From 624ca40817026b26c274069ea78aae1a16589fcf Mon Sep 17 00:00:00 2001 From: Anmol Sachan Date: Mon, 22 Jun 2020 21:08:42 +0530 Subject: [PATCH] ceph: added PVC utilization alerts Added warning and critical alerts for all the PVC's created by rook-ceph provisioners. This is required to notify a admin timely to check on PVC utilization and take a required action to prevent workloads from failing. Closes: BZ1849723 Signed-off-by: Anmol Sachan --- .../monitoring/prometheus-ceph-v14-rules.yaml | 28 +++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/cluster/examples/kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml b/cluster/examples/kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml index 8d4490e19..57464e564 100644 --- a/cluster/examples/kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml +++ b/cluster/examples/kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml @@ -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