KubeZero/charts/kubezero-metrics/adjust_alarms.patch

67 lines
3.9 KiB
Diff

diff -turN charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/etcd.yaml
--- charts/kube-prometheus-stack/templates/prometheus/rules-1.14/etcd.yaml 2021-04-14 22:13:29.000000000 +0200
+++ charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/etcd.yaml 2021-04-15 14:43:03.074281889 +0200
@@ -54,34 +54,6 @@
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
- - alert: etcdHighNumberOfFailedGRPCRequests
- annotations:
- message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
- expr: |-
- 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
- /
- sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
- > 1
- for: 10m
- labels:
- severity: warning
-{{- if .Values.defaultRules.additionalRuleLabels }}
-{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
-{{- end }}
- - alert: etcdHighNumberOfFailedGRPCRequests
- annotations:
- message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
- expr: |-
- 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
- /
- sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) BY (job, instance, grpc_service, grpc_method)
- > 5
- for: 5m
- labels:
- severity: critical
-{{- if .Values.defaultRules.additionalRuleLabels }}
-{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
-{{- end }}
- alert: etcdGRPCRequestsSlow
annotations:
message: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": gRPC requests to {{`{{`}} $labels.grpc_method {{`}}`}} are taking {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'
diff -turN charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/node-exporter.yaml
--- charts/kube-prometheus-stack/templates/prometheus/rules-1.14/node-exporter.yaml 2021-04-14 22:13:29.000000000 +0200
+++ charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/node-exporter.yaml 2021-04-15 14:49:41.614282790 +0200
@@ -30,7 +30,7 @@
summary: Filesystem is predicted to run out of space within the next 24 hours.
expr: |-
(
- node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 40
+ node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 25
and
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
and
@@ -48,7 +48,7 @@
summary: Filesystem is predicted to run out of space within the next 4 hours.
expr: |-
(
- node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 15
+ node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 10
and
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
and
@@ -259,4 +259,4 @@
{{- if .Values.defaultRules.additionalRuleLabels }}
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
{{- end }}
-{{- end }}
\ No newline at end of file
+{{- end }}