Added nopo11y-client chart

znsio · May 13, 2024 · 7f9b90b · 7f9b90b
1 parent 4331027
commit 7f9b90b
Show file tree

Hide file tree

Showing 5 changed files with 1,922 additions and 0 deletions.
diff --git a/charts/nopo11y-client/Chart.yaml b/charts/nopo11y-client/Chart.yaml
@@ -0,0 +1,24 @@
+apiVersion: v2
+name: nopo11y
+description: A Helm chart to setup a generic observability for any microservice
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 1.0.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.0.0"
diff --git a/charts/nopo11y-client/templates/defaultAlerts.yaml b/charts/nopo11y-client/templates/defaultAlerts.yaml
@@ -0,0 +1,127 @@
+{{- if .Values.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  namespace: {{ .Values.namespace }}
+  name: {{ .Values.appLabel }}-default-alert-rules
+  labels:
+    release: {{ .Values.prometheusReleaseLabel }}
+spec:
+  groups:
+  - name: {{ .Values.appLabel }}-default-alert-rules
+    rules:
+    - alert: {{ .Values.appLabel }}HighCpuUtilization
+      {{- if .Values.includeReleaseNameInMetricsLabels }}
+      expr: 100 * max(rate(container_cpu_usage_seconds_total{pod=~"{{ .Release.Name }}-{{ .Values.deploymentName }}.*"}[5m])/ on (container, pod) kube_pod_container_resource_requests{resource="cpu"}) by (pod) > 80
+      {{- else }}
+      expr: 100 * max(rate(container_cpu_usage_seconds_total{pod=~"{{ .Values.deploymentName }}.*"}[5m])/ on (container, pod) kube_pod_container_resource_requests{resource="cpu"}) by (pod) > 80
+      {{- end }}
+      for: 10m
+      annotations:
+        description: CPU utilization of pod {{ "{{" }} $labels.pod {{ "}}" }} is above 80% from last 5 minutes .
+        summary: CPU Utilization went over 80% for pod {{ "{{" }} $labels.pod {{ "}}" }}.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{- if .Values.includeReleaseNameInMetricsLabels }}{{ .Release.Name }}-{{ .Values.appLabel }}{{- else }}{{ .Values.appLabel }}{{- end }}-overview
+        {{- end }}
+      labels:
+            severity: warning
+    - alert: {{ .Values.appLabel }}HighCpuUtilization
+      {{- if .Values.includeReleaseNameInMetricsLabels }}
+      expr: 100 * max(rate(container_cpu_usage_seconds_total{pod=~"{{ .Release.Name }}-{{ .Values.deploymentName }}.*"}[5m])/ on (container, pod) kube_pod_container_resource_requests{resource="cpu"}) by (pod) > 90
+      {{- else }}
+      expr: 100 * max(rate(container_cpu_usage_seconds_total{pod=~"{{ .Values.deploymentName }}.*"}[5m])/ on (container, pod) kube_pod_container_resource_requests{resource="cpu"}) by (pod) > 90
+      {{- end }}
+      for: 10m
+      annotations:
+        description: CPU utilization of pod {{ "{{" }} $labels.pod {{ "}}" }} is above 90% from last 5 minutes.
+        summary: CPU Utilization went over 90% for pod {{ "{{" }} $labels.pod {{ "}}" }}.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{- if .Values.includeReleaseNameInMetricsLabels }}{{ .Release.Name }}-{{ .Values.appLabel }}{{- else }}{{ .Values.appLabel }}{{- end }}-overview
+        {{- end }}
+      labels:
+            severity: critical
+    - alert: {{ .Values.appLabel }}HighMemoryUtilization
+      {{- if .Values.includeReleaseNameInMetricsLabels }}
+      expr: 100 * max( container_memory_working_set_bytes{pod=~"{{ .Release.Name }}-{{ .Values.deploymentName }}.*"} / on (container, pod) kube_pod_container_resource_limits{resource="memory"}) by (pod) > 80
+      {{- else }}
+      expr: 100 * max( container_memory_working_set_bytes{pod=~"{{ .Values.deploymentName }}.*"} / on (container, pod) kube_pod_container_resource_limits{resource="memory"}) by (pod) > 80
+      {{- end }}
+      for: 10m
+      annotations:
+        description: Memory utilization of pod {{ "{{" }} $labels.pod {{ "}}" }} is above 80% from last 5 minutes.
+        summary: Memory Utilization went over 80% for pod {{ "{{" }} $labels.pod {{ "}}" }}.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{- if .Values.includeReleaseNameInMetricsLabels }}{{ .Release.Name }}-{{ .Values.appLabel }}{{- else }}{{ .Values.appLabel }}{{- end }}-overview
+        {{- end }}
+      labels:
+            severity: warning
+    - alert: {{ .Values.appLabel }}HighMemoryUtilization
+      {{- if .Values.includeReleaseNameInMetricsLabels }}
+      expr: 100 * max( container_memory_working_set_bytes{pod=~"{{ .Release.Name }}-{{ .Values.deploymentName }}.*"} / on (container, pod) kube_pod_container_resource_limits{resource="memory"}) by (pod) > 90
+      {{- else }}
+      expr: 100 * max( container_memory_working_set_bytes{pod=~"{{ .Values.deploymentName }}.*"} / on (container, pod) kube_pod_container_resource_limits{resource="memory"}) by (pod) > 90
+      {{- end }}
+      for: 10m
+      annotations:
+        description: Memory utilization of pod {{ "{{" }} $labels.pod {{ "}}" }} is above 90% from last 5 minutes.
+        summary: Memory Utilization went over 90% for pod {{ "{{" }} $labels.pod {{ "}}" }}.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{- if .Values.includeReleaseNameInMetricsLabels }}{{ .Release.Name }}-{{ .Values.appLabel }}{{- else }}{{ .Values.appLabel }}{{- end }}-overview
+        {{- end }}
+      labels:
+            severity: critical
+    {{- if .Values.istioMetrics.enabled }}
+    - alert: {{ .Values.appLabel }}High5xxErrorRate
+      {{- if .Values.includeReleaseNameInMetricsLabels }}
+      expr: sum(rate(istio_requests_total{app="{{ .Release.Name }}-{{ .Values.appLabel }}", destination_app=~"{{ .Release.Name }}-{{ .Values.appLabel }}", response_code=~"5.."}[5m])) by (instance) / sum(rate(istio_requests_total{app="{{ .Release.Name }}-{{ .Values.appLabel }}", destination_app=~"{{ .Release.Name }}-{{ .Values.appLabel }}"}[5m])) by (instance) * 100 > {{ .Values.errorRate5xx }}
+      {{- else }}
+      expr: sum(rate(istio_requests_total{app="{{ .Values.appLabel }}", destination_app=~"{{ .Values.appLabel }}", response_code=~"5.."}[5m])) by (instance) / sum(rate(istio_requests_total{app="{{ .Values.appLabel }}", destination_app=~"{{ .Values.appLabel }}"}[5m])) by (instance) * 100 > {{ .Values.errorRate5xx }}
+      {{- end }}
+      annotations:
+        description: {{- if .Values.includeReleaseNameInMetricsLabels }} {{ .Release.Name }}-{{ .Values.appLabel }}{{- else }} {{ .Values.appLabel }}{{- end }} service is experiencing high 5xx errors rate from last 5 minutes.
+        summary: {{- if .Values.includeReleaseNameInMetricsLabels }} {{ .Release.Name }}-{{ .Values.appLabel }}{{- else }} {{ .Values.appLabel }}{{- end }} service is experiencing high 5xx error rate.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{- if .Values.includeReleaseNameInMetricsLabels }}{{ .Release.Name }}-{{ .Values.appLabel }}{{- else }}{{ .Values.appLabel }}{{- end }}-overview
+        {{- end }}
+      labels:
+            severity: critical
+    - alert: {{ .Values.appLabel }}High4xxErrorRate
+      {{- if .Values.includeReleaseNameInMetricsLabels }}
+      expr: sum(rate(istio_requests_total{app="{{ .Release.Name }}-{{ .Values.appLabel }}", destination_app=~"{{ .Release.Name }}-{{ .Values.appLabel }}", response_code=~"4.."}[5m])) by (instance) / sum(rate(istio_requests_total{app="{{ .Release.Name }}-{{ .Values.appLabel }}", destination_app=~"{{ .Release.Name }}-{{ .Values.appLabel }}"}[5m])) by (instance) * 100 > {{ .Values.errorRate4xx }}
+      {{- else }}
+      expr: sum(rate(istio_requests_total{app="{{ .Values.appLabel }}", destination_app=~"{{ .Values.appLabel }}", response_code=~"4.."}[5m])) by (instance) / sum(rate(istio_requests_total{app="{{ .Values.appLabel }}", destination_app=~"{{ .Values.appLabel }}"}[5m])) by (instance) * 100 > {{ .Values.errorRate4xx }}
+      {{- end }}
+      for: 5m
+      annotations:
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{- if .Values.includeReleaseNameInMetricsLabels }}{{ .Release.Name }}-{{ .Values.appLabel }}{{- else }}{{ .Values.appLabel }}{{- end }}-overview
+        {{- end }}
+        description: {{- if .Values.includeReleaseNameInMetricsLabels }} {{ .Release.Name }}-{{ .Values.appLabel }}{{- else }} {{ .Values.appLabel }}{{- end }} service is experiencing high 4xx errors rate from last 5 minutes.
+        summary: {{- if .Values.includeReleaseNameInMetricsLabels }} {{ .Release.Name }}-{{ .Values.appLabel }}{{- else }} {{ .Values.appLabel }}{{- end }} service is experiencing high 4xx error rate.
+      labels:
+            severity: warning
+    {{- end }}
+    {{- if .Values.nginxIngressMetrics.enabled }}
+    - alert: {{ .Values.appLabel }}IngressHigh5xxErrorRate
+      expr: sum(rate(nginx_ingress_controller_requests{ingress=~"{{ .Values.nginxIngressMetrics.ingressName }}",status=~"5.."}[5m])) / sum(rate(nginx_ingress_controller_requests{ingress=~"{{ .Values.nginxIngressMetrics.ingressName }}"}[5m])) * 100 > {{ .Values.errorRate5xx }}
+      annotations:
+        description: {{ .Values.appLabel }} service is experiencing high 5xx errors rate from last 5 minutes.
+        summary: {{ .Values.appLabel }} is experiencing high 5xx error rate.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{ .Values.appLabel }}-overview
+        {{- end }}
+      labels:
+            severity: critical
+    - alert: {{ .Values.appLabel }}IngressHigh4xxErrorRate
+      expr: sum(rate(nginx_ingress_controller_requests{ingress=~"{{ .Values.nginxIngressMetrics.ingressName }}",status=~"4.."}[5m])) / sum(rate(nginx_ingress_controller_requests{ingress=~"{{ .Values.nginxIngressMetrics.ingressName }}"}[5m])) * 100 > {{ .Values.rrorRate4xx }}
+      for: 10m
+      annotations:
+        description: {{ .Values.appLabel }} service is experiencing high 4xx errors rate from last 5 minutes.
+        summary: {{ .Values.appLabel }} service is experiencing high 4xx error rate.
+        {{- if .Values.grafanaURL }}
+        dashboard: {{ .Values.grafanaURL }}/d/{{ .Values.appLabel }}-overview
+        {{- end }}
+      labels:
+            severity: warning
+    {{- end }}
+{{- end }}