[kube-prometheus-stack] Allow to configure keep_firing_for for all Pr…

…ometheus rules (prometheus-community#3890) * [kube-prometheus-stack] Allow to configure keep_firing_for for all Prometheus rules Signed-off-by: Jan-Otto Kröpke <[email protected]> * s/keep_firing_fore/keep_firing_for Signed-off-by: Jan-Otto Kröpke <[email protected]> --------- Signed-off-by: Jan-Otto Kröpke <[email protected]>
giffgaff · Mar 20, 2024 · afdf523 · afdf523
1 parent 5264bf2
commit afdf523
Show file tree

Hide file tree

Showing 22 changed files with 420 additions and 1 deletion.
diff --git a/charts/kube-prometheus-stack/Chart.yaml b/charts/kube-prometheus-stack/Chart.yaml
@@ -21,7 +21,7 @@ name: kube-prometheus-stack
 sources:
   - https://github.com/prometheus-community/helm-charts
   - https://github.com/prometheus-operator/kube-prometheus
-version: 51.6.1
+version: 51.7.0
 appVersion: v0.68.0
 kubeVersion: ">=1.19.0-0"
 home: https://github.com/prometheus-operator/kube-prometheus

diff --git a/charts/kube-prometheus-stack/hack/sync_prometheus_rules.py b/charts/kube-prometheus-stack/hack/sync_prometheus_rules.py
@@ -358,6 +358,28 @@ def add_custom_annotations(rules, group, indent=4):
 
     return rules
 
+
+def add_custom_keep_firing_for(rules, indent=4):
+    """Add if wrapper for additional rules annotations"""
+    indent_spaces = " " * indent + "  "
+    keep_firing_for = (indent_spaces + '{{- with .Values.defaultRules.keepFiringFor }}\n' +
+                        indent_spaces + 'keep_firing_for: "{{ . }}"\n' +
+                        indent_spaces + '{{- end }}')
+    keep_firing_for_len = len(keep_firing_for) + 1
+
+    separator = " " * indent + "  for:.*"
+    alerts_positions = re.finditer(separator, rules)
+    alert = 0
+
+    for alert_position in alerts_positions:
+        # Add rule_condition after 'annotations:' statement
+        index = alert_position.end() + keep_firing_for_len * alert
+        rules = rules[:index] + "\n" + keep_firing_for + rules[index:]
+        alert += 1
+
+    return rules
+
+
 def write_group_to_file(group, url, destination, min_kubernetes, max_kubernetes):
     fix_expr(group['rules'])
     group_name = group['name']
@@ -374,6 +396,7 @@ def write_group_to_file(group, url, destination, min_kubernetes, max_kubernetes)
     # append per-alert rules
     rules = add_custom_labels(rules, group)
     rules = add_custom_annotations(rules, group)
+    rules = add_custom_keep_firing_for(rules)
     rules = add_rules_conditions_from_condition_map(rules)
     rules = add_rules_per_rule_conditions(rules, group)
     # initialize header

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/alertmanager.rules.yaml
@@ -43,6 +43,9 @@ spec:
         # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
         max_over_time(alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) == 0
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -73,6 +76,9 @@ spec:
         < on (namespace,service,cluster) group_left
           count by (namespace,service,cluster) (max_over_time(alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]))
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -104,6 +110,9 @@ spec:
         )
         > 0.01
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -135,6 +144,9 @@ spec:
         )
         > 0.01
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -166,6 +178,9 @@ spec:
         )
         > 0.01
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -195,6 +210,9 @@ spec:
         )
         != 1
       for: 20m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -230,6 +248,9 @@ spec:
         )
         >= 0.5
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}
@@ -265,6 +286,9 @@ spec:
         )
         >= 0.5
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.alertmanager }}

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/config-reloaders.yaml
@@ -40,6 +40,9 @@ spec:
         summary: config-reloader sidecar has not had a successful reload for 10m
       expr: max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.configReloaders }}

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml
@@ -45,6 +45,9 @@ spec:
         )
         > 0
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -69,6 +72,9 @@ spec:
         summary: etcd cluster has insufficient number of members.
       expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
       for: 3m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -93,6 +99,9 @@ spec:
         summary: etcd cluster has no leader.
       expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
       for: 1m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -117,6 +126,9 @@ spec:
         summary: etcd cluster has high number of leader changes.
       expr: increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~".*etcd.*"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~".*etcd.*"}))[15m:1m]) >= 4
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -145,6 +157,9 @@ spec:
         sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
           > 1
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -173,6 +188,9 @@ spec:
         sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code)
           > 5
       for: 5m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -199,6 +217,9 @@ spec:
         histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type))
         > 0.15
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -225,6 +246,9 @@ spec:
         histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m]))
         > 0.15
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -249,6 +273,9 @@ spec:
         summary: etcd cluster has high number of proposal failures.
       expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -275,6 +302,9 @@ spec:
         histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
         > 0.5
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -301,6 +331,9 @@ spec:
         histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
         > 1
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -327,6 +360,9 @@ spec:
         histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~".*etcd.*"}[5m]))
         > 0.25
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -351,6 +387,9 @@ spec:
         summary: etcd cluster database is running full.
       expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_server_quota_backend_bytes{job=~".*etcd.*"}[5m]))*100 > 95
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -375,6 +414,9 @@ spec:
         summary: etcd cluster database growing very fast.
       expr: predict_linear(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[4h], 4*60*60) > etcd_server_quota_backend_bytes{job=~".*etcd.*"}
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}
@@ -400,6 +442,9 @@ spec:
         summary: etcd database size in use is less than 50% of the actual allocated storage.
       expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"}[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes{job=~".*etcd.*"}[5m])) < 0.5 and etcd_mvcc_db_total_size_in_use_in_bytes{job=~".*etcd.*"} > 104857600
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.etcd }}

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/general.rules.yaml
@@ -38,6 +38,9 @@ spec:
         summary: One or more targets are unreachable.
       expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job, namespace, service)) > 10
       for: 10m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: warning
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.general }}

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-apiserver-slos.yaml
@@ -41,6 +41,9 @@ spec:
         and
         sum(apiserver_request:burnrate5m) > (14.40 * 0.01000)
       for: 2m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         long: 1h
         severity: critical
@@ -71,6 +74,9 @@ spec:
         and
         sum(apiserver_request:burnrate30m) > (6.00 * 0.01000)
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         long: 6h
         severity: critical
@@ -101,6 +107,9 @@ spec:
         and
         sum(apiserver_request:burnrate2h) > (3.00 * 0.01000)
       for: 1h
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         long: 1d
         severity: warning
@@ -131,6 +140,9 @@ spec:
         and
         sum(apiserver_request:burnrate6h) > (1.00 * 0.01000)
       for: 3h
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         long: 3d
         severity: warning

diff --git a/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml b/charts/kube-prometheus-stack/templates/prometheus/rules-1.14/kube-state-metrics.yaml
@@ -42,6 +42,9 @@ spec:
         sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])) by (cluster))
         > 0.01
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubeStateMetrics }}
@@ -71,6 +74,9 @@ spec:
         sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])) by (cluster))
         > 0.01
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubeStateMetrics }}
@@ -96,6 +102,9 @@ spec:
         summary: kube-state-metrics sharding is misconfigured.
       expr: stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) != 0
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubeStateMetrics }}
@@ -125,6 +134,9 @@ spec:
         sum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) by (cluster)
         != 0
       for: 15m
+      {{- with .Values.defaultRules.keepFiringFor }}
+      keep_firing_for: "{{ . }}"
+      {{- end }}
       labels:
         severity: critical
       {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubeStateMetrics }}