鄧佑權讀源碼之Spark源碼解密：spark shell本質！

Spark的源碼解密：spark shell本質！

spark-shell腳本在bin目錄下：

#!/usr/bin/env bash

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

#
# Shell script for starting the Spark Shell REPL

cygwin=false
case "`uname`" in
  CYGWIN*) cygwin=true;;
esac

# Enter posix mode for bash
set -o posix

if [ -z "${SPARK_HOME}" ]; then
  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
fi

export _SPARK_CMD_USAGE="Usage: ./bin/spark-shell [options]"

# SPARK-4161: scala does not assume use of the java classpath,
# so we need to add the "-Dscala.usejavacp=true" flag manually. We
# do this specifically for the Spark shell because the scala REPL
# has its own class loader, and any additional classpath specified
# through spark.driver.extraClassPath is not automatically propagated.
SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Dscala.usejavacp=true"

function main() {
  if $cygwin; then
    # Workaround for issue involving JLine and Cygwin
    # (see http://sourceforge.net/p/jline/bugs/40/).
    # If you're using the Mintty terminal emulator in Cygwin, may need to set the
    # "Backspace sends ^H" setting in "Keys" section of the Mintty options
    # (see https://github.com/sbt/sbt/issues/562).
    stty -icanon min 1 -echo > /dev/null 2>&1
    export SPARK_SUBMIT_OPTS="$SPARK_SUBMIT_OPTS -Djline.terminal=unix"
    "${SPARK_HOME}"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
    stty icanon echo > /dev/null 2>&1
  else
    export SPARK_SUBMIT_OPTS
    "${SPARK_HOME}"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
  fi
}

# Copy restore-TTY-on-exit functions from Scala script so spark-shell exits properly even in
# binary distribution of Spark where Scala is not installed
exit_status=127
saved_stty=""

# restore stty settings (echo in particular)
function restoreSttySettings() {
  stty $saved_stty
  saved_stty=""
}

function onExit() {
  if [[ "$saved_stty" != "" ]]; then
    restoreSttySettings
  fi
  exit $exit_status
}

# to reenable echo if we are interrupted before completing.
trap onExit INT

# save terminal settings
saved_stty=$(stty -g 2>/dev/null)
# clear on error so we don't later try to restore them
if [[ ! $? ]]; then
  saved_stty=""
fi

main "$@"

# record the exit status lest it be overwritten:
# then reenable echo and propagate the code.
exit_status=$?
onExit

看見實質是spark-submit --class org.apache.spark.repl.Main --name "Spark shell"

主類是repl的main方法，應用的名稱爲Spark shell。

spark-submit的內容爲：

if [ -z "${SPARK_HOME}" ]; then
  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
fi

# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0

exec "${SPARK_HOME}"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

繼續調用spark-class來進行提交。

spark-class的內容爲：

if [ -z "${SPARK_HOME}" ]; then
  export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
fi

. "${SPARK_HOME}"/bin/load-spark-env.sh

# Find the java binary
if [ -n "${JAVA_HOME}" ]; then
  RUNNER="${JAVA_HOME}/bin/java"
else
  if [ `command -v java` ]; then
    RUNNER="java"
  else
    echo "JAVA_HOME is not set" >&2
    exit 1
  fi
fi

# Find assembly jar
SPARK_ASSEMBLY_JAR=
if [ -f "${SPARK_HOME}/RELEASE" ]; then
  ASSEMBLY_DIR="${SPARK_HOME}/lib"
else
  ASSEMBLY_DIR="${SPARK_HOME}/assembly/target/scala-$SPARK_SCALA_VERSION"
fi

GREP_OPTIONS=
num_jars="$(ls -1 "$ASSEMBLY_DIR" | grep "^spark-assembly.*hadoop.*\.jar$" | wc -l)"
if [ "$num_jars" -eq "0" -a -z "$SPARK_ASSEMBLY_JAR" -a "$SPARK_PREPEND_CLASSES" != "1" ]; then
  echo "Failed to find Spark assembly in $ASSEMBLY_DIR." 1>&2
  echo "You need to build Spark before running this program." 1>&2
  exit 1
fi
if [ -d "$ASSEMBLY_DIR" ]; then
  ASSEMBLY_JARS="$(ls -1 "$ASSEMBLY_DIR" | grep "^spark-assembly.*hadoop.*\.jar$" || true)"
  if [ "$num_jars" -gt "1" ]; then
    echo "Found multiple Spark assembly jars in $ASSEMBLY_DIR:" 1>&2
    echo "$ASSEMBLY_JARS" 1>&2
    echo "Please remove all but one jar." 1>&2
    exit 1
  fi
fi

SPARK_ASSEMBLY_JAR="${ASSEMBLY_DIR}/${ASSEMBLY_JARS}"

LAUNCH_CLASSPATH="$SPARK_ASSEMBLY_JAR"

# Add the launcher build dir to the classpath if requested.
if [ -n "$SPARK_PREPEND_CLASSES" ]; then
  LAUNCH_CLASSPATH="${SPARK_HOME}/launcher/target/scala-$SPARK_SCALA_VERSION/classes:$LAUNCH_CLASSPATH"
fi

export _SPARK_ASSEMBLY="$SPARK_ASSEMBLY_JAR"

# For tests
if [[ -n "$SPARK_TESTING" ]]; then
  unset YARN_CONF_DIR
  unset HADOOP_CONF_DIR
fi

# The launcher library will print arguments separated by a NULL character, to allow arguments with
# characters that would be otherwise interpreted by the shell. Read that in a while loop, populating
# an array that will be used to exec the final command.
CMD=()
while IFS= read -d '' -r ARG; do
  CMD+=("$ARG")
done < <("$RUNNER" -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@")
exec "${CMD[@]}"

1、從load-spark-env.sh裏獲取java命令地址。

2、尋找assembly jar

3、exec the final command.