Files
homelab/k8s/infra/monitoring/dashboards/svc-authentik.yaml

144 lines
6.9 KiB
YAML

apiVersion: v1
kind: ConfigMap
metadata:
name: svc-authentik-dashboard
namespace: logging
labels:
grafana_dashboard: "1"
annotations:
grafana_folder: "Authentik"
data:
svc-authentik.json: |
{
"title": "Authentik — Service Overview",
"uid": "svc-authentik",
"schemaVersion": 39,
"timezone": "browser",
"time": { "from": "now-6h", "to": "now" },
"refresh": "30s",
"panels": [
{
"id": 1, "title": "Row: Availability & Golden Signals", "type": "row",
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
"panels": [
{
"id": 2, "title": "Up", "type": "stat",
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 1 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"color": { "mode": "thresholds" },
"mappings": [
{ "type": "value", "options": { "0": { "text": "DOWN", "color": "red" }, "1": { "text": "UP", "color": "green" } } }
],
"thresholds": { "mode": "absolute", "steps": [ { "value": null, "color": "red" }, { "value": 1, "color": "green" } ] }
}
},
"targets": [{ "expr": "min(up{job=\"authentik-server\"})" }]
},
{
"id": 3, "title": "HTTP request rate by status", "type": "timeseries",
"gridPos": { "h": 8, "w": 9, "x": 6, "y": 1 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "sum(rate(authentik_flows_execution_stage_time_count[5m])) by (flow_slug)", "legendFormat": "{{flow_slug}}" }]
},
{
"id": 4, "title": "Error rate % (5xx)", "type": "timeseries",
"gridPos": { "h": 8, "w": 9, "x": 15, "y": 1 },
"fieldConfig": { "defaults": { "unit": "percent" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "(1 - (authentik_flows_cached / authentik_flows_execution_stage_time_count)) * 100" }]
},
{
"id": 5, "title": "Request duration p50/p95/p99", "type": "timeseries",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 9 },
"fieldConfig": { "defaults": { "unit": "s" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [
{ "expr": "histogram_quantile(0.50, sum(rate(authentik_main_request_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p50" },
{ "expr": "histogram_quantile(0.95, sum(rate(authentik_main_request_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p95" },
{ "expr": "histogram_quantile(0.99, sum(rate(authentik_main_request_duration_seconds_bucket[5m])) by (le))", "legendFormat": "p99" }
]
}
]
},
{
"id": 10, "title": "Row: Resource Usage", "type": "row",
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 1 },
"panels": [
{
"id": 11, "title": "CPU by pod", "type": "timeseries",
"gridPos": { "h": 8, "w": 8, "x": 0, "y": 2 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "sum(rate(container_cpu_usage_seconds_total{namespace=\"iam\",pod=~\"authentik.*\"}[5m])) by (pod)", "legendFormat": "{{pod}}" }]
},
{
"id": 12, "title": "Memory by pod", "type": "timeseries",
"gridPos": { "h": 8, "w": 8, "x": 8, "y": 2 },
"fieldConfig": { "defaults": { "unit": "bytes" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "sum(container_memory_working_set_bytes{namespace=\"iam\",pod=~\"authentik.*\"}) by (pod)", "legendFormat": "{{pod}}" }]
},
{
"id": 13, "title": "Restart rate by pod", "type": "timeseries",
"gridPos": { "h": 8, "w": 8, "x": 16, "y": 2 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "sum(rate(kube_pod_container_status_restarts_total{namespace=\"iam\",pod=~\"authentik.*\"}[15m])) by (pod)", "legendFormat": "{{pod}}" }]
}
]
},
{
"id": 20, "title": "Row: Identity Provider (OIDC / OAuth2)", "type": "row",
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 2 },
"panels": [
{
"id": 21, "title": "Outpost connections", "type": "stat",
"gridPos": { "h": 7, "w": 6, "x": 0, "y": 3 },
"fieldConfig": { "defaults": { "unit": "short" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "authentik_outposts_connected" }]
},
{
"id": 22, "title": "Flows cached", "type": "stat",
"gridPos": { "h": 7, "w": 6, "x": 6, "y": 3 },
"fieldConfig": { "defaults": { "unit": "short" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "authentik_flows_cached" }]
},
{
"id": 23, "title": "Policies cached", "type": "stat",
"gridPos": { "h": 7, "w": 6, "x": 12, "y": 3 },
"fieldConfig": { "defaults": { "unit": "short" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "authentik_policies_cached" }]
},
{
"id": 24, "title": "Queued tasks", "type": "stat",
"gridPos": { "h": 7, "w": 6, "x": 18, "y": 3 },
"fieldConfig": { "defaults": { "color": { "mode": "thresholds" }, "unit": "short" } },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "authentik_tasks_queued" }]
},
{
"id": 25, "title": "Admin workers", "type": "timeseries",
"gridPos": { "h": 7, "w": 12, "x": 0, "y": 10 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"targets": [{ "expr": "authentik_admin_workers" }]
}
]
},
{
"id": 30, "title": "Row: Logs", "type": "row",
"collapsed": true, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 3 },
"panels": [
{
"id": 31, "title": "Recent logs", "type": "logs",
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 4 },
"datasource": { "type": "loki", "uid": "loki" },
"targets": [{ "expr": "{namespace=\"iam\"}" }]
}
]
}
]
}