awesome-prometheus-alerts/dist/rules/hadoop/jmx_exporter.yml

groups:

- name: Jmx_exporter

  
  rules:

    # When targets are managed via service discovery, a disappeared target goes stale rather than reporting up==0,
    # so this alert may not fire. Prefer application-level availability metrics if available.
    # Rename job="hadoop-namenode" to match the actual job name in your Prometheus scrape config.
    - alert: HadoopNameNodeDown
      expr: 'up{job="hadoop-namenode"} == 0'
      for: 5m
      labels:
        severity: critical
      annotations:
        summary: Hadoop Name Node Down (instance {{ $labels.instance }})
        description: "The Hadoop NameNode service is unavailable.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # When targets are managed via service discovery, a disappeared target goes stale rather than reporting up==0,
    # so this alert may not fire. Prefer application-level availability metrics if available.
    # Rename job="hadoop-resourcemanager" to match the actual job name in your Prometheus scrape config.
    - alert: HadoopResourceManagerDown
      expr: 'up{job="hadoop-resourcemanager"} == 0'
      for: 5m
      labels:
        severity: critical
      annotations:
        summary: Hadoop Resource Manager Down (instance {{ $labels.instance }})
        description: "The Hadoop ResourceManager service is unavailable.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopDataNodeOutOfService
      expr: 'hadoop_datanode_last_heartbeat == 0'
      for: 10m
      labels:
        severity: warning
      annotations:
        summary: Hadoop Data Node Out Of Service (instance {{ $labels.instance }})
        description: "The Hadoop DataNode is not sending heartbeats.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopHdfsDiskSpaceLow
      expr: '(hadoop_hdfs_bytes_total - hadoop_hdfs_bytes_used) / hadoop_hdfs_bytes_total < 0.1 and hadoop_hdfs_bytes_total > 0'
      for: 15m
      labels:
        severity: warning
      annotations:
        summary: Hadoop HDFS Disk Space Low (instance {{ $labels.instance }})
        description: "Available HDFS disk space is running low.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopMapReduceTaskFailures
      expr: 'increase(hadoop_mapreduce_task_failures_total[1h]) > 100'
      for: 10m
      labels:
        severity: critical
      annotations:
        summary: Hadoop Map Reduce Task Failures (instance {{ $labels.instance }})
        description: "There is an unusually high number of MapReduce task failures.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopResourceManagerMemoryHigh
      expr: 'hadoop_resourcemanager_memory_bytes / hadoop_resourcemanager_memory_max_bytes > 0.8 and hadoop_resourcemanager_memory_max_bytes > 0'
      for: 15m
      labels:
        severity: warning
      annotations:
        summary: Hadoop Resource Manager Memory High (instance {{ $labels.instance }})
        description: "The Hadoop ResourceManager is approaching its memory limit.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopYarnContainerAllocationFailures
      expr: 'increase(hadoop_yarn_container_allocation_failures_total[1h]) > 10'
      for: 10m
      labels:
        severity: warning
      annotations:
        summary: Hadoop YARN Container Allocation Failures (instance {{ $labels.instance }})
        description: "There is a significant number of YARN container allocation failures.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopHbaseRegionCountHigh
      expr: 'hadoop_hbase_region_count > 5000'
      for: 15m
      labels:
        severity: warning
      annotations:
        summary: Hadoop HBase Region Count High (instance {{ $labels.instance }})
        description: "The HBase cluster has an unusually high number of regions.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopHbaseRegionServerHeapLow
      expr: 'hadoop_hbase_region_server_heap_bytes / hadoop_hbase_region_server_max_heap_bytes > 0.8 and hadoop_hbase_region_server_max_heap_bytes > 0'
      for: 10m
      labels:
        severity: warning
      annotations:
        summary: Hadoop HBase Region Server Heap Low (instance {{ $labels.instance }})
        description: "HBase Region Servers are running low on heap space.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: HadoopHbaseWriteRequestsLatencyHigh
      expr: 'hadoop_hbase_write_requests_latency_seconds > 0.5'
      for: 10m
      labels:
        severity: warning
      annotations:
        summary: Hadoop HBase Write Requests Latency High (instance {{ $labels.instance }})
        description: "HBase Write Requests are experiencing high latency.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"