GistPin/infrastructure/monitoring/replication-lag.yml at main · ghzhost/GistPin · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
groups:
  - name: rds-replication
    rules:
      # Replica lag warning — risk of stale reads
      - alert: ReplicaLagWarning
        expr: aws_rds_replica_lag_average > 10
        for: 5m
        labels:
          severity: warning
          team: platform
        annotations:
          summary: "RDS replica lag elevated ({{ $labels.db_instance_identifier }})"
          description: "Replica lag is {{ $value }}s — stale reads may occur. Threshold: 10s."

      # Replica lag critical — trigger failover consideration
      - alert: ReplicaLagCritical
        expr: aws_rds_replica_lag_average > 60
        for: 2m
        labels:
          severity: critical
          team: platform
        annotations:
          summary: "RDS replica lag critical ({{ $labels.db_instance_identifier }})"
          description: "Replica lag is {{ $value }}s. Consider routing reads back to primary."

      # Replica not replicating (lag goes to 0 and replica is not active)
      - alert: ReplicaReplicationStopped
        expr: aws_rds_replica_lag_average == 0 and aws_rds_database_connections_average == 0
        for: 3m
        labels:
          severity: critical
          team: platform
        annotations:
          summary: "Replica replication may have stopped ({{ $labels.db_instance_identifier }})"
          description: "Replica shows 0 lag but 0 connections — replication may be broken."

      # Primary DB high CPU (may affect replication throughput)
      - alert: PrimaryDBHighCPU
        expr: aws_rds_cpuutilization_average{role="primary"} > 80
        for: 10m
        labels:
          severity: warning
          team: platform
        annotations:
          summary: "Primary RDS CPU > 80%"
          description: "High CPU on primary may impact replication to replicas."