Prometheus self-monitoring Prometheus Alert Rules

groups:
- name: EmbeddedExporter
  rules:
      # Only fire if at least one target in the job is still up.
      # If all targets are down, PrometheusJobMissing or PrometheusAllTargetsMissing will fire instead.
    - alert: PrometheusTargetMissing
      expr: up == 0 unless on(job) (sum by (job) (up) == 0)
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Prometheus target missing (instance {{ $labels.instance }})
        description: "A Prometheus target has disappeared. An exporter might be crashed.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusAllTargetsMissing
      expr: sum by (job) (up) == 0
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Prometheus all targets missing (instance {{ $labels.instance }})
        description: "A Prometheus job does not have living target anymore.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTargetMissingWithWarmupTime
      expr: sum by (instance, job) ((up == 0) * on (instance) group_left(__name__) (node_time_seconds - node_boot_time_seconds > 600))
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Prometheus target missing with warmup time (instance {{ $labels.instance }})
        description: "Allow a job time to start up (10 minutes) before alerting that it's down.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusNotConnectedToAlertmanager
      expr: prometheus_notifications_alertmanagers_discovered < 1
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
        description: "Prometheus cannot connect the alertmanager\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
      # Replace job="prometheus" with the actual job name in your Prometheus configuration.
    - alert: PrometheusJobMissing
      expr: absent(up{job="prometheus"})
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Prometheus job missing (instance {{ $labels.instance }})
        description: "A Prometheus job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
      # Replace job="alertmanager" with the actual job name in your Prometheus configuration.
    - alert: PrometheusAlertManagerJobMissing
      expr: absent(up{job="alertmanager"})
      for: 1m
      labels:
        severity: critical
      annotations:
        summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
        description: "A Prometheus AlertManager job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTargetScrapeOutOfOrder
      expr: increase(prometheus_target_scrapes_sample_out_of_order_total[5m]) > 3
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus target scrape out of order (instance {{ $labels.instance }})
        description: "Prometheus is dropping samples because their timestamps arrive out of order ({{ $value }} samples in the last 5 minutes), indicating a misbehaving target or clock skew.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusAlertManagerE2EDeadManSwitch
      expr: vector(1)
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
        description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusRuleEvaluationFailures
      expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTemplateTextExpansionFailures
      expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} template text expansion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusAlertManagerNotificationFailing
      expr: (rate(alertmanager_notifications_failed_total[5m]) / ignoring(reason) group_left rate(alertmanager_notifications_total[5m])) > 0.01 and ignoring(reason) rate(alertmanager_notifications_total[5m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
        description: "Alertmanager is failing to send {{ $value | humanizePercentage }} of notifications\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTargetEmpty
      expr: prometheus_sd_discovered_targets == 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus target empty (instance {{ $labels.instance }})
        description: "Prometheus has no target in service discovery\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBCheckpointCreationFailures
      expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} checkpoint creation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBCheckpointDeletionFailures
      expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBCompactionsFailed
      expr: increase(prometheus_tsdb_compactions_failed_total[10m]) > 0
      for: 30m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} TSDB compactions failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBHeadTruncationsFailed
      expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBReloadFailures
      expr: increase(prometheus_tsdb_reloads_failures_total[10m]) > 0
      for: 30m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} TSDB reload failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBWALCorruptions
      expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTSDBWALTruncationsFailed
      expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
      for: 0m
      labels:
        severity: critical
      annotations:
        summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
        description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusErrorSendingAlertsToAnyAlertManager
      expr: min without (alertmanager) (rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])) * 100 > 3
      for: 15m
      labels:
        severity: critical
      annotations:
        summary: Prometheus error sending alerts to any AlertManager (instance {{ $labels.instance }})
        description: "Prometheus is failing to send at least {{ $value | humanize }}% of alerts to every configured Alertmanager, meaning alert delivery is broadly impaired.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusNotIngestingSamples
      expr: sum without(type) (rate(prometheus_tsdb_head_samples_appended_total[5m])) <= 0 and (sum without(scrape_job) (prometheus_target_metadata_cache_entries) > 0 or sum without(rule_group) (prometheus_rule_group_rules) > 0)
      for: 10m
      labels:
        severity: critical
      annotations:
        summary: Prometheus not ingesting samples (instance {{ $labels.instance }})
        description: "Prometheus has stopped appending new samples to its TSDB head although targets or rule groups are still configured, meaning monitoring data may be lost.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTargetSyncFailure
      expr: increase(prometheus_target_sync_failed_total[10m]) > 0
      for: 5m
      labels:
        severity: critical
      annotations:
        summary: Prometheus target sync failure (instance {{ $labels.instance }})
        description: "{{ $value }} Prometheus targets failed to sync because invalid scrape configuration was supplied, meaning those targets are not being scraped.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTooManyRestarts
      expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus too many restarts (instance {{ $labels.instance }})
        description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusRuleEvaluationSlow
      expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
        description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusNotificationsBacklog
      expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus notifications backlog (instance {{ $labels.instance }})
        description: "The Prometheus notification queue has not been empty for 10 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTargetScrapingSlow
      expr: prometheus_target_interval_length_seconds{quantile="0.9"} / on (interval, instance, job) prometheus_target_interval_length_seconds{quantile="0.5"} > 1.05
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Prometheus target scraping slow (instance {{ $labels.instance }})
        description: "Prometheus is scraping exporters slowly since it exceeded the requested interval time. Your Prometheus server is under-provisioned.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusLargeScrape
      expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Prometheus large scrape (instance {{ $labels.instance }})
        description: "Prometheus has many scrapes that exceed the sample limit ({{ $value }} scrapes)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusTargetScrapeDuplicate
      expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 3
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
        description: "Prometheus has many samples rejected due to duplicate timestamps but different values ({{ $value }} samples)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
      # 10000 series threshold is a rough default; cardinality scales with how many distinct label combinations your monitored infrastructure produces (dashboards, sharding, high-cardinality labels like user IDs) — adjust based on your metric design, not server size.
    - alert: PrometheusTimeseriesCardinality
      expr: label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus timeseries cardinality (instance {{ $labels.instance }})
        description: "The \"{{ $labels.name }}\" timeseries cardinality is getting very high: {{ $value }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusErrorSendingAlertsToAlertManager
      expr: (rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])) * 100 > 1
      for: 15m
      labels:
        severity: warning
      annotations:
        summary: Prometheus error sending alerts to AlertManager (instance {{ $labels.instance }})
        description: "Prometheus is failing to send {{ $value | humanize }}% of alerts to a specific Alertmanager instance, meaning some alerts may not be delivered.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusServiceDiscoveryRefreshFailure
      expr: increase(prometheus_sd_refresh_failures_total[10m]) > 0
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Prometheus service discovery refresh failure (instance {{ $labels.instance }})
        description: "Prometheus failed to refresh service discovery targets using mechanism {{ $labels.mechanism }}, meaning target lists may become stale.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusRuleEvaluationsMissed
      expr: increase(prometheus_rule_group_iterations_missed_total[5m]) > 0
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Prometheus rule evaluations missed (instance {{ $labels.instance }})
        description: "Prometheus missed {{ $value }} rule group evaluations in the last 5 minutes, usually caused by rule groups taking longer to evaluate than their configured interval.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusHighQueryLoad
      expr: prometheus_engine_queries / prometheus_engine_queries_concurrent_max > 0.8
      for: 5m
      labels:
        severity: warning
      annotations:
        summary: Prometheus high query load (instance {{ $labels.instance }})
        description: "Prometheus query engine has less than 20% available capacity for concurrent queries, meaning it is approaching its configured concurrency limit and may start rejecting queries.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusConfigurationReloadFailure
      expr: prometheus_config_last_reload_successful != 1
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
        description: "Prometheus configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
    - alert: PrometheusAlertManagerConfigurationReloadFailure
      expr: alertmanager_config_last_reload_successful != 1
      for: 0m
      labels:
        severity: warning
      annotations:
        summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
        description: "AlertManager configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"
    
      # for: 20m tolerates the time a rolling config change takes to propagate across the
      # Alertmanager cluster, avoiding false positives mid-deploy.
    - alert: PrometheusAlertManagerConfigNotSynced
      expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
      for: 20m
      labels:
        severity: warning
      annotations:
        summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
        description: "Configurations of AlertManager cluster instances are out of sync\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

wget https://raw.githubusercontent.com/samber/awesome-prometheus-alerts/refs/heads/master/dist/rules/prometheus-self-monitoring/embedded-exporter.yml

  # Only fire if at least one target in the job is still up.
  # If all targets are down, PrometheusJobMissing or PrometheusAllTargetsMissing will fire instead.
- alert: PrometheusTargetMissing
  expr: up == 0 unless on(job) (sum by (job) (up) == 0)
  for: 1m
  labels:
    severity: critical
  annotations:
    summary: Prometheus target missing (instance {{ $labels.instance }})
    description: "A Prometheus target has disappeared. An exporter might be crashed.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusAllTargetsMissing
  expr: sum by (job) (up) == 0
  for: 1m
  labels:
    severity: critical
  annotations:
    summary: Prometheus all targets missing (instance {{ $labels.instance }})
    description: "A Prometheus job does not have living target anymore.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTargetMissingWithWarmupTime
  expr: sum by (instance, job) ((up == 0) * on (instance) group_left(__name__) (node_time_seconds - node_boot_time_seconds > 600))
  for: 1m
  labels:
    severity: critical
  annotations:
    summary: Prometheus target missing with warmup time (instance {{ $labels.instance }})
    description: "Allow a job time to start up (10 minutes) before alerting that it's down.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusNotConnectedToAlertmanager
  expr: prometheus_notifications_alertmanagers_discovered < 1
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus not connected to alertmanager (instance {{ $labels.instance }})
    description: "Prometheus cannot connect the alertmanager\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  # Replace job="prometheus" with the actual job name in your Prometheus configuration.
- alert: PrometheusJobMissing
  expr: absent(up{job="prometheus"})
  for: 1m
  labels:
    severity: critical
  annotations:
    summary: Prometheus job missing (instance {{ $labels.instance }})
    description: "A Prometheus job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  # Replace job="alertmanager" with the actual job name in your Prometheus configuration.
- alert: PrometheusAlertManagerJobMissing
  expr: absent(up{job="alertmanager"})
  for: 1m
  labels:
    severity: critical
  annotations:
    summary: Prometheus AlertManager job missing (instance {{ $labels.instance }})
    description: "A Prometheus AlertManager job has disappeared\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTargetScrapeOutOfOrder
  expr: increase(prometheus_target_scrapes_sample_out_of_order_total[5m]) > 3
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus target scrape out of order (instance {{ $labels.instance }})
    description: "Prometheus is dropping samples because their timestamps arrive out of order ({{ $value }} samples in the last 5 minutes), indicating a misbehaving target or clock skew.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusAlertManagerE2EDeadManSwitch
  expr: vector(1)
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus AlertManager E2E dead man switch (instance {{ $labels.instance }})
    description: "Prometheus DeadManSwitch is an always-firing alert. It's used as an end-to-end test of Prometheus through the Alertmanager.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusRuleEvaluationFailures
  expr: increase(prometheus_rule_evaluation_failures_total[3m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus rule evaluation failures (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} rule evaluation failures, leading to potentially ignored alerts.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTemplateTextExpansionFailures
  expr: increase(prometheus_template_text_expansion_failures_total[3m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus template text expansion failures (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} template text expansion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusAlertManagerNotificationFailing
  expr: (rate(alertmanager_notifications_failed_total[5m]) / ignoring(reason) group_left rate(alertmanager_notifications_total[5m])) > 0.01 and ignoring(reason) rate(alertmanager_notifications_total[5m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }})
    description: "Alertmanager is failing to send {{ $value | humanizePercentage }} of notifications\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTargetEmpty
  expr: prometheus_sd_discovered_targets == 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus target empty (instance {{ $labels.instance }})
    description: "Prometheus has no target in service discovery\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBCheckpointCreationFailures
  expr: increase(prometheus_tsdb_checkpoint_creations_failed_total[1m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB checkpoint creation failures (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} checkpoint creation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBCheckpointDeletionFailures
  expr: increase(prometheus_tsdb_checkpoint_deletions_failed_total[1m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB checkpoint deletion failures (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} checkpoint deletion failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBCompactionsFailed
  expr: increase(prometheus_tsdb_compactions_failed_total[10m]) > 0
  for: 30m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB compactions failed (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} TSDB compactions failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBHeadTruncationsFailed
  expr: increase(prometheus_tsdb_head_truncations_failed_total[1m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB head truncations failed (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} TSDB head truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBReloadFailures
  expr: increase(prometheus_tsdb_reloads_failures_total[10m]) > 0
  for: 30m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB reload failures (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} TSDB reload failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBWALCorruptions
  expr: increase(prometheus_tsdb_wal_corruptions_total[1m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB WAL corruptions (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} TSDB WAL corruptions\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTSDBWALTruncationsFailed
  expr: increase(prometheus_tsdb_wal_truncations_failed_total[1m]) > 0
  for: 0m
  labels:
    severity: critical
  annotations:
    summary: Prometheus TSDB WAL truncations failed (instance {{ $labels.instance }})
    description: "Prometheus encountered {{ $value }} TSDB WAL truncation failures\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusErrorSendingAlertsToAnyAlertManager
  expr: min without (alertmanager) (rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])) * 100 > 3
  for: 15m
  labels:
    severity: critical
  annotations:
    summary: Prometheus error sending alerts to any AlertManager (instance {{ $labels.instance }})
    description: "Prometheus is failing to send at least {{ $value | humanize }}% of alerts to every configured Alertmanager, meaning alert delivery is broadly impaired.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusNotIngestingSamples
  expr: sum without(type) (rate(prometheus_tsdb_head_samples_appended_total[5m])) <= 0 and (sum without(scrape_job) (prometheus_target_metadata_cache_entries) > 0 or sum without(rule_group) (prometheus_rule_group_rules) > 0)
  for: 10m
  labels:
    severity: critical
  annotations:
    summary: Prometheus not ingesting samples (instance {{ $labels.instance }})
    description: "Prometheus has stopped appending new samples to its TSDB head although targets or rule groups are still configured, meaning monitoring data may be lost.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTargetSyncFailure
  expr: increase(prometheus_target_sync_failed_total[10m]) > 0
  for: 5m
  labels:
    severity: critical
  annotations:
    summary: Prometheus target sync failure (instance {{ $labels.instance }})
    description: "{{ $value }} Prometheus targets failed to sync because invalid scrape configuration was supplied, meaning those targets are not being scraped.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTooManyRestarts
  expr: changes(process_start_time_seconds{job=~"prometheus|pushgateway|alertmanager"}[15m]) > 2
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus too many restarts (instance {{ $labels.instance }})
    description: "Prometheus has restarted more than twice in the last 15 minutes. It might be crashlooping.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusRuleEvaluationSlow
  expr: prometheus_rule_group_last_duration_seconds > prometheus_rule_group_interval_seconds
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: Prometheus rule evaluation slow (instance {{ $labels.instance }})
    description: "Prometheus rule evaluation took more time than the scheduled interval. It indicates a slower storage backend access or too complex query.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusNotificationsBacklog
  expr: min_over_time(prometheus_notifications_queue_length[10m]) > 0
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus notifications backlog (instance {{ $labels.instance }})
    description: "The Prometheus notification queue has not been empty for 10 minutes\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTargetScrapingSlow
  expr: prometheus_target_interval_length_seconds{quantile="0.9"} / on (interval, instance, job) prometheus_target_interval_length_seconds{quantile="0.5"} > 1.05
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: Prometheus target scraping slow (instance {{ $labels.instance }})
    description: "Prometheus is scraping exporters slowly since it exceeded the requested interval time. Your Prometheus server is under-provisioned.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusLargeScrape
  expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total[10m]) > 10
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: Prometheus large scrape (instance {{ $labels.instance }})
    description: "Prometheus has many scrapes that exceed the sample limit ({{ $value }} scrapes)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusTargetScrapeDuplicate
  expr: increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 3
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus target scrape duplicate (instance {{ $labels.instance }})
    description: "Prometheus has many samples rejected due to duplicate timestamps but different values ({{ $value }} samples)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  # 10000 series threshold is a rough default; cardinality scales with how many distinct label combinations your monitored infrastructure produces (dashboards, sharding, high-cardinality labels like user IDs) — adjust based on your metric design, not server size.
- alert: PrometheusTimeseriesCardinality
  expr: label_replace(count by(__name__) ({__name__=~".+"}), "name", "$1", "__name__", "(.+)") > 10000
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus timeseries cardinality (instance {{ $labels.instance }})
    description: "The \"{{ $labels.name }}\" timeseries cardinality is getting very high: {{ $value }}\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusErrorSendingAlertsToAlertManager
  expr: (rate(prometheus_notifications_errors_total[5m]) / rate(prometheus_notifications_sent_total[5m])) * 100 > 1
  for: 15m
  labels:
    severity: warning
  annotations:
    summary: Prometheus error sending alerts to AlertManager (instance {{ $labels.instance }})
    description: "Prometheus is failing to send {{ $value | humanize }}% of alerts to a specific Alertmanager instance, meaning some alerts may not be delivered.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusServiceDiscoveryRefreshFailure
  expr: increase(prometheus_sd_refresh_failures_total[10m]) > 0
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: Prometheus service discovery refresh failure (instance {{ $labels.instance }})
    description: "Prometheus failed to refresh service discovery targets using mechanism {{ $labels.mechanism }}, meaning target lists may become stale.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusRuleEvaluationsMissed
  expr: increase(prometheus_rule_group_iterations_missed_total[5m]) > 0
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: Prometheus rule evaluations missed (instance {{ $labels.instance }})
    description: "Prometheus missed {{ $value }} rule group evaluations in the last 5 minutes, usually caused by rule groups taking longer to evaluate than their configured interval.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusHighQueryLoad
  expr: prometheus_engine_queries / prometheus_engine_queries_concurrent_max > 0.8
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: Prometheus high query load (instance {{ $labels.instance }})
    description: "Prometheus query engine has less than 20% available capacity for concurrent queries, meaning it is approaching its configured concurrency limit and may start rejecting queries.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusConfigurationReloadFailure
  expr: prometheus_config_last_reload_successful != 1
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus configuration reload failure (instance {{ $labels.instance }})
    description: "Prometheus configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

- alert: PrometheusAlertManagerConfigurationReloadFailure
  expr: alertmanager_config_last_reload_successful != 1
  for: 0m
  labels:
    severity: warning
  annotations:
    summary: Prometheus AlertManager configuration reload failure (instance {{ $labels.instance }})
    description: "AlertManager configuration reload error\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  # for: 20m tolerates the time a rolling config change takes to propagate across the
  # Alertmanager cluster, avoiding false positives mid-deploy.
- alert: PrometheusAlertManagerConfigNotSynced
  expr: count(count_values("config_hash", alertmanager_config_hash)) > 1
  for: 20m
  labels:
    severity: warning
  annotations:
    summary: Prometheus AlertManager config not synced (instance {{ $labels.instance }})
    description: "Configurations of AlertManager cluster instances are out of sync\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"