From 1522e02af0241a81a5f8760f9c7928ad6ec8522c Mon Sep 17 00:00:00 2001 From: Arun Kumar Mohan Date: Mon, 4 Oct 2021 10:29:53 +0530 Subject: [PATCH] ceph: reverting the time delay of 'CephMonHighNumberOfLeaderChanges' As 'CephMonHighNumberOfLeaderChanges' means there is a multiple monitor election and indicate some communication issue between the monitors. Increasing interval timing for this alert is not considered as safe. So reverting this change back to 5m Signed-off-by: Arun Kumar Mohan (cherry picked from commit 4d845425e652a109abe7f61c3460e947d3e797f8) --- .../kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) 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 a21ed9a14b45..1bf41f5204c7 100644 --- a/cluster/examples/kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml +++ b/cluster/examples/kubernetes/ceph/monitoring/prometheus-ceph-v14-rules.yaml @@ -91,7 +91,7 @@ spec: storage_type: ceph expr: | (ceph_mon_metadata{job="rook-ceph-mgr"} * on (ceph_daemon) group_left() (rate(ceph_mon_num_elections{job="rook-ceph-mgr"}[5m]) * 60)) > 0.95 - for: 15m + for: 5m labels: severity: warning - name: ceph-node-alert.rules @@ -326,4 +326,3 @@ spec: for: 1m labels: severity: critical -