jakman85andClaude Opus 4.8
dbffb8fab8
- platform/kubevirt: pinned KubeVirt v1.9.0 + CDI v1.66.0 operators (remote bases); KubeVirt/CDI CRs tuned for Longhorn; useEmulation=true (prefer real KVM, emulate fallback). - Controllers/configs split (F-MON1): CRs + ServiceMonitors + alerts via platform-config. - Observability: ServiceMonitors, KubeVirt platform-health alerts (R-OBS-04), VM dashboard. - catalog/vm-demo.yaml (kind: vm) + rendered VirtualMachine/DataVolume fixture. - Conformance: vm-lifecycle (R-PLAT-03/04), vm-data-survival (R-STATE-01, L3), vm-default-deny (R-NET-01) — self-skipping until KubeVirt+longhorn exist. - ci/SPEC_PIN: adopt accepted spec b633b7f (ADR-0015 egress work already merged). - conformance/run.sh: document R-ENV-02/R-GITOPS-01 coverage gaps (WS-GITOPS/INFRA-owned). Co-Authored-By: Claude Opus 4.8 <[email protected]>
65 lines
2.2 KiB
YAML
65 lines
2.2 KiB
YAML
---
|
|
# Grafana dashboard for VM health (docs/10 — per-platform-component dashboard). A plain ConfigMap
|
|
# labeled `grafana_dashboard` that the kube-prometheus-stack Grafana sidecar auto-loads (searchNamespace
|
|
# ALL, see platform/monitoring/kube-prometheus-stack.yaml). No CRD dependency, but co-located with the
|
|
# rest of the KubeVirt monitoring wiring and applied via platform-config for locality.
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: kubevirt-vm-health-dashboard
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
data:
|
|
kubevirt-vm-health.json: |
|
|
{
|
|
"title": "KubeVirt — VM Health",
|
|
"uid": "kubevirt-vm-health",
|
|
"schemaVersion": 39,
|
|
"timezone": "browser",
|
|
"tags": ["kubevirt", "platform"],
|
|
"time": {"from": "now-6h", "to": "now"},
|
|
"templating": {"list": []},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "stat",
|
|
"title": "Running VMIs",
|
|
"gridPos": {"h": 6, "w": 8, "x": 0, "y": 0},
|
|
"targets": [
|
|
{"expr": "sum(kubevirt_vmi_phase_count{phase=\"Running\"})", "legendFormat": "running"}
|
|
]
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "stat",
|
|
"title": "Failed VMIs",
|
|
"gridPos": {"h": 6, "w": 8, "x": 8, "y": 0},
|
|
"fieldConfig": {"defaults": {"thresholds": {"steps": [
|
|
{"color": "green", "value": null}, {"color": "red", "value": 1}
|
|
]}}},
|
|
"targets": [
|
|
{"expr": "sum(kubevirt_vmi_phase_count{phase=\"Failed\"})", "legendFormat": "failed"}
|
|
]
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "timeseries",
|
|
"title": "VMI count by phase",
|
|
"gridPos": {"h": 8, "w": 24, "x": 0, "y": 6},
|
|
"targets": [
|
|
{"expr": "sum by (phase) (kubevirt_vmi_phase_count)", "legendFormat": "{{phase}}"}
|
|
]
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "timeseries",
|
|
"title": "virt-launcher restarts (15m)",
|
|
"gridPos": {"h": 8, "w": 24, "x": 0, "y": 14},
|
|
"targets": [
|
|
{"expr": "increase(kube_pod_container_status_restarts_total{pod=~\"virt-launcher-.*\"}[15m])", "legendFormat": "{{namespace}}/{{pod}}"}
|
|
]
|
|
}
|
|
]
|
|
}
|