feat(obs): add bounded metrics dimensions (#5645)

* feat(obs): add drive topology detail metrics Expose additive drive info, topology, state, and per-drive API metrics while preserving the existing drive metric label sets. Backlog: rustfs/backlog#1655 Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): preserve suspect drive runtime state Keep suspect as a bounded drive runtime state and avoid all-zero runtime_state samples for that storage health state. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): skip unknown drive inode samples Avoid exporting zero inode gauges for missing or stale drive snapshots and ignore zero-count API latency buckets. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add scanner source work detail metrics Expose additive scanner source and cycle work metrics with bounded server/source/state labels while leaving the existing aggregate scanner metrics unchanged. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add ilm action detail metrics Expose additive ILM action/state task metrics with a server label while preserving the existing aggregate ILM series. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add delivery target server metrics Expose additive audit and notification delivery target metrics with server labels and extend removed-target tombstones for the server-aware series. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add replication target flow metrics Expose additive bucket replication target sent and failed-flow metrics while preserving existing bucket aggregates and target backlog series. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add request server metrics Expose additive API request metrics with server labels while preserving the existing request and traffic metric label sets. Co-Authored-By: heihutu <heihutu@gmail.com> * style(obs): apply rustfmt to metrics changes Apply rustfmt output to the metrics dimension changes without altering behavior. Co-Authored-By: heihutu <heihutu@gmail.com> * style(obs): reuse audit target label constant Use the exported audit target_id label constant for legacy audit target metrics. Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): populate drive disk metrics Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add scanner bucket drive result metrics Co-Authored-By: heihutu <heihutu@gmail.com> * feat(obs): add replication proxy server metrics Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address metric liveness review Use checked division for drive API latency aggregation and keep recovered drive, scanner current-cycle, replication flow, audit target, and notification target series from retaining stale values. Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address metric dimension review Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address additional metric review Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): count drive calls at start Co-Authored-By: heihutu <heihutu@gmail.com> * fix(obs): address metrics dimension review Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address dimension review gaps Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address scanner review follow-ups Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address runtime review follow-ups Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): reduce disk metric contention Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): address runtime review follow-ups Co-Authored-By: heihutu <heihutu@gmail.com> * fix(metrics): retire stale dimension series Co-Authored-By: heihutu <heihutu@gmail.com> --------- Co-authored-by: heihutu <heihutu@gmail.com>
2026-09-03 10:48:13 +00:00 · 2026-08-03 09:03:34 +08:00
parent 988cd8adbb
commit 035ce5d784
36 changed files with 6282 additions and 666 deletions
@@ -29,9 +29,111 @@ pub const SET_INDEX_LABEL: &str = "set_index";
 pub const DRIVE_INDEX_LABEL: &str = "drive_index";
 /// API label
 pub const API_LABEL: &str = "api";
+/// Disk id label
+pub const DISK_ID_LABEL: &str = "disk_id";
+/// State label
+pub const STATE_LABEL: &str = "state";

 /// All drive-related labels
 pub const ALL_DRIVE_LABELS: [&str; 2] = [SERVER_LABEL, DRIVE_LABEL];
+/// Drive labels with erasure-set topology.
+pub const DRIVE_TOPOLOGY_LABELS: [&str; 5] = [
+    SERVER_LABEL,
+    DRIVE_LABEL,
+    POOL_INDEX_LABEL,
+    SET_INDEX_LABEL,
+    DRIVE_INDEX_LABEL,
+];
+/// Drive info labels.
+pub const DRIVE_INFO_LABELS: [&str; 6] = [
+    SERVER_LABEL,
+    DRIVE_LABEL,
+    POOL_INDEX_LABEL,
+    SET_INDEX_LABEL,
+    DRIVE_INDEX_LABEL,
+    DISK_ID_LABEL,
+];
+/// Drive topology labels with a state dimension.
+pub const DRIVE_TOPOLOGY_STATE_LABELS: [&str; 6] = [
+    SERVER_LABEL,
+    DRIVE_LABEL,
+    POOL_INDEX_LABEL,
+    SET_INDEX_LABEL,
+    DRIVE_INDEX_LABEL,
+    STATE_LABEL,
+];
+/// Drive topology labels with an API dimension.
+pub const DRIVE_TOPOLOGY_API_LABELS: [&str; 6] = [
+    SERVER_LABEL,
+    DRIVE_LABEL,
+    POOL_INDEX_LABEL,
+    SET_INDEX_LABEL,
+    DRIVE_INDEX_LABEL,
+    API_LABEL,
+];
+
+pub static DRIVE_INFO_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("info".to_string()),
+        "Drive topology and stable disk identity information",
+        &DRIVE_INFO_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});
+
+pub static DRIVE_RUNTIME_STATE_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("runtime_state".to_string()),
+        "Drive runtime state (1 for the active state label, 0 otherwise)",
+        &DRIVE_TOPOLOGY_STATE_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});
+
+pub static DRIVE_HEALING_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("healing".to_string()),
+        "Whether the drive is currently healing",
+        &DRIVE_TOPOLOGY_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});
+
+pub static DRIVE_SCANNING_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("scanning".to_string()),
+        "Whether the drive is currently being scanned",
+        &DRIVE_TOPOLOGY_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});
+
+pub static DRIVE_OFFLINE_DURATION_SECONDS_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("offline_duration_seconds".to_string()),
+        "Duration in seconds the drive has been offline",
+        &DRIVE_TOPOLOGY_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});
+
+pub static DRIVE_API_CALLS_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_counter_md(
+        MetricName::Custom("api_calls_total".to_string()),
+        "Total drive API calls by operation",
+        &DRIVE_TOPOLOGY_API_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});
+
+pub static DRIVE_API_LATENCY_BY_API_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("api_latency_by_api_micros".to_string()),
+        "Average last minute drive API latency in microseconds by operation",
+        &DRIVE_TOPOLOGY_API_LABELS,
+        subsystems::SYSTEM_DRIVE,
+    )
+});

 pub static DRIVE_USED_BYTES_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
    new_gauge_md(