{ "name": "Kubernetes readiness probes failing", "description": "Readiness probes are failing across the cluster at roughly double the normal rate -- pods are being pulled out of service", "query": "service=kubelet event_kind=probe_failed earliest=-10m | stats count", "query_language": "spl", "condition_type": "threshold", "eval_interval_seconds": 60, "for_minutes": 5, "notification_target_id": "__TARGET_PLATFORM__", "enabled": true, "comparator": "gt", "threshold_value": 55 }