# Alert rules from docs/partition-catalog-monitoring.md. Keep them identical to # the doc; partition-catalog-monitoring.rules.test.yml tests them. groups: - name: buzz-partition-catalog rules: - alert: BuzzPartitionAuditStale expr: time() - buzz_partition_audit_last_success_timestamp_seconds > 1800 for: 10m - alert: BuzzPartitionAuditNotRunning expr: | sum without (outcome) (increase(buzz_partition_audit_runs_total[30m])) == 0 and sum without (outcome) (buzz_partition_audit_runs_total) and sum without (outcome) (buzz_partition_audit_runs_total offset 30m) for: 5m - alert: BuzzPartitionAuditFailing expr: | increase(buzz_partition_audit_failures_total[1h]) >= 2 and buzz_partition_audit_failures_total