Skip to content

Commit

Permalink
Prometheus Alertmanager config for PagerDuty
Browse files Browse the repository at this point in the history
Send alerts to PagerDuty when jupyterhub-home-nfs
disk usage is above 90%
  • Loading branch information
sunu committed Dec 17, 2024
1 parent 72edf0c commit 90502df
Showing 1 changed file with 25 additions and 0 deletions.
25 changes: 25 additions & 0 deletions config/clusters/nasa-veda/support.values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,18 @@ redirects:
to: staging.hub.openveda.cloud

prometheus:
alertmanager:
enabled: true
config:
route:
group_wait: 10s
group_interval: 5m
receiver: pagerduty
repeat_interval: 3h
routes:
- receiver: pagerduty
match:
channel: pagerduty
server:
ingress:
enabled: true
Expand All @@ -41,6 +53,19 @@ prometheus:
- secretName: prometheus-tls
hosts:
- prometheus.nasa-veda.2i2c.cloud
serverFiles:
alerting_rules.yml:
groups:
- name: NASA VEDA jupyterhub-home-nfs EBS volume full
rules:
- alert: jupyterhub-home-nfs-ebs-full
expr: node_filesystem_avail_bytes{mountpoint="/shared-volume", component="shared-volume-metrics"} / node_filesystem_size_bytes{mountpoint="/shared-volume", component="shared-volume-metrics"} < 0.1
for: 15m
labels:
severity: critical
channel: pagerduty
annotations:
summary: "jupyterhub-home-nfs EBS volume full in namespace {{ $labels.namespace }}"

aws-ce-grafana-backend:
enabled: true
Expand Down

0 comments on commit 90502df

Please sign in to comment.