monitoring: add Grafana dashboards + kube-state-metrics & node-exporter
Dashboards (provisioned via ConfigMaps into Grafana pod, 'K3s Cluster' folder): - Cluster Overview: per-namespace CPU/mem/net/fs, pod counts, pod health (KSM) - Pods & Services: per-pod CPU/mem/net/fs, throttling, pod status, restarts, PVCs - Nodes: per-node CPU%/mem%, load average, disk usage, network (node-exporter) - Control Plane & API Server: request rate, latency p95, 5xx, kubelet/PLEG - Prometheus Self-Monitoring: ingestion, series, scrape duration, memory Exporters (auto-scraped via existing kubernetes-service-endpoints job): - kube-state-metrics: pod/deployment/PVC/replica state (kube_pod_status_phase, kube_pod_container_status_restarts_total, kube_persistentvolumeclaim_*) - node-exporter (DaemonSet, hostNetwork): node_cpu_seconds_total, node_memory_*, node_filesystem_*, node_load*, node_network_*
This commit is contained in:
Roger Oriol
209
monitoring/grafana-dashboard-control-plane.yaml
Normal file
209
monitoring/grafana-dashboard-control-plane.yaml
Normal file
@@ -0,0 +1,209 @@
|
||||
apiVersion: v1
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
name: grafana-dashboard-control-plane
|
||||
namespace: monitoring
|
||||
labels:
|
||||
app: grafana
|
||||
grafana_dashboard: "1"
|
||||
data:
|
||||
control-plane.json: |
|
||||
{
|
||||
"annotations": {"list": []},
|
||||
"editable": true,
|
||||
"graphTooltip": 1,
|
||||
"id": null,
|
||||
"links": [],
|
||||
"liveNow": false,
|
||||
"panels": [
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "palette-classic"},
|
||||
"custom": {
|
||||
"drawStyle": "line", "fillOpacity": 10, "lineInterpolation": "linear", "lineWidth": 1, "showPoints": "never", "spanNulls": true,
|
||||
"stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 9, "w": 12, "x": 0, "y": 0},
|
||||
"id": 1,
|
||||
"options": {
|
||||
"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true},
|
||||
"tooltip": {"mode": "multi", "sort": "desc"}
|
||||
},
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "sum(rate(apiserver_request_total[5m])) by (verb)", "legendFormat": "{{verb}}", "refId": "A"}],
|
||||
"title": "API Server Requests by Verb",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "palette-classic"},
|
||||
"custom": {
|
||||
"drawStyle": "line", "fillOpacity": 10, "lineInterpolation": "linear", "lineWidth": 1, "showPoints": "never", "spanNulls": true,
|
||||
"stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 9, "w": 12, "x": 12, "y": 0},
|
||||
"id": 2,
|
||||
"options": {
|
||||
"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true},
|
||||
"tooltip": {"mode": "multi", "sort": "desc"}
|
||||
},
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "histogram_quantile(0.95, sum(rate(apiserver_request_duration_seconds_bucket[5m])) by (le, verb))", "legendFormat": "p95 {{verb}}", "refId": "A"}],
|
||||
"title": "API Server Request Latency p95",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "palette-classic"},
|
||||
"custom": {
|
||||
"drawStyle": "line", "fillOpacity": 10, "lineInterpolation": "linear", "lineWidth": 1, "showPoints": "never", "spanNulls": true,
|
||||
"stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
|
||||
"unit": "ops"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 9, "w": 12, "x": 0, "y": 9},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true},
|
||||
"tooltip": {"mode": "multi", "sort": "desc"}
|
||||
},
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "sum(rate(apiserver_request_total{code=~\"5..\"}[5m])) by (verb)", "legendFormat": "{{verb}}", "refId": "A"}],
|
||||
"title": "API Server 5xx Errors",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "palette-classic"},
|
||||
"custom": {
|
||||
"drawStyle": "line", "fillOpacity": 10, "lineInterpolation": "linear", "lineWidth": 1, "showPoints": "never", "spanNulls": true,
|
||||
"stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 9, "w": 12, "x": 12, "y": 9},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true},
|
||||
"tooltip": {"mode": "multi", "sort": "desc"}
|
||||
},
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "sum(rate(kubelet_container_log_filesystem_used_bytes[5m]))", "legendFormat": "log fs", "refId": "A"}, {"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "histogram_quantile(0.95, sum(rate(kubelet_pod_start_duration_seconds_bucket[5m])) by (le))", "legendFormat": "pod start p95", "refId": "B"}],
|
||||
"title": "Kubelet Pod Start Latency",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "palette-classic"},
|
||||
"custom": {
|
||||
"drawStyle": "line", "fillOpacity": 10, "lineInterpolation": "linear", "lineWidth": 1, "showPoints": "never", "spanNulls": true,
|
||||
"stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 9, "w": 12, "x": 0, "y": 18},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true},
|
||||
"tooltip": {"mode": "multi", "sort": "desc"}
|
||||
},
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "histogram_quantile(0.95, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket[5m])) by (le, instance))", "legendFormat": "{{instance}}", "refId": "A"}],
|
||||
"title": "Kubelet Cgroup Manager Duration p95",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "palette-classic"},
|
||||
"custom": {
|
||||
"drawStyle": "line", "fillOpacity": 10, "lineInterpolation": "linear", "lineWidth": 1, "showPoints": "never", "spanNulls": true,
|
||||
"stacking": {"group": "A", "mode": "none"}, "thresholdsStyle": {"mode": "off"}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "green", "value": null}]},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 9, "w": 12, "x": 12, "y": 18},
|
||||
"id": 6,
|
||||
"options": {
|
||||
"legend": {"calcs": ["lastNotNull"], "displayMode": "table", "placement": "right", "showLegend": true},
|
||||
"tooltip": {"mode": "multi", "sort": "desc"}
|
||||
},
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "rate(kubelet_pleg_relist_duration_seconds_count[5m])", "legendFormat": "relists/s {{instance}}", "refId": "A"}],
|
||||
"title": "Kubelet PLEG Relist Rate",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {"type": "prometheus", "uid": "Prometheus"},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {"mode": "thresholds"},
|
||||
"mappings": [
|
||||
{"options": {"0": {"text": "Down", "color": "red"}, "1": {"text": "Up", "color": "green"}}, "type": "value"}
|
||||
],
|
||||
"thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {"h": 6, "w": 24, "x": 0, "y": 27},
|
||||
"id": 7,
|
||||
"options": {
|
||||
"colorMode": "background",
|
||||
"graphMode": "none",
|
||||
"justifyMode": "center",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false},
|
||||
"textMode": "value_and_name"
|
||||
},
|
||||
"pluginVersion": "10.2.3",
|
||||
"targets": [{"datasource": {"type": "prometheus", "uid": "Prometheus"}, "expr": "up", "refId": "A"}],
|
||||
"title": "All Scrape Targets Status",
|
||||
"type": "stat"
|
||||
}
|
||||
],
|
||||
"refresh": "30s",
|
||||
"schemaVersion": 38,
|
||||
"style": "dark",
|
||||
"tags": ["k3s", "control-plane"],
|
||||
"templating": {"list": []},
|
||||
"time": {"from": "now-6h", "to": "now"},
|
||||
"timepicker": {},
|
||||
"timezone": "",
|
||||
"title": "Control Plane & API Server",
|
||||
"uid": "k3s-control-plane",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
Reference in New Issue
Block a user