Glama
Reaper MCP Server

groups:
  - name: storage_alerts
    rules:
      # Elasticsearch alerts
      - alert: ElasticsearchClusterRed
        expr: elasticsearch_cluster_health_status{color="red"} == 1
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Elasticsearch cluster is RED"
          description: "Elasticsearch cluster has been in RED status for 5 minutes"

      - alert: ElasticsearchClusterYellow
        expr: elasticsearch_cluster_health_status{color="yellow"} == 1
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "Elasticsearch cluster is YELLOW"
          description: "Elasticsearch cluster has been in YELLOW status for 15 minutes"

      - alert: ElasticsearchHighDiskUsage
        expr: elasticsearch_filesystem_data_available_bytes / elasticsearch_filesystem_data_size_bytes * 100 < 15
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Elasticsearch disk space low"
          description: "Elasticsearch data node disk usage is above 85%"

      - alert: ElasticsearchHighJVMUsage
        expr: elasticsearch_jvm_memory_used_bytes / elasticsearch_jvm_memory_max_bytes * 100 > 90
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Elasticsearch JVM memory high"
          description: "Elasticsearch JVM memory usage is above 90%"

      # Redis alerts
      - alert: RedisDown
        expr: redis_up == 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Redis instance down"
          description: "Redis instance has been down for more than 1 minute"

      - alert: RedisHighMemoryUsage
        expr: redis_memory_used_bytes / redis_memory_max_bytes * 100 > 90
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Redis memory usage high"
          description: "Redis memory usage is above 90%"

      - alert: RedisHighKeyspaceEvictionRate
        expr: rate(redis_evicted_keys_total[5m]) > 100
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High Redis key eviction rate"
          description: "Redis is evicting more than 100 keys per second"

      - alert: RedisLowHitRate
        expr: rate(redis_keyspace_hits_total[5m]) / (rate(redis_keyspace_hits_total[5m]) + rate(redis_keyspace_misses_total[5m])) < 0.5
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "Redis low hit rate"
          description: "Redis cache hit rate is below 50% for 15 minutes"

      # Storage performance alerts
      - alert: ElasticsearchHighQueryLatency
        expr: elasticsearch_query_latency:p95 > 1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High Elasticsearch query latency"
          description: "95th percentile of Elasticsearch query latency is above 1 second"

      - alert: RedisHighCommandLatency
        expr: redis_command_latency:p95 > 0.1
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High Redis command latency"
          description: "95th percentile of Redis command latency is above 100ms"

      # Storage capacity alerts
      - alert: ElasticsearchIndexGrowthHigh
        expr: elasticsearch_index_size_bytes:rate5m > 1e6
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "High Elasticsearch index growth rate"
          description: "Elasticsearch index size is growing faster than 1MB/s"

      - alert: RedisKeyspaceFullSoon
        expr: predict_linear(redis_db_keys_total[1h], 24 * 3600) > redis_config_maxmemory
        for: 15m
        labels:
          severity: warning
        annotations:
          summary: "Redis keyspace will be full soon"
          description: "Redis keyspace is predicted to reach max memory within 24 hours"