Stéphane Tailland
3937b4f366
Deploys the whole stack into the observability namespace of the local cluster with Kustomize alone — no helm install, no dashboard created by hand in the UI. The Makefile carries every command: deploy, dashboards, diagnostics, PVC flush, teardown. Dashboards are files, never UI objects. Each carries a stable uid, which is what keeps URLs, cross-links and alerts alive across redeployments, and references datasources by stable uid rather than by name. The dashboard ConfigMap is generated without a name-suffix hash so applying it updates it in place and Grafana reloads without a restart, while the provisioning ConfigMaps keep their hash precisely so that a change there does force one. Prometheus scrapes the kubelet /metrics/resource endpoint rather than /metrics/cadvisor: on this cluster cadvisor exposes machine_* series only and no container_* at all, which would leave every CPU and memory panel empty. Alloy ships every pod's logs to Loki through the Kubernetes API, so no /var/log mount is needed. Tempo's metrics_generator feeds span metrics and the service graph back into Prometheus, and the datasources are wired so a log line's trace_id opens the matching trace. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
438 lines
9.1 KiB
JSON
438 lines
9.1 KiB
JSON
{
|
|
"uid": "obs-stack-health",
|
|
"title": "Observability — Stack Health",
|
|
"description": "Health of the Prometheus / Loki / Tempo / Alloy stack. Reference dashboard: stable UID, declaratively provisioned.",
|
|
"tags": [
|
|
"observability",
|
|
"stack",
|
|
"provisioned"
|
|
],
|
|
"editable": false,
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"refresh": "30s",
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timezone": "browser",
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "namespace",
|
|
"label": "Namespace",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"query": "label_values(kube_pod_info, namespace)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"current": {
|
|
"text": "observability",
|
|
"value": "observability"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "row",
|
|
"title": "Collection",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "stat",
|
|
"title": "Prometheus targets UP",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(up)",
|
|
"legendFormat": "up"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "stat",
|
|
"title": "Prometheus targets DOWN",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(up == bool 0)",
|
|
"legendFormat": "down"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "value",
|
|
"graphMode": "none",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "stat",
|
|
"title": "Log lines ingested (/s)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(loki_distributor_lines_received_total[5m]))",
|
|
"legendFormat": "lines/s"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 1,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "blue"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 5,
|
|
"type": "stat",
|
|
"title": "Spans ingested (/s)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"gridPos": {
|
|
"h": 5,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 1
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum(rate(tempo_distributor_spans_received_total[5m]))",
|
|
"legendFormat": "spans/s"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 1,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "purple"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"colorMode": "value",
|
|
"graphMode": "area",
|
|
"textMode": "auto"
|
|
}
|
|
},
|
|
{
|
|
"id": 6,
|
|
"type": "row",
|
|
"title": "Stack resources",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 6
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 7,
|
|
"type": "timeseries",
|
|
"title": "CPU per component (observability namespace)",
|
|
"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 (pod) (rate(container_cpu_usage_seconds_total{namespace=\"observability\", container!=\"\"}[$__rate_interval]))",
|
|
"legendFormat": "{{pod}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 10,
|
|
"showPoints": "never"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max"
|
|
]
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 8,
|
|
"type": "timeseries",
|
|
"title": "Memory per component (observability namespace)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 7
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"expr": "sum by (pod) (container_memory_working_set_bytes{namespace=\"observability\", container!=\"\"})",
|
|
"legendFormat": "{{pod}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 10,
|
|
"showPoints": "never"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": [
|
|
"mean",
|
|
"max"
|
|
]
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 9,
|
|
"type": "row",
|
|
"title": "Logs",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 15
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"id": 10,
|
|
"type": "logs",
|
|
"title": "Recent stack errors",
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "loki",
|
|
"uid": "loki"
|
|
},
|
|
"expr": "{namespace=\"observability\"} |~ \"(?i)(error|level=error|fatal)\"",
|
|
"queryType": "range"
|
|
}
|
|
],
|
|
"options": {
|
|
"showTime": true,
|
|
"showLabels": false,
|
|
"wrapLogMessage": true,
|
|
"sortOrder": "Descending",
|
|
"dedupStrategy": "none",
|
|
"enableLogDetails": true
|
|
}
|
|
}
|
|
]
|
|
}
|