Files
infra-observability/k8s/grafana/dashboards/obs-keycloak.json
T
Stéphane Tailland eb35419ad0 Split log search into access, application and audit dashboards
One consolidated search compromised on all three questions at once. It also
had a real defect: the Source selector carried `.+` as its All value, so
choosing "All" widened the query back to every stream in the cluster and the
scope preset only ever populated the picker. MongoDB and cert-manager showed up
in what was meant to be an application view.

Each query now carries both `job=~"${source:regex}"` and a literal job matcher,
so the selector actually restricts rather than widens.

The three kinds are subtracted from each other rather than merely filtered:
application logs exclude Keycloak's access-log and events loggers by name, the
Django container's NCSA lines by shape, and the Kong containers' stray access
lines by requiring the nginx date prefix.

Levels are read from the line rather than taken from Loki's detected_level.
That inference marks 78% of the Kong gateway output `unknown` even though every
one of those lines states [notice] or [warn], so filtering on it hid most of
the gateway's own logs. Each parser extracts the level and lowercases it, which
puts nginx's notice, Keycloak's INFO and LibreChat's info on one scale — and
removes the need for an `unknown` entry in the selector.

Applies move to server-side. Client-side apply stores a full copy of each
object in the last-applied-configuration annotation, capped at 256KB, and the
dashboard ConfigMap passed that at eight dashboards; the failure surfaced as
"metadata.annotations: Too long". Server-side apply tracks field ownership in
metadata instead, moving the ceiling to etcd's ~1MB.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-25 18:48:11 +02:00

1861 lines
45 KiB
JSON

{
"uid": "obs-keycloak",
"title": "Keycloak — Overview",
"description": "HTTP traffic, JVM runtime, connection pool and logs for Keycloak. Latencies come from Tempo span metrics: the Micrometer timer exposes no buckets.",
"tags": [
"observability",
"keycloak",
"application",
"metrics",
"logs"
],
"editable": false,
"schemaVersion": 39,
"version": 1,
"refresh": "30s",
"time": {
"from": "now-6h",
"to": "now"
},
"timezone": "browser",
"templating": {
"list": []
},
"panels": [
{
"id": 1,
"type": "row",
"title": "Overview",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"panels": []
},
{
"id": 2,
"type": "stat",
"title": "Requests / s",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 5,
"w": 6,
"x": 0,
"y": 1
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(http_server_requests_seconds_count{namespace=\"keycloak\"}[$__rate_interval]))",
"instant": false
}
],
"fieldConfig": {
"defaults": {
"unit": "reqps",
"mappings": [],
"decimals": 2,
"color": {
"mode": "fixed",
"fixedColor": "blue"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "blue",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "value",
"graphMode": "area",
"textMode": "auto",
"justifyMode": "auto"
}
},
{
"id": 3,
"type": "stat",
"title": "Error rate",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 5,
"w": 6,
"x": 6,
"y": 1
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "(sum(rate(http_server_requests_seconds_count{namespace=\"keycloak\",outcome=~\"CLIENT_ERROR|SERVER_ERROR\"}[$__rate_interval])) or vector(0)) / clamp_min(sum(rate(http_server_requests_seconds_count{namespace=\"keycloak\"}[$__rate_interval])), 0.001)",
"instant": false
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"mappings": [],
"decimals": 2,
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "orange",
"value": 0.01
},
{
"color": "red",
"value": 0.05
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "value",
"graphMode": "area",
"textMode": "auto",
"justifyMode": "auto"
},
"description": "Share of 4xx and 5xx responses. `or vector(0)` is required: with no errors at all the numerator is an empty vector, and empty/x stays empty -- the panel would read \"No data\" instead of 0%. clamp_min covers the zero-traffic case."
},
{
"id": 4,
"type": "stat",
"title": "Latency p95",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 5,
"w": 6,
"x": 12,
"y": 1
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_spanmetrics_latency_bucket{service=\"keycloak\",span_kind=\"SPAN_KIND_SERVER\"}[$__rate_interval])))",
"instant": false
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"mappings": [],
"decimals": 3,
"color": {
"mode": "thresholds"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "orange",
"value": 0.5
},
{
"color": "red",
"value": 2
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "value",
"graphMode": "area",
"textMode": "auto",
"justifyMode": "auto"
},
"description": "Source: span metrics generated by Tempo. Keycloak's Micrometer timer exposes neither buckets nor quantiles, so no percentile is computable from /metrics."
},
{
"id": 5,
"type": "stat",
"title": "JVM heap used",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 5,
"w": 6,
"x": 18,
"y": 1
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(jvm_memory_used_bytes{namespace=\"keycloak\",area=\"heap\"})",
"instant": false
}
],
"fieldConfig": {
"defaults": {
"unit": "bytes",
"mappings": [],
"color": {
"mode": "fixed",
"fixedColor": "purple"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "purple",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"colorMode": "value",
"graphMode": "area",
"textMode": "auto",
"justifyMode": "auto"
}
},
{
"id": 6,
"type": "row",
"title": "HTTP traffic",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 6
},
"panels": []
},
{
"id": 7,
"type": "timeseries",
"title": "Requests by outcome",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 7
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (outcome) (rate(http_server_requests_seconds_count{namespace=\"keycloak\"}[$__rate_interval]))",
"legendFormat": "{{outcome}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "reqps",
"custom": {
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 70,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "linear",
"stacking": {
"mode": "normal",
"group": "A"
}
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "2xx"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "green"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "3xx"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "blue"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "4xx"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "orange"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "5xx"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "red"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "SUCCESS"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "green"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "REDIRECTION"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "blue"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "CLIENT_ERROR"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "orange"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "SERVER_ERROR"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "red"
}
}
]
}
]
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "Stacked: total height is throughput, status colours isolate the failing share."
},
{
"id": 8,
"type": "timeseries",
"title": "Latency (Tempo span metrics)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 7
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le) (rate(traces_spanmetrics_latency_bucket{service=\"keycloak\",span_kind=\"SPAN_KIND_SERVER\"}[$__rate_interval])))",
"legendFormat": "p50"
},
{
"refId": "B",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_spanmetrics_latency_bucket{service=\"keycloak\",span_kind=\"SPAN_KIND_SERVER\"}[$__rate_interval])))",
"legendFormat": "p95"
},
{
"refId": "C",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le) (rate(traces_spanmetrics_latency_bucket{service=\"keycloak\",span_kind=\"SPAN_KIND_SERVER\"}[$__rate_interval])))",
"legendFormat": "p99"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 0,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "p50"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "light-blue"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "p95"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "blue"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "p99"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "dark-blue"
}
}
]
}
]
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "One hue from light to dark: p50/p95/p99 are ordered magnitudes of the same measure, not distinct entities."
},
{
"id": 9,
"type": "bargauge",
"title": "Busiest endpoints",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 15
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "topk(10, sum by (uri) (rate(http_server_requests_seconds_count{namespace=\"keycloak\"}[$__rate_interval])))",
"legendFormat": "{{uri}}",
"instant": true
}
],
"fieldConfig": {
"defaults": {
"unit": "reqps",
"min": 0,
"mappings": [],
"color": {
"mode": "continuous-BlPu"
},
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "blue",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"displayMode": "gradient",
"orientation": "horizontal",
"showUnfilled": true,
"valueMode": "text",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
}
}
},
{
"id": 10,
"type": "timeseries",
"title": "Mean latency per endpoint",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 15
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "topk(10, sum by (uri) (rate(http_server_requests_seconds_sum{namespace=\"keycloak\"}[$__rate_interval])) / clamp_min(sum by (uri) (rate(http_server_requests_seconds_count{namespace=\"keycloak\"}[$__rate_interval])), 0.001))",
"legendFormat": "{{uri}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 0,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "A mean, not a percentile: that is all a bucket-less timer allows. A mean hides the tail -- for the tail, see the p99 panel."
},
{
"id": 11,
"type": "row",
"title": "JVM runtime",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 23
},
"panels": []
},
{
"id": 12,
"type": "timeseries",
"title": "JVM memory by area",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 0,
"y": 24
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (area) (jvm_memory_used_bytes{namespace=\"keycloak\"})",
"legendFormat": "{{area}}"
},
{
"refId": "B",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(jvm_memory_max_bytes{namespace=\"keycloak\",area=\"heap\"} > 0)",
"legendFormat": "max heap"
}
],
"fieldConfig": {
"defaults": {
"unit": "bytes",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 8,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 13,
"type": "timeseries",
"title": "GC pauses",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 8,
"y": 24
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(rate(jvm_gc_pause_seconds_sum{namespace=\"keycloak\"}[$__rate_interval])) / clamp_min(sum(rate(jvm_gc_pause_seconds_count{namespace=\"keycloak\"}[$__rate_interval])), 0.001)",
"legendFormat": "mean duration"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 8,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0,
"decimals": 4
},
"overrides": []
},
"options": {
"legend": {
"showLegend": false,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "Mean GC pause duration. Drift here usually precedes a rise in p99 latency."
},
{
"id": 14,
"type": "timeseries",
"title": "JVM threads",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 8,
"w": 8,
"x": 16,
"y": 24
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(jvm_threads_live_threads{namespace=\"keycloak\"})",
"legendFormat": "live"
},
{
"refId": "B",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(jvm_threads_daemon_threads{namespace=\"keycloak\"})",
"legendFormat": "daemon"
},
{
"refId": "C",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(jvm_threads_peak_threads{namespace=\"keycloak\"})",
"legendFormat": "peak"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 0,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 15,
"type": "row",
"title": "PostgreSQL connection pool (Agroal)",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 32
},
"panels": []
},
{
"id": 16,
"type": "timeseries",
"title": "Pool connections",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 33
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (datasource) (agroal_active_count{namespace=\"keycloak\"})",
"legendFormat": "active"
},
{
"refId": "B",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (datasource) (agroal_available_count{namespace=\"keycloak\"})",
"legendFormat": "available"
},
{
"refId": "C",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (datasource) (agroal_max_used_count{namespace=\"keycloak\"})",
"legendFormat": "peak used"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 0,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 17,
"type": "timeseries",
"title": "Waiting for a connection",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 33
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(agroal_awaiting_count{namespace=\"keycloak\"})",
"legendFormat": "requests waiting"
},
{
"refId": "B",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(agroal_blocking_time_average_milliseconds{namespace=\"keycloak\"})",
"legendFormat": "mean blocking time (ms)"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 0,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "A non-zero waiting count means the pool is saturated: requests queue before they even reach PostgreSQL."
},
{
"id": 18,
"type": "row",
"title": "Logs",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 40
},
"panels": []
},
{
"id": 19,
"type": "timeseries",
"title": "Log volume by level",
"datasource": {
"type": "loki",
"uid": "loki"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 41
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "loki",
"uid": "loki"
},
"expr": "sum by (detected_level) (count_over_time({namespace=\"keycloak\",container=\"keycloak\"}[$__auto]))",
"legendFormat": "{{detected_level}}",
"queryType": "range"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0,
"mappings": [],
"color": {
"mode": "palette-classic"
},
"custom": {
"drawStyle": "bars",
"lineWidth": 1,
"fillOpacity": 80,
"showPoints": "never",
"barAlignment": 0,
"stacking": {
"mode": "normal",
"group": "A"
},
"axisLabel": "",
"axisPlacement": "auto"
}
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "critical"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "dark-red"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "error"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "red"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "warn"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "orange"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "info"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "green"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "debug"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "blue"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "unknown"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "text"
}
}
]
}
]
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"sum"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "`detected_level` is inferred by Loki at ingestion, so one query works across every log format."
},
{
"id": 20,
"type": "timeseries",
"title": "Errors by container (whole namespace)",
"datasource": {
"type": "loki",
"uid": "loki"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 41
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "loki",
"uid": "loki"
},
"expr": "sum by (container) (count_over_time({namespace=\"keycloak\"} | detected_level =~ \"error|critical\" [$__auto]))",
"legendFormat": "{{container}}",
"queryType": "range"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0,
"mappings": [],
"color": {
"mode": "palette-classic"
},
"custom": {
"drawStyle": "bars",
"lineWidth": 1,
"fillOpacity": 80,
"showPoints": "never",
"barAlignment": 0,
"stacking": {
"mode": "normal",
"group": "A"
},
"axisLabel": "",
"axisPlacement": "auto"
}
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"sum"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "Namespace-wide so the datastore's failures show up next to the application's."
},
{
"id": 26,
"type": "table",
"title": "Errors and warnings",
"datasource": {
"type": "loki",
"uid": "loki"
},
"gridPos": {
"h": 11,
"w": 24,
"x": 0,
"y": 49
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "loki",
"uid": "loki"
},
"expr": "{namespace=\"keycloak\", container=\"keycloak\"} | json | detected_level =~ \"error|critical|warn\"",
"queryType": "range",
"maxLines": 500
}
],
"transformations": [
{
"id": "extractFields",
"options": {
"source": "labels",
"replace": false
}
},
{
"id": "filterFieldsByName",
"options": {
"include": {
"pattern": "^(timestamp|body|level|loggerName|message|threadName)$"
}
}
},
{
"id": "organize",
"options": {
"excludeByName": {},
"indexByName": {
"Time": 0,
"level": 1,
"loggerName": 2,
"message": 3,
"threadName": 4,
"body": 5
},
"renameByName": {
"level": "Level",
"loggerName": "Logger",
"message": "Message",
"threadName": "Thread",
"body": "Raw record",
"timestamp": "Time"
}
}
}
],
"fieldConfig": {
"defaults": {
"custom": {
"align": "auto",
"cellOptions": {
"type": "auto"
},
"inspect": true,
"filterable": true
},
"mappings": []
},
"overrides": [
{
"matcher": {
"id": "byName",
"options": "Level"
},
"properties": [
{
"id": "custom.width",
"value": 90
},
{
"id": "mappings",
"value": [
{
"type": "regex",
"options": {
"pattern": "^(fatal|FATAL|Fatal|critical|CRITICAL|Critical)$",
"result": {
"color": "dark-red",
"index": 0
}
}
},
{
"type": "regex",
"options": {
"pattern": "^(error|ERROR|Error)$",
"result": {
"color": "red",
"index": 1
}
}
},
{
"type": "regex",
"options": {
"pattern": "^(warn|WARN|Warn|warning|WARNING|Warning)$",
"result": {
"color": "orange",
"index": 2
}
}
},
{
"type": "regex",
"options": {
"pattern": "^(info|INFO|Info)$",
"result": {
"color": "green",
"index": 3
}
}
},
{
"type": "regex",
"options": {
"pattern": "^(debug|DEBUG|Debug)$",
"result": {
"color": "blue",
"index": 4
}
}
}
]
},
{
"id": "custom.cellOptions",
"value": {
"type": "color-text"
}
}
]
},
{
"matcher": {
"id": "byName",
"options": "Logger"
},
"properties": [
{
"id": "custom.width",
"value": 280
}
]
},
{
"matcher": {
"id": "byName",
"options": "Thread"
},
"properties": [
{
"id": "custom.width",
"value": 160
}
]
},
{
"matcher": {
"id": "byName",
"options": "Raw record"
},
"properties": [
{
"id": "custom.width",
"value": 260
}
]
}
]
},
"options": {
"showHeader": true,
"cellHeight": "sm",
"footer": {
"show": false,
"reducer": [
"sum"
],
"countRows": false,
"fields": ""
},
"sortBy": [
{
"displayName": "Time",
"desc": true
}
]
},
"description": "Keycloak logs JSON, so the fields come straight from `| json`. Scoped to the Keycloak container: PostgreSQL in the same namespace is not JSON and would parse to empty columns."
},
{
"id": 27,
"type": "row",
"title": "Raw log lines",
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 60
},
"panels": [
{
"id": 21,
"type": "logs",
"title": "Raw log lines",
"datasource": {
"type": "loki",
"uid": "loki"
},
"gridPos": {
"h": 11,
"w": 24,
"x": 0,
"y": 61
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "loki",
"uid": "loki"
},
"expr": "{namespace=\"keycloak\"} | detected_level =~ \"error|critical|warn\"",
"queryType": "range"
}
],
"options": {
"showTime": true,
"showLabels": false,
"showCommonLabels": false,
"wrapLogMessage": true,
"prettifyLogMessage": false,
"sortOrder": "Descending",
"dedupStrategy": "none",
"enableLogDetails": true
},
"description": "Kept alongside the table: the logs panel renders ANSI colour, expands a record's detail inline, tails live, and turns a trace id into a link to Tempo — none of which a table can do. Collapsed so it stays out of the way until needed."
}
]
},
{
"id": 22,
"type": "row",
"title": "Container resources",
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 61
},
"panels": []
},
{
"id": 23,
"type": "timeseries",
"title": "CPU per container",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 62
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (pod, container) (rate(container_cpu_usage_seconds_total{namespace=\"keycloak\",pod=~\"keycloak-.*\",container!=\"\"}[$__rate_interval]))",
"legendFormat": "{{pod}}/{{container}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 8,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0,
"decimals": 3
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "Cores consumed."
},
{
"id": 24,
"type": "timeseries",
"title": "Memory per container",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 62
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (pod, container) (container_memory_working_set_bytes{namespace=\"keycloak\",pod=~\"keycloak-.*\",container!=\"\"})",
"legendFormat": "{{pod}}/{{container}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "bytes",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 8,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "Working set: what the kernel cannot reclaim under pressure. This is the figure the OOM killer compares against the limit."
},
{
"id": 25,
"type": "timeseries",
"title": "Restarts over the window",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 62
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum by (pod) (changes(container_start_time_seconds{namespace=\"keycloak\",pod=~\"keycloak-.*\",container!=\"\"}[$__range]))",
"legendFormat": "{{pod}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 0,
"showPoints": "never",
"pointSize": 8,
"gradientMode": "none",
"spanNulls": false,
"axisLabel": "",
"axisPlacement": "auto",
"lineInterpolation": "smooth"
},
"mappings": [],
"color": {
"mode": "palette-classic"
},
"min": 0,
"decimals": 0
},
"overrides": []
},
"options": {
"legend": {
"showLegend": true,
"displayMode": "table",
"placement": "bottom",
"calcs": [
"mean",
"max"
]
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"description": "Container start count over the displayed window. Stays at 0 in nominal operation."
}
]
}