awesome-prometheus-alerts/dist/rules/pulsar/embedded-exporter.yml

groups:

- name: EmbeddedExporter

  
  rules:

    - alert: PulsarSubscriptionHighNumberOfBacklogEntries
      expr: 'sum(pulsar_subscription_back_log) by (subscription) > 5000'
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Pulsar subscription high number of backlog entries (instance {{ $labels.instance }})
        description: "The number of subscription backlog entries is over 5k\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PulsarSubscriptionVeryHighNumberOfBacklogEntries
      expr: 'sum(pulsar_subscription_back_log) by (subscription) > 100000'
      for: 1h
      labels:
        severity: critical
      annotations:
        summary: Pulsar subscription very high number of backlog entries (instance {{ $labels.instance }})
        description: "The number of subscription backlog entries is over 100k\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PulsarTopicLargeBacklogStorageSize
      expr: 'sum(pulsar_storage_size) by (topic) > 5*1024*1024*1024'
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Pulsar topic large backlog storage size (instance {{ $labels.instance }})
        description: "The topic backlog storage size is over 5 GB\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PulsarTopicVeryLargeBacklogStorageSize
      expr: 'sum(pulsar_storage_size) by (topic) > 20*1024*1024*1024'
      for: 1h
      labels:
        severity: critical
      annotations:
        summary: Pulsar topic very large backlog storage size (instance {{ $labels.instance }})
        description: "The topic backlog storage size is over 20 GB\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # pulsar_storage_write_latency_le_overflow is the overflow bucket of Pulsar's non-standard histogram.
    # It counts write operations exceeding all defined latency bounds (> 1000ms).
    - alert: PulsarHighWriteLatency
      expr: 'sum(pulsar_storage_write_latency_le_overflow > 0) by (topic)'
      for: 1h
      labels:
        severity: critical
      annotations:
        summary: Pulsar high write latency (instance {{ $labels.instance }})
        description: "Pulsar topic {{ $labels.topic }} has {{ $value }} storage write operations exceeding the maximum latency bucket (> 1000ms)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # pulsar_entry_size_le_overflow is the overflow bucket of Pulsar's non-standard histogram.
    # It counts message entries exceeding all defined size bounds.
    - alert: PulsarLargeMessagePayload
      expr: 'sum(pulsar_entry_size_le_overflow > 0) by (topic)'
      for: 1h
      labels:
        severity: warning
      annotations:
        summary: Pulsar large message payload (instance {{ $labels.instance }})
        description: "Pulsar topic {{ $labels.topic }} has {{ $value }} message entries exceeding the maximum size bucket (> 1MB)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    # This metric name is path-dependent and may differ based on your BookKeeper data directory configuration.
    # Adjust the metric name to match your actual ledger directory path.
    - alert: PulsarHighLedgerDiskUsage
      expr: 'sum(bookie_ledger_dir__pulsar_data_bookkeeper_ledgers_usage) by (kubernetes_pod_name) > 75'
      for: 1h
      labels:
        severity: critical
      annotations:
        summary: Pulsar high ledger disk usage (instance {{ $labels.instance }})
        description: "Observing Ledger Disk Usage (> 75%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PulsarReadOnlyBookies
      expr: 'count(bookie_SERVER_STATUS{} == 0) by (pod)'
      for: 5m
      labels:
        severity: critical
      annotations:
        summary: Pulsar read only bookies (instance {{ $labels.instance }})
        description: "Observing Readonly Bookies\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PulsarHighNumberOfFunctionErrors
      expr: 'sum(rate(pulsar_function_user_exceptions_total[1m]) + rate(pulsar_function_system_exceptions_total[1m])) by (name) > 10'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Pulsar high number of function errors (instance {{ $labels.instance }})
        description: "Pulsar function {{ $labels.name }} has more than 10 errors per second ({{ $value | printf \"%.2f\" }}/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

    - alert: PulsarHighNumberOfSinkErrors
      expr: 'sum(rate(pulsar_sink_sink_exceptions_total[1m])) by (name) > 10'
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Pulsar high number of sink errors (instance {{ $labels.instance }})
        description: "Pulsar sink {{ $labels.name }} has more than 10 errors per second ({{ $value | printf \"%.2f\" }}/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"