2021-07-01 11:36:35 +00:00
|
|
|
diff -tubr charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl charts/kube-prometheus-stack.zdt/charts/grafana/templates/_pod.tpl
|
|
|
|
--- charts/kube-prometheus-stack/charts/grafana/templates/_pod.tpl 2021-06-26 19:54:57.000000000 +0200
|
|
|
|
+++ charts/kube-prometheus-stack.zdt/charts/grafana/templates/_pod.tpl 2021-07-01 13:31:20.750609396 +0200
|
|
|
|
@@ -198,11 +198,16 @@
|
2021-04-25 09:59:54 +00:00
|
|
|
- name: FOLDER_ANNOTATION
|
|
|
|
value: "{{ .Values.sidecar.dashboards.folderAnnotation }}"
|
|
|
|
{{- end }}
|
|
|
|
+ - name: SCRIPT
|
|
|
|
+ value: /opt/script.sh
|
|
|
|
resources:
|
|
|
|
{{ toYaml .Values.sidecar.resources | indent 6 }}
|
|
|
|
volumeMounts:
|
|
|
|
- name: sc-dashboard-volume
|
|
|
|
mountPath: {{ .Values.sidecar.dashboards.folder | quote }}
|
|
|
|
+ - name: script-volume
|
|
|
|
+ mountPath: /opt/script.sh
|
|
|
|
+ subPath: script.sh
|
|
|
|
{{- end}}
|
|
|
|
- name: {{ .Chart.Name }}
|
|
|
|
{{- if .Values.image.sha }}
|
2021-07-01 11:36:35 +00:00
|
|
|
diff -tubr 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 2021-06-26 19:54:57.000000000 +0200
|
|
|
|
+++ charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/etcd.yaml 2021-07-01 13:31:20.750609396 +0200
|
2021-04-15 13:03:52 +00:00
|
|
|
@@ -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 {{`}}`}}.'
|
2021-07-01 11:36:35 +00:00
|
|
|
diff -tubr 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 2021-06-26 19:54:57.000000000 +0200
|
|
|
|
+++ charts/kube-prometheus-stack.zdt/templates/prometheus/rules-1.14/node-exporter.yaml 2021-07-01 13:31:20.753942729 +0200
|
|
|
|
@@ -31,7 +31,7 @@
|
2021-04-15 13:03:52 +00:00
|
|
|
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
|
2021-07-01 11:36:35 +00:00
|
|
|
@@ -50,7 +50,7 @@
|
2021-04-15 13:03:52 +00:00
|
|
|
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
|