From 35490f3e28cb5628e256ceafec933c8c4208da1e Mon Sep 17 00:00:00 2001 From: "lucas.mathieu" Date: Tue, 30 Dec 2025 00:08:43 +0100 Subject: [PATCH] feat(prometheus): add prometheus self alerts --- .../prometheus/alerts/embedded-exporter.yml | 258 ++++++++++++++++++ .../node-exporter.yml} | 0 monitoring/prometheus/prometheus.yml | 2 +- 3 files changed, 259 insertions(+), 1 deletion(-) create mode 100644 monitoring/prometheus/alerts/embedded-exporter.yml rename monitoring/prometheus/{node-exporter.rules => alerts/node-exporter.yml} (100%) diff --git a/monitoring/prometheus/alerts/embedded-exporter.yml b/monitoring/prometheus/alerts/embedded-exporter.yml new file mode 100644 index 0000000..5c623d5 --- /dev/null +++ b/monitoring/prometheus/alerts/embedded-exporter.yml @@ -0,0 +1,258 @@ +groups: + +- name: EmbeddedExporter + + + rules: + + - alert: PrometheusJobMissing + expr: 'absent(up{job="prometheus"})' + for: 0m + labels: + severity: warning + annotations: + summary: Prometheus job missing (instance {{ $labels.instance }}) + description: "A Prometheus job has disappeared\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: PrometheusTargetMissing + expr: 'up == 0' + for: 0m + 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: 0m + 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: 0m + 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: 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: 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: PrometheusAlertmanagerJobMissing + expr: 'absent(up{job="alertmanager"})' + for: 0m + labels: + severity: warning + annotations: + summary: Prometheus AlertManager job missing (instance {{ $labels.instance }}) + description: "A Prometheus AlertManager job has disappeared\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 }}" + + - alert: PrometheusAlertmanagerConfigNotSynced + expr: 'count(count_values("config_hash", alertmanager_config_hash)) > 1' + for: 0m + 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 }}" + + - 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: 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 }}" + + - 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: 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: PrometheusAlertmanagerNotificationFailing + expr: 'rate(alertmanager_notifications_failed_total[1m]) > 0' + for: 0m + labels: + severity: critical + annotations: + summary: Prometheus AlertManager notification failing (instance {{ $labels.instance }}) + description: "Alertmanager is failing sending 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: 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\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + + - alert: PrometheusTargetScrapeDuplicate + expr: 'increase(prometheus_target_scrapes_sample_duplicate_timestamp_total[5m]) > 0' + 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\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[1m]) > 0' + for: 0m + 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[1m]) > 0' + for: 0m + 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: 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 }}" diff --git a/monitoring/prometheus/node-exporter.rules b/monitoring/prometheus/alerts/node-exporter.yml similarity index 100% rename from monitoring/prometheus/node-exporter.rules rename to monitoring/prometheus/alerts/node-exporter.yml diff --git a/monitoring/prometheus/prometheus.yml b/monitoring/prometheus/prometheus.yml index ab8fc20..7e8062e 100644 --- a/monitoring/prometheus/prometheus.yml +++ b/monitoring/prometheus/prometheus.yml @@ -11,7 +11,7 @@ global: # Load and evaluate rules in this file every 'evaluation_interval' seconds. rule_files: - - '/etc/prometheus/*.rules' + - '/etc/prometheus/alerts/*' # alert alerting: