adamcarr/pi-swarm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

k3s cluster dashboard: kube-state-metrics + kubelet/cAdvisor scraping, fix empty-label relabel bug

Browse Source
This commit is contained in:
Adam Carr
2026-09-20 13:30:57 -07:00
parent e3f381f807
commit c284205db4
3 changed files with 181 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

66
manifests/monitoring/grafana-dashboards.yaml
View File

@@ -22,6 +22,72 @@ metadata:
name: grafana-dashboards
namespace: monitoring
data:
k3s-cluster.json: |
{
"title": "planck k3s cluster",
"uid": "planckk3s",
"timezone": "browser",
"refresh": "15s",
"time": { "from": "now-3h", "to": "now" },
"panels": [
{
"id": 1, "type": "timeseries", "title": "Pods running by node",
"gridPos": {"x": 0, "y": 0, "w": 12, "h": 9},
"targets": [{"expr": "count by (node) (kube_pod_status_phase{phase=\"Running\"} == 1)", "legendFormat": "{{node}}"}],
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
},
{
"id": 2, "type": "timeseries", "title": "Deployment replicas: ready vs desired",
"gridPos": {"x": 12, "y": 0, "w": 12, "h": 9},
"targets": [
{"expr": "sum by (deployment, namespace) (kube_deployment_status_replicas_ready)", "legendFormat": "ready {{namespace}}/{{deployment}}"},
{"expr": "sum by (deployment, namespace) (kube_deployment_spec_replicas)", "legendFormat": "want {{namespace}}/{{deployment}}"}
],
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
},
{
"id": 3, "type": "timeseries", "title": "Top pods by CPU (cores)",
"gridPos": {"x": 0, "y": 9, "w": 12, "h": 9},
"targets": [{"expr": "topk(12, sum by (pod, namespace) (rate(container_cpu_usage_seconds_total{container!=\"\", container!=\"POD\"}[2m])))", "legendFormat": "{{namespace}}/{{pod}}"}],
"fieldConfig": {"defaults": {"unit": "none"}, "overrides": []}
},
{
"id": 4, "type": "timeseries", "title": "Top pods by memory (working set)",
"gridPos": {"x": 12, "y": 9, "w": 12, "h": 9},
"targets": [{"expr": "topk(12, sum by (pod, namespace) (container_memory_working_set_bytes{container!=\"\", container!=\"POD\"}))", "legendFormat": "{{namespace}}/{{pod}}"}],
"fieldConfig": {"defaults": {"unit": "bytes"}, "overrides": []}
},
{
"id": 5, "type": "timeseries", "title": "Container restarts (cumulative)",
"gridPos": {"x": 0, "y": 18, "w": 12, "h": 9},
"targets": [{"expr": "sum by (pod, namespace) (kube_pod_container_status_restarts_total)", "legendFormat": "{{namespace}}/{{pod}}"}],
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
},
{
"id": 6, "type": "timeseries", "title": "CPU: requested vs allocatable (per node, top 10 nodes)",
"gridPos": {"x": 12, "y": 18, "w": 12, "h": 9},
"targets": [
{"expr": "topk(10, sum by (node) (kube_pod_container_resource_requests{resource=\"cpu\", unit=\"core\"}))", "legendFormat": "requested {{node}}"},
{"expr": "kube_node_status_allocatable{resource=\"cpu\", unit=\"core\"}", "legendFormat": "allocatable {{node}}"}
],
"fieldConfig": {"defaults": {"unit": "none"}, "overrides": []}
},
{
"id": 7, "type": "timeseries", "title": "Nodes Ready",
"gridPos": {"x": 0, "y": 27, "w": 12, "h": 7},
"targets": [{"expr": "count(kube_node_status_condition{condition=\"Ready\", status=\"true\"} == 1)", "legendFormat": "nodes ready"}],
"fieldConfig": {"defaults": {"unit": "short", "min": 0, "max": 20}, "overrides": []}
},
{
"id": 8, "type": "timeseries", "title": "Pods not Running (pending/failed/succeeded)",
"gridPos": {"x": 12, "y": 27, "w": 12, "h": 7},
"targets": [{"expr": "count by (phase) (kube_pod_status_phase == 1) unless on(pod, namespace, phase) label_replace(kube_pod_status_phase{phase=\"Running\"}, \"phase\", \"running\", \"\", \"\") * 0", "legendFormat": "{{phase}}"}],
"fieldConfig": {"defaults": {"unit": "short", "min": 0}, "overrides": []}
}
],
"schemaVersion": 39,
"version": 1
}
node-health.json: |
{
"title": "planck node health",