bstein/titan-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

monitoring: tune cpu and maintenance alerts

Browse Source
This commit is contained in:
Brad Stein 2026-01-27 23:23:42 -03:00
parent 19d10ce585
commit c5a7eece35
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
services/monitoring/grafana-alerting-config.yaml
View File

@ -145,7 +145,7 @@ data:
model:
intervalMs: 60000
maxDataPoints: 43200
expr: avg_over_time((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100)[10m:1m]
expr: avg_over_time((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100)[10m:1m] * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")
legendFormat: '{{instance}}'
datasource:
type: prometheus
@ -175,9 +175,9 @@ data:
type: last
type: query
noDataState: NoData
execErrState: Error
execErrState: NoData
annotations:
summary: "{{ $labels.instance }} CPU >90% for 10m"
summary: "{{ $labels.node }} CPU >90% for 10m"
labels:
severity: warning
- orgId: 1
@ -297,7 +297,7 @@ data:
to: 0
datasourceUid: atlas-vm
model:
expr: time() - max by (cronjob) (kube_cronjob_status_last_successful_time{namespace="maintenance",cronjob="image-sweeper"})
expr: time() - max by (cronjob) (kube_cronjob_status_last_successful_time{namespace="maintenance",cronjob="image-sweeper"}) and on(cronjob) (kube_cronjob_spec_suspend{namespace="maintenance",cronjob="image-sweeper"} == 0)
intervalMs: 60000
maxDataPoints: 43200
legendFormat: '{{cronjob}}'