Story Crater Bot
63d7256b9e
- Loki log aggregation (MinIO backed, 10-day retention) - Promtail daemonset (pod + talos journal logs) - Prometheus + kube-state-metrics - Grafana dashboards (6-row template per service)
49 lines
1.2 KiB
YAML
49 lines
1.2 KiB
YAML
service: argocd
|
|
display_name: "Argo CD"
|
|
namespace: argocd
|
|
service_type: web-app
|
|
folder: "Argo CD"
|
|
jobs: [argocd-server, argocd-repo-server]
|
|
metrics:
|
|
prefix: argocd
|
|
up_selector: 'job=~"argocd-.*"'
|
|
rate:
|
|
metric: argocd_http_request_total
|
|
labels: [method, path, status]
|
|
duration:
|
|
metric: argocd_http_request_duration_seconds
|
|
type: histogram
|
|
unit: s
|
|
error:
|
|
metric: argocd_http_request_total
|
|
filter: 'status=~"5.."'
|
|
domain:
|
|
- metric: argocd_app_total
|
|
kind: gauge
|
|
- metric: argocd_app_sync_total
|
|
kind: counter
|
|
labels: [sync_status]
|
|
- metric: argocd_app_health_degraded_total
|
|
kind: counter
|
|
- metric: argocd_git_sync_total
|
|
kind: counter
|
|
labels: [git_operation, git_status]
|
|
- metric: argocd_reconcile_total
|
|
kind: counter
|
|
labels: [app_name]
|
|
correlation_ids: []
|
|
logs:
|
|
loki_namespace_selector: 'namespace="argocd"'
|
|
alerts:
|
|
- name: HighErrorRate
|
|
expr_template: rate_error_ratio
|
|
threshold: 0.05
|
|
for: 10m
|
|
severity: warning
|
|
- name: AppSyncFailure
|
|
expr_template: gauge_above_threshold
|
|
metric: argocd_app_health_degraded_total
|
|
threshold: 1
|
|
for: 10m
|
|
severity: warning
|