Files
rustfs/scripts/run.sh
Copilot fdcdb30d28 Optimize concurrent GetObject performance with Moka cache, comprehensive metrics, complete test suite, cache writeback, and comprehensive documentation (#916)
* Initial plan

* feat: add concurrency-aware buffer sizing and hot object caching for GetObject

- Implement adaptive buffer sizing based on concurrent request load
- Add per-request tracking with automatic cleanup using RAII guards
- Implement hot object cache (LRU) for frequently accessed small files (<= 10MB)
- Add disk I/O semaphore to prevent saturation under extreme load
- Integrate concurrency module into GetObject implementation
- Buffer sizes now adapt: low concurrency uses large buffers for throughput,
  high concurrency uses smaller buffers for fairness and memory efficiency
- Add comprehensive metrics collection for monitoring performance

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* docs: add comprehensive documentation and tests for concurrent GetObject optimization

- Add detailed technical documentation explaining the solution
- Document root cause analysis and solution architecture
- Include performance expectations and testing recommendations
- Add integration tests for concurrency tracking and buffer sizing
- Add cache behavior tests
- Include benchmark tests for concurrent request handling

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix: address code review issues in concurrency module

- Fix race condition in cache size tracking by using consistent atomic operations within lock
- Correct buffer sizing logic: 1-2 requests use 100%, 3-4 use 75%, 5-8 use 50%, >8 use 40%
- Improve error message for semaphore acquire failure
- Document limitation of streaming cache implementation (not yet implemented)
- Add TODO for proper streaming cache with suggested approaches
- Update tests to match corrected buffer sizing thresholds

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* docs: add comprehensive implementation summary for concurrent GetObject optimization

- Executive summary of problem and solution
- Detailed architecture documentation for each optimization
- Integration points and code examples
- Complete testing strategy and performance validation steps
- Monitoring and observability guidelines with Prometheus queries
- Deployment considerations and rollout strategy
- Future enhancement roadmap
- Success criteria and quantitative metrics

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fix

* refactor: optimize cache with lru 0.16.2 read-first pattern and add advanced features

- Implement optimized read-first cache access using peek() to reduce write lock contention
- Add batch cache operations: get_cached_batch() for efficient multi-object retrieval
- Add cache utility methods: is_cached(), remove_cached(), get_hot_keys()
- Implement warm_cache() for pre-populating cache on startup
- Add get_advanced_buffer_size() with file size and sequential read optimization
- Enhance test suite with 8 new comprehensive tests covering:
  - Batch operations and cache warming
  - Hot keys tracking and analysis
  - Cache removal and LRU behavior verification
  - Concurrent cache access performance
  - Advanced buffer sizing strategies
- Improve documentation and code comments in English throughout

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* docs: add final comprehensive optimization summary

- Complete technical documentation of all optimizations
- Detailed performance analysis and metrics
- Production deployment guide with examples
- Comprehensive API reference and usage patterns
- Migration guide and future enhancement roadmap
- All documentation in professional English

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fix

* add moka crate for cache

* feat: replace LRU with Moka cache and add comprehensive metrics

- Replace lru crate with moka 0.12.11 for superior concurrent performance
- Implement lock-free cache with automatic TTL/TTI expiration
- Add size-based eviction using Moka's weigher function
- Integrate comprehensive metrics collection throughout GetObject flow:
  * Cache hit/miss tracking with per-key access counts
  * Request concurrency gauges
  * Disk permit wait time histograms
  * Total request duration tracking
  * Response size and buffer size histograms
- Deep integration with ecfs.rs GetObject operation
- Add hit rate calculation method
- Enhanced CacheStats with hit/miss counters
- Lock-free concurrent reads for better scalability

Moka advantages over LRU:
- True lock-free concurrent access
- Built-in TTL and TTI support
- Automatic size-based eviction
- Better performance under high concurrency
- Native async support

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* docs: add comprehensive Moka cache migration and metrics documentation

- Complete technical documentation of LRU to Moka migration
- Detailed performance comparison and benchmarks
- Comprehensive metrics catalog with 15+ Prometheus metrics
- Prometheus query examples for monitoring
- Dashboard and alerting recommendations
- Migration guide with code examples
- Troubleshooting guide for common issues
- Future enhancement roadmap

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fix

* refactor: update tests for Moka cache implementation

- Completely refactor test suite to align with Moka-based concurrency.rs
- Add Clone derive to ConcurrencyManager for test convenience
- Update all tests to handle Moka's async behavior with proper delays
- Add new tests:
  * test_cache_hit_rate - validate hit rate calculation
  * test_ttl_expiration - verify TTL configuration
  * test_is_cached_no_side_effects - ensure contains doesn't affect LRU
  * bench_concurrent_cache_performance - benchmark concurrent access
- Updated existing tests:
  * test_moka_cache_operations - renamed and updated for Moka API
  * test_moka_cache_eviction - validate automatic eviction
  * test_hot_keys_tracking - improved assertions for sorted results
  * test_concurrent_cache_access - validate lock-free performance
- All tests now include appropriate sleep delays for Moka's async processing
- Enhanced documentation and assertions for better test clarity
- Total: 18 comprehensive integration tests

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* docs: add comprehensive Moka test suite documentation

- Complete test suite documentation for all 18 tests
- Detailed test patterns and best practices for Moka
- Debugging guide for common test failures
- Performance expectations and CI integration
- 100% API coverage validation
- Future enhancement roadmap

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fmt

* docs: enhance code comments and test documentation throughout

- Significantly improve module-level documentation in concurrency.rs
- Add detailed explanations of performance characteristics and expected improvements
- Document the solution to issue #911 with before/after metrics
- Enhance constant documentation with purpose and impact explanations
- Add comprehensive RAII guard documentation with thread safety notes
- Improve test documentation with detailed test strategy and rationale
- Add Moka-specific test patterns and timing guidance
- Include performance expectations for each test category
- Document why each test matters for solving the original issue
- All documentation written in professional English
- Follow Rust documentation best practices with examples

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* remove lru crate

* upgrade version

* fix: resolve test errors by correcting module structure and test assertions

- Fix test import paths to use crate:: instead of rustfs:: (binary-only crate)
- Keep test file in src/storage/ instead of tests/ (no lib.rs exists)
- Add #[cfg(test)] guard to mod declaration in storage/mod.rs
- Fix Arc type annotations for Moka's ConcurrencyManager in concurrent tests
- Correct test_buffer_size_bounds assertions to match actual implementation:
  * Minimum buffer is 32KB for files <100KB, 64KB otherwise
  * Maximum buffer respects base_buffer_size when concurrency is low
  * Buffer sizing doesn't cap at file size, only at min/max constraints
- All 17 integration tests now pass successfully

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix: modify `TimeoutLayer::new` to `TimeoutLayer::with_status_code` and improve docker health check

* fix

* feat: implement cache writeback for small objects in GetObject

- Add cache writeback logic for objects meeting caching criteria:
  * No range/part request (full object retrieval)
  * Object size known and <= 10MB (max_object_size threshold)
  * Not encrypted (SSE-C or managed encryption)
- Read eligible objects into memory and cache via background task
- Serve response from in-memory data for immediate client response
- Add metrics counter for cache writeback operations
- Add 3 new tests for cache writeback functionality:
  * test_cache_writeback_flow - validates round-trip caching
  * test_cache_writeback_size_limit - ensures large objects aren't cached
  * test_cache_writeback_concurrent - validates thread-safe concurrent writes
- Update test suite documentation (now 20 comprehensive tests)

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* improve code for const

* cargo clippy

* feat: add cache enable/disable configuration via environment variable

- Add is_cache_enabled() method to ConcurrencyManager
- Read RUSTFS_OBJECT_CACHE_ENABLE env var (default: false) at startup
- Update ecfs.rs to check is_cache_enabled() before cache lookup and writeback
- Cache lookup and writeback now respect the enable flag
- Add test_cache_enable_configuration test
- Constants already exist in rustfs_config:
  * ENV_OBJECT_CACHE_ENABLE = "RUSTFS_OBJECT_CACHE_ENABLE"
  * DEFAULT_OBJECT_CACHE_ENABLE = false
- Total: 21 comprehensive tests passing

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fmt

* fix

* fix

* feat: implement comprehensive CachedGetObject response cache with metadata

- Add CachedGetObject struct with full response metadata fields:
  * body, content_length, content_type, e_tag, last_modified
  * expires, cache_control, content_disposition, content_encoding
  * storage_class, version_id, delete_marker, tag_count, etc.
- Add dual cache architecture in HotObjectCache:
  * Legacy simple byte cache for backward compatibility
  * New response cache for complete GetObject responses
- Add ConcurrencyManager methods for response caching:
  * get_cached_object() - retrieve cached response with metadata
  * put_cached_object() - store complete response
  * invalidate_cache() - invalidate on write operations
  * invalidate_cache_versioned() - invalidate both version and latest
  * make_cache_key() - generate cache keys with version support
  * max_object_size() - get cache threshold
- Add builder pattern for CachedGetObject construction
- Add 6 new tests for response cache functionality (27 total):
  * test_cached_get_object_basic - basic operations
  * test_cached_get_object_versioned - version key handling
  * test_cache_invalidation - write operation invalidation
  * test_cache_invalidation_versioned - versioned invalidation
  * test_cached_get_object_size_limit - size enforcement
  * test_max_object_size - threshold accessor

All 27 tests pass successfully.

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* feat: integrate CachedGetObject cache in ecfs.rs with full metadata and cache invalidation

Integration of CachedGetObject response cache in ecfs.rs:
1. get_object: Cache lookup uses get_cached_object() with full metadata
   - Returns complete response with e_tag, last_modified, content_type, etc.
   - Parses last_modified from RFC3339 string
   - Supports versioned cache keys via make_cache_key()

2. get_object: Cache writeback uses put_cached_object() with metadata
   - Stores content_type, e_tag, last_modified in CachedGetObject
   - Background writeback via tokio::spawn()

3. Cache invalidation added to write operations:
   - put_object: invalidate_cache_versioned() after store.put_object()
   - put_object_extract: invalidate_cache_versioned() after each file extraction
   - copy_object: invalidate_cache_versioned() after store.copy_object()
   - delete_object: invalidate_cache_versioned() after store.delete_object()
   - delete_objects: invalidate_cache_versioned() for each deleted object
   - complete_multipart_upload: invalidate_cache_versioned() after completion

4. Fixed test_adaptive_buffer_sizing to be more robust with parallel tests

All 27 tests pass.

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix: add error logging for time parsing in cache lookup and writeback

- Add warning log when RFC3339 parsing fails in cache lookup
- Add warning log when time formatting fails in cache writeback
- Improves debugging for cache-related issues

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fix

* upgrade version

* fmt

* add http: 4138 and add max_object_size key

* fix

* fix

* fix

* modify metrics key

* add

* upgrade crates version and improve docker observability

* feat: implement adaptive I/O strategy based on disk permit wait time

Implements adaptive I/O strategy for GetObject operations based on disk permit
wait times, as requested in issue #911.

Key changes:

1. New types in concurrency.rs:
   - IoLoadLevel enum: Low (<10ms), Medium (10-50ms), High (50-200ms), Critical (>200ms)
   - IoStrategy struct: contains optimized I/O parameters based on load level
   - IoLoadMetrics: rolling window metrics for load tracking

2. New ConcurrencyManager methods:
   - calculate_io_strategy(): calculates adaptive strategy from permit wait duration
   - record_permit_wait(): records observation for load tracking
   - smoothed_load_level(): returns averaged load level for stability
   - io_load_stats(): returns (avg_wait, p95_wait, max_wait, count) for monitoring
   - adaptive_buffer_size(): convenience method for buffer sizing

3. Integration in ecfs.rs get_object:
   - Calculate IoStrategy after acquiring disk permit
   - Use strategy buffer_size instead of static sizing
   - Consider strategy.cache_writeback_enabled in cache decision
   - Record new metrics: io.load.level gauge, io.buffer.multiplier gauge,
     io.strategy.selected counter by load level

4. New tests (4 added, 31 total):
   - test_io_load_level_classification: validates load level thresholds
   - test_io_strategy_buffer_sizing: validates buffer multipliers
   - test_calculate_io_strategy: validates manager strategy calculation
   - test_io_load_stats: validates stats tracking

All 31 tests pass. Clippy clean. Formatted.

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* fix

* docs: add comprehensive architecture design and fix cache hit event notification

1. Added CONCURRENCY_ARCHITECTURE.md with complete design documentation:
   - Executive summary and problem statement
   - Architecture overview with request flow diagram
   - Detailed module analysis for concurrency.rs and ecfs.rs
   - Critical analysis of helper.complete() for cache hits
   - Adaptive I/O strategy design with algorithm
   - Cache architecture with CachedGetObject structure
   - Metrics and monitoring with Prometheus queries
   - Performance characteristics and future enhancements

2. Fixed critical issue: Cache hit path now calls helper.complete()
   - S3 bucket notifications (s3:GetObject events) now trigger for cache hits
   - Event-driven workflows (Lambda, SNS) work correctly for all object access
   - Maintains audit trail for both cache hits and misses

All 31 tests pass.

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix: set object info and version_id on helper before complete() for cache hits

When serving from cache, properly configure the OperationHelper before
calling complete() to ensure S3 bucket notifications include complete
object metadata:

1. Build ObjectInfo from cached metadata:
   - bucket, name, size, actual_size
   - etag, mod_time, version_id, delete_marker
   - storage_class, content_type, content_encoding
   - user_metadata (user_defined)

2. Set helper.object(event_info).version_id(version_id_str) before complete()

3. Updated CONCURRENCY_ARCHITECTURE.md with:
   - Complete code example for cache hit event notification
   - Explanation of why ObjectInfo is required
   - Documentation of version_id handling

This ensures:
- Lambda triggers receive proper object metadata for cache hits
- SNS/SQS notifications include complete information
- Audit logs contain accurate object details
- Version-specific event routing works correctly

All 31 tests pass.

Co-authored-by: houseme <4829346+houseme@users.noreply.github.com>

* fix

* improve code

* fmt

---------

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>
2025-11-30 01:16:55 +08:00

155 lines
6.8 KiB
Bash
Executable File

#!/bin/bash -e
# 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.
# check ./rustfs/static/index.html not exists
if [ ! -f ./rustfs/static/index.html ]; then
echo "Downloading rustfs-console-latest.zip"
# download rustfs-console-latest.zip do not show log
curl -s -L "https://dl.rustfs.com/artifacts/console/rustfs-console-latest.zip" -o tempfile.zip && unzip -q -o tempfile.zip -d ./rustfs/static && rm tempfile.zip
fi
if [ -z "$SKIP_BUILD" ]; then
cargo build -p rustfs --bins
fi
current_dir=$(pwd)
echo "Current directory: $current_dir"
# mkdir -p ./target/volume/test
mkdir -p ./target/volume/test{1..4}
if [ -z "$RUST_LOG" ]; then
export RUST_BACKTRACE=1
export RUST_LOG="rustfs=debug,ecstore=info,s3s=debug,iam=info"
fi
# export RUSTFS_ERASURE_SET_DRIVE_COUNT=5
# export RUSTFS_STORAGE_CLASS_INLINE_BLOCK="512 KB"
export RUSTFS_VOLUMES="./target/volume/test{1...4}"
# export RUSTFS_VOLUMES="./target/volume/test"
export RUSTFS_ADDRESS=":9000"
export RUSTFS_CONSOLE_ENABLE=true
export RUSTFS_CONSOLE_ADDRESS=":9001"
# export RUSTFS_SERVER_DOMAINS="localhost:9000"
# HTTPS certificate directory
# export RUSTFS_TLS_PATH="./deploy/certs"
# Observability related configuration
#export RUSTFS_OBS_ENDPOINT=http://localhost:4318 # OpenTelemetry Collector address
# RustFS OR OTEL exporter configuration
#export RUSTFS_OBS_TRACE_ENDPOINT=http://localhost:4318/v1/traces # OpenTelemetry Collector trace address http://localhost:4318/v1/traces
#export OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://localhost:14318/v1/traces
#export RUSTFS_OBS_METRIC_ENDPOINT=http://localhost:9090/api/v1/otlp/v1/metrics # OpenTelemetry Collector metric address
#export OTEL_EXPORTER_OTLP_METRICS_ENDPOINT=http://localhost:9090/api/v1/otlp/v1/metrics
#export RUSTFS_OBS_LOG_ENDPOINT=http://loki:3100/otlp/v1/logs # OpenTelemetry Collector logs address http://loki:3100/otlp/v1/logs
#export OTEL_EXPORTER_OTLP_LOGS_ENDPOINT=http://loki:3100/otlp/v1/logs
#export RUSTFS_OBS_USE_STDOUT=true # Whether to use standard output
#export RUSTFS_OBS_SAMPLE_RATIO=2.0 # Sample ratio, between 0.0-1.0, 0.0 means no sampling, 1.0 means full sampling
#export RUSTFS_OBS_METER_INTERVAL=1 # Sampling interval in seconds
#export RUSTFS_OBS_SERVICE_NAME=rustfs # Service name
#export RUSTFS_OBS_SERVICE_VERSION=0.1.0 # Service version
export RUSTFS_OBS_ENVIRONMENT=production # Environment name
export RUSTFS_OBS_LOGGER_LEVEL=warn # Log level, supports trace, debug, info, warn, error
export RUSTFS_OBS_LOG_STDOUT_ENABLED=false # Whether to enable local stdout logging
export RUSTFS_OBS_LOG_DIRECTORY="$current_dir/deploy/logs" # Log directory
export RUSTFS_OBS_LOG_ROTATION_TIME="hour" # Log rotation time unit, can be "second", "minute", "hour", "day"
export RUSTFS_OBS_LOG_ROTATION_SIZE_MB=100 # Log rotation size in MB
export RUSTFS_OBS_LOG_POOL_CAPA=10240 # Log pool capacity
export RUSTFS_OBS_LOG_MESSAGE_CAPA=32768 # Log message capacity
export RUSTFS_OBS_LOG_FLUSH_MS=300 # Log flush interval in milliseconds
#tokio runtime
export RUSTFS_RUNTIME_WORKER_THREADS=16
export RUSTFS_RUNTIME_MAX_BLOCKING_THREADS=1024
export RUSTFS_RUNTIME_THREAD_PRINT_ENABLED=true
# shellcheck disable=SC2125
export RUSTFS_RUNTIME_THREAD_STACK_SIZE=1024*1024
export RUSTFS_RUNTIME_THREAD_KEEP_ALIVE=60
export RUSTFS_RUNTIME_GLOBAL_QUEUE_INTERVAL=31
export OTEL_INSTRUMENTATION_NAME="rustfs"
export OTEL_INSTRUMENTATION_VERSION="0.1.1"
export OTEL_INSTRUMENTATION_SCHEMA_URL="https://opentelemetry.io/schemas/1.31.0"
export OTEL_INSTRUMENTATION_ATTRIBUTES="env=production"
# notify
export RUSTFS_NOTIFY_WEBHOOK_ENABLE="on" # Whether to enable webhook notification
export RUSTFS_NOTIFY_WEBHOOK_ENDPOINT="http://[::]:3020/webhook" # Webhook notification address
export RUSTFS_NOTIFY_WEBHOOK_QUEUE_DIR="$current_dir/deploy/logs/notify"
export RUSTFS_NOTIFY_WEBHOOK_ENABLE_PRIMARY="on" # Whether to enable webhook notification
export RUSTFS_NOTIFY_WEBHOOK_ENDPOINT_PRIMARY="http://[::]:3020/webhook" # Webhook notification address
export RUSTFS_NOTIFY_WEBHOOK_QUEUE_DIR_PRIMARY="$current_dir/deploy/logs/notify"
export RUSTFS_NOTIFY_WEBHOOK_ENABLE_MASTER="on" # Whether to enable webhook notification
export RUSTFS_NOTIFY_WEBHOOK_ENDPOINT_MASTER="http://[::]:3020/webhook" # Webhook notification address
export RUSTFS_NOTIFY_WEBHOOK_QUEUE_DIR_MASTER="$current_dir/deploy/logs/notify"
# export RUSTFS_POLICY_PLUGIN_URL="http://localhost:8181/v1/data/rustfs/authz/allow" # The URL of the OPA system
# export RUSTFS_POLICY_PLUGIN_AUTH_TOKEN="your-opa-token" # The authentication token for the OPA system is optional
export RUSTFS_NS_SCANNER_INTERVAL=60 # Object scanning interval in seconds
# exportRUSTFS_SKIP_BACKGROUND_TASK=true
# export RUSTFS_COMPRESSION_ENABLED=true # Whether to enable compression
#export RUSTFS_REGION="us-east-1"
export RUSTFS_ENABLE_SCANNER=false
export RUSTFS_ENABLE_HEAL=false
# Object cache configuration
export RUSTFS_OBJECT_CACHE_ENABLE=true
# Profiling configuration
export RUSTFS_ENABLE_PROFILING=false
if [ -n "$1" ]; then
export RUSTFS_VOLUMES="$1"
fi
# Enable jemalloc for memory profiling
# MALLOC_CONF parameters:
# prof:true - Enable heap profiling
# prof_active:true - Start profiling immediately
# lg_prof_sample:16 - Average number of bytes between samples (2^16 = 65536 bytes)
# log:true - Enable logging
# narenas:2 - Number of arenas (controls concurrency and memory fragmentation)
# lg_chunk:21 - Chunk size (2^21 = 2MB)
# background_thread:true - Enable background threads for purging
# dirty_decay_ms:1000 - Time (ms) before dirty pages are purged
# muzzy_decay_ms:1000 - Time (ms) before muzzy pages are purged
# You can override these defaults by setting the MALLOC_CONF environment variable before running this script.
if [ -z "$MALLOC_CONF" ]; then
export MALLOC_CONF="prof:true,prof_active:true,lg_prof_sample:16,log:true,narenas:2,lg_chunk:21,background_thread:true,dirty_decay_ms:1000,muzzy_decay_ms:1000"
fi
# Start webhook server
#cargo run --example webhook -p rustfs-notify &
# Start main service
# To run with profiling enabled, uncomment the following line and comment the next line
#cargo run --profile profiling --bin rustfs
# To run in release mode, use the following line
#cargo run --profile release --bin rustfs
# To run in debug mode, use the following line
cargo run --bin rustfs