kubezero/charts/kubezero-metrics/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/prometheus.yaml

448 lines
25 KiB
YAML

{{- /*
Generated from 'prometheus' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/prometheus-prometheusRule.yaml
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.prometheus }}
{{- $prometheusJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" }}
{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }}
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "prometheus" | trunc 63 | trimSuffix "-" }}
namespace: {{ template "kube-prometheus-stack.namespace" . }}
labels:
app: {{ template "kube-prometheus-stack.name" . }}
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
{{- if .Values.defaultRules.labels }}
{{ toYaml .Values.defaultRules.labels | indent 4 }}
{{- end }}
{{- if .Values.defaultRules.annotations }}
annotations:
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
{{- end }}
spec:
groups:
- name: prometheus
rules:
{{- if not (.Values.defaultRules.disabled.PrometheusBadConfig | default false) }}
- alert: PrometheusBadConfig
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to reload its configuration.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusbadconfig
summary: Failed Prometheus configuration reload.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(prometheus_config_last_reload_successful{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) == 0
for: 10m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusNotificationQueueRunningFull | default false) }}
- alert: PrometheusNotificationQueueRunningFull
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Alert notification queue of Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is running full.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusnotificationqueuerunningfull
summary: Prometheus alert notification queue predicted to run full in less than 30m.
expr: |-
# Without min_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
predict_linear(prometheus_notifications_queue_length{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m], 60 * 30)
>
min_over_time(prometheus_notifications_queue_capacity{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
)
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusErrorSendingAlertsToSomeAlertmanagers | default false) }}
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to Alertmanager {{`{{`}}$labels.alertmanager{{`}}`}}.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheuserrorsendingalertstosomealertmanagers
summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
expr: |-
(
rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
/
rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
)
* 100
> 1
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusNotConnectedToAlertmanagers | default false) }}
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not connected to any Alertmanagers.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusnotconnectedtoalertmanagers
summary: Prometheus is not connected to any Alertmanagers.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(prometheus_notifications_alertmanagers_discovered{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) < 1
for: 10m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusTSDBReloadsFailing | default false) }}
- alert: PrometheusTSDBReloadsFailing
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} reload failures over the last 3h.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustsdbreloadsfailing
summary: Prometheus has issues reloading blocks from disk.
expr: increase(prometheus_tsdb_reloads_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0
for: 4h
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusTSDBCompactionsFailing | default false) }}
- alert: PrometheusTSDBCompactionsFailing
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has detected {{`{{`}}$value | humanize{{`}}`}} compaction failures over the last 3h.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustsdbcompactionsfailing
summary: Prometheus has issues compacting blocks.
expr: increase(prometheus_tsdb_compactions_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[3h]) > 0
for: 4h
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusNotIngestingSamples | default false) }}
- alert: PrometheusNotIngestingSamples
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is not ingesting samples.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusnotingestingsamples
summary: Prometheus is not ingesting samples.
expr: |-
(
rate(prometheus_tsdb_head_samples_appended_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) <= 0
and
(
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}) > 0
or
sum without(rule_group) (prometheus_rule_group_rules{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}) > 0
)
)
for: 10m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusDuplicateTimestamps | default false) }}
- alert: PrometheusDuplicateTimestamps
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with different values but duplicated timestamp.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusduplicatetimestamps
summary: Prometheus is dropping samples with duplicate timestamps.
expr: rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 10m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusOutOfOrderTimestamps | default false) }}
- alert: PrometheusOutOfOrderTimestamps
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} is dropping {{`{{`}} printf "%.4g" $value {{`}}`}} samples/s with timestamps arriving out of order.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusoutofordertimestamps
summary: Prometheus drops samples with out-of-order timestamps.
expr: rate(prometheus_target_scrapes_sample_out_of_order_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 10m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusRemoteStorageFailures | default false) }}
- alert: PrometheusRemoteStorageFailures
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} failed to send {{`{{`}} printf "%.1f" $value {{`}}`}}% of the samples to {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusremotestoragefailures
summary: Prometheus fails to send samples to remote storage.
expr: |-
(
(rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]))
/
(
(rate(prometheus_remote_storage_failed_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]))
+
(rate(prometheus_remote_storage_succeeded_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) or rate(prometheus_remote_storage_samples_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]))
)
)
* 100
> 1
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusRemoteWriteBehind | default false) }}
- alert: PrometheusRemoteWriteBehind
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} remote write is {{`{{`}} printf "%.1f" $value {{`}}`}}s behind for {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusremotewritebehind
summary: Prometheus remote write is behind.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
- ignoring(remote_name, url) group_right
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
)
> 120
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusRemoteWriteDesiredShards | default false) }}
- alert: PrometheusRemoteWriteDesiredShards
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} remote write desired shards calculation wants to run {{`{{`}} $value {{`}}`}} shards for queue {{`{{`}} $labels.remote_name{{`}}`}}:{{`{{`}} $labels.url {{`}}`}}, which is more than the max of {{`{{`}} printf `prometheus_remote_storage_shards_max{instance="%s",job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}` $labels.instance | query | first | value {{`}}`}}.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusremotewritedesiredshards
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
expr: |-
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_shards_desired{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
>
max_over_time(prometheus_remote_storage_shards_max{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m])
)
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusRuleFailures | default false) }}
- alert: PrometheusRuleFailures
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed to evaluate {{`{{`}} printf "%.0f" $value {{`}}`}} rules in the last 5m.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusrulefailures
summary: Prometheus is failing rule evaluations.
expr: increase(prometheus_rule_evaluation_failures_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusMissingRuleEvaluations | default false) }}
- alert: PrometheusMissingRuleEvaluations
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has missed {{`{{`}} printf "%.0f" $value {{`}}`}} rule group evaluations in the last 5m.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusmissingruleevaluations
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
expr: increase(prometheus_rule_group_iterations_missed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusTargetLimitHit | default false) }}
- alert: PrometheusTargetLimitHit
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has dropped {{`{{`}} printf "%.0f" $value {{`}}`}} targets because the number of targets exceeded the configured target_limit.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustargetlimithit
summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
expr: increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusLabelLimitHit | default false) }}
- alert: PrometheusLabelLimitHit
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has dropped {{`{{`}} printf "%.0f" $value {{`}}`}} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheuslabellimithit
summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit.
expr: increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusScrapeBodySizeLimitHit | default false) }}
- alert: PrometheusScrapeBodySizeLimitHit
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed {{`{{`}} printf "%.0f" $value {{`}}`}} scrapes in the last 5m because some targets exceeded the configured body_size_limit.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusscrapebodysizelimithit
summary: Prometheus has dropped some targets that exceeded body size limit.
expr: increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusScrapeSampleLimitHit | default false) }}
- alert: PrometheusScrapeSampleLimitHit
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} has failed {{`{{`}} printf "%.0f" $value {{`}}`}} scrapes in the last 5m because some targets exceeded the configured sample_limit.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheusscrapesamplelimithit
summary: Prometheus has failed scrapes that have exceeded the configured sample limit.
expr: increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusTargetSyncFailure | default false) }}
- alert: PrometheusTargetSyncFailure
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: '{{`{{`}} printf "%.0f" $value {{`}}`}} targets in Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} have failed to sync because invalid configuration was supplied.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheustargetsyncfailure
summary: Prometheus has failed to sync targets.
expr: increase(prometheus_target_sync_failed_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[30m]) > 0
for: 5m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusHighQueryLoad | default false) }}
- alert: PrometheusHighQueryLoad
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} query API has less than 20% available capacity in its query engine for the last 15 minutes.
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheushighqueryload
summary: Prometheus is reaching its maximum capacity serving concurrent requests.
expr: avg_over_time(prometheus_engine_queries{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="{{ $prometheusJob }}",namespace="{{ $namespace }}"}[5m]) > 0.8
for: 15m
labels:
severity: warning
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.PrometheusErrorSendingAlertsToAnyAlertmanager | default false) }}
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
description: '{{`{{`}} printf "%.1f" $value {{`}}`}}% minimum errors while sending alerts from Prometheus {{`{{`}}$labels.namespace{{`}}`}}/{{`{{`}}$labels.pod{{`}}`}} to any Alertmanager.'
runbook_url: {{ .Values.defaultRules.runbookUrl }}/prometheus/prometheuserrorsendingalertstoanyalertmanager
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |-
min without (alertmanager) (
rate(prometheus_notifications_errors_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}",alertmanager!~``}[5m])
/
rate(prometheus_notifications_sent_total{job="{{ $prometheusJob }}",namespace="{{ $namespace }}",alertmanager!~``}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
{{- end }}
{{- end }}