Skip to content

Commit accf1dc

Browse files
committed
remove alert HighlyAvailableWorkloadIncorrectlySpread
1 parent 9070ffb commit accf1dc

File tree

6 files changed

+1
-267
lines changed

6 files changed

+1
-267
lines changed

CHANGELOG.md

+1
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,7 @@
99
- [#1439](https://github.com/openshift/cluster-monitoring-operator/pull/1439) Expose PodDisruptionBudget labels from kube-state-metrics metrics.
1010
- [#1377](https://github.com/openshift/cluster-monitoring-operator/pull/1377) Allow OpenShift users to configure audit logs for prometheus-adapter
1111
- [#1481](https://github.com/openshift/cluster-monitoring-operator/pull/1481) Removing one of the AlertmanagerClusterFailedToSendAlerts alerts
12+
- [#1488](https://github.com/openshift/cluster-monitoring-operator/pull/1488) Removing the alert HighlyAvailableWorkloadIncorrectlySpread.
1213

1314
## 4.9
1415

assets/cluster-monitoring-operator/prometheus-rule.yaml

-33
Original file line numberDiff line numberDiff line change
@@ -28,39 +28,6 @@ spec:
2828
for: 15m
2929
labels:
3030
severity: warning
31-
- alert: HighlyAvailableWorkloadIncorrectlySpread
32-
annotations:
33-
description: Workload {{ $labels.namespace }}/{{ $labels.workload }} is incorrectly
34-
spread across multiple nodes which breaks high-availability requirements.
35-
Since the workload is using persistent volumes, manual intervention is needed.
36-
Please follow the guidelines provided in the runbook of this alert to fix
37-
this issue.
38-
runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/HighlyAvailableWorkloadIncorrectlySpread.md
39-
summary: Highly-available workload is incorrectly spread across multiple nodes
40-
and manual intervention is needed.
41-
expr: |
42-
count without (node)
43-
(
44-
group by (node, workload, namespace)
45-
(
46-
kube_pod_info{node!=""}
47-
* on(namespace,pod) group_left(workload)
48-
(
49-
max by(namespace, pod, workload) (kube_pod_spec_volumes_persistentvolumeclaims_info)
50-
* on(namespace,pod) group_left(workload)
51-
(
52-
namespace_workload_pod:kube_pod_owner:relabel
53-
* on(namespace,workload,workload_type) group_left()
54-
(
55-
count without(pod) (namespace_workload_pod:kube_pod_owner:relabel{namespace=~"(openshift-.*|kube-.*|default)"}) > 1
56-
)
57-
)
58-
)
59-
)
60-
) == 1
61-
for: 1h
62-
labels:
63-
severity: warning
6431
- name: openshift-kubernetes.rules
6532
rules:
6633
- expr: sum(rate(container_cpu_usage_seconds_total{container="",pod!=""}[5m]))

jsonnet/rules.libsonnet

-33
Original file line numberDiff line numberDiff line change
@@ -22,39 +22,6 @@ function(params) {
2222
severity: 'warning',
2323
},
2424
},
25-
{
26-
expr: |||
27-
count without (node)
28-
(
29-
group by (node, workload, namespace)
30-
(
31-
kube_pod_info{node!=""}
32-
* on(namespace,pod) group_left(workload)
33-
(
34-
max by(namespace, pod, workload) (kube_pod_spec_volumes_persistentvolumeclaims_info)
35-
* on(namespace,pod) group_left(workload)
36-
(
37-
namespace_workload_pod:kube_pod_owner:relabel
38-
* on(namespace,workload,workload_type) group_left()
39-
(
40-
count without(pod) (namespace_workload_pod:kube_pod_owner:relabel{%(namespaceSelector)s}) > 1
41-
)
42-
)
43-
)
44-
)
45-
) == 1
46-
||| % cfg,
47-
alert: 'HighlyAvailableWorkloadIncorrectlySpread',
48-
'for': '1h',
49-
annotations: {
50-
description: 'Workload {{ $labels.namespace }}/{{ $labels.workload }} is incorrectly spread across multiple nodes which breaks high-availability requirements. Since the workload is using persistent volumes, manual intervention is needed. Please follow the guidelines provided in the runbook of this alert to fix this issue.',
51-
summary: 'Highly-available workload is incorrectly spread across multiple nodes and manual intervention is needed.',
52-
runbook_url: 'https://github.com/openshift/runbooks/blob/master/alerts/HighlyAvailableWorkloadIncorrectlySpread.md',
53-
},
54-
labels: {
55-
severity: 'warning',
56-
},
57-
},
5825
],
5926
},
6027
{

jsonnet/utils/sanitize-rules.libsonnet

-1
Original file line numberDiff line numberDiff line change
@@ -336,7 +336,6 @@ local includeRunbooks = {
336336
AlertmanagerFailedReload: openShiftRunbookCMO('AlertmanagerFailedReload.md'),
337337
ClusterOperatorDegraded: openShiftRunbookCMO('ClusterOperatorDegraded.md'),
338338
ClusterOperatorDown: openShiftRunbookCMO('ClusterOperatorDown.md'),
339-
HighlyAvailableWorkloadIncorrectlySpread: openShiftRunbook('alerts/HighlyAvailableWorkloadIncorrectlySpread.md'),
340339
KubeAPIDown: openShiftRunbookCMO('KubeAPIDown.md'),
341340
KubeDeploymentReplicasMismatch: openShiftRunbookCMO('KubeDeploymentReplicasMismatch.md'),
342341
KubeJobFailed: openShiftRunbookCMO('KubeJobFailed.md'),

test/rules/bz2006561.yaml

-61
This file was deleted.

0 commit comments

Comments
 (0)