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 18:55:39 +00:00 · 2026-08-03 09:03:34 +08:00
parent 988cd8adbb
commit 035ce5d784
36 changed files with 6282 additions and 666 deletions
@@ -17,6 +17,50 @@
 use crate::{MetricDescriptor, MetricName, new_counter_md, new_gauge_md, subsystems};
 use std::sync::LazyLock;

+pub const SERVER_LABEL: &str = "server";
+pub const SOURCE_LABEL: &str = "source";
+pub const STATE_LABEL: &str = "state";
+pub const CYCLE_SCOPE_LABEL: &str = "cycle_scope";
+pub const BUCKET_LABEL: &str = "bucket";
+pub const DRIVE_LABEL: &str = "drive";
+pub const RESULT_LABEL: &str = "result";
+
+pub static SCANNER_SOURCE_WORK_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_counter_md(
+        MetricName::Custom("source_work_total".to_string()),
+        "Total scanner work by source and state since server start",
+        &[SERVER_LABEL, SOURCE_LABEL, STATE_LABEL],
+        subsystems::SCANNER,
+    )
+});
+
+pub static SCANNER_CYCLE_SOURCE_WORK_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("cycle_source_work".to_string()),
+        "Scanner work by cycle scope, source, and state",
+        &[SERVER_LABEL, CYCLE_SCOPE_LABEL, SOURCE_LABEL, STATE_LABEL],
+        subsystems::SCANNER,
+    )
+});
+
+pub static SCANNER_BUCKET_DRIVE_RESULT_TOTAL_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_counter_md(
+        MetricName::Custom("bucket_drive_result_total".to_string()),
+        "Total scanner bucket-drive scan results by server, bucket, drive, and result",
+        &[SERVER_LABEL, BUCKET_LABEL, DRIVE_LABEL, RESULT_LABEL],
+        subsystems::SCANNER,
+    )
+});
+
+pub static SCANNER_CYCLE_BUCKET_DRIVE_RESULT_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
+    new_gauge_md(
+        MetricName::Custom("cycle_bucket_drive_result".to_string()),
+        "Scanner bucket-drive scan results by cycle scope, server, bucket, drive, and result",
+        &[SERVER_LABEL, CYCLE_SCOPE_LABEL, BUCKET_LABEL, DRIVE_LABEL, RESULT_LABEL],
+        subsystems::SCANNER,
+    )
+});
+
 pub static SCANNER_BUCKET_SCANS_FINISHED_MD: LazyLock<MetricDescriptor> = LazyLock::new(|| {
    new_counter_md(
        MetricName::ScannerBucketScansFinished,