feat(alerts): ship Felis alert rules with promtool unit tests; document scraping & rules (troubleshooting §14)

2026-09-23 16:17:51 +08:00
1 parent 94f71eea19
commit 43df08b52a
@@ -0,0 +1,74 @@
+# prometheus-operator twin of felis-alerts.yaml (kube-prometheus-stack loads
+# rules through the PrometheusRule CRD, not rule_files). The plain file is the
+# promtool-tested source; keep the groups in sync.
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: felis-alerts
+  namespace: monitoring
+  labels:
+    # Change to match your stack's ruleSelector (kube-prometheus-stack's
+    # default selects on the Helm release name).
+    release: kube-prometheus-stack
+spec:
+  groups:
+    - name: felis.rules
+      rules:
+        - alert: FelisImageBuildFailures
+          expr: increase(felis_image_build_failures_total[6h]) > 0
+          for: 5m
+          labels:
+            severity: warning
+          annotations:
+            summary: "modpack/image build failed in the last 6h"
+            description: >-
+              felis_image_build_failures_total increased. Inspect the failed build Job
+              (kubectl logs -n felis-build job/<build-job>); the same error text is on
+              GET /api/v1/images/build/{id} and in the submitter's row in the panel.
+        - alert: FelisSlowServerStarts
+          expr: histogram_quantile(0.9, sum by (le) (rate(felis_start_duration_seconds_bucket[30m]))) > 300
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "p90 server start time exceeds 5 minutes"
+            description: >-
+              Starts regularly take over five minutes (felis_start_duration_seconds,
+              observed when readiness is first reached). A start that never completes
+              records nothing — cross-check desiredState=Running servers with no ready
+              phase (troubleshooting §1).
+    - name: felis.node.rules
+      rules:
+        - alert: FelisNodeDiskSpaceLow
+          expr: >-
+            node_filesystem_avail_bytes{fstype=~"ext4|xfs|btrfs"}
+            / node_filesystem_size_bytes{fstype=~"ext4|xfs|btrfs"} < 0.15
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "node filesystem {{ $labels.mountpoint }} below 15% available"
+            description: >-
+              Sustained disk pressure evicts game pods and garbage-collects images
+              (troubleshooting §13b). Free space before kubelet raises DiskPressure.
+        - alert: FelisNodeDiskPressure
+          expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
+          for: 5m
+          labels:
+            severity: critical
+          annotations:
+            summary: "kubelet reports DiskPressure on {{ $labels.node }}"
+            description: >-
+              The eviction chain is in progress: control-plane pods hold
+              system-cluster-critical and survive, game pods do not. Free disk now
+              (troubleshooting §13b).
+        - alert: FelisNodeMemoryLow
+          expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes < 0.10
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "node memory available below 10% for 15m"
+            description: >-
+              PostgreSQL, the control plane, the registry and game servers share one
+              node; sustained memory pressure risks OOM kills.