forked from k-space/kube
		
	prometheus-operator: Less noisy alerting from node-exporter
This commit is contained in:
		| @@ -4,6 +4,7 @@ kind: Probe | ||||
| metadata: | ||||
|   name: nodes-proxmox | ||||
| spec: | ||||
|   scrapeTimeout: 30s | ||||
|   targets: | ||||
|     staticConfig: | ||||
|       static: | ||||
| @@ -86,37 +87,37 @@ spec: | ||||
|             summary: Host memory under memory pressure (instance {{ $labels.instance }}) | ||||
|             description: The node is under heavy memory pressure. High rate of major page faults | ||||
|         - alert: HostUnusualNetworkThroughputIn | ||||
|           expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) > 160e+06 | ||||
|           expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) > 800e+06 | ||||
|           for: 1h | ||||
|           labels: | ||||
|             severity: warning | ||||
|           annotations: | ||||
|             summary: Host unusual network throughput in (instance {{ $labels.instance }}) | ||||
|             description: Host network interfaces are probably receiving too much data (> 160 MB/s) | ||||
|             description: Host network interfaces are probably receiving too much data (> 800 MB/s) | ||||
|         - alert: HostUnusualNetworkThroughputOut | ||||
|           expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) > 160e+06 | ||||
|           expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) > 800e+06 | ||||
|           for: 1h | ||||
|           labels: | ||||
|             severity: warning | ||||
|           annotations: | ||||
|             summary: Host unusual network throughput out (instance {{ $labels.instance }}) | ||||
|             description: Host network interfaces are probably sending too much data (> 160 MB/s) | ||||
|             description: Host network interfaces are probably sending too much data (> 800 MB/s) | ||||
|         - alert: HostUnusualDiskReadRate | ||||
|           expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) > 50000000 | ||||
|           expr: sum by (instance) (rate(node_disk_read_bytes_total[2m])) > 500e+06 | ||||
|           for: 1h | ||||
|           labels: | ||||
|             severity: warning | ||||
|           annotations: | ||||
|             summary: Host unusual disk read rate (instance {{ $labels.instance }}) | ||||
|             description: Disk is probably reading too much data (> 50 MB/s) | ||||
|             description: Disk is probably reading too much data (> 500 MB/s) | ||||
|         - alert: HostUnusualDiskWriteRate | ||||
|           expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) > 50000000 | ||||
|           expr: sum by (instance) (rate(node_disk_written_bytes_total[2m])) > 500e+06 | ||||
|           for: 1h | ||||
|           labels: | ||||
|             severity: warning | ||||
|           annotations: | ||||
|             summary: Host unusual disk write rate (instance {{ $labels.instance }}) | ||||
|             description: Disk is probably writing too much data (> 50 MB/s) | ||||
|             description: Disk is probably writing too much data (> 500 MB/s) | ||||
|         # Please add ignored mountpoints in node_exporter parameters like | ||||
|         # "--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|run)($|/)". | ||||
|         # Same rule using "node_filesystem_free_bytes" will fire when disk fills for non-root users. | ||||
| @@ -361,11 +362,13 @@ kind: PodMonitor | ||||
| metadata: | ||||
|   name: node-exporter | ||||
| spec: | ||||
|  | ||||
|   selector: | ||||
|     matchLabels: | ||||
|       app: node-exporter | ||||
|   podMetricsEndpoints: | ||||
|     - port: web | ||||
|       scrapeTimeout: 30s | ||||
|       relabelings: | ||||
|         - sourceLabels: [__meta_kubernetes_pod_node_name] | ||||
|           targetLabel: node | ||||
|   | ||||
		Reference in New Issue
	
	Block a user