Files
my-rook-config/deploy/examples/monitoring/externalrules.yaml
T
Travis Nielsen 8dd4b77d8a monitoring: update to the latest ceph prometheus rules
Pick up the latest ceph prometheus rules from the ceph repo
found at https://github.com/ceph/ceph/blob/master/monitoring/ceph-mixin/prometheus_alerts.yml.
The updates include many new rules for monitoring of ceph.

Signed-off-by: Travis Nielsen <tnielsen@redhat.com>
2022-03-21 14:47:56 -06:00

36 lines
2.4 KiB
YAML

# Copied from /deploy/charts/rook-ceph-cluster/prometheus/, CR header added, and indentation increased on the groups
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
labels:
prometheus: rook-prometheus
role: alert-rules
name: prometheus-ceph-rules
namespace: rook-ceph
spec:
groups:
- name: persistent-volume-alert.rules
rules:
- alert: PersistentVolumeUsageNearFull
annotations:
description: PVC {{ $labels.persistentvolumeclaim }} utilization has crossed 75%. Free up some space or expand the PVC.
message: PVC {{ $labels.persistentvolumeclaim }} is nearing full. Data deletion or PVC expansion 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 or expand the PVC immediately.
message: PVC {{ $labels.persistentvolumeclaim }} is critically full. Data deletion or PVC expansion 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