在 K8S 部署一个 Spark History Server - 篇2

FROM openjdk:8-alpine

ARG spark_uid=185

RUN set -ex && \
    apk upgrade --no-cache && \
    ln -s /lib /lib64 && \
    apk add --no-cache bash tini libc6-compat linux-pam krb5 krb5-libs nss && \
    mkdir -p /opt/spark && \
    mkdir -p /opt/spark/examples && \
    mkdir -p /opt/spark/work-dir && \
    touch /opt/spark/RELEASE && \
    rm /bin/sh && \
    ln -sv /bin/bash /bin/sh && \
    echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
    chgrp root /etc/passwd && chmod ug+rw /etc/passwd

COPY jars /opt/spark/jars
COPY bin /opt/spark/bin
COPY sbin /opt/spark/sbin
COPY kubernetes/dockerfiles/spark/entrypoint.sh /opt/
COPY examples /opt/spark/examples
COPY kubernetes/tests /opt/spark/tests
COPY data /opt/spark/data

ENV SPARK_HOME /opt/spark

WORKDIR /opt/spark/work-dir
RUN chmod g+w /opt/spark/work-dir

ENTRYPOINT [ "/opt/entrypoint.sh" ]

# Specify the User that the actual main process will run as
USER ${spark_uid}

case "$1" in
  driver)
    shift 1
    CMD=(
      "$SPARK_HOME/bin/spark-submit"
      --conf "spark.driver.bindAddress=$SPARK_DRIVER_BIND_ADDRESS"
      --deploy-mode client
      "$@"
    )
    ;;
  executor)
    shift 1
    CMD=(
      ${JAVA_HOME}/bin/java
      "${SPARK_EXECUTOR_JAVA_OPTS[@]}"
      -Xms$SPARK_EXECUTOR_MEMORY
      -Xmx$SPARK_EXECUTOR_MEMORY
      -cp "$SPARK_CLASSPATH"
      org.apache.spark.executor.CoarseGrainedExecutorBackend
      --driver-url $SPARK_DRIVER_URL
      --executor-id $SPARK_EXECUTOR_ID
      --cores $SPARK_EXECUTOR_CORES
      --app-id $SPARK_APPLICATION_ID
      --hostname $SPARK_EXECUTOR_POD_IP
    )
    ;;

  *)
    echo "Non-spark-on-k8s command provided, proceeding in pass-through mode..."
    CMD=("$@")
    ;;
esac

./bin/docker-image-tool.sh -t v3.0.0 build

docker run -it spark:v3.0.0 /opt/spark/bin/spark-class org.apache.spark.deploy.history.HistoryServer

➜  spark git:(master) ✗ docker run -it spark:v3.0.0 /opt/spark/bin/spark-class org.apache.spark.deploy.history.HistoryServer
++ id -u
+ myuid=0
++ id -g
+ mygid=0
+ set +e
++ getent passwd 0
+ uidentry=root:x:0:0:root:/root:/bin/ash
+ set -e
+ '[' -z root:x:0:0:root:/root:/bin/ash ']'
+ SPARK_CLASSPATH=':/opt/spark/jars/*'
+ env
+ grep SPARK_JAVA_OPT_
+ sort -t_ -k4 -n
+ sed 's/[^=]*=\(.*\)/\1/g'
+ readarray -t SPARK_EXECUTOR_JAVA_OPTS
+ '[' -n '' ']'
+ '[' '' == 2 ']'
+ '[' '' == 3 ']'
+ '[' -z ']'
+ case "$1" in
+ echo 'Non-spark-on-k8s command provided, proceeding in pass-through mode...'
Non-spark-on-k8s command provided, proceeding in pass-through mode...
+ CMD=("$@")
+ exec /sbin/tini -s -- /opt/spark/bin/spark-class org.apache.spark.deploy.history.HistoryServer
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
19/07/09 03:59:22 INFO HistoryServer: Started daemon with process name: 14@df0f7b9fd0cf
19/07/09 03:59:22 INFO SignalUtils: Registered signal handler for TERM
19/07/09 03:59:22 INFO SignalUtils: Registered signal handler for HUP
19/07/09 03:59:22 INFO SignalUtils: Registered signal handler for INT
19/07/09 03:59:23 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
19/07/09 03:59:23 INFO SecurityManager: Changing view acls to: root
19/07/09 03:59:23 INFO SecurityManager: Changing modify acls to: root
19/07/09 03:59:23 INFO SecurityManager: Changing view acls groups to:
19/07/09 03:59:23 INFO SecurityManager: Changing modify acls groups to:
19/07/09 03:59:23 INFO SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users  with view permissions: Set(root); groups with view permissions: Set(); users  with modify permissions: Set(root); groups with modify permissions: Set()
19/07/09 03:59:23 INFO FsHistoryProvider: History server ui acls disabled; users with admin permissions: ; groups with admin permissions
Exception in thread "main" java.lang.reflect.InvocationTargetException
	at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
	at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
	at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
	at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
	at org.apache.spark.deploy.history.HistoryServer$.main(HistoryServer.scala:278)
	at org.apache.spark.deploy.history.HistoryServer.main(HistoryServer.scala)
Caused by: java.io.FileNotFoundException: Log directory specified does not exist: file:/tmp/spark-events Did you configure the correct one through spark.history.fs.logDirectory?
	at org.apache.spark.deploy.history.FsHistoryProvider.startPolling(FsHistoryProvider.scala:259)