add metrics

crates/obs/src/metrics/audit.rs

@@ -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(

crates/obs/src/metrics/bucket.rs

@@ -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(

crates/obs/src/metrics/bucket_replication.rs

@@ -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(

crates/obs/src/metrics/cluster_erasure_set.rs

@@ -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
+        );
+}

crates/obs/src/metrics/cluster_health.rs

@@ -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
+        );
+}

crates/obs/src/metrics/cluster_iam.rs

@@ -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
+        );
+}

crates/obs/src/metrics/cluster_notification.rs

@@ -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
+        );
+}

crates/obs/src/metrics/cluster_usage.rs

@@ -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
+        );
+}

crates/obs/src/metrics/entry/descriptor.rs

@@ -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();

crates/obs/src/metrics/entry/metric_name.rs

@@ -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(),
         }
     }

crates/obs/src/metrics/entry/metric_type.rs

@@ -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.",

crates/obs/src/metrics/entry/namespace.rs

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

crates/obs/src/metrics/entry/path_utils.rs

@@ -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)]

crates/obs/src/metrics/entry/subsystem.rs

@@ -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");
     }

crates/obs/src/metrics/ilm.rs

@@ -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
+        );
+}

crates/obs/src/metrics/logger_webhook.rs

@@ -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
+        );
+}

crates/obs/src/metrics/mod.rs

@@ -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;

crates/obs/src/metrics/replication.rs

@@ -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
+        );
+}

crates/obs/src/metrics/scanner.rs

@@ -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
+        );
+}

crates/obs/src/metrics/system_cpu.rs

@@ -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
+        );
+}

crates/obs/src/metrics/system_drive.rs

@@ -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
+        );
+}

crates/obs/src/metrics/system_memory.rs

@@ -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
+        );
+}

crates/obs/src/metrics/system_network.rs

@@ -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
+        );
+}

crates/obs/src/metrics/system_process.rs

@@ -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
+        );
+}