Add dell-exporter

Change-Id: I55877064e5ba72abae8037578b1b50f51a67e518

charts/dell-exporter/Chart.yaml

@@ -0,0 +1,11 @@
+---
+apiVersion: v1
+name: dell-exporter
+version: 0.1.1
+description: Dell exporter for Prometheus
+home: https://github.com/vexxhost/helm-charts
+maintainers:
+- name: Mohammed Naser
+  email: mnaser@vexxhost.com
+  url: https://github.com/mnaser
+appVersion: v1.4.0

charts/dell-exporter/templates/_helpers.tpl

@@ -0,0 +1,45 @@
+{{/* vim: set filetype=mustache: */}}
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "dell-exporter.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "dell-exporter.fullname" -}}
+{{- if .Values.fullnameOverride -}}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- $name := default .Chart.Name .Values.nameOverride -}}
+{{- if contains $name .Release.Name -}}
+{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
+{{- else -}}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+
+{{/*
+Generate basic labels
+*/}}
+{{- define "dell-exporter.labels" }}
+app.kubernetes.io/name: {{ include "dell-exporter.fullname" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+app.kubernetes.io/component: metrics
+app.kubernetes.io/part-of: hardware
+{{- if .Values.commonLabels }}
+{{ toYaml .Values.commonLabels }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "dell-exporter.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
+{{- end -}}

charts/dell-exporter/templates/daemonset.yaml

@@ -0,0 +1,43 @@
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  namespace: {{ .Release.Namespace }}
+  name: {{ include "dell-exporter.fullname" . }}
+  labels:
+{{ include "dell-exporter.labels" . | indent 4 }}
+spec:
+  selector:
+    matchLabels:
+{{ include "dell-exporter.labels" . | indent 6 }}
+  template:
+    metadata:
+      labels:
+{{ include "dell-exporter.labels" . | indent 8 }}
+    spec:
+      containers:
+      - name: dell-exporter
+        image: {{ .Values.image }}
+        ports:
+        - name: metrics
+          containerPort: 9137
+        resources:
+          limits:
+            cpu: 6000m
+            memory: 512Mi
+          requests:
+            cpu: 500m
+            memory: 512Mi
+        securityContext:
+          privileged: true
+    {{- with $.Values.tolerations }}
+      tolerations:
+{{ toYaml . | indent 8 }}
+    {{- end }}
+    {{- with $.Values.nodeSelector }}
+      nodeSelector:
+{{ toYaml . | indent 8 }}
+    {{- end }}
+  updateStrategy:
+    rollingUpdate:
+      maxUnavailable: 10%

charts/dell-exporter/templates/prometheusrule.yaml

@@ -0,0 +1,111 @@
+---
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  namespace: {{ .Release.Namespace }}
+  name: {{ include "dell-exporter.fullname" . }}
+  labels:
+{{ include "dell-exporter.labels" . | indent 4 }}
+spec:
+  groups:
+  - name: dell
+    rules:
+    - alert: DellSystemStatus
+      expr: |
+        dell_hw_system_status == 2
+      for: 1m
+      labels:
+        severity: P4
+      annotations:
+        summary: "[`{{`{{$labels.instance}}`}}`] System warning"
+        description: >
+          The host `{{`{{$labels.instance}}`}}` is reporting a non-critical status,
+          please investigate.  If this is the only firing alert, please add
+          another one to handle the specific failure.
+
+    - alert: DellSystemStatus
+      expr: |
+        dell_hw_system_status == 1
+      for: 1m
+      labels:
+        severity: P3
+      annotations:
+        summary: "[`{{`{{$labels.instance}}`}}`] System failure"
+        description: >
+          The host `{{`{{$labels.instance}}`}}` is reporting a critical status,
+          please investigate.  If this is the only firing alert, please add
+          another one to handle the specific failure.
+
+    - alert: DellFanFailure
+      expr: |
+        dell_hw_chassis_fan_status != 0
+      for: 1m
+      labels:
+        severity: P4
+      annotations:
+        summary: "[`{{`{{$labels.instance}}`}}`] Fan failure"
+        description: >
+          The `{{`{{$labels.fan}}`}}` on host `{{`{{$labels.instance}}`}}` is reporting
+          a failure, please replace it.
+
+    - alert: DellMemoryFailure
+      expr: |
+        dell_hw_chassis_memory_status != 0
+      for: 1m
+      labels:
+        severity: P4
+      annotations:
+        summary: "[`{{`{{$labels.instance}}`}}`] Memory failure"
+        description: >
+          The `{{`{{$labels.memory}}`}}` on host `{{`{{$labels.instance}}`}}` is reporting
+          a failure, please replace it.
+
+    - alert: DellPowerSupplyFailure
+      expr: |
+        dell_hw_ps_status != 0
+      for: 1m
+      labels:
+        severity: P3
+      annotations:
+        summary: "[`{{`{{$labels.instance}}`}}`] Power failure"
+        description: >
+          The PSU `{{`{{$labels.id}}`}}` on host `{{`{{$labels.instance}}`}}` is reporting
+          a failure, please investigate if power is lost or power supply
+          requires replacement.
+
+    - alert: DellHardwareStorageFailure
+      expr: |
+        dell_hw_storage_controller_status != 0
+      for: 1m
+      labels:
+        severity: P3
+      annotations:
+        summary: "[`{{`{{$labels.instance}}`}}`] Storage failure"
+        description: >
+          The storage controller `{{`{{$labels.id}}`}}` on host `{{`{{$labels.instance}}`}}`
+          is reporting a failure, please investigate inside the host and add the
+          appropriate alerting rules if no alerts except this one have fired.
+
+    - alert: DellChassisTemperature
+      expr: |
+        dell_hw_chassis_temps_reading > dell_hw_chassis_temps_max_warning
+      labels:
+        severity: P3
+      annotations:
+        summary: "[{{`{{$labels.instance}}`}}] {{`{{$labels.component}}`}}"
+        description: >
+          The component {{`{{$labels.component}}`}} is reporting temperatures
+          of {{`{{$value}}`}} which is above the critical reading for
+          {{`{{$labels.instance}}`}}.
+
+    - alert: DellChassisTemperature
+      expr: |
+        dell_hw_chassis_temps_reading > dell_hw_chassis_temps_max_warning
+      labels:
+        severity: P4
+      annotations:
+        summary: "[{{`{{$labels.instance}}`}}] {{`{{$labels.component}}`}}"
+        description: >
+          The component {{`{{$labels.component}}`}} is reporting temperatures
+          of {{`{{$value}}`}} which is above the warning reading for
+          {{`{{$labels.instance}}`}}.

charts/dell-exporter/templates/service.yaml

@@ -0,0 +1,16 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  namespace: {{ .Release.Namespace }}
+  name: {{ include "dell-exporter.fullname" . }}
+  labels:
+{{ include "dell-exporter.labels" . | indent 4 }}
+spec:
+  clusterIP: None
+  ports:
+  - name: metrics
+    port: 9137
+    targetPort: metrics
+  selector:
+{{ include "dell-exporter.labels" . | indent 4 }}

charts/dell-exporter/templates/servicemonitor.yaml

@@ -0,0 +1,25 @@
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  namespace: {{ .Release.Namespace }}
+  name: {{ include "dell-exporter.fullname" . }}
+  labels:
+{{ include "dell-exporter.labels" $ | indent 4 }}
+spec:
+  endpoints:
+  - port: metrics
+    scrapeTimeout: 30s
+    relabelings:
+    - action: replace
+      regex: (.*)
+      replacment: $1
+      sourceLabels:
+      - __meta_kubernetes_pod_node_name
+      targetLabel: instance
+    - action: labeldrop
+      regex: '^(endpoint|namespace|pod|service)$'
+  jobLabel: jobLabel
+  selector:
+    matchLabels:
+{{ include "dell-exporter.labels" $ | indent 6 }}

charts/dell-exporter/values.yaml

@@ -0,0 +1,2 @@
+---
+image: galexrt/dellhw_exporter@sha256:09ce2b8459dcd30a2bfdb6f3b2764dd461d09844d18a893ca5eb273c39eadce4