Merge pull request #5685 from anmolsachan/pvc_alerts_1.2

ceph: added PVC utilization alerts
This commit is contained in:
Sébastien Han authored and GitHub committed 2020-06-25 09:05:29 +02:00
commit ebf74ceb68
1 file changed
+28
@@ -184,6 +184,34 @@ spec:
for: 1h
labels:
severity: warning
- name: persistent-volume-alert.rules
rules:
- alert: PersistentVolumeUsageNearFull
annotations:
description: PVC {{ $labels.persistentvolumeclaim }} utilization has crossed
75%. Free up some space.
message: PVC {{ $labels.persistentvolumeclaim }} is nearing full. Data deletion
is required.
severity_level: warning
storage_type: ceph
expr: |
(kubelet_volume_stats_used_bytes * on (namespace,persistentvolumeclaim) group_left(storageclass, provisioner) (kube_persistentvolumeclaim_info * on (storageclass) group_left(provisioner) kube_storageclass_info {provisioner=~"(.*rbd.csi.ceph.com)|(.*cephfs.csi.ceph.com)"})) / (kubelet_volume_stats_capacity_bytes * on (namespace,persistentvolumeclaim) group_left(storageclass, provisioner) (kube_persistentvolumeclaim_info * on (storageclass) group_left(provisioner) kube_storageclass_info {provisioner=~"(.*rbd.csi.ceph.com)|(.*cephfs.csi.ceph.com)"})) > 0.75
for: 5s
labels:
severity: warning
- alert: PersistentVolumeUsageCritical
annotations:
description: PVC {{ $labels.persistentvolumeclaim }} utilization has crossed
85%. Free up some space immediately.
message: PVC {{ $labels.persistentvolumeclaim }} is critically full. Data
deletion is required.
severity_level: error
storage_type: ceph
expr: |
(kubelet_volume_stats_used_bytes * on (namespace,persistentvolumeclaim) group_left(storageclass, provisioner) (kube_persistentvolumeclaim_info * on (storageclass) group_left(provisioner) kube_storageclass_info {provisioner=~"(.*rbd.csi.ceph.com)|(.*cephfs.csi.ceph.com)"})) / (kubelet_volume_stats_capacity_bytes * on (namespace,persistentvolumeclaim) group_left(storageclass, provisioner) (kube_persistentvolumeclaim_info * on (storageclass) group_left(provisioner) kube_storageclass_info {provisioner=~"(.*rbd.csi.ceph.com)|(.*cephfs.csi.ceph.com)"})) > 0.85
for: 5s
labels:
severity: critical
- name: cluster-state-alert.rules
rules:
- alert: CephClusterErrorState