Files
factorio/monitoring.yaml
T

75 lines
2.6 KiB
YAML
Raw Permalink Normal View History

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
name: factorio
2026-10-27 07:16:05 +01:00
namespace: {{ .Release.Namespace }}
labels:
app.kubernetes.io/name: factorio
spec:
selector:
matchLabels:
app.kubernetes.io/name: factorio
app.kubernetes.io/component: metrics
endpoints:
- port: metrics
interval: 30s
scrapeTimeout: 10s
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: factorio
2026-10-27 07:16:05 +01:00
namespace: {{ .Release.Namespace }}
labels:
app.kubernetes.io/name: factorio
spec:
groups:
- name: factorio
rules:
- alert: FactorioUnavailable
2026-10-27 07:16:05 +01:00
expr: kube_deployment_status_replicas_available{namespace="{{ .Release.Namespace }}",deployment="factorio"}
< 1 or absent(kube_deployment_status_replicas_available{namespace="{{ .Release.Namespace }}",deployment="factorio"})
for: 5m
labels:
severity: warning
annotations:
summary: Factorio has no ready server
- alert: FactorioMetricsUnavailable
2026-10-27 07:16:05 +01:00
expr: up{namespace="{{ .Release.Namespace }}",service="factorio-metrics"} == 0 or absent(up{namespace="{{ .Release.Namespace }}",service="factorio-metrics"})
for: 5m
labels:
severity: warning
annotations:
summary: Factorio metrics collection is failing
- alert: FactorioRestarting
2026-10-27 07:16:05 +01:00
expr: sum by (container) (increase(kube_pod_container_status_restarts_total{namespace="{{ .Release.Namespace }}"}[15m]))
> 2
for: 5m
labels:
severity: warning
annotations:
summary: Factorio container is repeatedly restarting
- alert: FactorioStorageAlmostFull
2026-10-27 07:16:05 +01:00
expr: kubelet_volume_stats_available_bytes{namespace="{{ .Release.Namespace }}",persistentvolumeclaim="factorio-data"}
/ kubelet_volume_stats_capacity_bytes{namespace="{{ .Release.Namespace }}",persistentvolumeclaim="factorio-data"}
< 0.15
for: 10m
labels:
severity: warning
annotations:
summary: Factorio save storage has less than 15% free
- alert: FactorioGameNotResponding
2026-10-27 07:16:05 +01:00
expr: factorio_server_up{namespace="{{ .Release.Namespace }}"} == 0 or absent(factorio_server_up{namespace="{{ .Release.Namespace }}"})
for: 3m
labels:
severity: warning
annotations:
summary: Factorio is not answering authenticated player queries
- alert: FactorioPlayerCollectorStale
2026-10-27 07:16:05 +01:00
expr: time() - factorio_collector_last_poll_timestamp_seconds{namespace="{{ .Release.Namespace }}"}
> 60
for: 2m
labels:
severity: warning
annotations:
summary: Factorio player collector has stopped updating