Files
rustfs/deploy/observability/grafana/rustfs-kms-observability.json
T

794 lines
23 KiB
JSON

{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"description": "KMS backend operation metrics emitted at the operation-policy choke point (crates/kms/src/policy.rs). All label values are bounded enums or fixed call-site tokens; key identifiers, key material, and tokens never appear in labels. These metrics do not carry the RustFS `server` label — use your scrape topology (job/instance or promoted OTel resource attributes) to split by node. Alert response procedures: docs/operations/kms-observability-runbook.md.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"liveNow": false,
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Terminal outcomes of KMS backend operations. `fatal` is non-retryable; `budget_exhausted` and `deadline_exceeded` mean retry limits ran out; `backpressure_timeout` and `backpressure_rejected` are admission failures; `circuit_open` means the breaker opened or rejected the operation; `cancelled` is normal during shutdown.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"id": 1,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (outcome) (rate(rustfs_kms_backend_operations_total{operation=~\"$operation\"}[$__rate_interval]))",
"legendFormat": "{{outcome}}",
"range": true,
"refId": "A"
}
],
"title": "Backend Operation Rate by Outcome",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Operation names are static per-call-site identifiers (e.g. vault_kv2_read_key_version, vault_transit_encrypt, vault_login). `op_class` distinguishes read_idempotent, mutating_non_idempotent, and auth operations.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"id": 2,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (operation, op_class) (rate(rustfs_kms_backend_operations_total{operation=~\"$operation\"}[$__rate_interval]))",
"legendFormat": "{{operation}} ({{op_class}})",
"range": true,
"refId": "A"
}
],
"title": "Backend Operation Rate by Operation",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Share of operations that terminated in fatal, budget_exhausted, deadline_exceeded, backpressure_timeout, backpressure_rejected, or circuit_open. The cancelled outcome is plotted separately because shutdown windows legitimately spike it. The ratio is meaningless at near-zero traffic — read it together with the operation rate panels.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"max": 1,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "percentunit"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"id": 3,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(rustfs_kms_backend_operations_total{outcome!~\"success|cancelled\",operation=~\"$operation\"}[$__rate_interval])) / clamp_min(sum(rate(rustfs_kms_backend_operations_total{operation=~\"$operation\"}[$__rate_interval])), 1e-9)",
"legendFormat": "non-success (excl. cancelled)",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum(rate(rustfs_kms_backend_operations_total{outcome=\"cancelled\",operation=~\"$operation\"}[$__rate_interval])) / clamp_min(sum(rate(rustfs_kms_backend_operations_total{operation=~\"$operation\"}[$__rate_interval])), 1e-9)",
"legendFormat": "cancelled",
"range": true,
"refId": "B"
}
],
"title": "Non-Success Outcome Ratio",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Per-attempt failures by retry classification. retryable_conn covers connection-level failures, retryable_status covers retryable backend status codes, attempt_timeout covers attempts cut off by the per-attempt timeout, and fatal covers non-retryable failures (auth, permission, malformed request). Sustained fatal traffic is always actionable.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "ops"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 8
},
"id": 4,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (error_class) (rate(rustfs_kms_backend_attempt_failures_total{operation=~\"$operation\"}[$__rate_interval]))",
"legendFormat": "{{error_class}}",
"range": true,
"refId": "A"
}
],
"title": "Attempt Failure Rate by Error Class",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Wall-clock duration of whole operations, including retries and backoff sleeps. A rising p99 with a flat p50 usually means a slow retry tail (backend degradation), not a uniform slowdown.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 16
},
"id": 5,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "histogram_quantile(0.50, sum by (le) (rate(rustfs_kms_backend_operation_duration_seconds_bucket{operation=~\"$operation\"}[$__rate_interval])))",
"legendFormat": "p50",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by (le) (rate(rustfs_kms_backend_operation_duration_seconds_bucket{operation=~\"$operation\"}[$__rate_interval])))",
"legendFormat": "p99",
"range": true,
"refId": "B"
}
],
"title": "Operation Duration p50 / p99",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "p99 duration split by operation. Auth operations (vault_login, vault_token_renew) and mutating writes are expected to sit higher than idempotent reads.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "s"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 16
},
"id": 6,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by (le, operation) (rate(rustfs_kms_backend_operation_duration_seconds_bucket{operation=~\"$operation\"}[$__rate_interval])))",
"legendFormat": "{{operation}}",
"range": true,
"refId": "A"
}
],
"title": "Operation Duration p99 by Operation",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Attempts one operation used before completing. Healthy operations average close to 1. A rising average or p99 means the retry policy is absorbing backend failures — read together with the attempt-failure panel to see the failure class.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 12,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 4,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "never",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 24
},
"id": 7,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "sum by (operation) (rate(rustfs_kms_backend_operation_attempts_sum{operation=~\"$operation\"}[$__rate_interval])) / clamp_min(sum by (operation) (rate(rustfs_kms_backend_operation_attempts_count{operation=~\"$operation\"}[$__rate_interval])), 1e-9)",
"legendFormat": "{{operation}} avg",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"expr": "histogram_quantile(0.99, sum by (le) (rate(rustfs_kms_backend_operation_attempts_bucket{operation=~\"$operation\"}[$__rate_interval])))",
"legendFormat": "p99 (all operations)",
"range": true,
"refId": "B"
}
],
"title": "Operation Attempts Distribution",
"type": "timeseries"
},
{
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 24
},
"id": 8,
"options": {
"code": {
"language": "plaintext",
"showLineNumbers": false,
"showMiniMap": false
},
"content": "Placeholder for KMS metrics planned by sibling changes of rustfs/backlog#1584 that have **not landed yet**. Do not add panels for these names until the emitting code is merged, or the panels will render empty and mask real gaps.\n\n- TODO: key-cache effectiveness — hit/miss counters, entry gauge, eviction counter (replaces the former hardcoded-zero miss stat).\n- TODO: key lifecycle — pending-deletion/tombstone gauges from the deletion worker sweep, aggregate rotation-age gauge.\n- TODO: Vault credentials — token TTL remaining and fail-closed state gauges.\n- TODO: synthetic backend probe — probe outcome/failure-class metrics feeding the readiness cache.\n\nWhen a family lands, replace one bullet with a real panel and keep this list in sync with docs/operations/kms-observability-runbook.md (Coverage gaps).",
"mode": "markdown"
},
"title": "Planned Panels (TODO — metrics not landed yet)",
"type": "text"
}
],
"refresh": "30s",
"schemaVersion": 39,
"style": "dark",
"tags": [
"rustfs",
"observability",
"kms"
],
"templating": {
"list": [
{
"current": {},
"hide": 0,
"includeAll": false,
"label": "Prometheus",
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"allValue": ".*",
"current": {
"selected": true,
"text": "All",
"value": "$__all"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values(rustfs_kms_backend_operations_total, operation)",
"hide": 0,
"includeAll": true,
"label": "KMS operation",
"multi": true,
"name": "operation",
"options": [],
"query": "label_values(rustfs_kms_backend_operations_total, operation)",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"type": "query"
}
]
},
"time": {
"from": "now-6h",
"to": "now"
},
"timepicker": {},
"timezone": "",
"title": "RustFS KMS Observability",
"uid": "rustfs-kms-observability",
"version": 1,
"weekStart": ""
}