up

ops/devops/lnm/alerts/lnm-alerts.yaml

@@ -0,0 +1,57 @@
+# LNM Migration Alert Rules
+# Prometheus alerting rules for linkset/advisory migrations
+
+groups:
+  - name: lnm-migration
+    rules:
+      - alert: LnmMigrationErrorRate
+        expr: rate(lnm_migration_errors_total[5m]) > 0.1
+        for: 5m
+        labels:
+          severity: warning
+          team: concelier
+        annotations:
+          summary: "LNM migration error rate elevated"
+          description: "Migration errors: {{ $value | printf \"%.2f\" }}/s"
+
+      - alert: LnmBackfillStalled
+        expr: increase(lnm_backfill_processed_total[10m]) == 0 and lnm_backfill_running == 1
+        for: 10m
+        labels:
+          severity: critical
+          team: concelier
+        annotations:
+          summary: "LNM backfill stalled"
+          description: "No progress in 10 minutes while backfill is running"
+
+      - alert: LnmLinksetCountMismatch
+        expr: abs(lnm_linksets_total - lnm_linksets_expected) > 100
+        for: 15m
+        labels:
+          severity: warning
+          team: concelier
+        annotations:
+          summary: "Linkset count mismatch"
+          description: "Expected {{ $labels.expected }}, got {{ $value }}"
+
+      - alert: LnmObservationsBacklogHigh
+        expr: lnm_observations_backlog > 10000
+        for: 5m
+        labels:
+          severity: warning
+          team: excititor
+        annotations:
+          summary: "Advisory observations backlog high"
+          description: "Backlog: {{ $value }} items"
+
+  - name: lnm-sla
+    rules:
+      - alert: LnmIngestToApiLatencyHigh
+        expr: histogram_quantile(0.95, rate(lnm_ingest_to_api_latency_seconds_bucket[5m])) > 30
+        for: 10m
+        labels:
+          severity: warning
+          team: platform
+        annotations:
+          summary: "Ingest to API latency exceeds SLA"
+          description: "P95 latency: {{ $value | printf \"%.1f\" }}s (SLA: 30s)"