diff --git a/charts/kubezero-metrics/Chart.yaml b/charts/kubezero-metrics/Chart.yaml index 6a3e45d..eeddf7b 100644 --- a/charts/kubezero-metrics/Chart.yaml +++ b/charts/kubezero-metrics/Chart.yaml @@ -2,7 +2,7 @@ apiVersion: v2 name: kubezero-metrics description: KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all Kubernetes integrations. type: application -version: 0.5.1 +version: 0.5.2 home: https://kubezero.com icon: https://cdn.zero-downtime.net/assets/kubezero/logo-small-64.png keywords: diff --git a/charts/kubezero-metrics/README.md b/charts/kubezero-metrics/README.md index 9c6f50e..91b1ea1 100644 --- a/charts/kubezero-metrics/README.md +++ b/charts/kubezero-metrics/README.md @@ -1,6 +1,6 @@ # kubezero-metrics -![Version: 0.5.1](https://img.shields.io/badge/Version-0.5.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) +![Version: 0.5.2](https://img.shields.io/badge/Version-0.5.2-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) KubeZero Umbrella Chart for Prometheus, Grafana and Alertmanager as well as all Kubernetes integrations. diff --git a/charts/kubezero-metrics/configs/jsonnetfile.lock.json b/charts/kubezero-metrics/configs/jsonnetfile.lock.json index bdb5d22..cb8f160 100644 --- a/charts/kubezero-metrics/configs/jsonnetfile.lock.json +++ b/charts/kubezero-metrics/configs/jsonnetfile.lock.json @@ -38,7 +38,7 @@ "subdir": "grafana-builder" } }, - "version": "b9941184e4c9987077898e788343e21a800d8465", + "version": "bc9b685050691a78ee414cd8f789857de0eabe8d", "sum": "GRf2GvwEU4jhXV+JOonXSZ4wdDv8mnHBPCQ6TUVd+g8=" }, { diff --git a/charts/kubezero-metrics/templates/rules/etcd-mixin.yaml b/charts/kubezero-metrics/templates/rules/etcd-mixin.yaml index ef8f7a2..0423fb3 100644 --- a/charts/kubezero-metrics/templates/rules/etcd-mixin.yaml +++ b/charts/kubezero-metrics/templates/rules/etcd-mixin.yaml @@ -59,28 +59,6 @@ spec: {{- toYaml .Values.additionalRuleLabels | nindent 8 }} {{- end }} severity: warning - - alert: etcdHighNumberOfFailedGRPCRequests - annotations: - description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' - summary: etcd cluster has high number of failed grpc requests. - expr: "100 * sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[5m])) without (grpc_type, grpc_code)\n /\nsum(rate(grpc_server_handled_total{job=~\".*etcd.*\"}[5m])) without (grpc_type, grpc_code)\n > 1\n" - for: 10m - labels: - {{- if .Values.additionalRuleLabels }} - {{- toYaml .Values.additionalRuleLabels | nindent 8 }} - {{- end }} - severity: warning - - alert: etcdHighNumberOfFailedGRPCRequests - annotations: - description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": {{`{{`}} $value {{`}}`}}% of requests for {{`{{`}} $labels.grpc_method {{`}}`}} failed on etcd instance {{`{{`}} $labels.instance {{`}}`}}.' - summary: etcd cluster has high number of failed grpc requests. - expr: "100 * sum(rate(grpc_server_handled_total{job=~\".*etcd.*\", grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[5m])) without (grpc_type, grpc_code)\n /\nsum(rate(grpc_server_handled_total{job=~\".*etcd.*\"}[5m])) without (grpc_type, grpc_code)\n > 5\n" - for: 5m - labels: - {{- if .Values.additionalRuleLabels }} - {{- toYaml .Values.additionalRuleLabels | nindent 8 }} - {{- end }} - severity: critical - alert: etcdGRPCRequestsSlow annotations: description: 'etcd cluster "{{`{{`}} $labels.job {{`}}`}}": 99th percentile of gRPC requests is {{`{{`}} $value {{`}}`}}s on etcd instance {{`{{`}} $labels.instance {{`}}`}}.'