Skip to content

Commit

Permalink
Added alerting rule for absence of MDS server
Browse files Browse the repository at this point in the history
ceph-mixins-bug-id: /issues/62
Signed-off-by: Shubhendu <shtripat@redhat.com>
  • Loading branch information
Shubhendu authored and shtripat committed May 24, 2019
1 parent 864c39b commit 92eac24
Show file tree
Hide file tree
Showing 4 changed files with 74 additions and 0 deletions.
21 changes: 21 additions & 0 deletions alerts/absent_alerts.libsonnet
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,27 @@
},
],
},
{
name: 'ceph-mds-status',
rules: [
{
alert: 'CephMdsMissingReplicas',
expr: |||
sum(ceph_mds_metadata{%(cephExporterSelector)s} == 1) < 2
||| % $._config,
'for': $._config.mdsMissingReplicasAlertTime,
labels: {
severity: 'warning',
},
annotations: {
message: 'Insufficient replicas for storage metadata service.',
description: 'Minimum required replicas for storage metadata service not available. Might affect the working of storage cluster.',
storage_type: $._config.storageType,
severity_level: 'warning',
},
},
],
},
],
},
}
1 change: 1 addition & 0 deletions config.libsonnet
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@
PGRepairAlertTime: '1h',
mgrMissingReplicasAlertTime: '5m',
mgrIsAbsentAlertTime: '5m',
mdsMissingReplicasAlertTime: '5m',

// Constants
storageType: 'ceph',
Expand Down
14 changes: 14 additions & 0 deletions extras/manifests/prometheus-ceph-rules.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,20 @@ spec:
for: 5m
labels:
severity: warning
- name: ceph-mds-status
rules:
- alert: CephMdsMissingReplicas
annotations:
description: Minimum required replicas for storage metadata service not available.
Might affect the working of storage cluster.
message: Insufficient replicas for storage metadata service.
severity_level: warning
storage_type: ceph
expr: |
sum(ceph_mds_metadata{job="rook-ceph-mgr"} == 1) < 2
for: 5m
labels:
severity: warning
- name: quorum-alert.rules
rules:
- alert: CephMonQuorumAtRisk
Expand Down
38 changes: 38 additions & 0 deletions test_alerts.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -468,3 +468,41 @@ tests:
severity_level: 'error'
- alertname: CephOSDDiskUnavailable
eval_time: 6m
- interval: 1m
input_series:
- series: 'ceph_mds_metadata{ceph_daemon="mds.myfs-a", job="rook-ceph-mgr"}'
values: '1+0x15'
- series: 'ceph_mds_metadata{ceph_daemon="mds.myfs-b", job="rook-ceph-mgr"}'
values: '1+0x05 0+0x10'
alert_rule_test:
- alertname: CephMdsMissingReplicas
eval_time: 4m
- alertname: CephMdsMissingReplicas
eval_time: 11m
exp_alerts:
- exp_labels:
severity: warning
exp_annotations:
message: 'Insufficient replicas for storage metadata service.'
description: 'Minimum required replicas for storage metadata service not available. Might affect the working of storage cluster.'
storage_type: 'ceph'
severity_level: 'warning'
- interval: 1m
input_series:
- series: 'ceph_mds_metadata{ceph_daemon="mds.myfs-a", job="rook-ceph-mgr"}'
values: '0+0x10 1+0x05'
- series: 'ceph_mds_metadata{ceph_daemon="mds.myfs-b", job="rook-ceph-mgr"}'
values: '1+0x15'
alert_rule_test:
- alertname: CephMdsMissingReplicas
eval_time: 6m
exp_alerts:
- exp_labels:
severity: warning
exp_annotations:
message: 'Insufficient replicas for storage metadata service.'
description: 'Minimum required replicas for storage metadata service not available. Might affect the working of storage cluster.'
storage_type: 'ceph'
severity_level: 'warning'
- alertname: CephMdsMissingReplicas
eval_time: 11m

0 comments on commit 92eac24

Please sign in to comment.