diff --git a/dist/rules/grafana-mimir/embedded-exporter.yml b/dist/rules/grafana-mimir/embedded-exporter.yml new file mode 100644 index 0000000..bed1f46 --- /dev/null +++ b/dist/rules/grafana-mimir/embedded-exporter.yml @@ -0,0 +1,449 @@ +groups: + +- name: EmbeddedExporter + + # Mimir uses the `cortex_` metric prefix for backward compatibility with Cortex. This is intentional and expected. + + rules: + + - alert: MimirIngesterUnhealthy + expr: 'min by (job) (cortex_ring_members{state="Unhealthy", name="ingester"}) > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Mimir ingester unhealthy (instance {{ $labels.instance }}) + description: "Mimir has {{ $value }} unhealthy ingester(s) in the ring.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRequestErrors + expr: '100 * sum by (job, route) (rate(cortex_request_duration_seconds_count{status_code=~"5..", route!~"ready|debug_pprof"}[5m])) / sum by (job, route) (rate(cortex_request_duration_seconds_count{route!~"ready|debug_pprof"}[5m])) > 1' + for: 15m + labels: + severity: critical + annotations: + summary: Mimir request errors (instance {{ $labels.instance }}) + description: "Mimir {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirInconsistentRuntimeConfig + expr: 'count(count by (job, sha256) (cortex_runtime_config_hash)) without(sha256) > 1' + for: 1h + labels: + severity: critical + annotations: + summary: Mimir inconsistent runtime config (instance {{ $labels.instance }}) + description: "An inconsistent runtime config file is used across Mimir instances.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirBadRuntimeConfig + expr: 'sum by (job) (cortex_runtime_config_last_reload_successful == 0) > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir bad runtime config (instance {{ $labels.instance }}) + description: "{{ $labels.job }} failed to reload runtime config.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirSchedulerQueriesStuck + expr: 'sum by (job) (min_over_time(cortex_query_scheduler_queue_length[1m])) > 0' + for: 7m + labels: + severity: critical + annotations: + summary: Mimir scheduler queries stuck (instance {{ $labels.instance }}) + description: "There are {{ $value }} queued up queries in {{ $labels.job }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCacheRequestErrors + expr: '(sum by (name, operation, job) (rate(thanos_cache_operation_failures_total[5m])) / sum by (name, operation, job) (rate(thanos_cache_operations_total[5m]))) * 100 > 5' + for: 5m + labels: + severity: warning + annotations: + summary: Mimir cache request errors (instance {{ $labels.instance }}) + description: "Mimir cache {{ $labels.name }} is experiencing {{ printf \"%.2f\" $value }}% errors for {{ $labels.operation }} operation.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirKvStoreFailure + expr: '(sum by (job, kv_name) (rate(cortex_kv_request_duration_seconds_count{status_code!~"2.."}[5m])) / sum by (job, kv_name) (rate(cortex_kv_request_duration_seconds_count[5m]))) == 1' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir KV store failure (instance {{ $labels.instance }}) + description: "Mimir {{ $labels.job }} KV store {{ $labels.kv_name }} is failing with 100% error rate.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirMemoryMapAreasTooHigh + expr: 'process_memory_map_areas{job=~".*(ingester|cortex|mimir|store-gateway).*"} / process_memory_map_areas_limit{job=~".*(ingester|cortex|mimir|store-gateway).*"} * 100 > 80' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir memory map areas too high (instance {{ $labels.instance }}) + description: "Mimir {{ $labels.job }} is using {{ printf \"%.0f\" $value }}% of its memory map area limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterInstanceHasNoTenants + expr: '(cortex_ingester_memory_users == 0) and on (instance) (cortex_ingester_memory_users offset 1h > 0)' + for: 1h + labels: + severity: warning + annotations: + summary: Mimir ingester instance has no tenants (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} has no tenants assigned.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRulerInstanceHasNoRuleGroups + expr: '(cortex_ruler_managers_total == 0) and on (instance) (cortex_ruler_managers_total offset 1h > 0)' + for: 1h + labels: + severity: warning + annotations: + summary: Mimir ruler instance has no rule groups (instance {{ $labels.instance }}) + description: "Mimir ruler {{ $labels.instance }} has no rule groups assigned.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngestedDataTooFarInTheFuture + expr: 'max by (job) (cortex_ingester_tsdb_head_max_timestamp_seconds - time() and cortex_ingester_tsdb_head_max_timestamp_seconds > 0) > 3600' + for: 5m + labels: + severity: warning + annotations: + summary: Mimir ingested data too far in the future (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.job }} has ingested samples with timestamps more than 1 hour in the future.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirStoreGatewayTooManyFailedOperations + expr: 'sum by (job) (rate(thanos_objstore_bucket_operation_failures_total[5m])) > 0' + for: 5m + labels: + severity: warning + annotations: + summary: Mimir store gateway too many failed operations (instance {{ $labels.instance }}) + description: "Mimir store-gateway {{ $labels.job }} bucket operations are failing.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRingMembersMismatch + expr: 'max by (name, job) (sum by (name, job, instance) (cortex_ring_members)) != min by (name, job) (sum by (name, job, instance) (cortex_ring_members))' + for: 15m + labels: + severity: warning + annotations: + summary: Mimir ring members mismatch (instance {{ $labels.instance }}) + description: "Mimir {{ $labels.name }} ring has inconsistent member counts across instances.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterReachingSeriesLimitWarning + expr: '(cortex_ingester_memory_series / ignoring(limit) cortex_ingester_instance_limits{limit="max_series"} * 100 > 80) and cortex_ingester_instance_limits{limit="max_series"} > 0' + for: 3h + labels: + severity: warning + annotations: + summary: Mimir ingester reaching series limit warning (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} has reached {{ printf \"%.0f\" $value }}% of its series limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterReachingSeriesLimitCritical + expr: '(cortex_ingester_memory_series / ignoring(limit) cortex_ingester_instance_limits{limit="max_series"} * 100 > 90) and cortex_ingester_instance_limits{limit="max_series"} > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir ingester reaching series limit critical (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} has reached {{ printf \"%.0f\" $value }}% of its series limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterReachingTenantsLimitWarning + expr: '(cortex_ingester_memory_users / ignoring(limit) cortex_ingester_instance_limits{limit="max_tenants"} * 100 > 70) and cortex_ingester_instance_limits{limit="max_tenants"} > 0' + for: 5m + labels: + severity: warning + annotations: + summary: Mimir ingester reaching tenants limit warning (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} has reached {{ printf \"%.0f\" $value }}% of its tenants limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterReachingTenantsLimitCritical + expr: '(cortex_ingester_memory_users / ignoring(limit) cortex_ingester_instance_limits{limit="max_tenants"} * 100 > 80) and cortex_ingester_instance_limits{limit="max_tenants"} > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir ingester reaching tenants limit critical (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} has reached {{ printf \"%.0f\" $value }}% of its tenants limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirReachingTcpConnectionsLimit + expr: 'cortex_tcp_connections / cortex_tcp_connections_limit * 100 > 80 and cortex_tcp_connections_limit > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir reaching TCP connections limit (instance {{ $labels.instance }}) + description: "Mimir instance {{ $labels.instance }} is using {{ printf \"%.0f\" $value }}% of its TCP connections limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirDistributorInflightRequestsHigh + expr: '(cortex_distributor_inflight_push_requests / ignoring(limit) cortex_distributor_instance_limits{limit="max_inflight_push_requests"} * 100 > 80) and cortex_distributor_instance_limits{limit="max_inflight_push_requests"} > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir distributor inflight requests high (instance {{ $labels.instance }}) + description: "Mimir distributor {{ $labels.instance }} is using {{ printf \"%.0f\" $value }}% of its inflight push requests limit.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterTsdbHeadCompactionFailed + expr: 'rate(cortex_ingester_tsdb_compactions_failed_total[5m]) > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Mimir ingester TSDB head compaction failed (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} is failing to compact TSDB head.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterTsdbHeadTruncationFailed + expr: 'rate(cortex_ingester_tsdb_head_truncations_failed_total[5m]) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Mimir ingester TSDB head truncation failed (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} is failing to truncate TSDB head.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterTsdbCheckpointCreationFailed + expr: 'rate(cortex_ingester_tsdb_checkpoint_creations_failed_total[5m]) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Mimir ingester TSDB checkpoint creation failed (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} is failing to create TSDB checkpoints.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterTsdbCheckpointDeletionFailed + expr: 'rate(cortex_ingester_tsdb_checkpoint_deletions_failed_total[5m]) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Mimir ingester TSDB checkpoint deletion failed (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} is failing to delete TSDB checkpoints.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterTsdbWalTruncationFailed + expr: 'rate(cortex_ingester_tsdb_wal_truncations_failed_total[5m]) > 0' + for: 0m + labels: + severity: warning + annotations: + summary: Mimir ingester TSDB WAL truncation failed (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} is failing to truncate TSDB WAL.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirIngesterTsdbWalWritesFailed + expr: 'rate(cortex_ingester_tsdb_wal_writes_failed_total[1m]) > 0' + for: 3m + labels: + severity: critical + annotations: + summary: Mimir ingester TSDB WAL writes failed (instance {{ $labels.instance }}) + description: "Mimir ingester {{ $labels.instance }} is failing to write to TSDB WAL.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirStoreGatewayHasNotSyncedBucket + expr: '(time() - cortex_bucket_stores_blocks_last_successful_sync_timestamp_seconds{component="store-gateway"} > 600) and cortex_bucket_stores_blocks_last_successful_sync_timestamp_seconds{component="store-gateway"} > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir store gateway has not synced bucket (instance {{ $labels.instance }}) + description: "Mimir store-gateway {{ $labels.instance }} has not synced the bucket for more than 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirStoreGatewayNoSyncedTenants + expr: '(min by (instance, job) (cortex_bucket_stores_tenants_synced{component="store-gateway"}) == 0) and on (instance) (cortex_bucket_stores_tenants_synced{component="store-gateway"} offset 1h > 0)' + for: 1h + labels: + severity: warning + annotations: + summary: Mimir store gateway no synced tenants (instance {{ $labels.instance }}) + description: "Mimir store-gateway {{ $labels.instance }} has no synced tenants.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirBucketIndexNotUpdated + expr: 'min by (user, job) (time() - cortex_bucket_index_last_successful_update_timestamp_seconds) > 2100' + for: 0m + labels: + severity: critical + annotations: + summary: Mimir bucket index not updated (instance {{ $labels.instance }}) + description: "Mimir bucket index for tenant {{ $labels.user }} has not been updated for more than 35 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCompactorNotCleaningUpBlocks + expr: '(time() - cortex_compactor_block_cleanup_last_successful_run_timestamp_seconds > 21600) and cortex_compactor_block_cleanup_last_successful_run_timestamp_seconds > 0' + for: 1h + labels: + severity: critical + annotations: + summary: Mimir compactor not cleaning up blocks (instance {{ $labels.instance }}) + description: "Mimir compactor {{ $labels.instance }} has not cleaned up blocks in the last 6 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCompactorNotRunningCompaction + expr: '(time() - cortex_compactor_last_successful_run_timestamp_seconds > 86400) and cortex_compactor_last_successful_run_timestamp_seconds > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Mimir compactor not running compaction (instance {{ $labels.instance }}) + description: "Mimir compactor {{ $labels.instance }} has not run compaction in the last 24 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCompactorHasConsecutiveFailures + expr: 'increase(cortex_compactor_runs_failed_total[2h]) > 1' + for: 0m + labels: + severity: critical + annotations: + summary: Mimir compactor has consecutive failures (instance {{ $labels.instance }}) + description: "Mimir compactor {{ $labels.instance }} has had 2+ compaction failures in the last 2 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCompactorHasRunOutOfDiskSpace + expr: 'increase(cortex_compactor_disk_out_of_space_errors_total[24h]) >= 1' + for: 0m + labels: + severity: critical + annotations: + summary: Mimir compactor has run out of disk space (instance {{ $labels.instance }}) + description: "Mimir compactor {{ $labels.instance }} has run out of disk space.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCompactorHasNotUploadedBlocks + expr: '(time() - thanos_objstore_bucket_last_successful_upload_time{component="compactor"} > 86400) and thanos_objstore_bucket_last_successful_upload_time{component="compactor"} > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Mimir compactor has not uploaded blocks (instance {{ $labels.instance }}) + description: "Mimir compactor {{ $labels.instance }} has not uploaded any block in the last 24 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirCompactorSkippedBlocks + expr: 'increase(cortex_compactor_blocks_marked_for_no_compaction_total[5m]) > 0' + for: 5m + labels: + severity: warning + annotations: + summary: Mimir compactor skipped blocks (instance {{ $labels.instance }}) + description: "Mimir compactor has found blocks that cannot be compacted (reason {{ $labels.reason }}).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRulerTooManyFailedPushes + expr: '100 * sum by (instance, job) (rate(cortex_ruler_write_requests_failed_total[5m])) / sum by (instance, job) (rate(cortex_ruler_write_requests_total[5m])) > 1' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir ruler too many failed pushes (instance {{ $labels.instance }}) + description: "Mimir ruler {{ $labels.instance }} is failing to push {{ printf \"%.2f\" $value }}% of write requests.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRulerTooManyFailedQueries + expr: '100 * sum by (instance, job) (rate(cortex_ruler_queries_failed_total[5m])) / sum by (instance, job) (rate(cortex_ruler_queries_total[5m])) > 1' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir ruler too many failed queries (instance {{ $labels.instance }}) + description: "Mimir ruler {{ $labels.instance }} is failing {{ printf \"%.2f\" $value }}% of query evaluations.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRulerMissedEvaluations + expr: '100 * sum by (instance, job) (rate(cortex_prometheus_rule_group_iterations_missed_total[5m])) / sum by (instance, job) (rate(cortex_prometheus_rule_group_iterations_total[5m])) > 1' + for: 5m + labels: + severity: warning + annotations: + summary: Mimir ruler missed evaluations (instance {{ $labels.instance }}) + description: "Mimir ruler {{ $labels.instance }} is missing {{ printf \"%.2f\" $value }}% of rule group evaluations.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirRulerFailedRingCheck + expr: 'sum by (job) (rate(cortex_ruler_ring_check_errors_total[5m])) > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Mimir ruler failed ring check (instance {{ $labels.instance }}) + description: "Mimir ruler {{ $labels.job }} is failing ring checks.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerSyncConfigsFailing + expr: 'rate(cortex_alertmanager_sync_configs_failed_total[5m]) > 0' + for: 30m + labels: + severity: critical + annotations: + summary: Mimir alertmanager sync configs failing (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.job }} is failing to sync configs.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerRingCheckFailing + expr: 'rate(cortex_alertmanager_ring_check_errors_total[5m]) > 0' + for: 10m + labels: + severity: critical + annotations: + summary: Mimir alertmanager ring check failing (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.job }} is failing ring checks.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerStateMergeFailing + expr: 'rate(cortex_alertmanager_partial_state_merges_failed_total[5m]) > 0' + for: 10m + labels: + severity: critical + annotations: + summary: Mimir alertmanager state merge failing (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.job }} is failing to merge state updates.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerReplicationFailing + expr: 'rate(cortex_alertmanager_state_replication_failed_total[5m]) > 0' + for: 10m + labels: + severity: critical + annotations: + summary: Mimir alertmanager replication failing (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.job }} is failing to replicate state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerPersistStateFailing + expr: 'rate(cortex_alertmanager_state_persist_failed_total[15m]) > 0' + for: 1h + labels: + severity: critical + annotations: + summary: Mimir alertmanager persist state failing (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.job }} is failing to persist state.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerInitialSyncFailed + expr: 'increase(cortex_alertmanager_state_initial_sync_completed_total{outcome="failed"}[1m]) > 0' + for: 0m + labels: + severity: warning + annotations: + summary: Mimir alertmanager initial sync failed (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.job }} failed initial state sync.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirAlertmanagerInstanceHasNoTenants + expr: '(cortex_alertmanager_tenants_owned == 0) and on (instance) (cortex_alertmanager_tenants_owned offset 1h > 0)' + for: 1h + labels: + severity: warning + annotations: + summary: Mimir alertmanager instance has no tenants (instance {{ $labels.instance }}) + description: "Mimir alertmanager {{ $labels.instance }} has no tenants assigned.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirGossipMembersCountTooHigh + expr: 'avg(memberlist_client_cluster_members_count{job=~".*(mimir|cortex).*"}) by (job) * 1.15 + 10 < max(memberlist_client_cluster_members_count{job=~".*(mimir|cortex).*"}) by (job)' + for: 20m + labels: + severity: warning + annotations: + summary: Mimir gossip members count too high (instance {{ $labels.instance }}) + description: "Mimir gossip cluster has more members than expected.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirGossipMembersCountTooLow + expr: 'avg(memberlist_client_cluster_members_count{job=~".*(mimir|cortex).*"}) by (job) * 0.5 > min(memberlist_client_cluster_members_count{job=~".*(mimir|cortex).*"}) by (job)' + for: 20m + labels: + severity: warning + annotations: + summary: Mimir gossip members count too low (instance {{ $labels.instance }}) + description: "Mimir gossip cluster has fewer members than expected.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + # A high number of Go threads may indicate a goroutine leak. + - alert: MimirGoThreadsTooHighWarning + expr: 'go_threads{job=~".*(mimir|cortex).*"} > 5000' + for: 15m + labels: + severity: warning + annotations: + summary: Mimir go threads too high warning (instance {{ $labels.instance }}) + description: "Mimir {{ $labels.instance }} has {{ $value }} Go threads.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: MimirGoThreadsTooHighCritical + expr: 'go_threads{job=~".*(mimir|cortex).*"} > 8000' + for: 15m + labels: + severity: critical + annotations: + summary: Mimir go threads too high critical (instance {{ $labels.instance }}) + description: "Mimir {{ $labels.instance }} has {{ $value }} Go threads.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" diff --git a/dist/rules/grafana-tempo/embedded-exporter.yml b/dist/rules/grafana-tempo/embedded-exporter.yml new file mode 100644 index 0000000..a06f097 --- /dev/null +++ b/dist/rules/grafana-tempo/embedded-exporter.yml @@ -0,0 +1,173 @@ +groups: + +- name: EmbeddedExporter + + + rules: + + - alert: TempoDistributorUnhealthy + expr: 'max by (job) (tempo_ring_members{state="Unhealthy", name="distributor"}) > 0' + for: 15m + labels: + severity: warning + annotations: + summary: Tempo distributor unhealthy (instance {{ $labels.instance }}) + description: "Tempo has {{ $value }} unhealthy distributor(s).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoLiveStoreUnhealthy + expr: 'max by (job) (tempo_ring_members{state="Unhealthy", name="live-store"}) > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Tempo live store unhealthy (instance {{ $labels.instance }}) + description: "Tempo has {{ $value }} unhealthy live store(s).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoMetricsGeneratorUnhealthy + expr: 'max by (job) (tempo_ring_members{state="Unhealthy", name="metrics-generator"}) > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Tempo metrics generator unhealthy (instance {{ $labels.instance }}) + description: "Tempo has {{ $value }} unhealthy metrics generator(s).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + # Uses a two-window approach: 1h for historical count and 5m to confirm the issue is ongoing. + - alert: TempoCompactionsFailing + expr: 'sum by (job) (increase(tempodb_compaction_errors_total[1h])) > 2 and sum by (job) (increase(tempodb_compaction_errors_total[5m])) > 0' + for: 1h + labels: + severity: critical + annotations: + summary: Tempo compactions failing (instance {{ $labels.instance }}) + description: "Greater than 2 compactions have failed in the past hour.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoPollsFailing + expr: 'sum by (job) (increase(tempodb_blocklist_poll_errors_total[1h])) > 2 and sum by (job) (increase(tempodb_blocklist_poll_errors_total[5m])) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Tempo polls failing (instance {{ $labels.instance }}) + description: "Greater than 2 blocklist polls have failed in the past hour.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoTenantIndexFailures + expr: 'sum by (job) (increase(tempodb_blocklist_tenant_index_errors_total[1h])) > 2 and sum by (job) (increase(tempodb_blocklist_tenant_index_errors_total[5m])) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Tempo tenant index failures (instance {{ $labels.instance }}) + description: "Greater than 2 tenant index failures in the past hour.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoNoTenantIndexBuilders + expr: 'sum by (tenant) (tempodb_blocklist_tenant_index_builder) == 0 and on() max(tempodb_blocklist_length) > 0' + for: 5m + labels: + severity: critical + annotations: + summary: Tempo no tenant index builders (instance {{ $labels.instance }}) + description: "No tenant index builders for tenant {{ $labels.tenant }}. Tenant index will quickly become stale.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + # Threshold of 600s (10 minutes). Adjust based on your tenant index build interval. + - alert: TempoTenantIndexTooOld + expr: 'max by (tenant) (tempodb_blocklist_tenant_index_age_seconds) > 600' + for: 5m + labels: + severity: critical + annotations: + summary: Tempo tenant index too old (instance {{ $labels.instance }}) + description: "Tenant index for {{ $labels.tenant }} is {{ $value }}s old.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + # Fires when the blocklist grows more than 40% over 7 days. + - alert: TempoBlockListRisingQuickly + expr: '(avg(tempodb_blocklist_length) / avg(tempodb_blocklist_length offset 7d) - 1) * 100 > 40' + for: 15m + labels: + severity: critical + annotations: + summary: Tempo block list rising quickly (instance {{ $labels.instance }}) + description: "Tempo blocklist length is up {{ printf \"%.0f\" $value }}% over the last 7 days. Consider scaling compactors.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoBadOverrides + expr: 'sum by (job) (tempo_runtime_config_last_reload_successful == 0) > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Tempo bad overrides (instance {{ $labels.instance }}) + description: "{{ $labels.job }} failed to reload runtime overrides.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoUserConfigurableOverridesReloadFailing + expr: 'sum by (job) (increase(tempo_overrides_user_configurable_overrides_reload_failed_total[1h])) > 5 and sum by (job) (increase(tempo_overrides_user_configurable_overrides_reload_failed_total[5m])) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Tempo user configurable overrides reload failing (instance {{ $labels.instance }}) + description: "Greater than 5 user-configurable overrides reloads have failed in the past hour.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + # Threshold of 100 blocks per compactor instance. Adjust based on your environment. + - alert: TempoCompactionTooManyOutstandingBlocksWarning + expr: 'sum by (instance) (tempodb_compaction_outstanding_blocks) > 100' + for: 6h + labels: + severity: warning + annotations: + summary: Tempo compaction too many outstanding blocks warning (instance {{ $labels.instance }}) + description: "There are too many outstanding compaction blocks for {{ $labels.instance }}. Consider increasing compactor resources.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoCompactionTooManyOutstandingBlocksCritical + expr: 'sum by (instance) (tempodb_compaction_outstanding_blocks) > 250' + for: 24h + labels: + severity: critical + annotations: + summary: Tempo compaction too many outstanding blocks critical (instance {{ $labels.instance }}) + description: "There are too many outstanding compaction blocks for {{ $labels.instance }}. Increase compactor resources immediately.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoDistributorUsageTrackerErrors + expr: 'sum by (job, reason) (rate(tempo_distributor_usage_tracker_errors_total[5m])) > 0' + for: 30m + labels: + severity: critical + annotations: + summary: Tempo distributor usage tracker errors (instance {{ $labels.instance }}) + description: "Tempo distributor usage tracker errors for {{ $labels.job }} (reason {{ $labels.reason }}).\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoMetricsGeneratorProcessorUpdatesFailing + expr: 'sum by (job) (increase(tempo_metrics_generator_active_processors_update_failed_total[5m])) > 0' + for: 15m + labels: + severity: critical + annotations: + summary: Tempo metrics generator processor updates failing (instance {{ $labels.instance }}) + description: "Tempo metrics generator processor updates are failing for {{ $labels.job }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoMetricsGeneratorServiceGraphsDroppingSpans + expr: '100 * sum by (job) (rate(tempo_metrics_generator_processor_service_graphs_dropped_spans[5m])) / sum by (job) (rate(tempo_metrics_generator_spans_received_total[5m])) > 0.5' + for: 15m + labels: + severity: warning + annotations: + summary: Tempo metrics generator service graphs dropping spans (instance {{ $labels.instance }}) + description: "Tempo metrics generator is dropping {{ printf \"%.2f\" $value }}% of spans in service graphs for {{ $labels.job }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: TempoMetricsGeneratorCollectionsFailing + expr: 'sum by (job) (increase(tempo_metrics_generator_registry_collections_failed_total[5m])) > 2' + for: 5m + labels: + severity: critical + annotations: + summary: Tempo metrics generator collections failing (instance {{ $labels.instance }}) + description: "Tempo metrics generator collections are failing for {{ $labels.job }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + # Fires when the memcached error rate exceeds 20%. Only relevant if Tempo is configured with memcached caching. + - alert: TempoMemcachedErrorsElevated + expr: '100 * sum by (name, job) (rate(tempo_memcache_request_duration_seconds_count{status_code="500"}[5m])) / sum by (name, job) (rate(tempo_memcache_request_duration_seconds_count[5m])) > 20' + for: 10m + labels: + severity: warning + annotations: + summary: Tempo memcached errors elevated (instance {{ $labels.instance }}) + description: "Tempo memcached error rate is {{ printf \"%.2f\" $value }}% for {{ $labels.name }} in {{ $labels.job }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"