Update node-problem-detector to v0.8.8

assets/charts/components/node-problem-detector/.helmignore

@@ -0,0 +1,21 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj

assets/charts/components/node-problem-detector/Chart.yaml

@@ -1,20 +1,20 @@
 apiVersion: v1
-name: node-problem-detector
-version: "1.8.6"
-appVersion: v0.8.5
-home: https://github.com/kubernetes/node-problem-detector
+appVersion: v0.8.8
 description: |
   This chart installs a [node-problem-detector](https://github.com/kubernetes/node-problem-detector) daemonset. This tool aims to make various node problems visible to the upstream layers in cluster management stack. It is a daemon which runs on each node, detects node problems and reports them to apiserver.
+engine: gotpl
+home: https://github.com/kubernetes/node-problem-detector
 icon: https://github.com/kubernetes/kubernetes/raw/master/logo/logo.png
 keywords:
 - node
 - problem
 - detector
 - monitoring
+maintainers:
+- email: no-reply@deliveryhero.com
+  name: max-rocket-internet
+name: node-problem-detector
 sources:
 - https://github.com/kubernetes/node-problem-detector
 - https://kubernetes.io/docs/concepts/architecture/nodes/#condition
-maintainers:
-- name: max-rocket-internet
-  email: no-reply@deliveryhero.com
-engine: gotpl
+version: 2.0.2

assets/charts/components/node-problem-detector/README.md

@@ -1,6 +1,6 @@
 # node-problem-detector
 
-![Version: 1.8.6](https://img.shields.io/badge/Version-1.8.6-informational?style=flat-square) ![AppVersion: v0.8.5](https://img.shields.io/badge/AppVersion-v0.8.5-informational?style=flat-square)
+![Version: 2.0.2](https://img.shields.io/badge/Version-2.0.2-informational?style=flat-square) ![AppVersion: v0.8.8](https://img.shields.io/badge/AppVersion-v0.8.8-informational?style=flat-square)
 
 This chart installs a [node-problem-detector](https://github.com/kubernetes/node-problem-detector) daemonset. This tool aims to make various node problems visible to the upstream layers in cluster management stack. It is a daemon which runs on each node, detects node problems and reports them to apiserver.
 
@@ -55,12 +55,13 @@ helm install my-release deliveryhero/node-problem-detector -f values.yaml
 | fullnameOverride | string | `""` |  |
 | hostNetwork | bool | `false` | Run pod on host network Flag to run Node Problem Detector on the host's network. This is typically not recommended, but may be useful for certain use cases. |
 | hostPID | bool | `false` |  |
-| hostpath.logdir | string | `"/var/log/"` | Log directory path on K8s host |
 | image.pullPolicy | string | `"IfNotPresent"` |  |
 | image.repository | string | `"k8s.gcr.io/node-problem-detector/node-problem-detector"` |  |
-| image.tag | string | `"v0.8.5"` |  |
+| image.tag | string | `"v0.8.8"` |  |
 | imagePullSecrets | list | `[]` |  |
 | labels | object | `{}` |  |
+| logDir.host | string | `"/var/log/"` | log directory on k8s host |
+| logDir.pod | string | `""` | log directory in pod (volume mount), use logDir.host if empty |
 | maxUnavailable | int | `1` | The max pods unavailable during an update |
 | metrics.serviceMonitor.additionalLabels | object | `{}` |  |
 | metrics.serviceMonitor.enabled | bool | `false` |  |

assets/charts/components/node-problem-detector/templates/_helpers.tpl

@@ -59,3 +59,37 @@ Return the appropriate apiVersion for podSecurityPolicy.
 {{- print "extensions/v1beta1" -}}
 {{- end -}}
 {{- end -}}
+
+
+{{/*
+  Concat npd.config.* to make node-problem-detector CLI args more readable
+*/}}
+{{- define "npd.cli.args" -}}
+{{ include "npd.config.systemLogMonitor" . }} {{ include "npd.config.customPluginMonitor" . }} {{ include "npd.config.prometheus" . }} {{ include "npd.config.k8sExporter" . }}
+{{- end -}}
+
+{{- define "npd.config.systemLogMonitor" -}}
+--config.system-log-monitor=
+{{- range $index, $monitor := .Values.settings.log_monitors -}}
+  {{- if ne $index 0 -}},{{- end -}}
+  {{- $monitor -}}
+{{- end -}}
+{{- end -}}
+
+{{- define "npd.config.customPluginMonitor" -}}
+{{- if .Values.settings.custom_plugin_monitors -}}
+--config.custom-plugin-monitor=
+{{- range $index, $monitor := .Values.settings.custom_plugin_monitors -}}
+  {{- if ne $index 0 -}},{{- end -}}
+  {{- $monitor -}}
+{{- end -}}
+{{- end -}}
+{{- end -}}
+
+{{- define "npd.config.prometheus" -}}
+{{- printf "--prometheus-address=%s --prometheus-port=%.0f" .Values.settings.prometheus_address .Values.settings.prometheus_port -}}
+{{- end -}}
+
+{{- define "npd.config.k8sExporter" -}}
+--k8s-exporter-heartbeat-period={{ .Values.settings.heartBeatPeriod }}
+{{- end -}}

assets/charts/components/node-problem-detector/templates/daemonset.yaml

@@ -13,10 +13,10 @@ metadata:
 spec:
   updateStrategy:
     type: {{ .Values.updateStrategy }}
-{{- if eq .Values.updateStrategy "RollingUpdate"}}
+    {{- if eq .Values.updateStrategy "RollingUpdate"}}
     rollingUpdate:
       maxUnavailable: {{ .Values.maxUnavailable }}
-{{- end}}
+    {{- end}}
   selector:
     matchLabels:
       app.kubernetes.io/name: {{ include "node-problem-detector.name" . }}
@@ -34,9 +34,9 @@ spec:
       annotations:
         checksum/config: {{ include (print $.Template.BasePath "/custom-config-configmap.yaml") . | sha256sum }}
         scheduler.alpha.kubernetes.io/critical-pod: ''
-{{- if .Values.annotations }}
-{{ toYaml .Values.annotations | indent 8 }}
-{{- end }}
+        {{- if .Values.annotations }}
+        {{- toYaml .Values.annotations | nindent 8 }}
+        {{- end }}
     spec:
       serviceAccountName: {{ template "node-problem-detector.serviceAccountName" . }}
       {{- if .Values.imagePullSecrets }}
@@ -55,59 +55,59 @@ spec:
           command:
             - "/bin/sh"
             - "-c"
-            - "exec /node-problem-detector --logtostderr --config.system-log-monitor={{- range $index, $monitor := .Values.settings.log_monitors }}{{if ne $index 0}},{{end}}{{ $monitor }}{{- end }} {{- if .Values.settings.custom_plugin_monitors }} --custom-plugin-monitors={{- range $index, $monitor := .Values.settings.custom_plugin_monitors }}{{if ne $index 0}},{{end}}{{ $monitor }}{{- end }} {{- end }} --prometheus-address={{ .Values.settings.prometheus_address }} --prometheus-port={{ .Values.settings.prometheus_port }} --k8s-exporter-heartbeat-period={{ .Values.settings.heartBeatPeriod }}"
-{{- if .Values.securityContext }}
+            - "exec /node-problem-detector --logtostderr {{ include "npd.cli.args" $ }}"
+          {{- if .Values.securityContext }}
           securityContext:
-{{ toYaml .Values.securityContext | indent 12 }}
-{{- end }}
+          {{- toYaml .Values.securityContext | nindent 12 }}
+          {{- end }}
           env:
             - name: NODE_NAME
               valueFrom:
                 fieldRef:
                   fieldPath: spec.nodeName
-{{- if .Values.env }}
-{{ toYaml .Values.env | indent 12 }}
-{{- end }}
+          {{- if .Values.env }}
+          {{- toYaml .Values.env | nindent 12 }}
+          {{- end }}
           volumeMounts:
             - name: log
-              mountPath: {{ .Values.hostpath.logdir }}
+              mountPath: {{ default (default "/var/log/" .Values.logDir.host) .Values.logDir.pod }}
             - name: localtime
               mountPath: /etc/localtime
               readOnly: true
             - name: custom-config
               mountPath: /custom-config
               readOnly: true
-{{- if .Values.extraVolumeMounts }}
-{{ toYaml .Values.extraVolumeMounts | indent 12 }}
-{{- end }}
+          {{- if .Values.extraVolumeMounts }}
+          {{- toYaml .Values.extraVolumeMounts | nindent 12 }}
+          {{- end }}
           ports:
             - containerPort: {{ .Values.settings.prometheus_port }}
               name: exporter
           resources:
-{{ toYaml .Values.resources | indent 12 }}
-    {{- with .Values.affinity }}
+          {{- toYaml .Values.resources | nindent 12 }}
+      {{- with .Values.affinity }}
       affinity:
-{{ toYaml . | indent 8 }}
-    {{- end }}
-    {{- with .Values.tolerations }}
+      {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
       tolerations:
-{{ toYaml . | indent 8 }}
-    {{- end }}
-{{- if .Values.nodeSelector }}
+      {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- if .Values.nodeSelector }}
       nodeSelector:
-{{ toYaml .Values.nodeSelector | indent 8 }}
-{{- end }}
+      {{- toYaml .Values.nodeSelector | nindent 8 }}
+      {{- end }}
       volumes:
         - name: log
           hostPath:
-            path: {{ .Values.hostpath.logdir }}
+            path: {{ default "/var/log/" .Values.logDir.host }}
         - name: localtime
           hostPath:
             path: /etc/localtime
             type: "FileOrCreate"
         - name: custom-config
           configMap:
             name: {{ include "node-problem-detector.customConfig" . }}
-{{- if .Values.extraVolumes }}
-{{ toYaml .Values.extraVolumes | indent 8 }}
-{{- end }}
+      {{- if .Values.extraVolumes }}
+      {{- toYaml .Values.extraVolumes | nindent 8 }}
+      {{- end }}

assets/charts/components/node-problem-detector/templates/servicemonitor.yaml

@@ -9,7 +9,7 @@ metadata:
     app.kubernetes.io/instance: {{ .Release.Name }}
     app.kubernetes.io/managed-by: {{ .Release.Service }}
     {{- if .Values.metrics.serviceMonitor.additionalLabels }}
-{{ toYaml .Values.metrics.serviceMonitor.additionalLabels | indent 4 }}
+    {{- toYaml .Values.metrics.serviceMonitor.additionalLabels | nindent 4 }}
     {{- end }}
   namespace: {{ .Release.Namespace }}
 spec:

assets/charts/components/node-problem-detector/values.yaml

@@ -5,12 +5,31 @@ settings:
   # https://github.com/kubernetes/node-problem-detector/tree/master/config
   # settings.custom_monitor_definitions -- Custom plugin monitor config files
   custom_monitor_definitions: {}
+    # docker-monitor-filelog.json: |
+    #   {
+    #     "plugin": "filelog",
+    #     "pluginConfig": {
+    #       "timestamp": "^time=\"(\\S*)\"",
+    #       "message": "msg=\"([^\n]*)\"",
+    #       "timestampFormat": "2006-01-02T15:04:05.999999999-07:00"
+    #     },
+    #     "logPath": "/var/log/docker.log",
+    #     "lookback": "5m",
+    #     "bufferSize": 10,
+    #     "source": "docker-monitor",
+    #     "conditions": [],
+    #     "rules": [
+    #       {
+    #         "type": "temporary",
+    #         "reason": "CorruptDockerImage",
+    #         "pattern": "Error trying v2 registry: failed to register layer: rename /var/lib/docker/image/(.+) /var/lib/docker/image/(.+): directory not empty.*"
+    #       }
+    #     ]
+    #   }
   # settings.log_monitors -- User-specified custom monitor definitions
   log_monitors:
     - /config/kernel-monitor.json
     - /config/docker-monitor.json
-    # - /custom-config/kernel-monitor.json
-    # - /custom-config/docker-monitor-filelog.json
     # An example of activating a custom log monitor definition in
     # Node Problem Detector
     # - /custom-config/docker-monitor-filelog.json
@@ -25,13 +44,15 @@ settings:
   # settings.heartBeatPeriod -- Syncing interval with API server
   heartBeatPeriod: 5m0s
 
-hostpath:
-  # hostpath.logdir -- Log directory path on K8s host
-  logdir: /var/log/
+logDir:
+  # logDir.host -- log directory on k8s host
+  host: /var/log/
+  # logDir.pod -- log directory in pod (volume mount), use logDir.host if empty
+  pod: ""
 
 image:
   repository: k8s.gcr.io/node-problem-detector/node-problem-detector
-  tag: v0.8.5
+  tag: v0.8.8
   pullPolicy: IfNotPresent
 
 imagePullSecrets: []

docs/development/updating-components.md

@@ -170,3 +170,17 @@ helm fetch --untar --untardir ./ vmware-tanzu/velero
 ```
 
 - Chart location: https://github.com/vmware-tanzu/helm-charts/tree/main/charts/velero
+
+## node-problem-detector
+
+Run the following commands in the root of this repository:
+
+```bash
+cd assets/charts/components
+rm -rf node-problem-detector
+helm repo add deliveryhero https://charts.deliveryhero.io/
+helm repo update
+helm fetch --untar --untardir ./ deliveryhero/node-problem-detector
+```
+
+- Chart location: https://github.com/deliveryhero/helm-charts/blob/master/stable/node-problem-detector/Chart.yaml.