdvancedIOMonitor {
+    /// create new advanced IO monitor
+    pub fn new(config: IOMonitorConfig) -> Self {
+        Self {
+            config: Arc::new(RwLock::new(config)),
+            current_metrics: Arc::new(RwLock::new(IOMetrics::default())),
+            history_metrics: Arc::new(RwLock::new(VecDeque::new())),
+            current_load_level: Arc::new(RwLock::new(LoadLevel::Low)),
+            load_level_history: Arc::new(RwLock::new(VecDeque::new())),
+            load_stats: Arc::new(RwLock::new(LoadLevelStats::default())),
+            business_metrics: Arc::new(BusinessIOMetrics::default()),
+            cancel_token: CancellationToken::new(),
+        }
+    }
+
+    /// start monitoring
+    pub async fn start(&self) -> Result<()> {
+        info!("start advanced IO monitor");
+
+        let monitor = self.clone_for_background();
+        tokio::spawn(async move {
+            if let Err(e) = monitor.monitoring_loop().await {
+                error!("IO monitoring loop failed: {}", e);
+            }
+        });
+
+        Ok(())
+    }
+
+    /// stop monitoring
+    pub async fn stop(&self) {
+        info!("stop IO monitor");
+        self.cancel_token.cancel();
+    }
+
+    /// monitoring loop
+    async fn monitoring_loop(&self) -> Result<()> {
+        let mut interval = {
+            let config = self.config.read().await;
+            tokio::time::interval(config.monitor_interval)
+        };
+
+        let mut last_load_level = LoadLevel::Low;
+        let mut load_level_start_time = SystemTime::now();
+
+        loop {
+            tokio::select! {
+                _ = self.cancel_token.cancelled() => {
+                    info!("IO monitoring loop cancelled");
+                    break;
+                }
+                _ = interval.tick() => {
+                    // collect system metrics
+                    let metrics = self.collect_system_metrics().await;
+
+                    // update current metrics
+                    *self.current_metrics.write().await = metrics.clone();
+
+                    // update history metrics
+                    self.update_metrics_history(metrics.clone()).await;
+
+                    // calculate load level
+                    let new_load_level = self.calculate_load_level(&metrics).await;
+
+                    // check if load level changed
+                    if new_load_level != last_load_level {
+                        self.handle_load_level_change(last_load_level, new_load_level, load_level_start_time).await;
+                        last_load_level = new_load_level;
+                        load_level_start_time = SystemTime::now();
+                    }
+
+                    // update current load level
+                    *self.current_load_level.write().await = new_load_level;
+
+                    debug!("IO monitor updated: IOPS={}, queue depth={}, latency={}ms, load level={:?}",
+                           metrics.iops, metrics.queue_depth, metrics.avg_latency, new_load_level);
+                }
+            }
+        }
+
+        Ok(())
+    }
+
+    /// collect system metrics
+    async fn collect_system_metrics(&self) -> IOMetrics {
+        let config = self.config.read().await;
+
+        if config.enable_system_monitoring {
+            // actual system monitoring implementation
+            self.collect_real_system_metrics().await
+        } else {
+            // simulated data
+            self.generate_simulated_metrics().await
+        }
+    }
+
+    /// collect real system metrics (need to be implemented according to specific system)
+    async fn collect_real_system_metrics(&self) -> IOMetrics {
+        // TODO: implement actual system metrics collection
+        // can use procfs, sysfs or other system API
+
+        let metrics = IOMetrics {
+            timestamp: SystemTime::now(),
+            ..Default::default()
+        };
+
+        // example: read /proc/diskstats
+        if let Ok(diskstats) = tokio::fs::read_to_string("/proc/diskstats").await {
+            // parse disk stats info
+            // here need to implement specific parsing logic
+            debug!("read disk stats info: {} bytes", diskstats.len());
+        }
+
+        // example: read /proc/stat to get CPU info
+        if let Ok(stat) = tokio::fs::read_to_string("/proc/stat").await {
+            // parse CPU stats info
+            debug!("read CPU stats info: {} bytes", stat.len());
+        }
+
+        // example: read /proc/meminfo to get memory info
+        if let Ok(meminfo) = tokio::fs::read_to_string("/proc/meminfo").await {
+            // parse memory stats info
+            debug!("read memory stats info: {} bytes", meminfo.len());
+        }
+
+        metrics
+    }
+
+    /// generate simulated metrics (for testing and development)
+    async fn generate_simulated_metrics(&self) -> IOMetrics {
+        use rand::Rng;
+        let mut rng = rand::rng();
+
+        // get business metrics impact
+        let business_latency = self.business_metrics.request_latency.load(Ordering::Relaxed);
+        let business_qps = self.business_metrics.request_qps.load(Ordering::Relaxed);
+
+        // generate simulated system metrics based on business load
+        let base_iops = 100 + (business_qps / 10);
+        let base_latency = 5 + (business_latency / 10);
+
+        IOMetrics {
+            timestamp: SystemTime::now(),
+            iops: base_iops + rng.random_range(0..50),
+            read_iops: (base_iops * 6 / 10) + rng.random_range(0..20),
+            write_iops: (base_iops * 4 / 10) + rng.random_range(0..20),
+            queue_depth: rng.random_range(1..20),
+            avg_latency: base_latency + rng.random_range(0..10),
+            read_latency: base_latency + rng.random_range(0..5),
+            write_latency: base_latency + rng.random_range(0..15),
+            cpu_usage: rng.random_range(10..70),
+            memory_usage: rng.random_range(30..80),
+            disk_utilization: rng.random_range(20..90),
+            network_io: rng.random_range(10..1000),
+        }
+    }
+
+    /// update metrics history
+    async fn update_metrics_history(&self, metrics: IOMetrics) {
+        let mut history = self.history_metrics.write().await;
+        let config = self.config.read().await;
+
+        // add new metrics
+        history.push_back(metrics);
+
+        // clean expired data
+        let retention_cutoff = SystemTime::now() - config.history_retention;
+        while let Some(front) = history.front() {
+            if front.timestamp < retention_cutoff {
+                history.pop_front();
+            } else {
+                break;
+            }
+        }
+
+        // limit window size
+        while history.len() > config.load_window_size {
+            history.pop_front();
+        }
+    }
+
+    /// calculate load level
+    async fn calculate_load_level(&self, metrics: &IOMetrics) -> LoadLevel {
+        // multi-dimensional load evaluation algorithm
+        let mut load_score = 0u32;
+
+        // IOPS load evaluation (weight: 25%)
+        let iops_score = match metrics.iops {
+            0..=200 => 0,
+            201..=500 => 15,
+            501..=1000 => 25,
+            _ => 35,
+        };
+        load_score += iops_score;
+
+        // latency load evaluation (weight: 30%)
+        let latency_score = match metrics.avg_latency {
+            0..=10 => 0,
+            11..=50 => 20,
+            51..=100 => 30,
+            _ => 40,
+        };
+        load_score += latency_score;
+
+        // queue depth evaluation (weight: 20%)
+        let queue_score = match metrics.queue_depth {
+            0..=5 => 0,
+            6..=15 => 10,
+            16..=30 => 20,
+            _ => 25,
+        };
+        load_score += queue_score;
+
+        // CPU usage evaluation (weight: 15%)
+        let cpu_score = match metrics.cpu_usage {
+            0..=30 => 0,
+            31..=60 => 8,
+            61..=80 => 12,
+            _ => 15,
+        };
+        load_score += cpu_score;
+
+        // disk usage evaluation (weight: 10%)
+        let disk_score = match metrics.disk_utilization {
+            0..=50 => 0,
+            51..=75 => 5,
+            76..=90 => 8,
+            _ => 10,
+        };
+        load_score += disk_score;
+
+        // business metrics impact
+        let business_latency = self.business_metrics.request_latency.load(Ordering::Relaxed);
+        let business_error_rate = self.business_metrics.error_rate.load(Ordering::Relaxed);
+
+        if business_latency > 100 {
+            load_score += 20; // business latency too high
+        }
+        if business_error_rate > 100 {
+            // > 1%
+            load_score += 15; // business error rate too high
+        }
+
+        // history trend analysis
+        let trend_score = self.calculate_trend_score().await;
+        load_score += trend_score;
+
+        // determine load level based on total score
+        match load_score {
+            0..=30 => LoadLevel::Low,
+            31..=60 => LoadLevel::Medium,
+            61..=90 => LoadLevel::High,
+            _ => LoadLevel::Critical,
+        }
+    }
+
+    /// calculate trend score
+    async fn calculate_trend_score(&self) -> u32 {
+        let history = self.history_metrics.read().await;
+
+        if history.len() < 5 {
+            return 0; // data insufficient, cannot analyze trend
+        }
+
+        // analyze trend of last 5 samples
+        let recent: Vec<_> = history.iter().rev().take(5).collect();
+
+        // check IOPS rising trend
+        let mut iops_trend = 0;
+        for i in 1..recent.len() {
+            if recent[i - 1].iops > recent[i].iops {
+                iops_trend += 1;
+            }
+        }
+
+        // check latency rising trend
+        let mut latency_trend = 0;
+        for i in 1..recent.len() {
+            if recent[i - 1].avg_latency > recent[i].avg_latency {
+                latency_trend += 1;
+            }
+        }
+
+        // if IOPS and latency are both rising, increase load score
+        if iops_trend >= 3 && latency_trend >= 3 {
+            15 // obvious rising trend
+        } else if iops_trend >= 2 || latency_trend >= 2 {
+            5 // slight rising trend
+        } else {
+            0 // no obvious trend
+        }
+    }
+
+    /// handle load level change
+    async fn handle_load_level_change(&self, old_level: LoadLevel, new_level: LoadLevel, start_time: SystemTime) {
+        let duration = SystemTime::now().duration_since(start_time).unwrap_or(Duration::ZERO);
+
+        // update stats
+        {
+            let mut stats = self.load_stats.write().await;
+            match old_level {
+                LoadLevel::Low => stats.low_load_duration += duration.as_secs(),
+                LoadLevel::Medium => stats.medium_load_duration += duration.as_secs(),
+                LoadLevel::High => stats.high_load_duration += duration.as_secs(),
+                LoadLevel::Critical => stats.critical_load_duration += duration.as_secs(),
+            }
+            stats.load_transitions += 1;
+        }
+
+        // update history
+        {
+            let mut history = self.load_level_history.write().await;
+            history.push_back((SystemTime::now(), new_level));
+
+            // keep history record in reasonable range
+            while history.len() > 100 {
+                history.pop_front();
+            }
+        }
+
+        info!("load level changed: {:?} -> {:?}, duration: {:?}", old_level, new_level, duration);
+
+        // if enter critical load state, record warning
+        if new_level == LoadLevel::Critical {
+            warn!("system entered critical load state, Scanner will pause running");
+        }
+    }
+
+    /// get current load level
+    pub async fn get_business_load_level(&self) -> LoadLevel {
+        *self.current_load_level.read().await
+    }
+
+    /// get current metrics
+    pub async fn get_current_metrics(&self) -> IOMetrics {
+        self.current_metrics.read().await.clone()
+    }
+
+    /// get history metrics
+    pub async fn get_history_metrics(&self) -> Vec<IOMetrics> {
+        self.history_metrics.read().await.iter().cloned().collect()
+    }
+
+    /// get load stats
+    pub async fn get_load_stats(&self) -> LoadLevelStats {
+        self.load_stats.read().await.clone()
+    }
+
+    /// update business IO metrics
+    pub async fn update_business_metrics(&self, latency: u64, qps: u64, error_rate: u64, connections: u64) {
+        self.business_metrics.request_latency.store(latency, Ordering::Relaxed);
+        self.business_metrics.request_qps.store(qps, Ordering::Relaxed);
+        self.business_metrics.error_rate.store(error_rate, Ordering::Relaxed);
+        self.business_metrics.active_connections.store(connections, Ordering::Relaxed);
+
+        *self.business_metrics.last_update.write().await = SystemTime::now();
+
+        debug!(
+            "update business metrics: latency={}ms, QPS={}, error rate={}‰, connections={}",
+            latency, qps, error_rate, connections
+        );
+    }
+
+    /// clone for background task
+    fn clone_for_background(&self) -> Self {
+        Self {
+            config: self.config.clone(),
+            current_metrics: self.current_metrics.clone(),
+            history_metrics: self.history_metrics.clone(),
+            current_load_level: self.current_load_level.clone(),
+            load_level_history: self.load_level_history.clone(),
+            load_stats: self.load_stats.clone(),
+            business_metrics: self.business_metrics.clone(),
+            cancel_token: self.cancel_token.clone(),
+        }
+    }
+
+    /// reset stats
+    pub async fn reset_stats(&self) {
+        *self.load_stats.write().await = LoadLevelStats::default();
+        self.load_level_history.write().await.clear();
+        self.history_metrics.write().await.clear();
+        info!("IO monitor stats reset");
+    }
+
+    /// get load level history
+    pub async fn get_load_level_history(&self) -> Vec<(SystemTime, LoadLevel)> {
+        self.load_level_history.read().await.iter().cloned().collect()
+    }
+}

crates/ahm/src/scanner/io_throttler.rs

@@ -0,0 +1,499 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::scanner::LoadLevel;
+use std::{
+    sync::{
+        Arc,
+        atomic::{AtomicU8, AtomicU64, Ordering},
+    },
+    time::{Duration, SystemTime},
+};
+use tokio::sync::RwLock;
+use tracing::{debug, info, warn};
+
+/// IO throttler config
+#[derive(Debug, Clone)]
+pub struct IOThrottlerConfig {
+    /// max IOPS limit
+    pub max_iops: u64,
+    /// business priority baseline (percentage)
+    pub base_business_priority: u8,
+    /// scanner minimum delay (milliseconds)
+    pub min_scan_delay: u64,
+    /// scanner maximum delay (milliseconds)
+    pub max_scan_delay: u64,
+    /// whether enable dynamic adjustment
+    pub enable_dynamic_adjustment: bool,
+    /// adjustment response time (seconds)
+    pub adjustment_response_time: u64,
+}
+
+impl Default for IOThrottlerConfig {
+    fn default() -> Self {
+        Self {
+            max_iops: 1000,             // default max 1000 IOPS
+            base_business_priority: 95, // business priority 95%
+            min_scan_delay: 5000,       // minimum 5s delay
+            max_scan_delay: 60000,      // maximum 60s delay
+            enable_dynamic_adjustment: true,
+            adjustment_response_time: 5, // 5 seconds response time
+        }
+    }
+}
+
+/// resource allocation strategy
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum ResourceAllocationStrategy {
+    /// business priority strategy
+    BusinessFirst,
+    /// balanced strategy
+    Balanced,
+    /// maintenance priority strategy (only used in special cases)
+    MaintenanceFirst,
+}
+
+/// throttle decision
+#[derive(Debug, Clone)]
+pub struct ThrottleDecision {
+    /// whether should pause scanning
+    pub should_pause: bool,
+    /// suggested scanning delay
+    pub suggested_delay: Duration,
+    /// resource allocation suggestion
+    pub resource_allocation: ResourceAllocation,
+    /// decision reason
+    pub reason: String,
+}
+
+/// resource allocation
+#[derive(Debug, Clone)]
+pub struct ResourceAllocation {
+    /// business IO allocation percentage (0-100)
+    pub business_percentage: u8,
+    /// scanner IO allocation percentage (0-100)
+    pub scanner_percentage: u8,
+    /// allocation strategy
+    pub strategy: ResourceAllocationStrategy,
+}
+
+/// enhanced IO throttler
+///
+/// dynamically adjust the resource usage of the scanner based on real-time system load and business demand,
+/// ensure business IO gets priority protection.
+pub struct AdvancedIOThrottler {
+    /// config
+    config: Arc<RwLock<IOThrottlerConfig>>,
+    /// current IOPS usage (reserved field)
+    #[allow(dead_code)]
+    current_iops: Arc<AtomicU64>,
+    /// business priority weight (0-100)
+    business_priority: Arc<AtomicU8>,
+    /// scanning operation delay (milliseconds)
+    scan_delay: Arc<AtomicU64>,
+    /// resource allocation strategy
+    allocation_strategy: Arc<RwLock<ResourceAllocationStrategy>>,
+    /// throttle history record
+    throttle_history: Arc<RwLock<Vec<ThrottleRecord>>>,
+    /// last adjustment time (reserved field)
+    #[allow(dead_code)]
+    last_adjustment: Arc<RwLock<SystemTime>>,
+}
+
+/// throttle record
+#[derive(Debug, Clone)]
+pub struct ThrottleRecord {
+    /// timestamp
+    pub timestamp: SystemTime,
+    /// load level
+    pub load_level: LoadLevel,
+    /// decision
+    pub decision: ThrottleDecision,
+    /// system metrics snapshot
+    pub metrics_snapshot: MetricsSnapshot,
+}
+
+/// metrics snapshot
+#[derive(Debug, Clone)]
+pub struct MetricsSnapshot {
+    /// IOPS
+    pub iops: u64,
+    /// latency
+    pub latency: u64,
+    /// CPU usage
+    pub cpu_usage: u8,
+    /// memory usage
+    pub memory_usage: u8,
+}
+
+impl AdvancedIOThrottler {
+    /// create new advanced IO throttler
+    pub fn new(config: IOThrottlerConfig) -> Self {
+        Self {
+            config: Arc::new(RwLock::new(config)),
+            current_iops: Arc::new(AtomicU64::new(0)),
+            business_priority: Arc::new(AtomicU8::new(95)),
+            scan_delay: Arc::new(AtomicU64::new(5000)),
+            allocation_strategy: Arc::new(RwLock::new(ResourceAllocationStrategy::BusinessFirst)),
+            throttle_history: Arc::new(RwLock::new(Vec::new())),
+            last_adjustment: Arc::new(RwLock::new(SystemTime::UNIX_EPOCH)),
+        }
+    }
+
+    /// adjust scanning delay based on load level
+    pub async fn adjust_for_load_level(&self, load_level: LoadLevel) -> Duration {
+        let config = self.config.read().await;
+
+        let delay_ms = match load_level {
+            LoadLevel::Low => {
+                // low load: use minimum delay
+                self.scan_delay.store(config.min_scan_delay, Ordering::Relaxed);
+                self.business_priority
+                    .store(config.base_business_priority.saturating_sub(5), Ordering::Relaxed);
+                config.min_scan_delay
+            }
+            LoadLevel::Medium => {
+                // medium load: increase delay moderately
+                let delay = config.min_scan_delay * 5; // 500ms
+                self.scan_delay.store(delay, Ordering::Relaxed);
+                self.business_priority.store(config.base_business_priority, Ordering::Relaxed);
+                delay
+            }
+            LoadLevel::High => {
+                // high load: increase delay significantly
+                let delay = config.min_scan_delay * 10; // 50s
+                self.scan_delay.store(delay, Ordering::Relaxed);
+                self.business_priority
+                    .store(config.base_business_priority.saturating_add(3), Ordering::Relaxed);
+                delay
+            }
+            LoadLevel::Critical => {
+                // critical load: maximum delay or pause
+                let delay = config.max_scan_delay; // 60s
+                self.scan_delay.store(delay, Ordering::Relaxed);
+                self.business_priority.store(99, Ordering::Relaxed);
+                delay
+            }
+        };
+
+        let duration = Duration::from_millis(delay_ms);
+
+        debug!("Adjust scanning delay based on load level {:?}: {:?}", load_level, duration);
+
+        duration
+    }
+
+    /// create throttle decision
+    pub async fn make_throttle_decision(&self, load_level: LoadLevel, metrics: Option<MetricsSnapshot>) -> ThrottleDecision {
+        let _config = self.config.read().await;
+
+        let should_pause = matches!(load_level, LoadLevel::Critical);
+
+        let suggested_delay = self.adjust_for_load_level(load_level).await;
+
+        let resource_allocation = self.calculate_resource_allocation(load_level).await;
+
+        let reason = match load_level {
+            LoadLevel::Low => "system load is low, scanner can run normally".to_string(),
+            LoadLevel::Medium => "system load is moderate, scanner is running at reduced speed".to_string(),
+            LoadLevel::High => "system load is high, scanner is running at significantly reduced speed".to_string(),
+            LoadLevel::Critical => "system load is too high, scanner is paused".to_string(),
+        };
+
+        let decision = ThrottleDecision {
+            should_pause,
+            suggested_delay,
+            resource_allocation,
+            reason,
+        };
+
+        // record decision history
+        if let Some(snapshot) = metrics {
+            self.record_throttle_decision(load_level, decision.clone(), snapshot).await;
+        }
+
+        decision
+    }
+
+    /// calculate resource allocation
+    async fn calculate_resource_allocation(&self, load_level: LoadLevel) -> ResourceAllocation {
+        let strategy = *self.allocation_strategy.read().await;
+
+        let (business_pct, scanner_pct) = match (strategy, load_level) {
+            (ResourceAllocationStrategy::BusinessFirst, LoadLevel::Low) => (90, 10),
+            (ResourceAllocationStrategy::BusinessFirst, LoadLevel::Medium) => (95, 5),
+            (ResourceAllocationStrategy::BusinessFirst, LoadLevel::High) => (98, 2),
+            (ResourceAllocationStrategy::BusinessFirst, LoadLevel::Critical) => (99, 1),
+
+            (ResourceAllocationStrategy::Balanced, LoadLevel::Low) => (80, 20),
+            (ResourceAllocationStrategy::Balanced, LoadLevel::Medium) => (85, 15),
+            (ResourceAllocationStrategy::Balanced, LoadLevel::High) => (90, 10),
+            (ResourceAllocationStrategy::Balanced, LoadLevel::Critical) => (95, 5),
+
+            (ResourceAllocationStrategy::MaintenanceFirst, _) => (70, 30), // special maintenance mode
+        };
+
+        ResourceAllocation {
+            business_percentage: business_pct,
+            scanner_percentage: scanner_pct,
+            strategy,
+        }
+    }
+
+    /// check whether should pause scanning
+    pub async fn should_pause_scanning(&self, load_level: LoadLevel) -> bool {
+        match load_level {
+            LoadLevel::Critical => {
+                warn!("System load reached critical level, pausing scanner");
+                true
+            }
+            _ => false,
+        }
+    }
+
+    /// record throttle decision
+    async fn record_throttle_decision(&self, load_level: LoadLevel, decision: ThrottleDecision, metrics: MetricsSnapshot) {
+        let record = ThrottleRecord {
+            timestamp: SystemTime::now(),
+            load_level,
+            decision,
+            metrics_snapshot: metrics,
+        };
+
+        let mut history = self.throttle_history.write().await;
+        history.push(record);
+
+        // keep history record in reasonable range (last 1000 records)
+        while history.len() > 1000 {
+            history.remove(0);
+        }
+    }
+
+    /// set resource allocation strategy
+    pub async fn set_allocation_strategy(&self, strategy: ResourceAllocationStrategy) {
+        *self.allocation_strategy.write().await = strategy;
+        info!("Set resource allocation strategy: {:?}", strategy);
+    }
+
+    /// get current resource allocation
+    pub async fn get_current_allocation(&self) -> ResourceAllocation {
+        let current_load = LoadLevel::Low; // need to get from external
+        self.calculate_resource_allocation(current_load).await
+    }
+
+    /// get throttle history
+    pub async fn get_throttle_history(&self) -> Vec<ThrottleRecord> {
+        self.throttle_history.read().await.clone()
+    }
+
+    /// get throttle stats
+    pub async fn get_throttle_stats(&self) -> ThrottleStats {
+        let history = self.throttle_history.read().await;
+
+        let total_decisions = history.len();
+        let pause_decisions = history.iter().filter(|r| r.decision.should_pause).count();
+
+        let mut delay_sum = Duration::ZERO;
+        for record in history.iter() {
+            delay_sum += record.decision.suggested_delay;
+        }
+
+        let avg_delay = if total_decisions > 0 {
+            delay_sum / total_decisions as u32
+        } else {
+            Duration::ZERO
+        };
+
+        // count by load level
+        let low_count = history.iter().filter(|r| r.load_level == LoadLevel::Low).count();
+        let medium_count = history.iter().filter(|r| r.load_level == LoadLevel::Medium).count();
+        let high_count = history.iter().filter(|r| r.load_level == LoadLevel::High).count();
+        let critical_count = history.iter().filter(|r| r.load_level == LoadLevel::Critical).count();
+
+        ThrottleStats {
+            total_decisions,
+            pause_decisions,
+            average_delay: avg_delay,
+            load_level_distribution: LoadLevelDistribution {
+                low_count,
+                medium_count,
+                high_count,
+                critical_count,
+            },
+        }
+    }
+
+    /// reset throttle history
+    pub async fn reset_history(&self) {
+        self.throttle_history.write().await.clear();
+        info!("Reset throttle history");
+    }
+
+    /// update config
+    pub async fn update_config(&self, new_config: IOThrottlerConfig) {
+        *self.config.write().await = new_config;
+        info!("Updated IO throttler configuration");
+    }
+
+    /// get current scanning delay
+    pub fn get_current_scan_delay(&self) -> Duration {
+        let delay_ms = self.scan_delay.load(Ordering::Relaxed);
+        Duration::from_millis(delay_ms)
+    }
+
+    /// get current business priority
+    pub fn get_current_business_priority(&self) -> u8 {
+        self.business_priority.load(Ordering::Relaxed)
+    }
+
+    /// simulate business load pressure test
+    pub async fn simulate_business_pressure(&self, duration: Duration) -> SimulationResult {
+        info!("Start simulating business load pressure test, duration: {:?}", duration);
+
+        let start_time = SystemTime::now();
+        let mut simulation_records = Vec::new();
+
+        // simulate different load level changes
+        let load_levels = [
+            LoadLevel::Low,
+            LoadLevel::Medium,
+            LoadLevel::High,
+            LoadLevel::Critical,
+            LoadLevel::High,
+            LoadLevel::Medium,
+            LoadLevel::Low,
+        ];
+
+        let step_duration = duration / load_levels.len() as u32;
+
+        for (i, &load_level) in load_levels.iter().enumerate() {
+            let _step_start = SystemTime::now();
+
+            // simulate metrics for this load level
+            let metrics = MetricsSnapshot {
+                iops: match load_level {
+                    LoadLevel::Low => 200,
+                    LoadLevel::Medium => 500,
+                    LoadLevel::High => 800,
+                    LoadLevel::Critical => 1200,
+                },
+                latency: match load_level {
+                    LoadLevel::Low => 10,
+                    LoadLevel::Medium => 25,
+                    LoadLevel::High => 60,
+                    LoadLevel::Critical => 150,
+                },
+                cpu_usage: match load_level {
+                    LoadLevel::Low => 30,
+                    LoadLevel::Medium => 50,
+                    LoadLevel::High => 75,
+                    LoadLevel::Critical => 95,
+                },
+                memory_usage: match load_level {
+                    LoadLevel::Low => 40,
+                    LoadLevel::Medium => 60,
+                    LoadLevel::High => 80,
+                    LoadLevel::Critical => 90,
+                },
+            };
+
+            let decision = self.make_throttle_decision(load_level, Some(metrics.clone())).await;
+
+            simulation_records.push(SimulationRecord {
+                step: i + 1,
+                load_level,
+                metrics,
+                decision: decision.clone(),
+                step_duration,
+            });
+
+            info!(
+                "simulate step {}: load={:?}, delay={:?}, pause={}",
+                i + 1,
+                load_level,
+                decision.suggested_delay,
+                decision.should_pause
+            );
+
+            // wait for step duration
+            tokio::time::sleep(step_duration).await;
+        }
+
+        let total_duration = SystemTime::now().duration_since(start_time).unwrap_or(Duration::ZERO);
+
+        SimulationResult {
+            total_duration,
+            simulation_records,
+            final_stats: self.get_throttle_stats().await,
+        }
+    }
+}
+
+/// throttle stats
+#[derive(Debug, Clone)]
+pub struct ThrottleStats {
+    /// total decisions
+    pub total_decisions: usize,
+    /// pause decisions
+    pub pause_decisions: usize,
+    /// average delay
+    pub average_delay: Duration,
+    /// load level distribution
+    pub load_level_distribution: LoadLevelDistribution,
+}
+
+/// load level distribution
+#[derive(Debug, Clone)]
+pub struct LoadLevelDistribution {
+    /// low load count
+    pub low_count: usize,
+    /// medium load count
+    pub medium_count: usize,
+    /// high load count
+    pub high_count: usize,
+    /// critical load count
+    pub critical_count: usize,
+}
+
+/// simulation result
+#[derive(Debug, Clone)]
+pub struct SimulationResult {
+    /// total duration
+    pub total_duration: Duration,
+    /// simulation records
+    pub simulation_records: Vec<SimulationRecord>,
+    /// final stats
+    pub final_stats: ThrottleStats,
+}
+
+/// simulation record
+#[derive(Debug, Clone)]
+pub struct SimulationRecord {
+    /// step number
+    pub step: usize,
+    /// load level
+    pub load_level: LoadLevel,
+    /// metrics snapshot
+    pub metrics: MetricsSnapshot,
+    /// throttle decision
+    pub decision: ThrottleDecision,
+    /// step duration
+    pub step_duration: Duration,
+}
+
+impl Default for AdvancedIOThrottler {
+    fn default() -> Self {
+        Self::new(IOThrottlerConfig::default())
+    }
+}

crates/ahm/src/scanner/lifecycle.rs

@@ -12,76 +12,289 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-use std::sync::Arc;
-
+use crate::{
+    Result,
+    scanner::metrics::{BucketMetrics, MetricsCollector},
+};
+use rustfs_common::data_usage::SizeSummary;
 use rustfs_common::metrics::IlmAction;
-use rustfs_ecstore::bucket::lifecycle::bucket_lifecycle_audit::LcEventSrc;
-use rustfs_ecstore::bucket::lifecycle::bucket_lifecycle_ops::{apply_lifecycle_action, eval_action_from_lifecycle};
-use rustfs_ecstore::bucket::metadata_sys::get_object_lock_config;
-use rustfs_ecstore::cmd::bucket_targets::VersioningConfig;
-use rustfs_ecstore::store_api::ObjectInfo;
-use rustfs_filemeta::FileMetaVersion;
-use rustfs_filemeta::metacache::MetaCacheEntry;
-use s3s::dto::BucketLifecycleConfiguration as LifecycleConfig;
-use tracing::info;
+use rustfs_ecstore::bucket::{
+    lifecycle::{
+        bucket_lifecycle_audit::LcEventSrc,
+        bucket_lifecycle_ops::{GLOBAL_ExpiryState, apply_lifecycle_action, eval_action_from_lifecycle},
+        lifecycle,
+        lifecycle::Lifecycle,
+    },
+    metadata_sys::get_object_lock_config,
+    object_lock::objectlock_sys::{BucketObjectLockSys, enforce_retention_for_deletion},
+    versioning::VersioningApi,
+    versioning_sys::BucketVersioningSys,
+};
+use rustfs_ecstore::bucket::{
+    replication::{GLOBAL_REPLICATION_POOL, ReplicationConfig, get_heal_replicate_object_info},
+    utils::is_meta_bucketname,
+};
+use rustfs_ecstore::store_api::{ObjectInfo, ObjectToDelete};
+use rustfs_filemeta::{FileInfo, ReplicationStatusType, replication_statuses_map};
+use rustfs_utils::http::headers::{AMZ_BUCKET_REPLICATION_STATUS, HeaderExt, VERSION_PURGE_STATUS_KEY};
+use s3s::dto::DefaultRetention;
+use s3s::dto::{BucketLifecycleConfiguration as LifecycleConfig, VersioningConfiguration};
+use std::{
+    collections::HashMap,
+    sync::{
+        Arc,
+        atomic::{AtomicU64, Ordering},
+    },
+    time::Duration as StdDuration,
+};
+use time::{Duration as TimeDuration, OffsetDateTime};
+use tokio::sync::Mutex;
+use tracing::{debug, info, warn};
+
+static SCANNER_EXCESS_OBJECT_VERSIONS: AtomicU64 = AtomicU64::new(100);
+static SCANNER_EXCESS_OBJECT_VERSIONS_TOTAL_SIZE: AtomicU64 = AtomicU64::new(1024 * 1024 * 1024 * 1024); // 1 TB
 
 #[derive(Clone)]
 pub struct ScannerItem {
-    bucket: String,
-    lifecycle: Option<Arc<LifecycleConfig>>,
-    versioning: Option<Arc<VersioningConfig>>,
+    pub bucket: String,
+    pub object_name: String,
+    pub replication: Option<ReplicationConfig>,
+    pub lifecycle: Option<Arc<LifecycleConfig>>,
+    pub versioning: Option<Arc<VersioningConfiguration>>,
+    pub object_lock_config: Option<DefaultRetention>,
+    pub replication_pending_grace: StdDuration,
+    pub replication_metrics: Option<ReplicationMetricsHandle>,
 }
 
-impl ScannerItem {
-    pub fn new(bucket: String, lifecycle: Option<Arc<LifecycleConfig>>, versioning: Option<Arc<VersioningConfig>>) -> Self {
+#[derive(Clone)]
+pub struct ReplicationMetricsHandle {
+    inner: Arc<ReplicationMetricsInner>,
+}
+
+struct ReplicationMetricsInner {
+    metrics: Arc<MetricsCollector>,
+    bucket_metrics: Arc<Mutex<HashMap<String, BucketMetrics>>>,
+}
+
+impl ReplicationMetricsHandle {
+    pub fn new(metrics: Arc<MetricsCollector>, bucket_metrics: Arc<Mutex<HashMap<String, BucketMetrics>>>) -> Self {
         Self {
-            bucket,
-            lifecycle,
-            versioning,
+            inner: Arc::new(ReplicationMetricsInner { metrics, bucket_metrics }),
         }
     }
 
-    pub async fn apply_actions(&mut self, object: &str, mut meta: MetaCacheEntry) -> anyhow::Result<()> {
-        info!("apply_actions called for object: {}", object);
-        if self.lifecycle.is_none() {
-            info!("No lifecycle config for object: {}", object);
-            return Ok(());
+    pub async fn record_status(&self, bucket: &str, status: ReplicationStatusType, lagging: bool) {
+        match status {
+            ReplicationStatusType::Pending => self.inner.metrics.increment_replication_pending_objects(1),
+            ReplicationStatusType::Failed => self.inner.metrics.increment_replication_failed_objects(1),
+            _ => {}
+        }
+        if lagging {
+            self.inner.metrics.increment_replication_lagging_objects(1);
         }
-        info!("Lifecycle config exists for object: {}", object);
 
-        let file_meta = match meta.xl_meta() {
-            Ok(meta) => meta,
-            Err(e) => {
-                tracing::error!("Failed to get xl_meta for {}: {}", object, e);
-                return Ok(());
-            }
-        };
-
-        let latest_version = file_meta.versions.first().cloned().unwrap_or_default();
-        let file_meta_version = FileMetaVersion::try_from(latest_version.meta.as_slice()).unwrap_or_default();
-
-        let obj_info = ObjectInfo {
-            bucket: self.bucket.clone(),
-            name: object.to_string(),
-            version_id: latest_version.header.version_id,
-            mod_time: latest_version.header.mod_time,
-            size: file_meta_version.object.as_ref().map_or(0, |o| o.size),
-            user_defined: serde_json::from_slice(file_meta.data.as_slice()).unwrap_or_default(),
+        let mut guard = self.inner.bucket_metrics.lock().await;
+        let entry = guard.entry(bucket.to_string()).or_insert_with(|| BucketMetrics {
+            bucket: bucket.to_string(),
             ..Default::default()
+        });
+
+        match status {
+            ReplicationStatusType::Pending => {
+                entry.replication_pending = entry.replication_pending.saturating_add(1);
+            }
+            ReplicationStatusType::Failed => {
+                entry.replication_failed = entry.replication_failed.saturating_add(1);
+            }
+            _ => {}
+        }
+
+        if lagging {
+            entry.replication_lagging = entry.replication_lagging.saturating_add(1);
+        }
+    }
+
+    pub async fn record_task_submission(&self, bucket: &str) {
+        self.inner.metrics.increment_replication_tasks_queued(1);
+        let mut guard = self.inner.bucket_metrics.lock().await;
+        let entry = guard.entry(bucket.to_string()).or_insert_with(|| BucketMetrics {
+            bucket: bucket.to_string(),
+            ..Default::default()
+        });
+        entry.replication_tasks_queued = entry.replication_tasks_queued.saturating_add(1);
+    }
+}
+
+impl ScannerItem {
+    const INTERNAL_REPLICATION_STATUS_KEY: &'static str = "x-rustfs-internal-replication-status";
+
+    pub fn new(
+        bucket: String,
+        replication: Option<ReplicationConfig>,
+        lifecycle: Option<Arc<LifecycleConfig>>,
+        versioning: Option<Arc<VersioningConfiguration>>,
+        object_lock_config: Option<DefaultRetention>,
+        replication_pending_grace: StdDuration,
+        replication_metrics: Option<ReplicationMetricsHandle>,
+    ) -> Self {
+        Self {
+            bucket,
+            object_name: "".to_string(),
+            replication,
+            lifecycle,
+            versioning,
+            object_lock_config,
+            replication_pending_grace,
+            replication_metrics,
+        }
+    }
+
+    pub async fn apply_versions_actions(&self, fivs: &[FileInfo]) -> Result<Vec<ObjectInfo>> {
+        let obj_infos = self.apply_newer_noncurrent_version_limit(fivs).await?;
+        if obj_infos.len() >= SCANNER_EXCESS_OBJECT_VERSIONS.load(Ordering::SeqCst) as usize {
+            // todo
+        }
+
+        let mut cumulative_size = 0;
+        for obj_info in obj_infos.iter() {
+            cumulative_size += obj_info.size;
+        }
+
+        if cumulative_size >= SCANNER_EXCESS_OBJECT_VERSIONS_TOTAL_SIZE.load(Ordering::SeqCst) as i64 {
+            //todo
+        }
+
+        Ok(obj_infos)
+    }
+
+    pub async fn apply_newer_noncurrent_version_limit(&self, fivs: &[FileInfo]) -> Result<Vec<ObjectInfo>> {
+        let lock_enabled = if let Some(rcfg) = BucketObjectLockSys::get(&self.bucket).await {
+            rcfg.mode.is_some()
+        } else {
+            false
         };
+        let _vcfg = BucketVersioningSys::get(&self.bucket).await?;
 
-        self.apply_lifecycle(&obj_info).await;
+        let versioned = match BucketVersioningSys::get(&self.bucket).await {
+            Ok(vcfg) => vcfg.versioned(&self.object_name),
+            Err(_) => false,
+        };
+        let mut object_infos = Vec::with_capacity(fivs.len());
 
-        Ok(())
+        if self.lifecycle.is_none() {
+            for info in fivs.iter() {
+                object_infos.push(ObjectInfo::from_file_info(info, &self.bucket, &self.object_name, versioned));
+            }
+            return Ok(object_infos);
+        }
+
+        let event = self
+            .lifecycle
+            .as_ref()
+            .expect("lifecycle err.")
+            .clone()
+            .noncurrent_versions_expiration_limit(&lifecycle::ObjectOpts {
+                name: self.object_name.clone(),
+                ..Default::default()
+            })
+            .await;
+        let lim = event.newer_noncurrent_versions;
+        if lim == 0 || fivs.len() <= lim + 1 {
+            for fi in fivs.iter() {
+                object_infos.push(ObjectInfo::from_file_info(fi, &self.bucket, &self.object_name, versioned));
+            }
+            return Ok(object_infos);
+        }
+
+        let overflow_versions = &fivs[lim + 1..];
+        for fi in fivs[..lim + 1].iter() {
+            object_infos.push(ObjectInfo::from_file_info(fi, &self.bucket, &self.object_name, versioned));
+        }
+
+        let mut to_del = Vec::<ObjectToDelete>::with_capacity(overflow_versions.len());
+        for fi in overflow_versions.iter() {
+            let obj = ObjectInfo::from_file_info(fi, &self.bucket, &self.object_name, versioned);
+            if lock_enabled && enforce_retention_for_deletion(&obj) {
+                //if enforce_retention_for_deletion(&obj) {
+                /*if self.debug {
+                    if obj.version_id.is_some() {
+                        info!("lifecycle: {} v({}) is locked, not deleting\n", obj.name, obj.version_id.expect("err"));
+                    } else {
+                        info!("lifecycle: {} is locked, not deleting\n", obj.name);
+                    }
+                }*/
+                object_infos.push(obj);
+                continue;
+            }
+
+            if OffsetDateTime::now_utc().unix_timestamp()
+                < lifecycle::expected_expiry_time(obj.successor_mod_time.expect("err"), event.noncurrent_days as i32)
+                    .unix_timestamp()
+            {
+                object_infos.push(obj);
+                continue;
+            }
+
+            to_del.push(ObjectToDelete {
+                object_name: obj.name,
+                version_id: obj.version_id,
+                ..Default::default()
+            });
+        }
+
+        if !to_del.is_empty() {
+            let mut expiry_state = GLOBAL_ExpiryState.write().await;
+            expiry_state.enqueue_by_newer_noncurrent(&self.bucket, to_del, event).await;
+        }
+
+        Ok(object_infos)
+    }
+
+    pub async fn apply_actions(&mut self, oi: &ObjectInfo, _size_s: &mut SizeSummary) -> (bool, i64) {
+        let object_locked = self.is_object_lock_protected(oi);
+
+        if let Err(err) = self.heal_replication(oi).await {
+            warn!(
+                "heal_replication failed for {}/{} (version {:?}): {}",
+                oi.bucket, oi.name, oi.version_id, err
+            );
+        }
+
+        if object_locked {
+            info!(
+                "apply_actions: Skipping lifecycle for {}/{} because object lock retention or legal hold is active",
+                oi.bucket, oi.name
+            );
+            return (false, oi.size);
+        }
+
+        let (action, _size) = self.apply_lifecycle(oi).await;
+
+        info!(
+            "apply_actions {} {} {:?} {:?}",
+            oi.bucket.clone(),
+            oi.name.clone(),
+            oi.version_id.clone(),
+            oi.user_defined.clone()
+        );
+
+        if action.delete_all() {
+            return (true, 0);
+        }
+
+        (false, oi.size)
     }
 
     async fn apply_lifecycle(&mut self, oi: &ObjectInfo) -> (IlmAction, i64) {
         let size = oi.size;
         if self.lifecycle.is_none() {
+            info!("apply_lifecycle: No lifecycle config for object: {}", oi.name);
             return (IlmAction::NoneAction, size);
         }
 
-        let (olcfg, rcfg) = if self.bucket != ".minio.sys" {
+        info!("apply_lifecycle: Lifecycle config exists for object: {}", oi.name);
+
+        let (olcfg, rcfg) = if !is_meta_bucketname(&self.bucket) {
             (
                 get_object_lock_config(&self.bucket).await.ok(),
                 None, // FIXME: replication config
@@ -90,36 +303,259 @@ impl ScannerItem {
             (None, None)
         };
 
+        info!("apply_lifecycle: Evaluating lifecycle for object: {}", oi.name);
+
+        let lifecycle = match self.lifecycle.as_ref() {
+            Some(lc) => lc,
+            None => {
+                info!("No lifecycle configuration found for object: {}", oi.name);
+                return (IlmAction::NoneAction, 0);
+            }
+        };
+
         let lc_evt = eval_action_from_lifecycle(
-            self.lifecycle.as_ref().unwrap(),
+            lifecycle,
             olcfg
                 .as_ref()
                 .and_then(|(c, _)| c.rule.as_ref().and_then(|r| r.default_retention.clone())),
             rcfg.clone(),
-            oi,
+            oi, // Pass oi directly
         )
         .await;
 
-        info!("lifecycle: {} Initial scan: {}", oi.name, lc_evt.action);
+        info!("lifecycle: {} Initial scan: {} (action: {:?})", oi.name, lc_evt.action, lc_evt.action);
 
         let mut new_size = size;
         match lc_evt.action {
             IlmAction::DeleteVersionAction | IlmAction::DeleteAllVersionsAction | IlmAction::DelMarkerDeleteAllVersionsAction => {
+                info!("apply_lifecycle: Object {} marked for version deletion, new_size=0", oi.name);
                 new_size = 0;
             }
             IlmAction::DeleteAction => {
+                info!("apply_lifecycle: Object {} marked for deletion", oi.name);
                 if let Some(vcfg) = &self.versioning {
-                    if !vcfg.is_enabled() {
+                    if !vcfg.enabled() {
+                        info!("apply_lifecycle: Versioning disabled, setting new_size=0");
                         new_size = 0;
                     }
                 } else {
+                    info!("apply_lifecycle: No versioning config, setting new_size=0");
                     new_size = 0;
                 }
             }
-            _ => (),
+            IlmAction::NoneAction => {
+                info!("apply_lifecycle: No action for object {}", oi.name);
+            }
+            _ => {
+                info!("apply_lifecycle: Other action {:?} for object {}", lc_evt.action, oi.name);
+            }
+        }
+
+        if lc_evt.action != IlmAction::NoneAction {
+            info!("apply_lifecycle: Applying lifecycle action {:?} for object {}", lc_evt.action, oi.name);
+            apply_lifecycle_action(&lc_evt, &LcEventSrc::Scanner, oi).await;
+        } else {
+            info!("apply_lifecycle: Skipping lifecycle action for object {} as no action is needed", oi.name);
         }
 
-        apply_lifecycle_action(&lc_evt, &LcEventSrc::Scanner, oi).await;
         (lc_evt.action, new_size)
     }
+
+    fn is_object_lock_protected(&self, oi: &ObjectInfo) -> bool {
+        enforce_retention_for_deletion(oi)
+    }
+
+    async fn heal_replication(&self, oi: &ObjectInfo) -> Result<()> {
+        warn!("heal_replication: healing replication for {}/{}", oi.bucket, oi.name);
+        warn!("heal_replication: ObjectInfo oi: {:?}", oi);
+
+        let enriched = Self::hydrate_replication_metadata(oi);
+        let pending_lagging = self.is_pending_lagging(&enriched);
+
+        if let Some(handle) = &self.replication_metrics {
+            handle
+                .record_status(&self.bucket, enriched.replication_status.clone(), pending_lagging)
+                .await;
+        }
+
+        debug!(
+            "heal_replication: evaluating {}/{} with status {:?} and internal {:?}",
+            enriched.bucket, enriched.name, enriched.replication_status, enriched.replication_status_internal
+        );
+
+        // if !self.needs_replication_heal(&enriched, pending_lagging) {
+        //     return Ok(());
+        // }
+
+        // let replication_cfg = match get_replication_config(&self.bucket).await {
+        //     Ok((cfg, _)) => Some(cfg),
+        //     Err(err) => {
+        //         debug!("heal_replication: failed to fetch replication config for bucket {}: {}", self.bucket, err);
+        //         None
+        //     }
+        // };
+
+        // if replication_cfg.is_none() {
+        //     return Ok(());
+        // }
+
+        // let bucket_targets = match get_bucket_targets_config(&self.bucket).await {
+        //     Ok(targets) => Some(targets),
+        //     Err(err) => {
+        //         debug!("heal_replication: no bucket targets for bucket {}: {}", self.bucket, err);
+        //         None
+        //     }
+        // };
+
+        // let replication_cfg = ReplicationConfig::new(replication_cfg, bucket_targets);
+
+        let replication_cfg = self.replication.clone().unwrap_or_default();
+
+        if replication_cfg.config.is_none() && replication_cfg.remotes.is_none() {
+            debug!("heal_replication: no replication config for {}/{}", enriched.bucket, enriched.name);
+            return Ok(());
+        }
+
+        let replicate_info = get_heal_replicate_object_info(&enriched, &replication_cfg).await;
+        let should_replicate = replicate_info.dsc.replicate_any()
+            || matches!(
+                enriched.replication_status,
+                ReplicationStatusType::Failed | ReplicationStatusType::Pending
+            );
+        if !should_replicate {
+            debug!("heal_replication: no actionable targets for {}/{}", enriched.bucket, enriched.name);
+            return Ok(());
+        }
+
+        if let Some(pool) = GLOBAL_REPLICATION_POOL.get() {
+            pool.queue_replica_task(replicate_info).await;
+            if let Some(handle) = &self.replication_metrics {
+                handle.record_task_submission(&self.bucket).await;
+            }
+            warn!("heal_replication: queued replication heal task for {}/{}", enriched.bucket, enriched.name);
+        } else {
+            warn!(
+                "heal_replication: GLOBAL_REPLICATION_POOL not initialized, skipping heal for {}/{}",
+                enriched.bucket, enriched.name
+            );
+        }
+
+        Ok(())
+    }
+
+    #[allow(dead_code)]
+    fn needs_replication_heal(&self, oi: &ObjectInfo, pending_lagging: bool) -> bool {
+        if matches!(oi.replication_status, ReplicationStatusType::Failed) {
+            return true;
+        }
+
+        if pending_lagging && matches!(oi.replication_status, ReplicationStatusType::Pending) {
+            return true;
+        }
+
+        if let Some(raw) = oi.replication_status_internal.as_ref() {
+            let statuses = replication_statuses_map(raw);
+            if statuses
+                .values()
+                .any(|status| matches!(status, ReplicationStatusType::Failed))
+            {
+                return true;
+            }
+
+            if pending_lagging
+                && statuses
+                    .values()
+                    .any(|status| matches!(status, ReplicationStatusType::Pending))
+            {
+                return true;
+            }
+        }
+
+        false
+    }
+
+    fn hydrate_replication_metadata(oi: &ObjectInfo) -> ObjectInfo {
+        let mut enriched = oi.clone();
+
+        if enriched.replication_status.is_empty() {
+            if let Some(status) = enriched.user_defined.lookup(AMZ_BUCKET_REPLICATION_STATUS) {
+                enriched.replication_status = ReplicationStatusType::from(status);
+            }
+        }
+
+        if enriched.replication_status_internal.is_none() {
+            if let Some(raw) = enriched.user_defined.lookup(Self::INTERNAL_REPLICATION_STATUS_KEY) {
+                if !raw.is_empty() {
+                    enriched.replication_status_internal = Some(raw.to_string());
+                }
+            }
+        }
+
+        if enriched.version_purge_status_internal.is_none() {
+            if let Some(raw) = enriched.user_defined.lookup(VERSION_PURGE_STATUS_KEY) {
+                if !raw.is_empty() {
+                    enriched.version_purge_status_internal = Some(raw.to_string());
+                }
+            }
+        }
+
+        enriched
+    }
+
+    fn is_pending_lagging(&self, oi: &ObjectInfo) -> bool {
+        if !matches!(oi.replication_status, ReplicationStatusType::Pending) {
+            return false;
+        }
+
+        let Some(mod_time) = oi.mod_time else {
+            return false;
+        };
+
+        let grace = TimeDuration::try_from(self.replication_pending_grace).unwrap_or_else(|_| {
+            warn!(
+                "replication_pending_grace is invalid, using default value: 0 seconds, grace: {:?}",
+                self.replication_pending_grace
+            );
+            TimeDuration::seconds(0)
+        });
+        if grace.is_zero() {
+            return true;
+        }
+
+        let elapsed = OffsetDateTime::now_utc() - mod_time;
+        elapsed >= grace
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[tokio::test]
+    async fn replication_metrics_handle_tracks_counts() {
+        let metrics = Arc::new(MetricsCollector::new());
+        let bucket_metrics = Arc::new(Mutex::new(HashMap::new()));
+        let handle = ReplicationMetricsHandle::new(metrics.clone(), bucket_metrics.clone());
+
+        handle
+            .record_status("test-bucket", ReplicationStatusType::Pending, true)
+            .await;
+        handle
+            .record_status("test-bucket", ReplicationStatusType::Failed, false)
+            .await;
+        handle.record_task_submission("test-bucket").await;
+
+        let snapshot = metrics.get_metrics();
+        assert_eq!(snapshot.replication_pending_objects, 1);
+        assert_eq!(snapshot.replication_failed_objects, 1);
+        assert_eq!(snapshot.replication_lagging_objects, 1);
+        assert_eq!(snapshot.replication_tasks_queued, 1);
+
+        let guard = bucket_metrics.lock().await;
+        let bucket_entry = guard.get("test-bucket").expect("bucket metrics exists");
+        assert_eq!(bucket_entry.replication_pending, 1);
+        assert_eq!(bucket_entry.replication_failed, 1);
+        assert_eq!(bucket_entry.replication_lagging, 1);
+        assert_eq!(bucket_entry.replication_tasks_queued, 1);
+    }
 }

crates/ahm/src/scanner/local_scan/mod.rs

@@ -0,0 +1,683 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::{Error, Result};
+use rustfs_common::data_usage::DiskUsageStatus;
+use rustfs_ecstore::data_usage::{
+    LocalUsageSnapshot, LocalUsageSnapshotMeta, data_usage_state_dir, ensure_data_usage_layout, snapshot_file_name,
+    write_local_snapshot,
+};
+use rustfs_ecstore::disk::DiskAPI;
+use rustfs_ecstore::store::ECStore;
+use rustfs_ecstore::store_api::ObjectInfo;
+use rustfs_filemeta::{FileInfo, FileMeta, FileMetaVersion, VersionType};
+use serde::{Deserialize, Serialize};
+use serde_json::{from_slice, to_vec};
+use std::collections::{HashMap, HashSet};
+use std::path::{Path, PathBuf};
+use std::sync::Arc;
+use std::time::{SystemTime, UNIX_EPOCH};
+use tokio::{fs, task};
+use tracing::warn;
+use walkdir::WalkDir;
+
+const STATE_FILE_EXTENSION: &str = "";
+
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct LocalObjectUsage {
+    pub bucket: String,
+    pub object: String,
+    pub last_modified_ns: Option<i128>,
+    pub versions_count: u64,
+    pub delete_markers_count: u64,
+    pub total_size: u64,
+    pub has_live_object: bool,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+struct IncrementalScanState {
+    last_scan_ns: Option<i128>,
+    objects: HashMap<String, LocalObjectUsage>,
+}
+
+struct DiskScanResult {
+    snapshot: LocalUsageSnapshot,
+    state: IncrementalScanState,
+    objects_by_bucket: HashMap<String, Vec<LocalObjectRecord>>,
+    status: DiskUsageStatus,
+}
+
+#[derive(Debug, Clone)]
+pub struct LocalObjectRecord {
+    pub usage: LocalObjectUsage,
+    pub object_info: Option<rustfs_ecstore::store_api::ObjectInfo>,
+    pub file_info: Option<FileInfo>,
+}
+
+#[derive(Debug, Default)]
+pub struct LocalScanOutcome {
+    pub snapshots: Vec<LocalUsageSnapshot>,
+    pub bucket_objects: HashMap<String, Vec<LocalObjectRecord>>,
+    pub disk_status: Vec<DiskUsageStatus>,
+}
+
+/// Scan all local primary disks and persist refreshed usage snapshots.
+pub async fn scan_and_persist_local_usage(store: Arc<ECStore>) -> Result<LocalScanOutcome> {
+    let mut snapshots = Vec::new();
+    let mut bucket_objects: HashMap<String, Vec<LocalObjectRecord>> = HashMap::new();
+    let mut disk_status = Vec::new();
+
+    for (pool_idx, pool) in store.pools.iter().enumerate() {
+        for set_disks in pool.disk_set.iter() {
+            let disks = {
+                let guard = set_disks.disks.read().await;
+                guard.clone()
+            };
+
+            for (disk_index, disk_opt) in disks.into_iter().enumerate() {
+                let Some(disk) = disk_opt else {
+                    continue;
+                };
+
+                if !disk.is_local() {
+                    continue;
+                }
+
+                // Count objects once by scanning only disk index zero from each set.
+                if disk_index != 0 {
+                    continue;
+                }
+
+                let disk_id = match disk.get_disk_id().await.map_err(Error::from)? {
+                    Some(id) => id.to_string(),
+                    None => {
+                        warn!("Skipping disk without ID: {}", disk.to_string());
+                        continue;
+                    }
+                };
+
+                let root = disk.path();
+                ensure_data_usage_layout(root.as_path()).await.map_err(Error::from)?;
+
+                let meta = LocalUsageSnapshotMeta {
+                    disk_id: disk_id.clone(),
+                    pool_index: Some(pool_idx),
+                    set_index: Some(set_disks.set_index),
+                    disk_index: Some(disk_index),
+                };
+
+                let state_path = state_file_path(root.as_path(), &disk_id);
+                let state = read_scan_state(&state_path).await?;
+
+                let root_clone = root.clone();
+                let meta_clone = meta.clone();
+
+                let handle = task::spawn_blocking(move || scan_disk_blocking(root_clone, meta_clone, state));
+
+                match handle.await {
+                    Ok(Ok(result)) => {
+                        write_local_snapshot(root.as_path(), &disk_id, &result.snapshot)
+                            .await
+                            .map_err(Error::from)?;
+                        write_scan_state(&state_path, &result.state).await?;
+                        snapshots.push(result.snapshot);
+                        for (bucket, records) in result.objects_by_bucket {
+                            bucket_objects.entry(bucket).or_default().extend(records.into_iter());
+                        }
+                        disk_status.push(result.status);
+                    }
+                    Ok(Err(err)) => {
+                        warn!("Failed to scan disk {}: {}", disk.to_string(), err);
+                    }
+                    Err(join_err) => {
+                        warn!("Disk scan task panicked for disk {}: {}", disk.to_string(), join_err);
+                    }
+                }
+            }
+        }
+    }
+
+    Ok(LocalScanOutcome {
+        snapshots,
+        bucket_objects,
+        disk_status,
+    })
+}
+
+fn scan_disk_blocking(root: PathBuf, meta: LocalUsageSnapshotMeta, mut state: IncrementalScanState) -> Result<DiskScanResult> {
+    let now = SystemTime::now();
+    let now_ns = system_time_to_ns(now);
+    let mut visited: HashSet<String> = HashSet::new();
+    let mut emitted: HashSet<String> = HashSet::new();
+    let mut objects_by_bucket: HashMap<String, Vec<LocalObjectRecord>> = HashMap::new();
+    let mut status = DiskUsageStatus {
+        disk_id: meta.disk_id.clone(),
+        pool_index: meta.pool_index,
+        set_index: meta.set_index,
+        disk_index: meta.disk_index,
+        last_update: None,
+        snapshot_exists: false,
+    };
+
+    for entry in WalkDir::new(&root).follow_links(false).into_iter().filter_map(|res| res.ok()) {
+        if !entry.file_type().is_file() {
+            continue;
+        }
+
+        if entry.file_name() != "xl.meta" {
+            continue;
+        }
+
+        let xl_path = entry.path().to_path_buf();
+        let Some(object_dir) = xl_path.parent() else {
+            continue;
+        };
+
+        let Some(rel_path) = object_dir.strip_prefix(&root).ok().map(normalize_path) else {
+            continue;
+        };
+
+        let mut components = rel_path.split('/');
+        let Some(bucket_name) = components.next() else {
+            continue;
+        };
+
+        if bucket_name.starts_with('.') {
+            continue;
+        }
+
+        let object_key = components.collect::<Vec<_>>().join("/");
+
+        visited.insert(rel_path.clone());
+
+        let metadata = match std::fs::metadata(&xl_path) {
+            Ok(meta) => meta,
+            Err(err) => {
+                warn!("Failed to read metadata for {xl_path:?}: {err}");
+                continue;
+            }
+        };
+
+        let mtime_ns = metadata.modified().ok().map(system_time_to_ns);
+
+        let should_parse = match state.objects.get(&rel_path) {
+            Some(existing) => existing.last_modified_ns != mtime_ns,
+            None => true,
+        };
+
+        if should_parse {
+            match std::fs::read(&xl_path) {
+                Ok(buf) => match FileMeta::load(&buf) {
+                    Ok(file_meta) => match compute_object_usage(bucket_name, object_key.as_str(), &file_meta) {
+                        Ok(Some(mut record)) => {
+                            record.usage.last_modified_ns = mtime_ns;
+                            state.objects.insert(rel_path.clone(), record.usage.clone());
+                            emitted.insert(rel_path.clone());
+                            warn!("compute_object_usage: record: {:?}", record.clone());
+                            objects_by_bucket.entry(record.usage.bucket.clone()).or_default().push(record);
+                        }
+                        Ok(None) => {
+                            warn!("compute_object_usage: None, rel_path: {:?}", rel_path);
+                            state.objects.remove(&rel_path);
+                        }
+                        Err(err) => {
+                            warn!("Failed to parse usage from {:?}: {}", xl_path, err);
+                        }
+                    },
+                    Err(err) => {
+                        warn!("Failed to decode xl.meta {:?}: {}", xl_path, err);
+                    }
+                },
+                Err(err) => {
+                    warn!("Failed to read xl.meta {:?}: {}", xl_path, err);
+                }
+            }
+        } else {
+            warn!("should_parse: false, rel_path: {:?}", rel_path);
+        }
+    }
+
+    state.objects.retain(|key, _| visited.contains(key));
+    state.last_scan_ns = Some(now_ns);
+
+    // for (key, usage) in &state.objects {
+    //     if emitted.contains(key) {
+    //         continue;
+    //     }
+    //     objects_by_bucket
+    //         .entry(usage.bucket.clone())
+    //         .or_default()
+    //         .push(LocalObjectRecord {
+    //             usage: usage.clone(),
+    //             object_info: None,
+    //             file_info: None,
+    //         });
+    // }
+
+    let snapshot = build_snapshot(meta, &state.objects, now);
+    status.snapshot_exists = true;
+    status.last_update = Some(now);
+
+    Ok(DiskScanResult {
+        snapshot,
+        state,
+        objects_by_bucket,
+        status,
+    })
+}
+
+fn compute_object_usage(bucket: &str, object: &str, file_meta: &FileMeta) -> Result<Option<LocalObjectRecord>> {
+    let mut versions_count = 0u64;
+    let mut delete_markers_count = 0u64;
+    let mut total_size = 0u64;
+    let mut has_live_object = false;
+
+    let mut latest_file_info: Option<FileInfo> = None;
+
+    for shallow in &file_meta.versions {
+        match shallow.header.version_type {
+            VersionType::Object => {
+                let version = match FileMetaVersion::try_from(shallow.meta.as_slice()) {
+                    Ok(version) => version,
+                    Err(err) => {
+                        warn!("Failed to parse file meta version: {}", err);
+                        continue;
+                    }
+                };
+                if let Some(obj) = version.object {
+                    if !has_live_object {
+                        total_size = obj.size.max(0) as u64;
+                    }
+                    has_live_object = true;
+                    versions_count = versions_count.saturating_add(1);
+
+                    if latest_file_info.is_none() {
+                        if let Ok(info) = file_meta.into_fileinfo(bucket, object, "", false, false) {
+                            latest_file_info = Some(info);
+                        }
+                    }
+                }
+            }
+            VersionType::Delete => {
+                delete_markers_count = delete_markers_count.saturating_add(1);
+                versions_count = versions_count.saturating_add(1);
+            }
+            _ => {}
+        }
+    }
+
+    if !has_live_object && delete_markers_count == 0 {
+        return Ok(None);
+    }
+
+    let object_info = latest_file_info.as_ref().map(|fi| {
+        let versioned = fi.version_id.is_some();
+        ObjectInfo::from_file_info(fi, bucket, object, versioned)
+    });
+    let file_info = latest_file_info.clone();
+
+    Ok(Some(LocalObjectRecord {
+        usage: LocalObjectUsage {
+            bucket: bucket.to_string(),
+            object: object.to_string(),
+            last_modified_ns: None,
+            versions_count,
+            delete_markers_count,
+            total_size,
+            has_live_object,
+        },
+        object_info,
+        file_info,
+    }))
+}
+
+fn build_snapshot(
+    meta: LocalUsageSnapshotMeta,
+    objects: &HashMap<String, LocalObjectUsage>,
+    now: SystemTime,
+) -> LocalUsageSnapshot {
+    let mut snapshot = LocalUsageSnapshot::new(meta);
+
+    for usage in objects.values() {
+        let bucket_entry = snapshot.buckets_usage.entry(usage.bucket.clone()).or_default();
+
+        if usage.has_live_object {
+            bucket_entry.objects_count = bucket_entry.objects_count.saturating_add(1);
+        }
+        bucket_entry.versions_count = bucket_entry.versions_count.saturating_add(usage.versions_count);
+        bucket_entry.delete_markers_count = bucket_entry.delete_markers_count.saturating_add(usage.delete_markers_count);
+        bucket_entry.size = bucket_entry.size.saturating_add(usage.total_size);
+    }
+
+    snapshot.last_update = Some(now);
+    snapshot.recompute_totals();
+    snapshot
+}
+
+fn normalize_path(path: &Path) -> String {
+    path.iter()
+        .map(|component| component.to_string_lossy())
+        .collect::<Vec<_>>()
+        .join("/")
+}
+
+fn system_time_to_ns(time: SystemTime) -> i128 {
+    match time.duration_since(UNIX_EPOCH) {
+        Ok(duration) => {
+            let secs = duration.as_secs() as i128;
+            let nanos = duration.subsec_nanos() as i128;
+            secs * 1_000_000_000 + nanos
+        }
+        Err(err) => {
+            let duration = err.duration();
+            let secs = duration.as_secs() as i128;
+            let nanos = duration.subsec_nanos() as i128;
+            -(secs * 1_000_000_000 + nanos)
+        }
+    }
+}
+
+fn state_file_path(root: &Path, disk_id: &str) -> PathBuf {
+    let mut path = data_usage_state_dir(root);
+    path.push(format!("{}{}", snapshot_file_name(disk_id), STATE_FILE_EXTENSION));
+    path
+}
+
+async fn read_scan_state(path: &Path) -> Result<IncrementalScanState> {
+    match fs::read(path).await {
+        Ok(bytes) => from_slice(&bytes).map_err(|err| Error::Serialization(err.to_string())),
+        Err(err) if err.kind() == std::io::ErrorKind::NotFound => Ok(IncrementalScanState::default()),
+        Err(err) => Err(err.into()),
+    }
+}
+
+async fn write_scan_state(path: &Path, state: &IncrementalScanState) -> Result<()> {
+    if let Some(parent) = path.parent() {
+        fs::create_dir_all(parent).await?;
+    }
+    let data = to_vec(state).map_err(|err| Error::Serialization(err.to_string()))?;
+    fs::write(path, data).await?;
+    Ok(())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use rustfs_filemeta::{ChecksumAlgo, ErasureAlgo, FileMetaShallowVersion, MetaDeleteMarker, MetaObject};
+    use std::collections::HashMap;
+    use std::fs;
+    use tempfile::TempDir;
+    use time::OffsetDateTime;
+    use uuid::Uuid;
+
+    fn build_file_meta_with_object(erasure_index: usize, size: i64) -> FileMeta {
+        let mut file_meta = FileMeta::default();
+
+        let meta_object = MetaObject {
+            version_id: Some(Uuid::new_v4()),
+            data_dir: Some(Uuid::new_v4()),
+            erasure_algorithm: ErasureAlgo::ReedSolomon,
+            erasure_m: 2,
+            erasure_n: 2,
+            erasure_block_size: 4096,
+            erasure_index,
+            erasure_dist: vec![0_u8, 1, 2, 3],
+            bitrot_checksum_algo: ChecksumAlgo::HighwayHash,
+            part_numbers: vec![1],
+            part_etags: vec!["etag".to_string()],
+            part_sizes: vec![size as usize],
+            part_actual_sizes: vec![size],
+            part_indices: Vec::new(),
+            size,
+            mod_time: Some(OffsetDateTime::now_utc()),
+            meta_sys: HashMap::new(),
+            meta_user: HashMap::new(),
+        };
+
+        let version = FileMetaVersion {
+            version_type: VersionType::Object,
+            object: Some(meta_object),
+            delete_marker: None,
+            write_version: 1,
+        };
+
+        let shallow = FileMetaShallowVersion::try_from(version).expect("convert version");
+        file_meta.versions.push(shallow);
+        file_meta
+    }
+
+    fn build_file_meta_with_delete_marker() -> FileMeta {
+        let mut file_meta = FileMeta::default();
+
+        let delete_marker = MetaDeleteMarker {
+            version_id: Some(Uuid::new_v4()),
+            mod_time: Some(OffsetDateTime::now_utc()),
+            meta_sys: HashMap::new(),
+        };
+
+        let version = FileMetaVersion {
+            version_type: VersionType::Delete,
+            object: None,
+            delete_marker: Some(delete_marker),
+            write_version: 2,
+        };
+
+        let shallow = FileMetaShallowVersion::try_from(version).expect("convert delete marker");
+        file_meta.versions.push(shallow);
+        file_meta
+    }
+
+    #[test]
+    fn compute_object_usage_primary_disk() {
+        let file_meta = build_file_meta_with_object(0, 1024);
+        let record = compute_object_usage("bucket", "foo/bar", &file_meta)
+            .expect("compute usage")
+            .expect("record should exist");
+
+        assert!(record.usage.has_live_object);
+        assert_eq!(record.usage.bucket, "bucket");
+        assert_eq!(record.usage.object, "foo/bar");
+        assert_eq!(record.usage.total_size, 1024);
+        assert!(record.object_info.is_some(), "object info should be synthesized");
+    }
+
+    #[test]
+    fn compute_object_usage_handles_non_primary_disk() {
+        let file_meta = build_file_meta_with_object(1, 2048);
+        let record = compute_object_usage("bucket", "obj", &file_meta)
+            .expect("compute usage")
+            .expect("record should exist for non-primary shard");
+        assert!(record.usage.has_live_object);
+    }
+
+    #[test]
+    fn compute_object_usage_reports_delete_marker() {
+        let file_meta = build_file_meta_with_delete_marker();
+        let record = compute_object_usage("bucket", "obj", &file_meta)
+            .expect("compute usage")
+            .expect("delete marker record");
+
+        assert!(!record.usage.has_live_object);
+        assert_eq!(record.usage.delete_markers_count, 1);
+        assert_eq!(record.usage.versions_count, 1);
+    }
+
+    #[test]
+    fn build_snapshot_accumulates_usage() {
+        let mut objects = HashMap::new();
+        objects.insert(
+            "bucket/a".to_string(),
+            LocalObjectUsage {
+                bucket: "bucket".to_string(),
+                object: "a".to_string(),
+                last_modified_ns: None,
+                versions_count: 2,
+                delete_markers_count: 1,
+                total_size: 512,
+                has_live_object: true,
+            },
+        );
+
+        let snapshot = build_snapshot(LocalUsageSnapshotMeta::default(), &objects, SystemTime::now());
+        let usage = snapshot.buckets_usage.get("bucket").expect("bucket entry should exist");
+        assert_eq!(usage.objects_count, 1);
+        assert_eq!(usage.versions_count, 2);
+        assert_eq!(usage.delete_markers_count, 1);
+        assert_eq!(usage.size, 512);
+    }
+
+    #[test]
+    fn scan_disk_blocking_handles_incremental_updates() {
+        let temp_dir = TempDir::new().expect("create temp dir");
+        let root = temp_dir.path();
+
+        let bucket_dir = root.join("bench");
+        let object1_dir = bucket_dir.join("obj1");
+        fs::create_dir_all(&object1_dir).expect("create first object directory");
+
+        let file_meta = build_file_meta_with_object(0, 1024);
+        let bytes = file_meta.marshal_msg().expect("serialize first object");
+        fs::write(object1_dir.join("xl.meta"), bytes).expect("write first xl.meta");
+
+        let meta = LocalUsageSnapshotMeta {
+            disk_id: "disk-test".to_string(),
+            ..Default::default()
+        };
+
+        let DiskScanResult {
+            snapshot: snapshot1,
+            state,
+            ..
+        } = scan_disk_blocking(root.to_path_buf(), meta.clone(), IncrementalScanState::default()).expect("initial scan succeeds");
+
+        let usage1 = snapshot1.buckets_usage.get("bench").expect("bucket stats recorded");
+        assert_eq!(usage1.objects_count, 1);
+        assert_eq!(usage1.size, 1024);
+        assert_eq!(state.objects.len(), 1);
+
+        let object2_dir = bucket_dir.join("nested").join("obj2");
+        fs::create_dir_all(&object2_dir).expect("create second object directory");
+        let second_meta = build_file_meta_with_object(0, 2048);
+        let bytes = second_meta.marshal_msg().expect("serialize second object");
+        fs::write(object2_dir.join("xl.meta"), bytes).expect("write second xl.meta");
+
+        let DiskScanResult {
+            snapshot: snapshot2,
+            state: state_next,
+            ..
+        } = scan_disk_blocking(root.to_path_buf(), meta.clone(), state).expect("incremental scan succeeds");
+
+        let usage2 = snapshot2
+            .buckets_usage
+            .get("bench")
+            .expect("bucket stats recorded after addition");
+        assert_eq!(usage2.objects_count, 2);
+        assert_eq!(usage2.size, 1024 + 2048);
+        assert_eq!(state_next.objects.len(), 2);
+
+        fs::remove_dir_all(&object1_dir).expect("remove first object");
+
+        let DiskScanResult {
+            snapshot: snapshot3,
+            state: state_final,
+            ..
+        } = scan_disk_blocking(root.to_path_buf(), meta, state_next).expect("scan after deletion succeeds");
+
+        let usage3 = snapshot3
+            .buckets_usage
+            .get("bench")
+            .expect("bucket stats recorded after deletion");
+        assert_eq!(usage3.objects_count, 1);
+        assert_eq!(usage3.size, 2048);
+        assert_eq!(state_final.objects.len(), 1);
+        assert!(
+            state_final.objects.keys().all(|path| path.contains("nested")),
+            "state should only keep surviving object"
+        );
+    }
+
+    #[test]
+    fn scan_disk_blocking_recovers_from_stale_state_entries() {
+        let temp_dir = TempDir::new().expect("create temp dir");
+        let root = temp_dir.path();
+
+        let mut stale_state = IncrementalScanState::default();
+        stale_state.objects.insert(
+            "bench/stale".to_string(),
+            LocalObjectUsage {
+                bucket: "bench".to_string(),
+                object: "stale".to_string(),
+                last_modified_ns: Some(42),
+                versions_count: 1,
+                delete_markers_count: 0,
+                total_size: 512,
+                has_live_object: true,
+            },
+        );
+        stale_state.last_scan_ns = Some(99);
+
+        let meta = LocalUsageSnapshotMeta {
+            disk_id: "disk-test".to_string(),
+            ..Default::default()
+        };
+
+        let DiskScanResult {
+            snapshot, state, status, ..
+        } = scan_disk_blocking(root.to_path_buf(), meta, stale_state).expect("scan succeeds");
+
+        assert!(state.objects.is_empty(), "stale entries should be cleared when files disappear");
+        assert!(
+            snapshot.buckets_usage.is_empty(),
+            "no real xl.meta files means bucket usage should stay empty"
+        );
+        assert!(status.snapshot_exists, "snapshot status should indicate a refresh");
+    }
+
+    #[test]
+    fn scan_disk_blocking_handles_large_volume() {
+        const OBJECTS: usize = 256;
+
+        let temp_dir = TempDir::new().expect("create temp dir");
+        let root = temp_dir.path();
+        let bucket_dir = root.join("bulk");
+
+        for idx in 0..OBJECTS {
+            let object_dir = bucket_dir.join(format!("obj-{idx:03}"));
+            fs::create_dir_all(&object_dir).expect("create object directory");
+            let size = 1024 + idx as i64;
+            let file_meta = build_file_meta_with_object(0, size);
+            let bytes = file_meta.marshal_msg().expect("serialize file meta");
+            fs::write(object_dir.join("xl.meta"), bytes).expect("write xl.meta");
+        }
+
+        let meta = LocalUsageSnapshotMeta {
+            disk_id: "disk-test".to_string(),
+            ..Default::default()
+        };
+
+        let DiskScanResult { snapshot, state, .. } =
+            scan_disk_blocking(root.to_path_buf(), meta, IncrementalScanState::default()).expect("bulk scan succeeds");
+
+        let bucket_usage = snapshot
+            .buckets_usage
+            .get("bulk")
+            .expect("bucket usage present for bulk scan");
+        assert_eq!(bucket_usage.objects_count as usize, OBJECTS, "should count all objects once");
+        assert!(
+            bucket_usage.size >= (1024 * OBJECTS) as u64,
+            "aggregated size should grow with object count"
+        );
+        assert_eq!(state.objects.len(), OBJECTS, "incremental state tracks every object");
+    }
+}

crates/ahm/src/scanner/local_stats.rs

@@ -0,0 +1,430 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::scanner::node_scanner::{BucketStats, DiskStats, LocalScanStats};
+use crate::{Error, Result};
+use rustfs_common::data_usage::DataUsageInfo;
+use serde::{Deserialize, Serialize};
+use std::{
+    path::{Path, PathBuf},
+    sync::Arc,
+    sync::atomic::{AtomicU64, Ordering},
+    time::{Duration, SystemTime},
+};
+use tokio::sync::RwLock;
+use tracing::{debug, error, info, warn};
+
+/// local stats manager
+pub struct LocalStatsManager {
+    /// node id
+    node_id: String,
+    /// stats file path
+    stats_file: PathBuf,
+    /// backup file path
+    backup_file: PathBuf,
+    /// temp file path
+    temp_file: PathBuf,
+    /// local stats data
+    stats: Arc<RwLock<LocalScanStats>>,
+    /// save interval
+    save_interval: Duration,
+    /// last save time
+    last_save: Arc<RwLock<SystemTime>>,
+    /// stats counters
+    counters: Arc<StatsCounters>,
+}
+
+/// stats counters
+pub struct StatsCounters {
+    /// total scanned objects
+    pub total_objects_scanned: AtomicU64,
+    /// total healthy objects
+    pub total_healthy_objects: AtomicU64,
+    /// total corrupted objects  
+    pub total_corrupted_objects: AtomicU64,
+    /// total scanned bytes
+    pub total_bytes_scanned: AtomicU64,
+    /// total scan errors
+    pub total_scan_errors: AtomicU64,
+    /// total heal triggered
+    pub total_heal_triggered: AtomicU64,
+}
+
+impl Default for StatsCounters {
+    fn default() -> Self {
+        Self {
+            total_objects_scanned: AtomicU64::new(0),
+            total_healthy_objects: AtomicU64::new(0),
+            total_corrupted_objects: AtomicU64::new(0),
+            total_bytes_scanned: AtomicU64::new(0),
+            total_scan_errors: AtomicU64::new(0),
+            total_heal_triggered: AtomicU64::new(0),
+        }
+    }
+}
+
+/// scan result entry
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ScanResultEntry {
+    /// object path
+    pub object_path: String,
+    /// bucket name
+    pub bucket_name: String,
+    /// object size
+    pub object_size: u64,
+    /// is healthy
+    pub is_healthy: bool,
+    /// error message (if any)
+    pub error_message: Option<String>,
+    /// scan time
+    pub scan_time: SystemTime,
+    /// disk id
+    pub disk_id: String,
+}
+
+/// batch scan result
+#[derive(Debug, Clone)]
+pub struct BatchScanResult {
+    /// disk id
+    pub disk_id: String,
+    /// scan result entries
+    pub entries: Vec<ScanResultEntry>,
+    /// scan start time
+    pub scan_start: SystemTime,
+    /// scan end time
+    pub scan_end: SystemTime,
+    /// scan duration
+    pub scan_duration: Duration,
+}
+
+impl LocalStatsManager {
+    /// create new local stats manager
+    pub fn new(node_id: &str, data_dir: &Path) -> Self {
+        // ensure data directory exists
+        if !data_dir.exists() {
+            if let Err(e) = std::fs::create_dir_all(data_dir) {
+                error!("create stats data directory failed {:?}: {}", data_dir, e);
+            }
+        }
+
+        let stats_file = data_dir.join(format!("scanner_stats_{node_id}.json"));
+        let backup_file = data_dir.join(format!("scanner_stats_{node_id}.backup"));
+        let temp_file = data_dir.join(format!("scanner_stats_{node_id}.tmp"));
+
+        Self {
+            node_id: node_id.to_string(),
+            stats_file,
+            backup_file,
+            temp_file,
+            stats: Arc::new(RwLock::new(LocalScanStats::default())),
+            save_interval: Duration::from_secs(60), // 60 seconds save once
+            last_save: Arc::new(RwLock::new(SystemTime::UNIX_EPOCH)),
+            counters: Arc::new(StatsCounters::default()),
+        }
+    }
+
+    /// load local stats data
+    pub async fn load_stats(&self) -> Result<()> {
+        if !self.stats_file.exists() {
+            info!("stats data file not exists, will create new stats data");
+            return Ok(());
+        }
+
+        match self.load_stats_from_file(&self.stats_file).await {
+            Ok(stats) => {
+                *self.stats.write().await = stats;
+                info!("success load local stats data");
+                Ok(())
+            }
+            Err(e) => {
+                warn!("load main stats file failed: {}, try backup file", e);
+
+                match self.load_stats_from_file(&self.backup_file).await {
+                    Ok(stats) => {
+                        *self.stats.write().await = stats;
+                        warn!("restore stats data from backup file");
+                        Ok(())
+                    }
+                    Err(backup_e) => {
+                        warn!("backup file also cannot load: {}, will use default stats data", backup_e);
+                        Ok(())
+                    }
+                }
+            }
+        }
+    }
+
+    /// load stats data from file
+    async fn load_stats_from_file(&self, file_path: &Path) -> Result<LocalScanStats> {
+        let content = tokio::fs::read_to_string(file_path)
+            .await
+            .map_err(|e| Error::IO(format!("read stats file failed: {e}")))?;
+
+        let stats: LocalScanStats =
+            serde_json::from_str(&content).map_err(|e| Error::Serialization(format!("deserialize stats data failed: {e}")))?;
+
+        Ok(stats)
+    }
+
+    /// save stats data to disk
+    pub async fn save_stats(&self) -> Result<()> {
+        let now = SystemTime::now();
+        let last_save = *self.last_save.read().await;
+
+        // frequency control
+        if now.duration_since(last_save).unwrap_or(Duration::ZERO) < self.save_interval {
+            return Ok(());
+        }
+
+        let stats = self.stats.read().await.clone();
+
+        // serialize
+        let json_data = serde_json::to_string_pretty(&stats)
+            .map_err(|e| Error::Serialization(format!("serialize stats data failed: {e}")))?;
+
+        // atomic write
+        tokio::fs::write(&self.temp_file, json_data)
+            .await
+            .map_err(|e| Error::IO(format!("write temp stats file failed: {e}")))?;
+
+        // backup existing file
+        if self.stats_file.exists() {
+            tokio::fs::copy(&self.stats_file, &self.backup_file)
+                .await
+                .map_err(|e| Error::IO(format!("backup stats file failed: {e}")))?;
+        }
+
+        // atomic replace
+        tokio::fs::rename(&self.temp_file, &self.stats_file)
+            .await
+            .map_err(|e| Error::IO(format!("replace stats file failed: {e}")))?;
+
+        *self.last_save.write().await = now;
+
+        debug!("save local stats data to {:?}", self.stats_file);
+        Ok(())
+    }
+
+    /// force save stats data
+    pub async fn force_save_stats(&self) -> Result<()> {
+        *self.last_save.write().await = SystemTime::UNIX_EPOCH;
+        self.save_stats().await
+    }
+
+    /// update disk scan result
+    pub async fn update_disk_scan_result(&self, result: &BatchScanResult) -> Result<()> {
+        let mut stats = self.stats.write().await;
+
+        // update disk stats
+        let disk_stat = stats.disks_stats.entry(result.disk_id.clone()).or_insert_with(|| DiskStats {
+            disk_id: result.disk_id.clone(),
+            ..Default::default()
+        });
+
+        let healthy_count = result.entries.iter().filter(|e| e.is_healthy).count() as u64;
+        let error_count = result.entries.iter().filter(|e| !e.is_healthy).count() as u64;
+
+        disk_stat.objects_scanned += result.entries.len() as u64;
+        disk_stat.errors_count += error_count;
+        disk_stat.last_scan_time = result.scan_end;
+        disk_stat.scan_duration = result.scan_duration;
+        disk_stat.scan_completed = true;
+
+        // update overall stats
+        stats.objects_scanned += result.entries.len() as u64;
+        stats.healthy_objects += healthy_count;
+        stats.corrupted_objects += error_count;
+        stats.last_update = SystemTime::now();
+
+        // update bucket stats
+        for entry in &result.entries {
+            let _bucket_stat = stats
+                .buckets_stats
+                .entry(entry.bucket_name.clone())
+                .or_insert_with(BucketStats::default);
+
+            // TODO: update BucketStats
+        }
+
+        // update atomic counters
+        self.counters
+            .total_objects_scanned
+            .fetch_add(result.entries.len() as u64, Ordering::Relaxed);
+        self.counters
+            .total_healthy_objects
+            .fetch_add(healthy_count, Ordering::Relaxed);
+        self.counters
+            .total_corrupted_objects
+            .fetch_add(error_count, Ordering::Relaxed);
+
+        let total_bytes: u64 = result.entries.iter().map(|e| e.object_size).sum();
+        self.counters.total_bytes_scanned.fetch_add(total_bytes, Ordering::Relaxed);
+
+        if error_count > 0 {
+            self.counters.total_scan_errors.fetch_add(error_count, Ordering::Relaxed);
+        }
+
+        drop(stats);
+
+        debug!(
+            "update disk {} scan result: objects {}, healthy {}, error {}",
+            result.disk_id,
+            result.entries.len(),
+            healthy_count,
+            error_count
+        );
+
+        Ok(())
+    }
+
+    /// record single object scan result
+    pub async fn record_object_scan(&self, entry: ScanResultEntry) -> Result<()> {
+        let result = BatchScanResult {
+            disk_id: entry.disk_id.clone(),
+            entries: vec![entry],
+            scan_start: SystemTime::now(),
+            scan_end: SystemTime::now(),
+            scan_duration: Duration::from_millis(0),
+        };
+
+        self.update_disk_scan_result(&result).await
+    }
+
+    /// get local stats data copy
+    pub async fn get_stats(&self) -> LocalScanStats {
+        self.stats.read().await.clone()
+    }
+
+    /// get real-time counters
+    pub fn get_counters(&self) -> Arc<StatsCounters> {
+        self.counters.clone()
+    }
+
+    /// reset stats data
+    pub async fn reset_stats(&self) -> Result<()> {
+        {
+            let mut stats = self.stats.write().await;
+            *stats = LocalScanStats::default();
+        }
+
+        // reset counters
+        self.counters.total_objects_scanned.store(0, Ordering::Relaxed);
+        self.counters.total_healthy_objects.store(0, Ordering::Relaxed);
+        self.counters.total_corrupted_objects.store(0, Ordering::Relaxed);
+        self.counters.total_bytes_scanned.store(0, Ordering::Relaxed);
+        self.counters.total_scan_errors.store(0, Ordering::Relaxed);
+        self.counters.total_heal_triggered.store(0, Ordering::Relaxed);
+
+        info!("reset local stats data");
+        Ok(())
+    }
+
+    /// get stats summary
+    pub async fn get_stats_summary(&self) -> StatsSummary {
+        let stats = self.stats.read().await;
+
+        StatsSummary {
+            node_id: self.node_id.clone(),
+            total_objects_scanned: self.counters.total_objects_scanned.load(Ordering::Relaxed),
+            total_healthy_objects: self.counters.total_healthy_objects.load(Ordering::Relaxed),
+            total_corrupted_objects: self.counters.total_corrupted_objects.load(Ordering::Relaxed),
+            total_bytes_scanned: self.counters.total_bytes_scanned.load(Ordering::Relaxed),
+            total_scan_errors: self.counters.total_scan_errors.load(Ordering::Relaxed),
+            total_heal_triggered: self.counters.total_heal_triggered.load(Ordering::Relaxed),
+            total_disks: stats.disks_stats.len(),
+            total_buckets: stats.buckets_stats.len(),
+            last_update: stats.last_update,
+            scan_progress: stats.scan_progress.clone(),
+            data_usage: stats.data_usage.clone(),
+        }
+    }
+
+    /// record heal triggered
+    pub async fn record_heal_triggered(&self, object_path: &str, error_message: &str) {
+        self.counters.total_heal_triggered.fetch_add(1, Ordering::Relaxed);
+
+        info!("record heal triggered: object={}, error={}", object_path, error_message);
+    }
+
+    /// update data usage stats
+    pub async fn update_data_usage(&self, data_usage: DataUsageInfo) {
+        let mut stats = self.stats.write().await;
+        stats.data_usage = data_usage;
+        stats.last_update = SystemTime::now();
+
+        debug!("update data usage stats");
+    }
+
+    /// cleanup stats files
+    pub async fn cleanup_stats_files(&self) -> Result<()> {
+        // delete main file
+        if self.stats_file.exists() {
+            tokio::fs::remove_file(&self.stats_file)
+                .await
+                .map_err(|e| Error::IO(format!("delete stats file failed: {e}")))?;
+        }
+
+        // delete backup file
+        if self.backup_file.exists() {
+            tokio::fs::remove_file(&self.backup_file)
+                .await
+                .map_err(|e| Error::IO(format!("delete backup stats file failed: {e}")))?;
+        }
+
+        // delete temp file
+        if self.temp_file.exists() {
+            tokio::fs::remove_file(&self.temp_file)
+                .await
+                .map_err(|e| Error::IO(format!("delete temp stats file failed: {e}")))?;
+        }
+
+        info!("cleanup all stats files");
+        Ok(())
+    }
+
+    /// set save interval
+    pub fn set_save_interval(&mut self, interval: Duration) {
+        self.save_interval = interval;
+        info!("set stats data save interval to {:?}", interval);
+    }
+}
+
+/// stats summary
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct StatsSummary {
+    /// node id
+    pub node_id: String,
+    /// total scanned objects
+    pub total_objects_scanned: u64,
+    /// total healthy objects
+    pub total_healthy_objects: u64,
+    /// total corrupted objects
+    pub total_corrupted_objects: u64,
+    /// total scanned bytes
+    pub total_bytes_scanned: u64,
+    /// total scan errors
+    pub total_scan_errors: u64,
+    /// total heal triggered
+    pub total_heal_triggered: u64,
+    /// total disks
+    pub total_disks: usize,
+    /// total buckets
+    pub total_buckets: usize,
+    /// last update time
+    pub last_update: SystemTime,
+    /// scan progress
+    pub scan_progress: super::node_scanner::ScanProgress,
+    /// data usage snapshot for the node
+    pub data_usage: DataUsageInfo,
+}

crates/ahm/src/scanner/metrics.rs

@@ -12,13 +12,12 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+use serde::{Deserialize, Serialize};
 use std::{
     collections::HashMap,
     sync::atomic::{AtomicU64, Ordering},
     time::{Duration, SystemTime},
 };
-
-use serde::{Deserialize, Serialize};
 use tracing::info;
 
 /// Scanner metrics
@@ -46,6 +45,14 @@ pub struct ScannerMetrics {
     pub healthy_objects: u64,
     /// Total corrupted objects found
     pub corrupted_objects: u64,
+    /// Replication heal tasks queued
+    pub replication_tasks_queued: u64,
+    /// Objects observed with pending replication
+    pub replication_pending_objects: u64,
+    /// Objects observed with failed replication
+    pub replication_failed_objects: u64,
+    /// Objects with replication pending longer than grace period
+    pub replication_lagging_objects: u64,
     /// Last scan activity time
     pub last_activity: Option<SystemTime>,
     /// Current scan cycle
@@ -87,6 +94,14 @@ pub struct BucketMetrics {
     pub heal_tasks_completed: u64,
     /// Heal tasks failed for this bucket
     pub heal_tasks_failed: u64,
+    /// Objects observed with pending replication status
+    pub replication_pending: u64,
+    /// Objects observed with failed replication status
+    pub replication_failed: u64,
+    /// Objects exceeding replication grace period
+    pub replication_lagging: u64,
+    /// Replication heal tasks queued for this bucket
+    pub replication_tasks_queued: u64,
 }
 
 /// Disk-specific metrics
@@ -128,6 +143,10 @@ pub struct MetricsCollector {
     total_cycles: AtomicU64,
     healthy_objects: AtomicU64,
     corrupted_objects: AtomicU64,
+    replication_tasks_queued: AtomicU64,
+    replication_pending_objects: AtomicU64,
+    replication_failed_objects: AtomicU64,
+    replication_lagging_objects: AtomicU64,
 }
 
 impl MetricsCollector {
@@ -147,6 +166,10 @@ impl MetricsCollector {
             total_cycles: AtomicU64::new(0),
             healthy_objects: AtomicU64::new(0),
             corrupted_objects: AtomicU64::new(0),
+            replication_tasks_queued: AtomicU64::new(0),
+            replication_pending_objects: AtomicU64::new(0),
+            replication_failed_objects: AtomicU64::new(0),
+            replication_lagging_objects: AtomicU64::new(0),
         }
     }
 
@@ -195,6 +218,26 @@ impl MetricsCollector {
         self.heal_tasks_failed.fetch_add(count, Ordering::Relaxed);
     }
 
+    /// Increment replication tasks queued
+    pub fn increment_replication_tasks_queued(&self, count: u64) {
+        self.replication_tasks_queued.fetch_add(count, Ordering::Relaxed);
+    }
+
+    /// Increment replication pending objects
+    pub fn increment_replication_pending_objects(&self, count: u64) {
+        self.replication_pending_objects.fetch_add(count, Ordering::Relaxed);
+    }
+
+    /// Increment replication failed objects
+    pub fn increment_replication_failed_objects(&self, count: u64) {
+        self.replication_failed_objects.fetch_add(count, Ordering::Relaxed);
+    }
+
+    /// Increment replication lagging objects
+    pub fn increment_replication_lagging_objects(&self, count: u64) {
+        self.replication_lagging_objects.fetch_add(count, Ordering::Relaxed);
+    }
+
     /// Set current cycle
     pub fn set_current_cycle(&self, cycle: u64) {
         self.current_cycle.store(cycle, Ordering::Relaxed);
@@ -229,6 +272,10 @@ impl MetricsCollector {
             heal_tasks_failed: self.heal_tasks_failed.load(Ordering::Relaxed),
             healthy_objects: self.healthy_objects.load(Ordering::Relaxed),
             corrupted_objects: self.corrupted_objects.load(Ordering::Relaxed),
+            replication_tasks_queued: self.replication_tasks_queued.load(Ordering::Relaxed),
+            replication_pending_objects: self.replication_pending_objects.load(Ordering::Relaxed),
+            replication_failed_objects: self.replication_failed_objects.load(Ordering::Relaxed),
+            replication_lagging_objects: self.replication_lagging_objects.load(Ordering::Relaxed),
             last_activity: Some(SystemTime::now()),
             current_cycle: self.current_cycle.load(Ordering::Relaxed),
             total_cycles: self.total_cycles.load(Ordering::Relaxed),
@@ -256,6 +303,10 @@ impl MetricsCollector {
         self.total_cycles.store(0, Ordering::Relaxed);
         self.healthy_objects.store(0, Ordering::Relaxed);
         self.corrupted_objects.store(0, Ordering::Relaxed);
+        self.replication_tasks_queued.store(0, Ordering::Relaxed);
+        self.replication_pending_objects.store(0, Ordering::Relaxed);
+        self.replication_failed_objects.store(0, Ordering::Relaxed);
+        self.replication_lagging_objects.store(0, Ordering::Relaxed);
 
         info!("Scanner metrics reset");
     }

crates/ahm/src/scanner/mod.rs

@@ -12,10 +12,25 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
+pub mod checkpoint;
 pub mod data_scanner;
 pub mod histogram;
+pub mod io_monitor;
+pub mod io_throttler;
 pub mod lifecycle;
+pub mod local_scan;
+pub mod local_stats;
 pub mod metrics;
+pub mod node_scanner;
+pub mod stats_aggregator;
 
-pub use data_scanner::Scanner;
-pub use metrics::ScannerMetrics;
+pub use checkpoint::{CheckpointData, CheckpointInfo, CheckpointManager};
+pub use data_scanner::{ScanMode, Scanner, ScannerConfig, ScannerState};
+pub use io_monitor::{AdvancedIOMonitor, IOMetrics, IOMonitorConfig};
+pub use io_throttler::{AdvancedIOThrottler, IOThrottlerConfig, MetricsSnapshot, ResourceAllocation, ThrottleDecision};
+pub use local_stats::{BatchScanResult, LocalStatsManager, ScanResultEntry, StatsSummary};
+pub use metrics::{BucketMetrics, DiskMetrics, MetricsCollector, ScannerMetrics};
+pub use node_scanner::{IOMonitor, IOThrottler, LoadLevel, LocalScanStats, NodeScanner, NodeScannerConfig};
+pub use stats_aggregator::{
+    AggregatedStats, DecentralizedStatsAggregator, DecentralizedStatsAggregatorConfig, NodeClient, NodeInfo,
+};

crates/ahm/src/scanner/stats_aggregator.rs

@@ -0,0 +1,769 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+use crate::scanner::{
+    local_stats::StatsSummary,
+    node_scanner::{BucketStats, LoadLevel, ScanProgress},
+};
+use crate::{Error, Result};
+use rustfs_common::data_usage::DataUsageInfo;
+use serde::{Deserialize, Serialize};
+use std::{
+    collections::HashMap,
+    sync::Arc,
+    time::{Duration, SystemTime},
+};
+use tokio::sync::RwLock;
+use tracing::{debug, info, warn};
+
+/// node client config
+#[derive(Debug, Clone)]
+pub struct NodeClientConfig {
+    /// connect timeout
+    pub connect_timeout: Duration,
+    /// request timeout
+    pub request_timeout: Duration,
+    /// retry times
+    pub max_retries: u32,
+    /// retry interval
+    pub retry_interval: Duration,
+}
+
+impl Default for NodeClientConfig {
+    fn default() -> Self {
+        Self {
+            connect_timeout: Duration::from_secs(5),
+            request_timeout: Duration::from_secs(10),
+            max_retries: 3,
+            retry_interval: Duration::from_secs(1),
+        }
+    }
+}
+
+/// node info
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct NodeInfo {
+    /// node id
+    pub node_id: String,
+    /// node address
+    pub address: String,
+    /// node port
+    pub port: u16,
+    /// is online
+    pub is_online: bool,
+    /// last heartbeat time
+    pub last_heartbeat: SystemTime,
+    /// node version
+    pub version: String,
+}
+
+/// aggregated stats
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct AggregatedStats {
+    /// aggregation timestamp
+    pub aggregation_timestamp: SystemTime,
+    /// number of nodes participating in aggregation
+    pub node_count: usize,
+    /// number of online nodes
+    pub online_node_count: usize,
+    /// total scanned objects
+    pub total_objects_scanned: u64,
+    /// total healthy objects
+    pub total_healthy_objects: u64,
+    /// total corrupted objects
+    pub total_corrupted_objects: u64,
+    /// total scanned bytes
+    pub total_bytes_scanned: u64,
+    /// total scan errors
+    pub total_scan_errors: u64,
+    /// total heal triggered
+    pub total_heal_triggered: u64,
+    /// total disks
+    pub total_disks: usize,
+    /// total buckets
+    pub total_buckets: usize,
+    /// aggregated data usage
+    pub aggregated_data_usage: DataUsageInfo,
+    /// node summaries
+    pub node_summaries: HashMap<String, StatsSummary>,
+    /// aggregated bucket stats
+    pub aggregated_bucket_stats: HashMap<String, BucketStats>,
+    /// aggregated scan progress
+    pub scan_progress_summary: ScanProgressSummary,
+    /// load level distribution
+    pub load_level_distribution: HashMap<LoadLevel, usize>,
+}
+
+impl Default for AggregatedStats {
+    fn default() -> Self {
+        Self {
+            aggregation_timestamp: SystemTime::now(),
+            node_count: 0,
+            online_node_count: 0,
+            total_objects_scanned: 0,
+            total_healthy_objects: 0,
+            total_corrupted_objects: 0,
+            total_bytes_scanned: 0,
+            total_scan_errors: 0,
+            total_heal_triggered: 0,
+            total_disks: 0,
+            total_buckets: 0,
+            aggregated_data_usage: DataUsageInfo::default(),
+            node_summaries: HashMap::new(),
+            aggregated_bucket_stats: HashMap::new(),
+            scan_progress_summary: ScanProgressSummary::default(),
+            load_level_distribution: HashMap::new(),
+        }
+    }
+}
+
+/// scan progress summary
+#[derive(Debug, Clone, Default, Serialize, Deserialize)]
+pub struct ScanProgressSummary {
+    /// average current cycle
+    pub average_current_cycle: f64,
+    /// total completed disks
+    pub total_completed_disks: usize,
+    /// total completed buckets
+    pub total_completed_buckets: usize,
+    /// latest scan start time
+    pub earliest_scan_start: Option<SystemTime>,
+    /// estimated completion time
+    pub estimated_completion: Option<SystemTime>,
+    /// node progress
+    pub node_progress: HashMap<String, ScanProgress>,
+}
+
+/// node client
+///
+/// responsible for communicating with other nodes, getting stats data
+pub struct NodeClient {
+    /// node info
+    node_info: NodeInfo,
+    /// config
+    config: NodeClientConfig,
+    /// HTTP client
+    http_client: reqwest::Client,
+}
+
+impl NodeClient {
+    /// create new node client
+    pub fn new(node_info: NodeInfo, config: NodeClientConfig) -> Self {
+        let http_client = reqwest::Client::builder()
+            .timeout(config.request_timeout)
+            .connect_timeout(config.connect_timeout)
+            .build()
+            .expect("Failed to create HTTP client");
+
+        Self {
+            node_info,
+            config,
+            http_client,
+        }
+    }
+
+    /// get node stats summary
+    pub async fn get_stats_summary(&self) -> Result<StatsSummary> {
+        let url = format!("http://{}:{}/internal/scanner/stats", self.node_info.address, self.node_info.port);
+
+        for attempt in 1..=self.config.max_retries {
+            match self.try_get_stats_summary(&url).await {
+                Ok(summary) => return Ok(summary),
+                Err(e) => {
+                    warn!("try to get node {} stats failed: {}", self.node_info.node_id, e);
+
+                    if attempt < self.config.max_retries {
+                        tokio::time::sleep(self.config.retry_interval).await;
+                    }
+                }
+            }
+        }
+
+        Err(Error::Other(format!("cannot get stats data from node {}", self.node_info.node_id)))
+    }
+
+    /// try to get stats summary
+    async fn try_get_stats_summary(&self, url: &str) -> Result<StatsSummary> {
+        let response = self
+            .http_client
+            .get(url)
+            .send()
+            .await
+            .map_err(|e| Error::Other(format!("HTTP request failed: {e}")))?;
+
+        if !response.status().is_success() {
+            return Err(Error::Other(format!("HTTP status error: {}", response.status())));
+        }
+
+        let summary = response
+            .json::<StatsSummary>()
+            .await
+            .map_err(|e| Error::Serialization(format!("deserialize stats data failed: {e}")))?;
+
+        Ok(summary)
+    }
+
+    /// check node health status
+    pub async fn check_health(&self) -> bool {
+        let url = format!("http://{}:{}/internal/health", self.node_info.address, self.node_info.port);
+
+        match self.http_client.get(&url).send().await {
+            Ok(response) => response.status().is_success(),
+            Err(_) => false,
+        }
+    }
+
+    /// get node info
+    pub fn get_node_info(&self) -> &NodeInfo {
+        &self.node_info
+    }
+
+    /// update node online status
+    pub fn update_online_status(&mut self, is_online: bool) {
+        self.node_info.is_online = is_online;
+        if is_online {
+            self.node_info.last_heartbeat = SystemTime::now();
+        }
+    }
+}
+
+/// decentralized stats aggregator config
+#[derive(Debug, Clone)]
+pub struct DecentralizedStatsAggregatorConfig {
+    /// aggregation interval
+    pub aggregation_interval: Duration,
+    /// cache ttl
+    pub cache_ttl: Duration,
+    /// node timeout
+    pub node_timeout: Duration,
+    /// max concurrent aggregations
+    pub max_concurrent_aggregations: usize,
+}
+
+impl Default for DecentralizedStatsAggregatorConfig {
+    fn default() -> Self {
+        Self {
+            aggregation_interval: Duration::from_secs(30), // 30 seconds to aggregate
+            cache_ttl: Duration::from_secs(3),             // 3 seconds to cache
+            node_timeout: Duration::from_secs(5),          // 5 seconds to node timeout
+            max_concurrent_aggregations: 10,               // max 10 nodes to aggregate concurrently
+        }
+    }
+}
+
+/// decentralized stats aggregator
+///
+/// real-time aggregate stats data from all nodes, provide global view
+pub struct DecentralizedStatsAggregator {
+    /// config
+    config: Arc<RwLock<DecentralizedStatsAggregatorConfig>>,
+    /// node clients
+    node_clients: Arc<RwLock<HashMap<String, Arc<NodeClient>>>>,
+    /// cached aggregated stats
+    cached_stats: Arc<RwLock<Option<AggregatedStats>>>,
+    /// cache timestamp
+    cache_timestamp: Arc<RwLock<SystemTime>>,
+    /// local node stats summary
+    local_stats_summary: Arc<RwLock<Option<StatsSummary>>>,
+}
+
+impl DecentralizedStatsAggregator {
+    /// create new decentralized stats aggregator
+    pub fn new(config: DecentralizedStatsAggregatorConfig) -> Self {
+        Self {
+            config: Arc::new(RwLock::new(config)),
+            node_clients: Arc::new(RwLock::new(HashMap::new())),
+            cached_stats: Arc::new(RwLock::new(None)),
+            cache_timestamp: Arc::new(RwLock::new(SystemTime::UNIX_EPOCH)),
+            local_stats_summary: Arc::new(RwLock::new(None)),
+        }
+    }
+
+    /// add node client
+    pub async fn add_node(&self, node_info: NodeInfo) {
+        let client_config = NodeClientConfig::default();
+        let client = Arc::new(NodeClient::new(node_info.clone(), client_config));
+
+        self.node_clients.write().await.insert(node_info.node_id.clone(), client);
+
+        info!("add node to aggregator: {}", node_info.node_id);
+    }
+
+    /// remove node client
+    pub async fn remove_node(&self, node_id: &str) {
+        self.node_clients.write().await.remove(node_id);
+        info!("remove node from aggregator: {}", node_id);
+    }
+
+    /// set local node stats summary
+    pub async fn set_local_stats(&self, stats: StatsSummary) {
+        *self.local_stats_summary.write().await = Some(stats);
+    }
+
+    /// get aggregated stats data (with cache)
+    pub async fn get_aggregated_stats(&self) -> Result<AggregatedStats> {
+        let config = self.config.read().await;
+        let cache_ttl = config.cache_ttl;
+        drop(config);
+
+        // check cache validity
+        let cache_timestamp = *self.cache_timestamp.read().await;
+        let now = SystemTime::now();
+
+        debug!(
+            "cache check: cache_timestamp={:?}, now={:?}, cache_ttl={:?}",
+            cache_timestamp, now, cache_ttl
+        );
+
+        // Check cache validity if timestamp is not initial value (UNIX_EPOCH)
+        if cache_timestamp != SystemTime::UNIX_EPOCH {
+            if let Ok(elapsed) = now.duration_since(cache_timestamp) {
+                if elapsed < cache_ttl {
+                    if let Some(cached) = self.cached_stats.read().await.as_ref() {
+                        debug!("Returning cached aggregated stats, remaining TTL: {:?}", cache_ttl - elapsed);
+                        return Ok(cached.clone());
+                    }
+                } else {
+                    debug!("Cache expired: elapsed={:?} >= ttl={:?}", elapsed, cache_ttl);
+                }
+            }
+        }
+
+        // cache expired, re-aggregate
+        info!("cache expired, start re-aggregating stats data");
+        let aggregation_timestamp = now;
+        let aggregated = self.aggregate_stats_from_all_nodes(aggregation_timestamp).await?;
+
+        // update cache
+        *self.cached_stats.write().await = Some(aggregated.clone());
+        *self.cache_timestamp.write().await = aggregation_timestamp;
+
+        Ok(aggregated)
+    }
+
+    /// force refresh aggregated stats (ignore cache)
+    pub async fn force_refresh_aggregated_stats(&self) -> Result<AggregatedStats> {
+        let now = SystemTime::now();
+        let aggregated = self.aggregate_stats_from_all_nodes(now).await?;
+
+        // update cache
+        *self.cached_stats.write().await = Some(aggregated.clone());
+        *self.cache_timestamp.write().await = now;
+
+        Ok(aggregated)
+    }
+
+    /// aggregate stats data from all nodes
+    async fn aggregate_stats_from_all_nodes(&self, aggregation_timestamp: SystemTime) -> Result<AggregatedStats> {
+        let node_clients = self.node_clients.read().await;
+        let config = self.config.read().await;
+
+        // concurrent get stats data from all nodes
+        let mut tasks = Vec::new();
+        let semaphore = Arc::new(tokio::sync::Semaphore::new(config.max_concurrent_aggregations));
+
+        // add local node stats
+        let mut node_summaries = HashMap::new();
+        if let Some(local_stats) = self.local_stats_summary.read().await.as_ref() {
+            node_summaries.insert(local_stats.node_id.clone(), local_stats.clone());
+        }
+
+        // get remote node stats
+        for (node_id, client) in node_clients.iter() {
+            let client = client.clone();
+            let semaphore = semaphore.clone();
+            let node_id = node_id.clone();
+
+            let task = tokio::spawn(async move {
+                let _permit = match semaphore.acquire().await {
+                    Ok(permit) => permit,
+                    Err(e) => {
+                        warn!("Failed to acquire semaphore for node {}: {}", node_id, e);
+                        return None;
+                    }
+                };
+
+                match client.get_stats_summary().await {
+                    Ok(summary) => {
+                        debug!("successfully get node {} stats data", node_id);
+                        Some((node_id, summary))
+                    }
+                    Err(e) => {
+                        warn!("get node {} stats data failed: {}", node_id, e);
+                        None
+                    }
+                }
+            });
+
+            tasks.push(task);
+        }
+
+        // wait for all tasks to complete
+        for task in tasks {
+            if let Ok(Some((node_id, summary))) = task.await {
+                node_summaries.insert(node_id, summary);
+            }
+        }
+
+        drop(node_clients);
+        drop(config);
+
+        // aggregate stats data
+        let aggregated = self.aggregate_node_summaries(node_summaries, aggregation_timestamp).await;
+
+        info!(
+            "aggregate stats completed: {} nodes, {} online",
+            aggregated.node_count, aggregated.online_node_count
+        );
+
+        Ok(aggregated)
+    }
+
+    /// aggregate node summaries
+    async fn aggregate_node_summaries(
+        &self,
+        node_summaries: HashMap<String, StatsSummary>,
+        aggregation_timestamp: SystemTime,
+    ) -> AggregatedStats {
+        let mut aggregated = AggregatedStats {
+            aggregation_timestamp,
+            node_count: node_summaries.len(),
+            online_node_count: node_summaries.len(), // assume all nodes with data are online
+            node_summaries: node_summaries.clone(),
+            ..Default::default()
+        };
+
+        // aggregate numeric stats
+        for (node_id, summary) in &node_summaries {
+            aggregated.total_objects_scanned += summary.total_objects_scanned;
+            aggregated.total_healthy_objects += summary.total_healthy_objects;
+            aggregated.total_corrupted_objects += summary.total_corrupted_objects;
+            aggregated.total_bytes_scanned += summary.total_bytes_scanned;
+            aggregated.total_scan_errors += summary.total_scan_errors;
+            aggregated.total_heal_triggered += summary.total_heal_triggered;
+            aggregated.total_disks += summary.total_disks;
+            aggregated.total_buckets += summary.total_buckets;
+            aggregated.aggregated_data_usage.merge(&summary.data_usage);
+
+            // aggregate scan progress
+            aggregated
+                .scan_progress_summary
+                .node_progress
+                .insert(node_id.clone(), summary.scan_progress.clone());
+
+            aggregated.scan_progress_summary.total_completed_disks += summary.scan_progress.completed_disks.len();
+            aggregated.scan_progress_summary.total_completed_buckets += summary.scan_progress.completed_buckets.len();
+        }
+
+        // calculate average scan cycle
+        if !node_summaries.is_empty() {
+            let total_cycles: u64 = node_summaries.values().map(|s| s.scan_progress.current_cycle).sum();
+            aggregated.scan_progress_summary.average_current_cycle = total_cycles as f64 / node_summaries.len() as f64;
+        }
+
+        // find earliest scan start time
+        aggregated.scan_progress_summary.earliest_scan_start =
+            node_summaries.values().map(|s| s.scan_progress.scan_start_time).min();
+
+        // TODO: aggregate bucket stats and data usage
+        // here we need to implement it based on the specific BucketStats and DataUsageInfo structure
+
+        aggregated
+    }
+
+    /// get nodes health status
+    pub async fn get_nodes_health(&self) -> HashMap<String, bool> {
+        let node_clients = self.node_clients.read().await;
+        let mut health_status = HashMap::new();
+
+        // concurrent check all nodes health status
+        let mut tasks = Vec::new();
+
+        for (node_id, client) in node_clients.iter() {
+            let client = client.clone();
+            let node_id = node_id.clone();
+
+            let task = tokio::spawn(async move {
+                let is_healthy = client.check_health().await;
+                (node_id, is_healthy)
+            });
+
+            tasks.push(task);
+        }
+
+        // collect results
+        for task in tasks {
+            if let Ok((node_id, is_healthy)) = task.await {
+                health_status.insert(node_id, is_healthy);
+            }
+        }
+
+        health_status
+    }
+
+    /// get online nodes list
+    pub async fn get_online_nodes(&self) -> Vec<String> {
+        let health_status = self.get_nodes_health().await;
+
+        health_status
+            .into_iter()
+            .filter_map(|(node_id, is_healthy)| if is_healthy { Some(node_id) } else { None })
+            .collect()
+    }
+
+    /// clear cache
+    pub async fn clear_cache(&self) {
+        *self.cached_stats.write().await = None;
+        *self.cache_timestamp.write().await = SystemTime::UNIX_EPOCH;
+        info!("clear aggregated stats cache");
+    }
+
+    /// get cache status
+    pub async fn get_cache_status(&self) -> CacheStatus {
+        let cached_stats = self.cached_stats.read().await;
+        let cache_timestamp = *self.cache_timestamp.read().await;
+        let config = self.config.read().await;
+
+        let is_valid = if let Ok(elapsed) = SystemTime::now().duration_since(cache_timestamp) {
+            elapsed < config.cache_ttl
+        } else {
+            false
+        };
+
+        CacheStatus {
+            has_cached_data: cached_stats.is_some(),
+            cache_timestamp,
+            is_valid,
+            ttl: config.cache_ttl,
+        }
+    }
+
+    /// update config
+    pub async fn update_config(&self, new_config: DecentralizedStatsAggregatorConfig) {
+        *self.config.write().await = new_config;
+        info!("update aggregator config");
+    }
+}
+
+/// cache status
+#[derive(Debug, Clone)]
+pub struct CacheStatus {
+    /// has cached data
+    pub has_cached_data: bool,
+    /// cache timestamp
+    pub cache_timestamp: SystemTime,
+    /// cache is valid
+    pub is_valid: bool,
+    /// cache ttl
+    pub ttl: Duration,
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::scanner::node_scanner::{BucketScanState, ScanProgress};
+    use rustfs_common::data_usage::{BucketUsageInfo, DataUsageInfo};
+    use std::collections::{HashMap, HashSet};
+    use std::time::Duration;
+
+    #[tokio::test]
+    async fn aggregated_stats_merge_data_usage() {
+        let aggregator = DecentralizedStatsAggregator::new(DecentralizedStatsAggregatorConfig::default());
+
+        let mut data_usage = DataUsageInfo::default();
+        let bucket_usage = BucketUsageInfo {
+            objects_count: 5,
+            size: 1024,
+            ..Default::default()
+        };
+        data_usage.buckets_usage.insert("bucket".to_string(), bucket_usage);
+        data_usage.objects_total_count = 5;
+        data_usage.objects_total_size = 1024;
+
+        let summary = StatsSummary {
+            node_id: "local-node".to_string(),
+            total_objects_scanned: 10,
+            total_healthy_objects: 9,
+            total_corrupted_objects: 1,
+            total_bytes_scanned: 2048,
+            total_scan_errors: 0,
+            total_heal_triggered: 0,
+            total_disks: 2,
+            total_buckets: 1,
+            last_update: SystemTime::now(),
+            scan_progress: ScanProgress::default(),
+            data_usage: data_usage.clone(),
+        };
+
+        aggregator.set_local_stats(summary).await;
+
+        // Wait briefly to ensure async cache writes settle in high-concurrency environments
+        tokio::time::sleep(Duration::from_millis(10)).await;
+
+        let aggregated = aggregator.get_aggregated_stats().await.expect("aggregated stats");
+
+        assert_eq!(aggregated.node_count, 1);
+        assert!(aggregated.node_summaries.contains_key("local-node"));
+        assert_eq!(aggregated.aggregated_data_usage.objects_total_count, 5);
+        assert_eq!(
+            aggregated
+                .aggregated_data_usage
+                .buckets_usage
+                .get("bucket")
+                .expect("bucket usage present")
+                .objects_count,
+            5
+        );
+    }
+
+    #[tokio::test]
+    async fn aggregated_stats_merge_multiple_nodes() {
+        let aggregator = DecentralizedStatsAggregator::new(DecentralizedStatsAggregatorConfig::default());
+
+        let mut local_usage = DataUsageInfo::default();
+        let local_bucket = BucketUsageInfo {
+            objects_count: 3,
+            versions_count: 3,
+            size: 150,
+            ..Default::default()
+        };
+        local_usage.buckets_usage.insert("local-bucket".to_string(), local_bucket);
+        local_usage.calculate_totals();
+        local_usage.buckets_count = local_usage.buckets_usage.len() as u64;
+        local_usage.last_update = Some(SystemTime::now());
+
+        let local_progress = ScanProgress {
+            current_cycle: 1,
+            completed_disks: {
+                let mut set = std::collections::HashSet::new();
+                set.insert("disk-local".to_string());
+                set
+            },
+            completed_buckets: {
+                let mut map = std::collections::HashMap::new();
+                map.insert(
+                    "local-bucket".to_string(),
+                    BucketScanState {
+                        completed: true,
+                        last_object_key: Some("obj1".to_string()),
+                        objects_scanned: 3,
+                        scan_timestamp: SystemTime::now(),
+                    },
+                );
+                map
+            },
+            ..Default::default()
+        };
+
+        let local_summary = StatsSummary {
+            node_id: "node-local".to_string(),
+            total_objects_scanned: 30,
+            total_healthy_objects: 30,
+            total_corrupted_objects: 0,
+            total_bytes_scanned: 1500,
+            total_scan_errors: 0,
+            total_heal_triggered: 0,
+            total_disks: 1,
+            total_buckets: 1,
+            last_update: SystemTime::now(),
+            scan_progress: local_progress,
+            data_usage: local_usage.clone(),
+        };
+
+        let mut remote_usage = DataUsageInfo::default();
+        let remote_bucket = BucketUsageInfo {
+            objects_count: 5,
+            versions_count: 5,
+            size: 250,
+            ..Default::default()
+        };
+        remote_usage.buckets_usage.insert("remote-bucket".to_string(), remote_bucket);
+        remote_usage.calculate_totals();
+        remote_usage.buckets_count = remote_usage.buckets_usage.len() as u64;
+        remote_usage.last_update = Some(SystemTime::now());
+
+        let remote_progress = ScanProgress {
+            current_cycle: 2,
+            completed_disks: {
+                let mut set = std::collections::HashSet::new();
+                set.insert("disk-remote".to_string());
+                set
+            },
+            completed_buckets: {
+                let mut map = std::collections::HashMap::new();
+                map.insert(
+                    "remote-bucket".to_string(),
+                    BucketScanState {
+                        completed: true,
+                        last_object_key: Some("remote-obj".to_string()),
+                        objects_scanned: 5,
+                        scan_timestamp: SystemTime::now(),
+                    },
+                );
+                map
+            },
+            ..Default::default()
+        };
+
+        let remote_summary = StatsSummary {
+            node_id: "node-remote".to_string(),
+            total_objects_scanned: 50,
+            total_healthy_objects: 48,
+            total_corrupted_objects: 2,
+            total_bytes_scanned: 2048,
+            total_scan_errors: 1,
+            total_heal_triggered: 1,
+            total_disks: 2,
+            total_buckets: 1,
+            last_update: SystemTime::now(),
+            scan_progress: remote_progress,
+            data_usage: remote_usage.clone(),
+        };
+        let node_summaries: HashMap<_, _> = [
+            (local_summary.node_id.clone(), local_summary.clone()),
+            (remote_summary.node_id.clone(), remote_summary.clone()),
+        ]
+        .into_iter()
+        .collect();
+
+        let aggregated = aggregator.aggregate_node_summaries(node_summaries, SystemTime::now()).await;
+
+        assert_eq!(aggregated.node_count, 2);
+        assert_eq!(aggregated.total_objects_scanned, 80);
+        assert_eq!(aggregated.total_corrupted_objects, 2);
+        assert_eq!(aggregated.total_disks, 3);
+        assert!(aggregated.node_summaries.contains_key("node-local"));
+        assert!(aggregated.node_summaries.contains_key("node-remote"));
+
+        assert_eq!(
+            aggregated.aggregated_data_usage.objects_total_count,
+            local_usage.objects_total_count + remote_usage.objects_total_count
+        );
+        assert_eq!(
+            aggregated.aggregated_data_usage.objects_total_size,
+            local_usage.objects_total_size + remote_usage.objects_total_size
+        );
+
+        let mut expected_buckets: HashSet<&str> = HashSet::new();
+        expected_buckets.insert("local-bucket");
+        expected_buckets.insert("remote-bucket");
+        let actual_buckets: HashSet<&str> = aggregated
+            .aggregated_data_usage
+            .buckets_usage
+            .keys()
+            .map(|s| s.as_str())
+            .collect();
+        assert_eq!(expected_buckets, actual_buckets);
+    }
+}

crates/ahm/tests/endpoint_index_test.rs

@@ -0,0 +1,82 @@
+// Copyright 2024 RustFS Team
+//
+// Licensed under the Apache License, Version 2.0 (the "License");
+// you may not use this file except in compliance with the License.
+// You may obtain a copy of the License at
+//
+//     http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+//! test endpoint index settings
+
+use rustfs_ecstore::disk::endpoint::Endpoint;
+use rustfs_ecstore::endpoints::{EndpointServerPools, Endpoints, PoolEndpoints};
+use std::net::SocketAddr;
+use tempfile::TempDir;
+use tokio_util::sync::CancellationToken;
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn test_endpoint_index_settings() -> anyhow::Result<()> {
+    let temp_dir = TempDir::new()?;
+
+    // create test disk paths
+    let disk_paths: Vec<_> = (0..4).map(|i| temp_dir.path().join(format!("disk{i}"))).collect();
+
+    for path in &disk_paths {
+        tokio::fs::create_dir_all(path).await?;
+    }
+
+    // build endpoints
+    let mut endpoints: Vec<Endpoint> = disk_paths
+        .iter()
+        .map(|p| Endpoint::try_from(p.to_string_lossy().as_ref()).unwrap())
+        .collect();
+
+    // set endpoint indexes correctly
+    for (i, endpoint) in endpoints.iter_mut().enumerate() {
+        endpoint.set_pool_index(0);
+        endpoint.set_set_index(0);
+        endpoint.set_disk_index(i); // note: disk_index is usize type
+        println!(
+            "Endpoint {}: pool_idx={}, set_idx={}, disk_idx={}",
+            i, endpoint.pool_idx, endpoint.set_idx, endpoint.disk_idx
+        );
+    }
+
+    let pool_endpoints = PoolEndpoints {
+        legacy: false,
+        set_count: 1,
+        drives_per_set: endpoints.len(),
+        endpoints: Endpoints::from(endpoints.clone()),
+        cmd_line: "test".to_string(),
+        platform: format!("OS: {} | Arch: {}", std::env::consts::OS, std::env::consts::ARCH),
+    };
+
+    let endpoint_pools = EndpointServerPools(vec![pool_endpoints]);
+
+    // validate all endpoint indexes are in valid range
+    for (i, ep) in endpoints.iter().enumerate() {
+        assert_eq!(ep.pool_idx, 0, "Endpoint {i} pool_idx should be 0");
+        assert_eq!(ep.set_idx, 0, "Endpoint {i} set_idx should be 0");
+        assert_eq!(ep.disk_idx, i as i32, "Endpoint {i} disk_idx should be {i}");
+        println!(
+            "Endpoint {} indices are valid: pool={}, set={}, disk={}",
+            i, ep.pool_idx, ep.set_idx, ep.disk_idx
+        );
+    }
+
+    // test ECStore initialization
+    rustfs_ecstore::store::init_local_disks(endpoint_pools.clone()).await?;
+
+    let server_addr: SocketAddr = "127.0.0.1:0".parse().unwrap();
+    let ecstore = rustfs_ecstore::store::ECStore::new(server_addr, endpoint_pools, CancellationToken::new()).await?;
+
+    println!("ECStore initialized successfully with {} pools", ecstore.pools.len());
+
+    Ok(())
+}