concord/deploy/alerts.yml
2025-10-30 01:31:11 +03:00

39 lines
1.2 KiB
YAML

groups:
- name: api_alerts
interval: 30s
rules:
- alert: HighErrorRate
expr: rate(concord_api_errors_total[5m]) > 0.05
for: 5m
labels:
severity: warning
annotations:
summary: "High error rate detected"
description: "Error rate is {{ $value }} errors/second"
- alert: HighLatency
expr: histogram_quantile(0.95, rate(concord_api_request_duration_seconds_bucket[5m])) > 1
for: 5m
labels:
severity: warning
annotations:
summary: "High latency detected"
description: "95th percentile latency is {{ $value }} seconds"
- alert: DatabaseDown
expr: up{job="postgres"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "Database is down"
description: "PostgreSQL database is not responding"
- alert: HighDatabaseConnections
expr: pg_stat_database_numbackends > 80
for: 5m
labels:
severity: warning
annotations:
summary: "High database connections"
description: "Database has {{ $value }} active connections"