Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions monitoring/alerts.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Error-rate alert for the payments API (Prometheus alerting rule, Alertmanager routes on `team`).
groups:
- name: payments-api
rules:
- alert: PaymentsApiHighErrorRate
expr: |
sum(rate(http_requests_total{job="payments-api", code=~"5.."}[5m]))
/
sum(rate(http_requests_total{job="payments-api"}[5m]))
> 0.05
for: 10m
labels:
severity: page
team: payments
annotations:
summary: "Payments API 5xx error rate above 5% for 10 minutes"
description: "{{ $value | humanizePercentage }} of payments-api requests returned 5xx over the last 5 minutes."
runbook_url: "https://coderifts.com/docs/"
Loading