charts/bitnami/spark/templates/NOTES.txt

** Please be patient while the chart is being deployed **

{{- if .Values.diagnosticMode.enabled }}
The chart has been deployed in diagnostic mode. All probes have been disabled and the command has been overwritten with:

  command: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.command "context" $) | nindent 4 }}
  args: {{- include "common.tplvalues.render" (dict "value" .Values.diagnosticMode.args "context" $) | nindent 4 }}

Get the list of pods by executing:

  kubectl get pods --namespace {{ .Release.Namespace }} -l app.kubernetes.io/instance={{ .Release.Name }}

Access the pod you want to debug by executing

  kubectl exec --namespace {{ .Release.Namespace }} -ti <NAME OF THE POD> -- bash

In order to replicate the container startup scripts execute this command:

    /opt/bitnami/scripts/spark/entrypoint.sh /opt/bitnami/scripts/spark/run.sh

{{- else }}

1. Get the Spark master WebUI URL by running these commands:
{{- if .Values.ingress.enabled }}

  export HOSTNAME=$(kubectl get ingress --namespace {{ .Release.Namespace }} {{ include "common.names.fullname" . }}-ingress -o jsonpath='{.spec.rules[0].host}')
  echo "Spark-master URL: http://$HOSTNAME/"

{{- else -}}
{{- if contains "NodePort" .Values.service.type }}

  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[?(@.name=='http')].nodePort}" services {{ include "spark.master.service.name" . }})
  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
  echo http://$NODE_IP:$NODE_PORT

{{- else if contains "LoadBalancer" .Values.service.type }}

    NOTE: It may take a few minutes for the LoadBalancer IP to be available.
    You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "spark.master.service.name" . }}'

  export SERVICE_IP=$(kubectl get --namespace {{ .Release.Namespace }} svc {{ include "spark.master.service.name" . }} -o jsonpath="{.status.loadBalancer.ingress[0]['ip', 'hostname'] }")
  echo http://$SERVICE_IP:{{ .Values.service.webPort }}

{{- else if contains "ClusterIP" .Values.service.type }}

  kubectl port-forward --namespace {{ .Release.Namespace }} svc/{{ template "spark.master.service.name" . }} {{ default "80" .Values.service.webPort }}:{{ default "80" .Values.service.webPort }}
  echo "Visit http://127.0.0.1:{{ .Values.service.webPort }} to use your application"

{{- end }}
{{- end }}

2. Submit an application to the cluster:

  To submit an application to the cluster the spark-submit script must be used. That script can be
  obtained at https://github.com/apache/spark/tree/master/bin. Also you can use kubectl run.

{{- if or (eq "NodePort" .Values.service.type) (eq "LoadBalancer" .Values.service.type) }}

  Run the commands below to obtain the master IP and submit your application.
{{- end }}

  export EXAMPLE_JAR=$(kubectl exec -ti --namespace {{ .Release.Namespace }} {{ include "common.names.fullname" . }}-worker-0 -- find examples/jars/ -name 'spark-example*\.jar' | tr -d '\r')
{{- if eq "NodePort" .Values.service.type }}
  export SUBMIT_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[?(@.name=='cluster')].nodePort}" services {{ include "spark.master.service.name" . }})
  export SUBMIT_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")

  kubectl run --namespace {{ .Release.Namespace }} {{ template "common.names.fullname" . }}-client --rm --tty -i --restart='Never' \
    --image {{ template "spark.image" . }} \
    -- spark-submit --master spark://$SUBMIT_IP:$SUBMIT_PORT \
    --class org.apache.spark.examples.SparkPi \
    --deploy-mode cluster \
    $EXAMPLE_JAR 1000

{{- else if eq "LoadBalancer" .Values.service.type }}
  export SUBMIT_IP=$(kubectl get --namespace {{ .Release.Namespace }} svc {{ include "spark.master.service.name" . }} -o jsonpath="{.status.loadBalancer.ingress[0]['ip', 'hostname'] }")

  kubectl run --namespace {{ .Release.Namespace }} {{ template "common.names.fullname" . }}-client --rm --tty -i --restart='Never' \
    --image {{ template "spark.image" . }} \
    -- spark-submit --master spark://$SUBMIT_IP:{{ .Values.service.clusterPort }} \
    --deploy-mode cluster \
    --class org.apache.spark.examples.SparkPi \
    $EXAMPLE_JAR 1000

{{- else }}

  kubectl exec -ti --namespace {{ .Release.Namespace }} {{ include "common.names.fullname" . }}-worker-0 -- spark-submit --master spark://{{ include "spark.master.service.name" . }}:{{ .Values.service.clusterPort }} \
    --class org.apache.spark.examples.SparkPi \
    $EXAMPLE_JAR 5

** IMPORTANT: When submit an application from outside the cluster service type should be set to the NodePort or LoadBalancer. **

{{- end }}

** IMPORTANT: When submit an application the --master parameter should be set to the service IP, if not, the application will not resolve the master. **
{{- end }}

{{ include "spark.checkRollingTags" . }}
{{ include "spark.validateValues" . }}