monitoring-mixins-website/assets/jaeger/alerts.yaml

groups:
- name: jaeger_alerts
  rules:
  - alert: JaegerAgentUDPPacketsBeingDropped
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is dropping {{ printf "%.2f" $value }} UDP packets per second.        
      summary: Jaeger agent is dropping UDP packets.
    expr: rate(jaeger_agent_thrift_udp_server_packets_dropped_total[1m]) > 1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerAgentHTTPServerErrs
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is experiencing {{ printf "%.2f" $value }}% HTTP errors.        
      summary: Jaeger agent is experiencing HTTP errors.
    expr: 100 * sum(rate(jaeger_agent_http_server_errors_total[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_agent_http_server_total[1m])) by (instance,
      job, namespace)> 1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerClientSpansDropped
    annotations:
      description: |
        service {{ $labels.job }} {{ $labels.instance }} is dropping {{ printf "%.2f" $value }}% spans.        
      summary: Jaeger client is dropping spans.
    expr: 100 * sum(rate(jaeger_reporter_spans{result=~"dropped|err"}[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_reporter_spans[1m])) by (instance, job, namespace)>
      1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerAgentSpansDropped
    annotations:
      description: |
        agent {{ $labels.job }} {{ $labels.instance }} is dropping {{ printf "%.2f" $value }}% spans.        
      summary: Jaeger agent is dropping spans.
    expr: 100 * sum(rate(jaeger_agent_reporter_batches_failures_total[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_agent_reporter_batches_submitted_total[1m]))
      by (instance, job, namespace)> 1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerCollectorQueueNotDraining
    annotations:
      description: |
        collector {{ $labels.job }} {{ $labels.instance }} is not able to drain the queue.        
      summary: Jaeger collector is not able to drain the queue.
    expr: avg_over_time(jaeger_collector_queue_length[10m]) > 1000
    for: 15m
    labels:
      severity: warning
  - alert: JaegerCollectorDroppingSpans
    annotations:
      description: |
        collector {{ $labels.job }} {{ $labels.instance }} is dropping {{ printf "%.2f" $value }}% spans.        
      summary: Jaeger collector is dropping spans.
    expr: 100 * sum(rate(jaeger_collector_spans_dropped_total[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_collector_spans_received_total[1m])) by (instance,
      job, namespace)> 1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerSamplingUpdateFailing
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is failing {{ printf "%.2f" $value }}% in updating sampling policies.        
      summary: Jaeger's sampling update is failing.
    expr: 100 * sum(rate(jaeger_sampler_queries{result="err"}[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_sampler_queries[1m])) by (instance, job, namespace)>
      1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerCollectorPersistenceSlow
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is slow at persisting spans.        
      summary: Jaeger collector is slow at persisting spans.
    expr: histogram_quantile(0.99, sum by (le) (rate(jaeger_collector_save_latency_bucket[1m])))
      > 0.5
    for: 15m
    labels:
      severity: warning
  - alert: JaegerThrottlingUpdateFailing
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is failing {{ printf "%.2f" $value }}% in updating throttling policies.        
      summary: Jaeger's throttling update is failing.
    expr: 100 * sum(rate(jaeger_throttler_updates{result="err"}[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_throttler_updates[1m])) by (instance, job,
      namespace)> 1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerQueryReqsFailing
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is seeing {{ printf "%.2f" $value }}% query errors on {{ $labels.operation }}.        
      summary: Jaeger queries are failing.
    expr: 100 * sum(rate(jaeger_query_requests_total{result="err"}[1m])) by (instance,
      job, namespace) / sum(rate(jaeger_query_requests_total[1m])) by (instance, job,
      namespace)> 1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerCassandraWritesFailing
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is seeing {{ printf "%.2f" $value }}% query errors on {{ $labels.operation }}.        
      summary: Jaeger writes to Cassandra are failing.
    expr: 100 * sum(rate(jaeger_cassandra_errors_total[1m])) by (instance, job, namespace)
      / sum(rate(jaeger_cassandra_attempts_total[1m])) by (instance, job, namespace)>
      1
    for: 15m
    labels:
      severity: warning
  - alert: JaegerCassandraReadsFailing
    annotations:
      description: |
        {{ $labels.job }} {{ $labels.instance }} is seeing {{ printf "%.2f" $value }}% query errors on {{ $labels.operation }}.        
      summary: Jaeger reads from Cassandra are failing.
    expr: 100 * sum(rate(jaeger_cassandra_read_errors_total[1m])) by (instance, job,
      namespace) / sum(rate(jaeger_cassandra_read_attempts_total[1m])) by (instance,
      job, namespace)> 1
    for: 15m
    labels:
      severity: warning