consultoria-as
3792e4053c
- docker-compose.monitoring.yml: added alertmanager service (port 9093) - prometheus.yml: alerting config + rule_files entry - alerts.yml: 5 alert rules (PostgreSQLDown, RedisDown, HighDiskUsage, HighMemoryUsage, NodeDown) - alertmanager.yml: SMTP + webhook receiver, inhibit rules
48 lines
1.4 KiB
YAML
48 lines
1.4 KiB
YAML
groups:
|
|
- name: nexus-alerts
|
|
rules:
|
|
- alert: PostgreSQLDown
|
|
expr: pg_up == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "PostgreSQL is down"
|
|
description: "PostgreSQL has been down for more than 1 minute."
|
|
|
|
- alert: RedisDown
|
|
expr: redis_up == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Redis is down"
|
|
description: "Redis has been down for more than 1 minute."
|
|
|
|
- alert: HighDiskUsage
|
|
expr: (node_filesystem_avail_bytes / node_filesystem_size_bytes) * 100 < 10
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Disk usage is high"
|
|
description: "Disk usage is above 90% on {{ $labels.device }}."
|
|
|
|
- alert: HighMemoryUsage
|
|
expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 85
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Memory usage is high"
|
|
description: "Memory usage is above 85%."
|
|
|
|
- alert: NodeDown
|
|
expr: up{job="node"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Node exporter is down"
|
|
description: "Node exporter has been down for more than 2 minutes."
|