Replace monolithic dashboards-configmap.yaml with 10 dedicated files, one per Grafana folder: Ingress, Observability, Infrastructure, Storage, Identity, DevTools, Search, Media, La Suite, Communications. New dashboards for Longhorn, PostgreSQL/CNPG, Cert-Manager, SeaweedFS, Hydra, Kratos, Gitea, OpenSearch, LiveKit, La Suite golden signals (Linkerd metrics), Matrix, and Email Pipeline.
107 lines
2.9 KiB
YAML
107 lines
2.9 KiB
YAML
# Grafana dashboard ConfigMaps — Observability
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-loki
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
annotations:
|
|
grafana_folder: "Observability"
|
|
data:
|
|
loki-overview.json: |
|
|
{
|
|
"annotations": { "list": [] },
|
|
"editable": true,
|
|
"panels": [
|
|
{
|
|
"title": "Log Volume by Namespace",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 24, "x": 0, "y": 0 },
|
|
"datasource": { "uid": "loki" },
|
|
"targets": [
|
|
{
|
|
"expr": "sum(count_over_time({namespace=~\".+\"}[5m])) by (namespace)",
|
|
"legendFormat": "{{namespace}}"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Error Logs",
|
|
"type": "logs",
|
|
"gridPos": { "h": 12, "w": 24, "x": 0, "y": 8 },
|
|
"datasource": { "uid": "loki" },
|
|
"targets": [
|
|
{
|
|
"expr": "{namespace=~\".+\"} |~ \"(?i)(error|panic|fatal|exception)\"",
|
|
"legendFormat": ""
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["loki", "logs"],
|
|
"time": { "from": "now-1h", "to": "now" },
|
|
"title": "Loki — Log Overview",
|
|
"uid": "loki-overview"
|
|
}
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: grafana-dashboard-tempo
|
|
namespace: monitoring
|
|
labels:
|
|
grafana_dashboard: "1"
|
|
annotations:
|
|
grafana_folder: "Observability"
|
|
data:
|
|
tempo-overview.json: |
|
|
{
|
|
"annotations": { "list": [] },
|
|
"editable": true,
|
|
"panels": [
|
|
{
|
|
"title": "Trace Ingestion Rate",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
|
|
"datasource": { "uid": "prometheus" },
|
|
"targets": [
|
|
{
|
|
"expr": "sum(rate(tempo_distributor_spans_received_total[5m]))",
|
|
"legendFormat": "spans/s"
|
|
}
|
|
],
|
|
"fieldConfig": { "defaults": { "unit": "ops" } }
|
|
},
|
|
{
|
|
"title": "Service Map (RED)",
|
|
"type": "nodeGraph",
|
|
"gridPos": { "h": 16, "w": 12, "x": 12, "y": 0 },
|
|
"datasource": { "uid": "tempo" },
|
|
"targets": [
|
|
{ "queryType": "serviceMap" }
|
|
]
|
|
},
|
|
{
|
|
"title": "Span Duration by Service (p95)",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
|
|
"datasource": { "uid": "prometheus" },
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.95, sum(rate(traces_spanmetrics_latency_bucket[5m])) by (le, service))",
|
|
"legendFormat": "{{service}}"
|
|
}
|
|
],
|
|
"fieldConfig": { "defaults": { "unit": "s" } }
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["tempo", "tracing"],
|
|
"time": { "from": "now-1h", "to": "now" },
|
|
"title": "Tempo — Trace Overview",
|
|
"uid": "tempo-overview"
|
|
}
|