feedc0de/my-rook-config
1
0 Fork 0
forked from rook/rook
Code Pull Requests Activity

Merge pull request #11842 from travisn/alert-cleanup

Browse Source 
monitoring: Remove alerts that don't apply to rook
This commit is contained in:
Travis Nielsen authored and GitHub committed 2023-03-06 16:33:30 -07:00
2 parents 1ad863e516 fd25eeecf1
commit 650a511c3b
2 files changed
-42
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

deploy/charts/rook-ceph-cluster/prometheus/localrules.yaml
-21
View File
@@ -524,15 +524,6 @@ groups:
type: "ceph_default"
- name: "pools"
rules:
- alert: "CephPoolGrowthWarning"
annotations:
description: "Pool '{{ $labels.name }}' will be full in less than 5 days assuming the average fill-up rate of the past 48 hours."
summary: "Pool growth rate may soon exceed capacity"
expr: "(predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id, instance) group_right() ceph_pool_metadata) >= 95"
labels:
oid: "1.3.6.1.4.1.50495.1.2.1.9.2"
severity: "warning"
type: "ceph_default"
- alert: "CephPoolBackfillFull"
annotations:
description: "A pool is approaching the near full threshold, which will prevent recovery/backfill operations from completing. Consider adding more capacity."
@@ -583,18 +574,6 @@ groups:
summary: "{{ $labels.ceph_daemon }} operations are slow to complete"
description: "{{ $labels.ceph_daemon }} operations are taking too long to process (complaint time exceeded)"
documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops"
- name: "PrometheusServer"
rules:
- alert: "PrometheusJobMissing"
annotations:
description: "The prometheus job that scrapes from Ceph is no longer defined, this will effectively mean you'll have no metrics or alerts for the cluster. Please review the job definitions in the prometheus.yml file of the prometheus instance."
summary: "The scrape job for Ceph is missing from Prometheus"
expr: "absent(up{job=\"ceph\"})"
for: "30s"
labels:
oid: "1.3.6.1.4.1.50495.1.2.1.12.1"
severity: "critical"
type: "ceph_default"
- name: "rados"
rules:
- alert: "CephObjectMissing"
deploy/examples/monitoring/localrules.yaml
-21
View File
@@ -533,15 +533,6 @@ spec:
type: "ceph_default"
- name: "pools"
rules:
- alert: "CephPoolGrowthWarning"
annotations:
description: "Pool '{{ $labels.name }}' will be full in less than 5 days assuming the average fill-up rate of the past 48 hours."
summary: "Pool growth rate may soon exceed capacity"
expr: "(predict_linear(ceph_pool_percent_used[2d], 3600 * 24 * 5) * on(pool_id, instance) group_right() ceph_pool_metadata) >= 95"
labels:
oid: "1.3.6.1.4.1.50495.1.2.1.9.2"
severity: "warning"
type: "ceph_default"
- alert: "CephPoolBackfillFull"
annotations:
description: "A pool is approaching the near full threshold, which will prevent recovery/backfill operations from completing. Consider adding more capacity."
@@ -592,18 +583,6 @@ spec:
summary: "{{ $labels.ceph_daemon }} operations are slow to complete"
description: "{{ $labels.ceph_daemon }} operations are taking too long to process (complaint time exceeded)"
documentation: "https://docs.ceph.com/en/latest/rados/operations/health-checks#slow-ops"
- name: "PrometheusServer"
rules:
- alert: "PrometheusJobMissing"
annotations:
description: "The prometheus job that scrapes from Ceph is no longer defined, this will effectively mean you'll have no metrics or alerts for the cluster. Please review the job definitions in the prometheus.yml file of the prometheus instance."
summary: "The scrape job for Ceph is missing from Prometheus"
expr: "absent(up{job=\"ceph\"})"
for: "30s"
labels:
oid: "1.3.6.1.4.1.50495.1.2.1.12.1"
severity: "critical"
type: "ceph_default"
- name: "rados"
rules:
- alert: "CephObjectMissing"