sdgoij/rustfs
1
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-01-17 01:30:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

add metrics

Browse Source
This commit is contained in:
houseme
2025-05-15 23:34:36 +08:00
parent 5304b73588
commit 60635aeb65
27 changed files with 1702 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

202
Cargo.lock generated
View File

@@ -835,6 +835,15 @@ dependencies = [
"windows-targets 0.52.6",
]
[[package]]
name = "base62"
version = "2.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "10e52a7bcb1d6beebee21fb5053af9e3cbb7a7ed1a4909e534040e676437ab1f"
dependencies = [
"rustversion",
]
[[package]]
name = "base64"
version = "0.21.7"
@@ -1012,6 +1021,16 @@ dependencies = [
"alloc-stdlib",
]
[[package]]
name = "bstr"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "234113d19d0d7d613b40e86fb654acf958910802bcceab913a4f9e7cda03b1a4"
dependencies = [
"memchr",
"serde",
]
[[package]]
name = "bumpalo"
version = "3.17.0"
@@ -1291,9 +1310,9 @@ dependencies = [
[[package]]
name = "clap"
version = "4.5.37"
version = "4.5.38"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eccb054f56cbd38340b380d4a8e69ef1f02f1af43db2f0cc817a4774d80ae071"
checksum = "ed93b9805f8ba930df42c2590f05453d5ec36cbb85d018868a5b24d31f6ac000"
dependencies = [
"clap_builder",
"clap_derive",
@@ -1301,9 +1320,9 @@ dependencies = [
[[package]]
name = "clap_builder"
version = "4.5.37"
version = "4.5.38"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "efd9466fac8543255d3b1fcad4762c5e116ffe808c8a3043d4263cd4fd4862a2"
checksum = "379026ff283facf611b0ea629334361c4211d1b12ee01024eec1591133b04120"
dependencies = [
"anstream",
"anstyle",
@@ -1722,6 +1741,25 @@ dependencies = [
"crossbeam-utils",
]
[[package]]
name = "crossbeam-deque"
version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
dependencies = [
"crossbeam-epoch",
"crossbeam-utils",
]
[[package]]
name = "crossbeam-epoch"
version = "0.9.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
dependencies = [
"crossbeam-utils",
]
[[package]]
name = "crossbeam-utils"
version = "0.8.21"
@@ -3795,6 +3833,30 @@ dependencies = [
"x11-dl",
]
[[package]]
name = "globset"
version = "0.4.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "54a1028dfc5f5df5da8a56a73e6c153c9a9708ec57232470703592a3f18e49f5"
dependencies = [
"aho-corasick",
"bstr",
"log",
"regex-automata 0.4.9",
"regex-syntax 0.8.5",
]
[[package]]
name = "globwalk"
version = "0.8.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "93e3af942408868f6934a7b85134a3230832b9977cf66125df2f9edcfce4ddcc"
dependencies = [
"bitflags 1.3.2",
"ignore",
"walkdir",
]
[[package]]
name = "gloo-net"
version = "0.6.0"
@@ -4389,6 +4451,22 @@ dependencies = [
"icu_properties",
]
[[package]]
name = "ignore"
version = "0.4.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6d89fd380afde86567dfba715db065673989d6253f42b88179abd3eae47bda4b"
dependencies = [
"crossbeam-deque",
"globset",
"log",
"memchr",
"regex-automata 0.4.9",
"same-file",
"walkdir",
"winapi-util",
]
[[package]]
name = "indexmap"
version = "1.9.3"
@@ -4471,6 +4549,15 @@ version = "1.70.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf"
[[package]]
name = "itertools"
version = "0.11.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b1c173a5686ce8bfa551b3563d0c2170bf24ca44da99c7ca4bfdab5418c3fe57"
dependencies = [
"either",
]
[[package]]
name = "itertools"
version = "0.12.1"
@@ -5284,6 +5371,15 @@ dependencies = [
"memchr",
]
[[package]]
name = "normpath"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8911957c4b1549ac0dc74e30db9c8b0e66ddcd6d7acc33098f4c63a64a6d7ed"
dependencies = [
"windows-sys 0.59.0",
]
[[package]]
name = "ntapi"
version = "0.4.1"
@@ -7219,6 +7315,60 @@ dependencies = [
"walkdir",
]
[[package]]
name = "rust-i18n"
version = "3.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a2b6307cde881492032919adf26e254981604a6657b339ae23cce8358e9ee203"
dependencies = [
"globwalk",
"once_cell",
"regex",
"rust-i18n-macro",
"rust-i18n-support",
"smallvec",
]
[[package]]
name = "rust-i18n-macro"
version = "3.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1c0dc724669fe2ddbbec5ed9daea8147a9030de87ebb46fdc7bb9315701d9912"
dependencies = [
"glob",
"once_cell",
"proc-macro2",
"quote",
"rust-i18n-support",
"serde",
"serde_json",
"serde_yaml",
"syn 2.0.100",
]
[[package]]
name = "rust-i18n-support"
version = "3.1.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b47501de04282525d0192c4b4133f9e3574e1fab3542ddc7bb109ff773dc108b"
dependencies = [
"arc-swap",
"base62",
"globwalk",
"itertools 0.11.0",
"lazy_static",
"normpath",
"once_cell",
"proc-macro2",
"regex",
"serde",
"serde_json",
"serde_yaml",
"siphasher 1.0.1",
"toml",
"triomphe",
]
[[package]]
name = "rust-ini"
version = "0.21.1"
@@ -7375,6 +7525,7 @@ dependencies = [
"lazy_static",
"rfd 0.15.3",
"rust-embed",
"rust-i18n",
"serde",
"serde_json",
"sha2 0.10.9",
@@ -7508,11 +7659,12 @@ dependencies = [
[[package]]
name = "rustls-pki-types"
version = "1.11.0"
version = "1.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "917ce264624a4b4db1c364dcc35bfca9ded014d0a958cd47ad3e960e988ea51c"
checksum = "229a4a4c221013e7e1f1a043678c5cc39fe5171437c88fb47151a21e6f5b5c79"
dependencies = [
"web-time",
"zeroize",
]
[[package]]
@@ -7841,6 +7993,19 @@ dependencies = [
"syn 2.0.100",
]
[[package]]
name = "serde_yaml"
version = "0.9.34+deprecated"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6a8b1a1a2ebf674015cc02edccce75287f1a0130d394307b36743c2f5d504b47"
dependencies = [
"indexmap 2.9.0",
"itoa 1.0.15",
"ryu",
"serde",
"unsafe-libyaml",
]
[[package]]
name = "server_fn"
version = "0.6.15"
@@ -8455,9 +8620,9 @@ checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
[[package]]
name = "tempfile"
version = "3.19.1"
version = "3.20.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7437ac7763b9b123ccf33c338a5cc1bac6f69b45a136c19bdd8a65e3916435bf"
checksum = "e8a64e3985349f2441a1a9ef0b853f869006c3855f2cda6862a94d26ebb9d6a1"
dependencies = [
"fastrand",
"getrandom 0.3.2",
@@ -8923,9 +9088,9 @@ dependencies = [
[[package]]
name = "tower-http"
version = "0.6.2"
version = "0.6.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "403fa3b783d4b626a8ad51d766ab03cb6d2dbfc46b1c5d4448395e6628dc9697"
checksum = "0fdb0c213ca27a9f57ab69ddb290fd80d970922355b83ae380b395d3986b8a2e"
dependencies = [
"async-compression",
"bitflags 2.9.0",
@@ -9116,6 +9281,17 @@ version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "343e926fc669bc8cde4fa3129ab681c63671bae288b1f1081ceee6d9d37904fc"
[[package]]
name = "triomphe"
version = "0.1.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ef8f7726da4807b58ea5c96fdc122f80702030edc33b35aff9190a51148ccc85"
dependencies = [
"arc-swap",
"serde",
"stable_deref_trait",
]
[[package]]
name = "try-lock"
version = "0.2.5"
@@ -9239,6 +9415,12 @@ dependencies = [
"subtle",
]
[[package]]
name = "unsafe-libyaml"
version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861"
[[package]]
name = "untrusted"
version = "0.9.0"

9
Cargo.toml
View File

@@ -67,7 +67,7 @@ blake2 = "0.10.6"
bytes = "1.10.1"
bytesize = "2.0.1"
chrono = { version = "0.4.41", features = ["serde"] }
clap = { version = "4.5.37", features = ["derive", "env"] }
clap = { version = "4.5.38", features = ["derive", "env"] }
config = "0.15.11"
const-str = { version = "0.6.2", features = ["std", "proc"] }
datafusion = "46.0.1"
@@ -147,8 +147,9 @@ rmp = "0.8.14"
rmp-serde = "1.3.0"
rumqttc = { version = "0.24" }
rust-embed = { version = "8.7.1" }
rust-i18n = { version = "3.1.4" }
rustls = { version = "0.23.27" }
rustls-pki-types = "1.11.0"
rustls-pki-types = "1.12.0"
rustls-pemfile = "2.2.0"
s3s = { git = "https://github.com/Nugine/s3s.git", rev = "4733cdfb27b2713e832967232cbff413bb768c10" }
s3s-policy = { git = "https://github.com/Nugine/s3s.git", rev = "4733cdfb27b2713e832967232cbff413bb768c10" }
@@ -163,7 +164,7 @@ snafu = "0.8.5"
socket2 = "0.5.9"
strum = { version = "0.27.1", features = ["derive"] }
sysinfo = "0.34.2"
tempfile = "3.19.1"
tempfile = "3.20.0"
test-case = "3.3.1"
thiserror = "2.0.12"
time = { version = "0.3.41", features = [
@@ -181,7 +182,7 @@ tokio-util = { version = "0.7.15", features = ["io", "compat"] }
tonic = { version = "0.13.1", features = ["gzip"] }
tonic-build = { version = "0.13.1" }
tower = { version = "0.5.2", features = ["timeout"] }
tower-http = { version = "0.6.2", features = ["cors"] }
tower-http = { version = "0.6.4", features = ["cors"] }
tracing = "0.1.41"
tracing-core = "0.1.33"
tracing-error = "0.2.1"

1
cli/rustfs-gui/Cargo.toml
View File

@@ -15,6 +15,7 @@ keyring = { workspace = true }
lazy_static = { 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 }

4
crates/obs/src/metrics/audit.rs
View File

@@ -1,8 +1,10 @@
/// audit related metric descriptors
///
/// This module contains the metric descriptors for the audit subsystem.
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
const TARGET_ID: &str = "target_id";
/// audit related metric descriptors
lazy_static::lazy_static! {
pub static ref AUDIT_FAILED_MESSAGES_MD: MetricDescriptor =
new_counter_md(

3
crates/obs/src/metrics/bucket.rs
View File

@@ -1,6 +1,7 @@
/// bucket level s3 metric descriptor
use crate::metrics::{new_counter_md, new_gauge_md, new_histogram_md, subsystems, MetricDescriptor, MetricName};
/// Bucket 级别 S3 指标描述符
lazy_static::lazy_static! {
pub static ref BUCKET_API_TRAFFIC_SENT_BYTES_MD: MetricDescriptor =
new_counter_md(

2
crates/obs/src/metrics/bucket_replication.rs
View File

@@ -1,3 +1,4 @@
/// Bucket copy metric descriptor
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
// Label constants
@@ -6,7 +7,6 @@ pub const OPERATION_L: &str = "operation";
pub const TARGET_ARN_L: &str = "targetArn";
pub const RANGE_L: &str = "range";
/// Bucket copy metric descriptor
lazy_static::lazy_static! {
pub static ref BUCKET_REPL_LAST_HR_FAILED_BYTES_MD: MetricDescriptor =
new_gauge_md(

96
crates/obs/src/metrics/cluster_erasure_set.rs Normal file
View File

@@ -0,0 +1,96 @@
use crate::metrics::{new_gauge_md, subsystems, MetricDescriptor, MetricName};
// 定义标签常量
pub const POOL_ID_L: &str = "pool_id";
pub const SET_ID_L: &str = "set_id";
/// 纠删码集合相关指标描述符
lazy_static::lazy_static! {
pub static ref ERASURE_SET_OVERALL_WRITE_QUORUM_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetOverallWriteQuorum,
"Overall write quorum across pools and sets",
&[], // 无标签
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_OVERALL_HEALTH_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetOverallHealth,
"Overall health across pools and sets (1=healthy, 0=unhealthy)",
&[], // 无标签
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_READ_QUORUM_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetReadQuorum,
"Read quorum for the erasure set in a pool",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_WRITE_QUORUM_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetWriteQuorum,
"Write quorum for the erasure set in a pool",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_ONLINE_DRIVES_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetOnlineDrivesCount,
"Count of online drives in the erasure set in a pool",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_HEALING_DRIVES_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetHealingDrivesCount,
"Count of healing drives in the erasure set in a pool",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_HEALTH_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetHealth,
"Health of the erasure set in a pool (1=healthy, 0=unhealthy)",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_READ_TOLERANCE_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetReadTolerance,
"No of drive failures that can be tolerated without disrupting read operations",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_WRITE_TOLERANCE_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetWriteTolerance,
"No of drive failures that can be tolerated without disrupting write operations",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_READ_HEALTH_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetReadHealth,
"Health of the erasure set in a pool for read operations (1=healthy, 0=unhealthy)",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
pub static ref ERASURE_SET_WRITE_HEALTH_MD: MetricDescriptor =
new_gauge_md(
MetricName::ErasureSetWriteHealth,
"Health of the erasure set in a pool for write operations (1=healthy, 0=unhealthy)",
&[POOL_ID_L, SET_ID_L],
subsystems::CLUSTER_ERASURE_SET
);
}

28
crates/obs/src/metrics/cluster_health.rs Normal file
View File

@@ -0,0 +1,28 @@
use crate::metrics::{new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 集群健康相关指标描述符
lazy_static::lazy_static! {
pub static ref HEALTH_DRIVES_OFFLINE_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::HealthDrivesOfflineCount,
"Count of offline drives in the cluster",
&[], // 无标签
subsystems::CLUSTER_HEALTH
);
pub static ref HEALTH_DRIVES_ONLINE_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::HealthDrivesOnlineCount,
"Count of online drives in the cluster",
&[], // 无标签
subsystems::CLUSTER_HEALTH
);
pub static ref HEALTH_DRIVES_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::HealthDrivesCount,
"Count of all drives in the cluster",
&[], // 无标签
subsystems::CLUSTER_HEALTH
);
}

84
crates/obs/src/metrics/cluster_iam.rs Normal file
View File

@@ -0,0 +1,84 @@
use crate::metrics::{new_counter_md, subsystems, MetricDescriptor, MetricName};
/// IAM 相关指标描述符
lazy_static::lazy_static! {
pub static ref LAST_SYNC_DURATION_MILLIS_MD: MetricDescriptor =
new_counter_md(
MetricName::LastSyncDurationMillis,
"Last successful IAM data sync duration in milliseconds",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref PLUGIN_AUTHN_SERVICE_FAILED_REQUESTS_MINUTE_MD: MetricDescriptor =
new_counter_md(
MetricName::PluginAuthnServiceFailedRequestsMinute,
"When plugin authentication is configured, returns failed requests count in the last full minute",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref PLUGIN_AUTHN_SERVICE_LAST_FAIL_SECONDS_MD: MetricDescriptor =
new_counter_md(
MetricName::PluginAuthnServiceLastFailSeconds,
"When plugin authentication is configured, returns time (in seconds) since the last failed request to the service",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref PLUGIN_AUTHN_SERVICE_LAST_SUCC_SECONDS_MD: MetricDescriptor =
new_counter_md(
MetricName::PluginAuthnServiceLastSuccSeconds,
"When plugin authentication is configured, returns time (in seconds) since the last successful request to the service",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref PLUGIN_AUTHN_SERVICE_SUCC_AVG_RTT_MS_MINUTE_MD: MetricDescriptor =
new_counter_md(
MetricName::PluginAuthnServiceSuccAvgRttMsMinute,
"When plugin authentication is configured, returns average round-trip-time of successful requests in the last full minute",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref PLUGIN_AUTHN_SERVICE_SUCC_MAX_RTT_MS_MINUTE_MD: MetricDescriptor =
new_counter_md(
MetricName::PluginAuthnServiceSuccMaxRttMsMinute,
"When plugin authentication is configured, returns maximum round-trip-time of successful requests in the last full minute",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref PLUGIN_AUTHN_SERVICE_TOTAL_REQUESTS_MINUTE_MD: MetricDescriptor =
new_counter_md(
MetricName::PluginAuthnServiceTotalRequestsMinute,
"When plugin authentication is configured, returns total requests count in the last full minute",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref SINCE_LAST_SYNC_MILLIS_MD: MetricDescriptor =
new_counter_md(
MetricName::SinceLastSyncMillis,
"Time (in milliseconds) since last successful IAM data sync.",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref SYNC_FAILURES_MD: MetricDescriptor =
new_counter_md(
MetricName::SyncFailures,
"Number of failed IAM data syncs since server start.",
&[], // 无标签
subsystems::CLUSTER_IAM
);
pub static ref SYNC_SUCCESSES_MD: MetricDescriptor =
new_counter_md(
MetricName::SyncSuccesses,
"Number of successful IAM data syncs since server start.",
&[], // 无标签
subsystems::CLUSTER_IAM
);
}

36
crates/obs/src/metrics/cluster_notification.rs Normal file
View File

@@ -0,0 +1,36 @@
use crate::metrics::{new_counter_md, subsystems, MetricDescriptor, MetricName};
/// 通知相关指标描述符
lazy_static::lazy_static! {
pub static ref NOTIFICATION_CURRENT_SEND_IN_PROGRESS_MD: MetricDescriptor =
new_counter_md(
MetricName::NotificationCurrentSendInProgress,
"Number of concurrent async Send calls active to all targets",
&[], // 无标签
subsystems::NOTIFICATION
);
pub static ref NOTIFICATION_EVENTS_ERRORS_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::NotificationEventsErrorsTotal,
"Events that were failed to be sent to the targets",
&[], // 无标签
subsystems::NOTIFICATION
);
pub static ref NOTIFICATION_EVENTS_SENT_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::NotificationEventsSentTotal,
"Total number of events sent to the targets",
&[], // 无标签
subsystems::NOTIFICATION
);
pub static ref NOTIFICATION_EVENTS_SKIPPED_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::NotificationEventsSkippedTotal,
"Events that were skipped to be sent to the targets due to the in-memory queue being full",
&[], // 无标签
subsystems::NOTIFICATION
);
}

131
crates/obs/src/metrics/cluster_usage.rs Normal file
View File

@@ -0,0 +1,131 @@
use crate::metrics::{new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 集群对象使用情况相关指标描述符
lazy_static::lazy_static! {
pub static ref USAGE_SINCE_LAST_UPDATE_SECONDS_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageSinceLastUpdateSeconds,
"Time since last update of usage metrics in seconds",
&[], // 无标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_TOTAL_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageTotalBytes,
"Total cluster usage in bytes",
&[], // 无标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_OBJECTS_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageObjectsCount,
"Total cluster objects count",
&[], // 无标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_VERSIONS_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageVersionsCount,
"Total cluster object versions (including delete markers) count",
&[], // 无标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_DELETE_MARKERS_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageDeleteMarkersCount,
"Total cluster delete markers count",
&[], // 无标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_BUCKETS_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketsCount,
"Total cluster buckets count",
&[], // 无标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_OBJECTS_DISTRIBUTION_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageSizeDistribution,
"Cluster object size distribution",
&["range"], // 标签
subsystems::CLUSTER_USAGE_OBJECTS
);
pub static ref USAGE_VERSIONS_DISTRIBUTION_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageVersionCountDistribution,
"Cluster object version count distribution",
&["range"], // 标签
subsystems::CLUSTER_USAGE_OBJECTS
);
}
/// 定义常量
pub const BUCKET_LABEL: &str = "bucket";
pub const RANGE_LABEL: &str = "range";
/// 桶使用情况相关指标描述符
lazy_static::lazy_static! {
pub static ref USAGE_BUCKET_TOTAL_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketTotalBytes,
"Total bucket size in bytes",
&[BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
pub static ref USAGE_BUCKET_OBJECTS_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketObjectsCount,
"Total objects count in bucket",
&[BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
pub static ref USAGE_BUCKET_VERSIONS_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketVersionsCount,
"Total object versions (including delete markers) count in bucket",
&[BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
pub static ref USAGE_BUCKET_DELETE_MARKERS_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketDeleteMarkersCount,
"Total delete markers count in bucket",
&[BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
pub static ref USAGE_BUCKET_QUOTA_TOTAL_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketQuotaTotalBytes,
"Total bucket quota in bytes",
&[BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
pub static ref USAGE_BUCKET_OBJECT_SIZE_DISTRIBUTION_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketObjectSizeDistribution,
"Bucket object size distribution",
&[RANGE_LABEL, BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
pub static ref USAGE_BUCKET_OBJECT_VERSION_COUNT_DISTRIBUTION_MD: MetricDescriptor =
new_gauge_md(
MetricName::UsageBucketObjectVersionCountDistribution,
"Bucket object version count distribution",
&[RANGE_LABEL, BUCKET_LABEL],
subsystems::CLUSTER_USAGE_BUCKETS
);
}

1
crates/obs/src/metrics/entry/descriptor.rs
View File

@@ -38,6 +38,7 @@ impl MetricDescriptor {
}
/// 获取完整的指标名称，包含前缀和格式化路径
#[allow(dead_code)]
pub fn get_full_metric_name(&self) -> String {
let prefix = self.metric_type.to_prom();
let namespace = self.namespace.as_str();

329
crates/obs/src/metrics/entry/metric_name.rs
View File

@@ -168,11 +168,175 @@ pub enum MetricName {
ConfigRRSParity,
ConfigStandardParity,
// 纠删码集合相关指标
ErasureSetOverallWriteQuorum,
ErasureSetOverallHealth,
ErasureSetReadQuorum,
ErasureSetWriteQuorum,
ErasureSetOnlineDrivesCount,
ErasureSetHealingDrivesCount,
ErasureSetHealth,
ErasureSetReadTolerance,
ErasureSetWriteTolerance,
ErasureSetReadHealth,
ErasureSetWriteHealth,
// 集群健康相关指标
HealthDrivesOfflineCount,
HealthDrivesOnlineCount,
HealthDrivesCount,
// IAM 相关指标
LastSyncDurationMillis,
PluginAuthnServiceFailedRequestsMinute,
PluginAuthnServiceLastFailSeconds,
PluginAuthnServiceLastSuccSeconds,
PluginAuthnServiceSuccAvgRttMsMinute,
PluginAuthnServiceSuccMaxRttMsMinute,
PluginAuthnServiceTotalRequestsMinute,
SinceLastSyncMillis,
SyncFailures,
SyncSuccesses,
// 通知相关指标
NotificationCurrentSendInProgress,
NotificationEventsErrorsTotal,
NotificationEventsSentTotal,
NotificationEventsSkippedTotal,
// 集群对象使用情况相关指标
UsageSinceLastUpdateSeconds,
UsageTotalBytes,
UsageObjectsCount,
UsageVersionsCount,
UsageDeleteMarkersCount,
UsageBucketsCount,
UsageSizeDistribution,
UsageVersionCountDistribution,
// 桶使用情况相关指标
UsageBucketQuotaTotalBytes,
UsageBucketTotalBytes,
UsageBucketObjectsCount,
UsageBucketVersionsCount,
UsageBucketDeleteMarkersCount,
UsageBucketObjectSizeDistribution,
UsageBucketObjectVersionCountDistribution,
// ILM 相关指标
IlmExpiryPendingTasks,
IlmTransitionActiveTasks,
IlmTransitionPendingTasks,
IlmTransitionMissedImmediateTasks,
IlmVersionsScanned,
// Webhook 日志相关指标
WebhookQueueLength,
WebhookTotalMessages,
WebhookFailedMessages,
// 复制相关指标
ReplicationAverageActiveWorkers,
ReplicationAverageQueuedBytes,
ReplicationAverageQueuedCount,
ReplicationAverageDataTransferRate,
ReplicationCurrentActiveWorkers,
ReplicationCurrentDataTransferRate,
ReplicationLastMinuteQueuedBytes,
ReplicationLastMinuteQueuedCount,
ReplicationMaxActiveWorkers,
ReplicationMaxQueuedBytes,
ReplicationMaxQueuedCount,
ReplicationMaxDataTransferRate,
ReplicationRecentBacklogCount,
// 扫描器相关指标
ScannerBucketScansFinished,
ScannerBucketScansStarted,
ScannerDirectoriesScanned,
ScannerObjectsScanned,
ScannerVersionsScanned,
ScannerLastActivitySeconds,
// CPU 系统相关指标
SysCPUAvgIdle,
SysCPUAvgIOWait,
SysCPULoad,
SysCPULoadPerc,
SysCPUNice,
SysCPUSteal,
SysCPUSystem,
SysCPUUser,
// 驱动器相关指标
DriveUsedBytes,
DriveFreeBytes,
DriveTotalBytes,
DriveUsedInodes,
DriveFreeInodes,
DriveTotalInodes,
DriveTimeoutErrorsTotal,
DriveIOErrorsTotal,
DriveAvailabilityErrorsTotal,
DriveWaitingIO,
DriveAPILatencyMicros,
DriveHealth,
DriveOfflineCount,
DriveOnlineCount,
DriveCount,
// iostat 相关指标
DriveReadsPerSec,
DriveReadsKBPerSec,
DriveReadsAwait,
DriveWritesPerSec,
DriveWritesKBPerSec,
DriveWritesAwait,
DrivePercUtil,
// 内存相关指标
MemTotal,
MemUsed,
MemUsedPerc,
MemFree,
MemBuffers,
MemCache,
MemShared,
MemAvailable,
// 网络相关指标
InternodeErrorsTotal,
InternodeDialErrorsTotal,
InternodeDialAvgTimeNanos,
InternodeSentBytesTotal,
InternodeRecvBytesTotal,
// 进程相关指标
ProcessLocksReadTotal,
ProcessLocksWriteTotal,
ProcessCPUTotalSeconds,
ProcessGoRoutineTotal,
ProcessIORCharBytes,
ProcessIOReadBytes,
ProcessIOWCharBytes,
ProcessIOWriteBytes,
ProcessStartTimeSeconds,
ProcessUptimeSeconds,
ProcessFileDescriptorLimitTotal,
ProcessFileDescriptorOpenTotal,
ProcessSyscallReadTotal,
ProcessSyscallWriteTotal,
ProcessResidentMemoryBytes,
ProcessVirtualMemoryBytes,
ProcessVirtualMemoryMaxBytes,
// 自定义指标
Custom(String),
}
impl MetricName {
#[allow(dead_code)]
pub fn as_str(&self) -> String {
match self {
Self::AuthTotal => "auth_total".to_string(),
@@ -317,10 +481,173 @@ impl MetricName {
Self::AuditTargetQueueLength => "target_queue_length".to_string(),
Self::AuditTotalMessages => "total_messages".to_string(),
/// metrics related to cluster configurations
// metrics related to cluster configurations
Self::ConfigRRSParity => "rrs_parity".to_string(),
Self::ConfigStandardParity => "standard_parity".to_string(),
// 纠删码集合相关指标
Self::ErasureSetOverallWriteQuorum => "overall_write_quorum".to_string(),
Self::ErasureSetOverallHealth => "overall_health".to_string(),
Self::ErasureSetReadQuorum => "read_quorum".to_string(),
Self::ErasureSetWriteQuorum => "write_quorum".to_string(),
Self::ErasureSetOnlineDrivesCount => "online_drives_count".to_string(),
Self::ErasureSetHealingDrivesCount => "healing_drives_count".to_string(),
Self::ErasureSetHealth => "health".to_string(),
Self::ErasureSetReadTolerance => "read_tolerance".to_string(),
Self::ErasureSetWriteTolerance => "write_tolerance".to_string(),
Self::ErasureSetReadHealth => "read_health".to_string(),
Self::ErasureSetWriteHealth => "write_health".to_string(),
// 集群健康相关指标
Self::HealthDrivesOfflineCount => "drives_offline_count".to_string(),
Self::HealthDrivesOnlineCount => "drives_online_count".to_string(),
Self::HealthDrivesCount => "drives_count".to_string(),
// IAM 相关指标
Self::LastSyncDurationMillis => "last_sync_duration_millis".to_string(),
Self::PluginAuthnServiceFailedRequestsMinute => "plugin_authn_service_failed_requests_minute".to_string(),
Self::PluginAuthnServiceLastFailSeconds => "plugin_authn_service_last_fail_seconds".to_string(),
Self::PluginAuthnServiceLastSuccSeconds => "plugin_authn_service_last_succ_seconds".to_string(),
Self::PluginAuthnServiceSuccAvgRttMsMinute => "plugin_authn_service_succ_avg_rtt_ms_minute".to_string(),
Self::PluginAuthnServiceSuccMaxRttMsMinute => "plugin_authn_service_succ_max_rtt_ms_minute".to_string(),
Self::PluginAuthnServiceTotalRequestsMinute => "plugin_authn_service_total_requests_minute".to_string(),
Self::SinceLastSyncMillis => "since_last_sync_millis".to_string(),
Self::SyncFailures => "sync_failures".to_string(),
Self::SyncSuccesses => "sync_successes".to_string(),
// 通知相关指标
Self::NotificationCurrentSendInProgress => "current_send_in_progress".to_string(),
Self::NotificationEventsErrorsTotal => "events_errors_total".to_string(),
Self::NotificationEventsSentTotal => "events_sent_total".to_string(),
Self::NotificationEventsSkippedTotal => "events_skipped_total".to_string(),
// 集群对象使用情况相关指标
Self::UsageSinceLastUpdateSeconds => "since_last_update_seconds".to_string(),
Self::UsageTotalBytes => "total_bytes".to_string(),
Self::UsageObjectsCount => "count".to_string(),
Self::UsageVersionsCount => "versions_count".to_string(),
Self::UsageDeleteMarkersCount => "delete_markers_count".to_string(),
Self::UsageBucketsCount => "buckets_count".to_string(),
Self::UsageSizeDistribution => "size_distribution".to_string(),
Self::UsageVersionCountDistribution => "version_count_distribution".to_string(),
// 桶使用情况相关指标
Self::UsageBucketQuotaTotalBytes => "quota_total_bytes".to_string(),
Self::UsageBucketTotalBytes => "total_bytes".to_string(),
Self::UsageBucketObjectsCount => "objects_count".to_string(),
Self::UsageBucketVersionsCount => "versions_count".to_string(),
Self::UsageBucketDeleteMarkersCount => "delete_markers_count".to_string(),
Self::UsageBucketObjectSizeDistribution => "object_size_distribution".to_string(),
Self::UsageBucketObjectVersionCountDistribution => "object_version_count_distribution".to_string(),
// ILM 相关指标
Self::IlmExpiryPendingTasks => "expiry_pending_tasks".to_string(),
Self::IlmTransitionActiveTasks => "transition_active_tasks".to_string(),
Self::IlmTransitionPendingTasks => "transition_pending_tasks".to_string(),
Self::IlmTransitionMissedImmediateTasks => "transition_missed_immediate_tasks".to_string(),
Self::IlmVersionsScanned => "versions_scanned".to_string(),
// Webhook 日志相关指标
Self::WebhookQueueLength => "queue_length".to_string(),
Self::WebhookTotalMessages => "total_messages".to_string(),
Self::WebhookFailedMessages => "failed_messages".to_string(),
// 复制相关指标
Self::ReplicationAverageActiveWorkers => "average_active_workers".to_string(),
Self::ReplicationAverageQueuedBytes => "average_queued_bytes".to_string(),
Self::ReplicationAverageQueuedCount => "average_queued_count".to_string(),
Self::ReplicationAverageDataTransferRate => "average_data_transfer_rate".to_string(),
Self::ReplicationCurrentActiveWorkers => "current_active_workers".to_string(),
Self::ReplicationCurrentDataTransferRate => "current_data_transfer_rate".to_string(),
Self::ReplicationLastMinuteQueuedBytes => "last_minute_queued_bytes".to_string(),
Self::ReplicationLastMinuteQueuedCount => "last_minute_queued_count".to_string(),
Self::ReplicationMaxActiveWorkers => "max_active_workers".to_string(),
Self::ReplicationMaxQueuedBytes => "max_queued_bytes".to_string(),
Self::ReplicationMaxQueuedCount => "max_queued_count".to_string(),
Self::ReplicationMaxDataTransferRate => "max_data_transfer_rate".to_string(),
Self::ReplicationRecentBacklogCount => "recent_backlog_count".to_string(),
// 扫描器相关指标
Self::ScannerBucketScansFinished => "bucket_scans_finished".to_string(),
Self::ScannerBucketScansStarted => "bucket_scans_started".to_string(),
Self::ScannerDirectoriesScanned => "directories_scanned".to_string(),
Self::ScannerObjectsScanned => "objects_scanned".to_string(),
Self::ScannerVersionsScanned => "versions_scanned".to_string(),
Self::ScannerLastActivitySeconds => "last_activity_seconds".to_string(),
// CPU 系统相关指标
Self::SysCPUAvgIdle => "avg_idle".to_string(),
Self::SysCPUAvgIOWait => "avg_iowait".to_string(),
Self::SysCPULoad => "load".to_string(),
Self::SysCPULoadPerc => "load_perc".to_string(),
Self::SysCPUNice => "nice".to_string(),
Self::SysCPUSteal => "steal".to_string(),
Self::SysCPUSystem => "system".to_string(),
Self::SysCPUUser => "user".to_string(),
// 驱动器相关指标
Self::DriveUsedBytes => "used_bytes".to_string(),
Self::DriveFreeBytes => "free_bytes".to_string(),
Self::DriveTotalBytes => "total_bytes".to_string(),
Self::DriveUsedInodes => "used_inodes".to_string(),
Self::DriveFreeInodes => "free_inodes".to_string(),
Self::DriveTotalInodes => "total_inodes".to_string(),
Self::DriveTimeoutErrorsTotal => "timeout_errors_total".to_string(),
Self::DriveIOErrorsTotal => "io_errors_total".to_string(),
Self::DriveAvailabilityErrorsTotal => "availability_errors_total".to_string(),
Self::DriveWaitingIO => "waiting_io".to_string(),
Self::DriveAPILatencyMicros => "api_latency_micros".to_string(),
Self::DriveHealth => "health".to_string(),
Self::DriveOfflineCount => "offline_count".to_string(),
Self::DriveOnlineCount => "online_count".to_string(),
Self::DriveCount => "count".to_string(),
// iostat 相关指标
Self::DriveReadsPerSec => "reads_per_sec".to_string(),
Self::DriveReadsKBPerSec => "reads_kb_per_sec".to_string(),
Self::DriveReadsAwait => "reads_await".to_string(),
Self::DriveWritesPerSec => "writes_per_sec".to_string(),
Self::DriveWritesKBPerSec => "writes_kb_per_sec".to_string(),
Self::DriveWritesAwait => "writes_await".to_string(),
Self::DrivePercUtil => "perc_util".to_string(),
// 内存相关指标
Self::MemTotal => "total".to_string(),
Self::MemUsed => "used".to_string(),
Self::MemUsedPerc => "used_perc".to_string(),
Self::MemFree => "free".to_string(),
Self::MemBuffers => "buffers".to_string(),
Self::MemCache => "cache".to_string(),
Self::MemShared => "shared".to_string(),
Self::MemAvailable => "available".to_string(),
// 网络相关指标
Self::InternodeErrorsTotal => "errors_total".to_string(),
Self::InternodeDialErrorsTotal => "dial_errors_total".to_string(),
Self::InternodeDialAvgTimeNanos => "dial_avg_time_nanos".to_string(),
Self::InternodeSentBytesTotal => "sent_bytes_total".to_string(),
Self::InternodeRecvBytesTotal => "recv_bytes_total".to_string(),
// 进程相关指标
Self::ProcessLocksReadTotal => "locks_read_total".to_string(),
Self::ProcessLocksWriteTotal => "locks_write_total".to_string(),
Self::ProcessCPUTotalSeconds => "cpu_total_seconds".to_string(),
Self::ProcessGoRoutineTotal => "go_routine_total".to_string(),
Self::ProcessIORCharBytes => "io_rchar_bytes".to_string(),
Self::ProcessIOReadBytes => "io_read_bytes".to_string(),
Self::ProcessIOWCharBytes => "io_wchar_bytes".to_string(),
Self::ProcessIOWriteBytes => "io_write_bytes".to_string(),
Self::ProcessStartTimeSeconds => "start_time_seconds".to_string(),
Self::ProcessUptimeSeconds => "uptime_seconds".to_string(),
Self::ProcessFileDescriptorLimitTotal => "file_descriptor_limit_total".to_string(),
Self::ProcessFileDescriptorOpenTotal => "file_descriptor_open_total".to_string(),
Self::ProcessSyscallReadTotal => "syscall_read_total".to_string(),
Self::ProcessSyscallWriteTotal => "syscall_write_total".to_string(),
Self::ProcessResidentMemoryBytes => "resident_memory_bytes".to_string(),
Self::ProcessVirtualMemoryBytes => "virtual_memory_bytes".to_string(),
Self::ProcessVirtualMemoryMaxBytes => "virtual_memory_max_bytes".to_string(),
Self::Custom(name) => name.clone(),
}
}

1
crates/obs/src/metrics/entry/metric_type.rs
View File

@@ -20,6 +20,7 @@ impl MetricType {
/// Convert the metric type to the Prometheus value type
/// In a Rust implementation, this might return the corresponding Prometheus Rust client type
#[allow(dead_code)]
pub fn to_prom(&self) -> &'static str {
match self {
Self::Counter => "counter.",

1
crates/obs/src/metrics/entry/namespace.rs
View File

@@ -5,6 +5,7 @@ pub enum MetricNamespace {
}
impl MetricNamespace {
#[allow(dead_code)]
pub fn as_str(&self) -> &'static str {
match self {
Self::RustFS => "rustfs",

3
crates/obs/src/metrics/entry/path_utils.rs
View File

@@ -1,7 +1,8 @@
/// Format the path to the metric name format
/// Replace '/' and '-' with '_'
#[allow(dead_code)]
pub fn format_path_to_metric_name(path: &str) -> String {
path.trim_start_matches('/').replace('/', "_").replace('-', "_")
path.trim_start_matches('/').replace(['/', '-'], "_")
}
#[cfg(test)]

48
crates/obs/src/metrics/entry/subsystem.rs
View File

@@ -1,27 +1,27 @@
use crate::metrics::entry::path_utils::format_path_to_metric_name;
/// The metrics subsystem is a subgroup of metrics within a namespace
/// 指标子系统，表示命名空间内指标的子分组
/// The metrics subsystem, which represents a subgroup of metrics within a namespace
#[derive(Debug, Clone, PartialEq, Eq, Hash)]
pub enum MetricSubsystem {
// API 相关子系统
// API related subsystems
ApiRequests,
// 桶相关子系统
// bucket related subsystems
BucketApi,
BucketReplication,
// 系统相关子系统
// system related subsystems
SystemNetworkInternode,
SystemDrive,
SystemMemory,
SystemCpu,
SystemProcess,
// 调试相关子系统
// debug related subsystems
DebugGo,
// 集群相关子系统
// cluster related subsystems
ClusterHealth,
ClusterUsageObjects,
ClusterUsageBuckets,
@@ -29,7 +29,7 @@ pub enum MetricSubsystem {
ClusterIam,
ClusterConfig,
// 其他服务相关子系统
// other service related subsystems
Ilm,
Audit,
LoggerWebhook,
@@ -37,32 +37,32 @@ pub enum MetricSubsystem {
Notification,
Scanner,
// 自定义路径
// Custom paths
Custom(String),
}
impl MetricSubsystem {
/// 获取原始路径字符串
/// Gets the original path string
pub fn path(&self) -> &str {
match self {
// API 相关子系统
// api related subsystems
Self::ApiRequests => "/api/requests",
// 桶相关子系统
// bucket related subsystems
Self::BucketApi => "/bucket/api",
Self::BucketReplication => "/bucket/replication",
// 系统相关子系统
// system related subsystems
Self::SystemNetworkInternode => "/system/network/internode",
Self::SystemDrive => "/system/drive",
Self::SystemMemory => "/system/memory",
Self::SystemCpu => "/system/cpu",
Self::SystemProcess => "/system/process",
// 调试相关子系统
// debug related subsystems
Self::DebugGo => "/debug/go",
// 集群相关子系统
// cluster related subsystems
Self::ClusterHealth => "/cluster/health",
Self::ClusterUsageObjects => "/cluster/usage/objects",
Self::ClusterUsageBuckets => "/cluster/usage/buckets",
@@ -70,7 +70,7 @@ impl MetricSubsystem {
Self::ClusterIam => "/cluster/iam",
Self::ClusterConfig => "/cluster/config",
// 其他服务相关子系统
// other service related subsystems
Self::Ilm => "/ilm",
Self::Audit => "/audit",
Self::LoggerWebhook => "/logger/webhook",
@@ -78,17 +78,18 @@ impl MetricSubsystem {
Self::Notification => "/notification",
Self::Scanner => "/scanner",
// 自定义路径
// Custom paths
Self::Custom(path) => path,
}
}
/// 获取格式化后的指标名称格式字符串
/// Get the formatted metric name format string
#[allow(dead_code)]
pub fn as_str(&self) -> String {
format_path_to_metric_name(self.path())
}
/// 从路径字符串创建子系统枚举
/// Create a subsystem enumeration from a path string
pub fn from_path(path: &str) -> Self {
match path {
// API 相关子系统
@@ -129,13 +130,14 @@ impl MetricSubsystem {
}
}
// 便利方法，直接创建自定义子系统
/// A convenient way to create custom subsystems directly
#[allow(dead_code)]
pub fn new(path: impl Into<String>) -> Self {
Self::Custom(path.into())
}
}
// 便于与字符串相互转换的实现
/// Implementations that facilitate conversion to and from strings
impl From<&str> for MetricSubsystem {
fn from(s: &str) -> Self {
Self::from_path(s)
@@ -158,10 +160,10 @@ impl std::fmt::Display for MetricSubsystem {
pub mod subsystems {
use super::MetricSubsystem;
// 集群基本路径常量
// cluster base path constant
pub const CLUSTER_BASE_PATH: &str = "/cluster";
// 快捷访问各子系统的常量
// Quick access to constants for each subsystem
pub const API_REQUESTS: MetricSubsystem = MetricSubsystem::ApiRequests;
pub const BUCKET_API: MetricSubsystem = MetricSubsystem::BucketApi;
pub const BUCKET_REPLICATION: MetricSubsystem = MetricSubsystem::BucketReplication;
@@ -198,7 +200,7 @@ mod tests {
assert_eq!(MetricSubsystem::BucketApi.as_str(), "bucket_api");
assert_eq!(MetricSubsystem::ClusterHealth.as_str(), "cluster_health");
// 测试自定义路径
// Test custom paths
let custom = MetricSubsystem::new("/custom/path-test");
assert_eq!(custom.as_str(), "custom_path_test");
}

44
crates/obs/src/metrics/ilm.rs Normal file
View File

@@ -0,0 +1,44 @@
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// ILM 相关指标描述符
lazy_static::lazy_static! {
pub static ref ILM_EXPIRY_PENDING_TASKS_MD: MetricDescriptor =
new_gauge_md(
MetricName::IlmExpiryPendingTasks,
"Number of pending ILM expiry tasks in the queue",
&[], // 无标签
subsystems::ILM
);
pub static ref ILM_TRANSITION_ACTIVE_TASKS_MD: MetricDescriptor =
new_gauge_md(
MetricName::IlmTransitionActiveTasks,
"Number of active ILM transition tasks",
&[], // 无标签
subsystems::ILM
);
pub static ref ILM_TRANSITION_PENDING_TASKS_MD: MetricDescriptor =
new_gauge_md(
MetricName::IlmTransitionPendingTasks,
"Number of pending ILM transition tasks in the queue",
&[], // 无标签
subsystems::ILM
);
pub static ref ILM_TRANSITION_MISSED_IMMEDIATE_TASKS_MD: MetricDescriptor =
new_counter_md(
MetricName::IlmTransitionMissedImmediateTasks,
"Number of missed immediate ILM transition tasks",
&[], // 无标签
subsystems::ILM
);
pub static ref ILM_VERSIONS_SCANNED_MD: MetricDescriptor =
new_counter_md(
MetricName::IlmVersionsScanned,
"Total number of object versions checked for ILM actions since server start",
&[], // 无标签
subsystems::ILM
);
}

35
crates/obs/src/metrics/logger_webhook.rs Normal file
View File

@@ -0,0 +1,35 @@
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 定义标签常量
pub const NAME_LABEL: &str = "name";
pub const ENDPOINT_LABEL: &str = "endpoint";
/// Webhook 日志相关指标描述符
lazy_static::lazy_static! {
// 所有 Webhook 指标使用的标签
static ref ALL_WEBHOOK_LABELS: [&'static str; 2] = [NAME_LABEL, ENDPOINT_LABEL];
pub static ref WEBHOOK_FAILED_MESSAGES_MD: MetricDescriptor =
new_counter_md(
MetricName::WebhookFailedMessages,
"Number of messages that failed to send",
&ALL_WEBHOOK_LABELS[..],
subsystems::LOGGER_WEBHOOK
);
pub static ref WEBHOOK_QUEUE_LENGTH_MD: MetricDescriptor =
new_gauge_md(
MetricName::WebhookQueueLength,
"Webhook queue length",
&ALL_WEBHOOK_LABELS[..],
subsystems::LOGGER_WEBHOOK
);
pub static ref WEBHOOK_TOTAL_MESSAGES_MD: MetricDescriptor =
new_counter_md(
MetricName::WebhookTotalMessages,
"Total number of messages sent to this target",
&ALL_WEBHOOK_LABELS[..],
subsystems::LOGGER_WEBHOOK
);
}

14
crates/obs/src/metrics/mod.rs
View File

@@ -1,8 +1,22 @@
mod audit;
mod bucket;
mod bucket_replication;
mod cluster_erasure_set;
mod cluster_health;
mod cluster_iam;
mod cluster_notification;
mod cluster_usage;
mod entry;
mod ilm;
mod logger_webhook;
mod replication;
mod request;
mod scanner;
mod system_cpu;
mod system_drive;
mod system_memory;
mod system_network;
mod system_process;
pub use entry::descriptor::MetricDescriptor;
pub use entry::metric_name::MetricName;

108
crates/obs/src/metrics/replication.rs Normal file
View File

@@ -0,0 +1,108 @@
use crate::metrics::{new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 复制相关指标描述符
lazy_static::lazy_static! {
pub static ref REPLICATION_AVERAGE_ACTIVE_WORKERS_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationAverageActiveWorkers,
"Average number of active replication workers",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_AVERAGE_QUEUED_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationAverageQueuedBytes,
"Average number of bytes queued for replication since server start",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_AVERAGE_QUEUED_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationAverageQueuedCount,
"Average number of objects queued for replication since server start",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_AVERAGE_DATA_TRANSFER_RATE_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationAverageDataTransferRate,
"Average replication data transfer rate in bytes/sec",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_CURRENT_ACTIVE_WORKERS_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationCurrentActiveWorkers,
"Total number of active replication workers",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_CURRENT_DATA_TRANSFER_RATE_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationCurrentDataTransferRate,
"Current replication data transfer rate in bytes/sec",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_LAST_MINUTE_QUEUED_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationLastMinuteQueuedBytes,
"Number of bytes queued for replication in the last full minute",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_LAST_MINUTE_QUEUED_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationLastMinuteQueuedCount,
"Number of objects queued for replication in the last full minute",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_MAX_ACTIVE_WORKERS_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationMaxActiveWorkers,
"Maximum number of active replication workers seen since server start",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_MAX_QUEUED_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationMaxQueuedBytes,
"Maximum number of bytes queued for replication since server start",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_MAX_QUEUED_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationMaxQueuedCount,
"Maximum number of objects queued for replication since server start",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_MAX_DATA_TRANSFER_RATE_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationMaxDataTransferRate,
"Maximum replication data transfer rate in bytes/sec seen since server start",
&[], // 无标签
subsystems::REPLICATION
);
pub static ref REPLICATION_RECENT_BACKLOG_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::ReplicationRecentBacklogCount,
"Total number of objects seen in replication backlog in the last 5 minutes",
&[], // 无标签
subsystems::REPLICATION
);
}

52
crates/obs/src/metrics/scanner.rs Normal file
View File

@@ -0,0 +1,52 @@
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 扫描器相关指标描述符
lazy_static::lazy_static! {
pub static ref SCANNER_BUCKET_SCANS_FINISHED_MD: MetricDescriptor =
new_counter_md(
MetricName::ScannerBucketScansFinished,
"Total number of bucket scans finished since server start",
&[], // 无标签
subsystems::SCANNER
);
pub static ref SCANNER_BUCKET_SCANS_STARTED_MD: MetricDescriptor =
new_counter_md(
MetricName::ScannerBucketScansStarted,
"Total number of bucket scans started since server start",
&[], // 无标签
subsystems::SCANNER
);
pub static ref SCANNER_DIRECTORIES_SCANNED_MD: MetricDescriptor =
new_counter_md(
MetricName::ScannerDirectoriesScanned,
"Total number of directories scanned since server start",
&[], // 无标签
subsystems::SCANNER
);
pub static ref SCANNER_OBJECTS_SCANNED_MD: MetricDescriptor =
new_counter_md(
MetricName::ScannerObjectsScanned,
"Total number of unique objects scanned since server start",
&[], // 无标签
subsystems::SCANNER
);
pub static ref SCANNER_VERSIONS_SCANNED_MD: MetricDescriptor =
new_counter_md(
MetricName::ScannerVersionsScanned,
"Total number of object versions scanned since server start",
&[], // 无标签
subsystems::SCANNER
);
pub static ref SCANNER_LAST_ACTIVITY_SECONDS_MD: MetricDescriptor =
new_gauge_md(
MetricName::ScannerLastActivitySeconds,
"Time elapsed (in seconds) since last scan activity.",
&[], // 无标签
subsystems::SCANNER
);
}

68
crates/obs/src/metrics/system_cpu.rs Normal file
View File

@@ -0,0 +1,68 @@
use crate::metrics::{new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// CPU 系统相关指标描述符
lazy_static::lazy_static! {
pub static ref SYS_CPU_AVG_IDLE_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPUAvgIdle,
"Average CPU idle time",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_AVG_IOWAIT_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPUAvgIOWait,
"Average CPU IOWait time",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_LOAD_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPULoad,
"CPU load average 1min",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_LOAD_PERC_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPULoadPerc,
"CPU load average 1min (percentage)",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_NICE_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPUNice,
"CPU nice time",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_STEAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPUSteal,
"CPU steal time",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_SYSTEM_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPUSystem,
"CPU system time",
&[], // 无标签
subsystems::SYSTEM_CPU
);
pub static ref SYS_CPU_USER_MD: MetricDescriptor =
new_gauge_md(
MetricName::SysCPUUser,
"CPU user time",
&[], // 无标签
subsystems::SYSTEM_CPU
);
}

192
crates/obs/src/metrics/system_drive.rs Normal file
View File

@@ -0,0 +1,192 @@
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 定义标签常量
pub const DRIVE_LABEL: &str = "drive";
pub const POOL_INDEX_LABEL: &str = "pool_index";
pub const SET_INDEX_LABEL: &str = "set_index";
pub const DRIVE_INDEX_LABEL: &str = "drive_index";
pub const API_LABEL: &str = "api";
/// 所有驱动器相关的标签
lazy_static::lazy_static! {
static ref ALL_DRIVE_LABELS: [&'static str; 4] = [DRIVE_LABEL, POOL_INDEX_LABEL, SET_INDEX_LABEL, DRIVE_INDEX_LABEL];
}
/// 驱动器相关指标描述符
lazy_static::lazy_static! {
pub static ref DRIVE_USED_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveUsedBytes,
"Total storage used on a drive in bytes",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_FREE_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveFreeBytes,
"Total storage free on a drive in bytes",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_TOTAL_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveTotalBytes,
"Total storage available on a drive in bytes",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_USED_INODES_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveUsedInodes,
"Total used inodes on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_FREE_INODES_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveFreeInodes,
"Total free inodes on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_TOTAL_INODES_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveTotalInodes,
"Total inodes available on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_TIMEOUT_ERRORS_MD: MetricDescriptor =
new_counter_md(
MetricName::DriveTimeoutErrorsTotal,
"Total timeout errors on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_IO_ERRORS_MD: MetricDescriptor =
new_counter_md(
MetricName::DriveIOErrorsTotal,
"Total I/O errors on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_AVAILABILITY_ERRORS_MD: MetricDescriptor =
new_counter_md(
MetricName::DriveAvailabilityErrorsTotal,
"Total availability errors (I/O errors, timeouts) on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_WAITING_IO_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveWaitingIO,
"Total waiting I/O operations on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_API_LATENCY_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveAPILatencyMicros,
"Average last minute latency in µs for drive API storage operations",
&[&ALL_DRIVE_LABELS[..], &[API_LABEL]].concat(),
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_HEALTH_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveHealth,
"Drive health (0 = offline, 1 = healthy, 2 = healing)",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_OFFLINE_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveOfflineCount,
"Count of offline drives",
&[],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_ONLINE_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveOnlineCount,
"Count of online drives",
&[],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_COUNT_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveCount,
"Count of all drives",
&[],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_READS_PER_SEC_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveReadsPerSec,
"Reads per second on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_READS_KB_PER_SEC_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveReadsKBPerSec,
"Kilobytes read per second on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_READS_AWAIT_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveReadsAwait,
"Average time for read requests served on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_WRITES_PER_SEC_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveWritesPerSec,
"Writes per second on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_WRITES_KB_PER_SEC_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveWritesKBPerSec,
"Kilobytes written per second on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_WRITES_AWAIT_MD: MetricDescriptor =
new_gauge_md(
MetricName::DriveWritesAwait,
"Average time for write requests served on a drive",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
pub static ref DRIVE_PERC_UTIL_MD: MetricDescriptor =
new_gauge_md(
MetricName::DrivePercUtil,
"Percentage of time the disk was busy",
&ALL_DRIVE_LABELS[..],
subsystems::SYSTEM_DRIVE
);
}

68
crates/obs/src/metrics/system_memory.rs Normal file
View File

@@ -0,0 +1,68 @@
use crate::metrics::{new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 内存相关指标描述符
lazy_static::lazy_static! {
pub static ref MEM_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemTotal,
"Total memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_USED_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemUsed,
"Used memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_USED_PERC_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemUsedPerc,
"Used memory percentage on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_FREE_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemFree,
"Free memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_BUFFERS_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemBuffers,
"Buffers memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_CACHE_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemCache,
"Cache memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_SHARED_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemShared,
"Shared memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
pub static ref MEM_AVAILABLE_MD: MetricDescriptor =
new_gauge_md(
MetricName::MemAvailable,
"Available memory on the node",
&[], // 无标签
subsystems::SYSTEM_MEMORY
);
}

44
crates/obs/src/metrics/system_network.rs Normal file
View File

@@ -0,0 +1,44 @@
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// 网络相关指标描述符
lazy_static::lazy_static! {
pub static ref INTERNODE_ERRORS_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::InternodeErrorsTotal,
"Total number of failed internode calls",
&[], // 无标签
subsystems::SYSTEM_NETWORK_INTERNODE
);
pub static ref INTERNODE_DIAL_ERRORS_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::InternodeDialErrorsTotal,
"Total number of internode TCP dial timeouts and errors",
&[], // 无标签
subsystems::SYSTEM_NETWORK_INTERNODE
);
pub static ref INTERNODE_DIAL_AVG_TIME_NANOS_MD: MetricDescriptor =
new_gauge_md(
MetricName::InternodeDialAvgTimeNanos,
"Average dial time of internode TCP calls in nanoseconds",
&[], // 无标签
subsystems::SYSTEM_NETWORK_INTERNODE
);
pub static ref INTERNODE_SENT_BYTES_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::InternodeSentBytesTotal,
"Total number of bytes sent to other peer nodes",
&[], // 无标签
subsystems::SYSTEM_NETWORK_INTERNODE
);
pub static ref INTERNODE_RECV_BYTES_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::InternodeRecvBytesTotal,
"Total number of bytes received from other peer nodes",
&[], // 无标签
subsystems::SYSTEM_NETWORK_INTERNODE
);
}

140
crates/obs/src/metrics/system_process.rs Normal file
View File

@@ -0,0 +1,140 @@
use crate::metrics::{new_counter_md, new_gauge_md, subsystems, MetricDescriptor, MetricName};
/// process related metric descriptors
lazy_static::lazy_static! {
pub static ref PROCESS_LOCKS_READ_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessLocksReadTotal,
"Number of current READ locks on this peer",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_LOCKS_WRITE_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessLocksWriteTotal,
"Number of current WRITE locks on this peer",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_CPU_TOTAL_SECONDS_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessCPUTotalSeconds,
"Total user and system CPU time spent in seconds",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_GO_ROUTINE_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessGoRoutineTotal,
"Total number of go routines running",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_IO_RCHAR_BYTES_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessIORCharBytes,
"Total bytes read by the process from the underlying storage system including cache, /proc/[pid]/io rchar",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_IO_READ_BYTES_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessIOReadBytes,
"Total bytes read by the process from the underlying storage system, /proc/[pid]/io read_bytes",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_IO_WCHAR_BYTES_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessIOWCharBytes,
"Total bytes written by the process to the underlying storage system including page cache, /proc/[pid]/io wchar",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_IO_WRITE_BYTES_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessIOWriteBytes,
"Total bytes written by the process to the underlying storage system, /proc/[pid]/io write_bytes",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_START_TIME_SECONDS_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessStartTimeSeconds,
"Start time for RustFS process in seconds since Unix epoc",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_UPTIME_SECONDS_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessUptimeSeconds,
"Uptime for RustFS process in seconds",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_FILE_DESCRIPTOR_LIMIT_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessFileDescriptorLimitTotal,
"Limit on total number of open file descriptors for the RustFS Server process",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_FILE_DESCRIPTOR_OPEN_TOTAL_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessFileDescriptorOpenTotal,
"Total number of open file descriptors by the RustFS Server process",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_SYSCALL_READ_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessSyscallReadTotal,
"Total read SysCalls to the kernel. /proc/[pid]/io syscr",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_SYSCALL_WRITE_TOTAL_MD: MetricDescriptor =
new_counter_md(
MetricName::ProcessSyscallWriteTotal,
"Total write SysCalls to the kernel. /proc/[pid]/io syscw",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_RESIDENT_MEMORY_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessResidentMemoryBytes,
"Resident memory size in bytes",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_VIRTUAL_MEMORY_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessVirtualMemoryBytes,
"Virtual memory size in bytes",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
pub static ref PROCESS_VIRTUAL_MEMORY_MAX_BYTES_MD: MetricDescriptor =
new_gauge_md(
MetricName::ProcessVirtualMemoryMaxBytes,
"Maximum virtual memory size in bytes",
&[], // 无标签
subsystems::SYSTEM_PROCESS
);
}