diff --git a/monitoring/alerts.yml b/monitoring/alerts.yml new file mode 100644 index 0000000..ebc46ae --- /dev/null +++ b/monitoring/alerts.yml @@ -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/"