spark 源代码分析 （二）spark启动过程

下载spark后，调用shell脚本启动：

./bin/spark-shell --master local[2]

接下来将分析这个一个过程。spark-shell

会启动 -- class org . apache . spark . repl . Main，

参数 -- name "Spark shell" "$@" ，然后会调用 spark - submit

   
   
cygwin=false
case "$(uname)" in
  CYGWIN*) cygwin=true;;
esac
# Enter posix mode for bash
set -o posix
if [ -z "${SPARK_HOME}" ]; then
  source "$(dirname "$0")"/find-spark-home
fi
export _SPARK_CMD_USAGE="Usage: ./bin/spark-shell [options]"
# SPARK-4161: scala does not assume use of the java classpath,
# so we need to add the "-Dscala.usejavacp=true" flag manually. We
# do this specifically for the Spark shell because the scala REPL
# has its own class loader, and any additional classpath specified
# through spark.driver.extraClassPath is not automatically propagated.
SPARK_SUBMIT_OPTS="$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"
## 这里自定了启动
  "${SPARK_HOME}"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
    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

spark-submit,这个简单，调用了 spark - class 参数 ：org . apache . spark . deploy . SparkSubmit

   
   
if [ -z "${SPARK_HOME}" ]; then
  source "$(dirname "$0")"/find-spark-home
fi
# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0
exec "${SPARK_HOME}"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"

spark-class如下：这里主要加载java class 和jar包

   
   
if [ -z "${SPARK_HOME}" ]; then
  source "$(dirname "$0")"/find-spark-home
fi
. "${SPARK_HOME}"/bin/load-spark-env.sh
# Find the java binary
if [ -n "${JAVA_HOME}" ]; then
  RUNNER="${JAVA_HOME}/bin/java"
else
  if [ "$(command -v java)" ]; then
    RUNNER="java"
  else
    echo "JAVA_HOME is not set" >&2
    exit 1
  fi
fi
# Find Spark jars.
if [ -d "${SPARK_HOME}/jars" ]; then
  SPARK_JARS_DIR="${SPARK_HOME}/jars"
else
  SPARK_JARS_DIR="${SPARK_HOME}/assembly/target/scala-$SPARK_SCALA_VERSION/jars"
fi
if [ ! -d "$SPARK_JARS_DIR" ] && [ -z "$SPARK_TESTING$SPARK_SQL_TESTING" ]; then
  echo "Failed to find Spark jars directory ($SPARK_JARS_DIR)." 1>&2
  echo "You need to build Spark with the target \"package\" before running this program." 1>&2
  exit 1
else
  LAUNCH_CLASSPATH="$SPARK_JARS_DIR/*"
fi
# 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
# For tests
if [[ -n "$SPARK_TESTING" ]]; then
  unset YARN_CONF_DIR
  unset HADOOP_CONF_DIR
fi
# The launcher library will print arguments separated by a NULL character, to allow arguments with
# characters that would be otherwise interpreted by the shell. Read that in a while loop, populating
# an array that will be used to exec the final command.
#
# The exit code of the launcher is appended to the output, so the parent shell removes it from the
# command array and checks the value to see if the launcher succeeded.
build_command() {
  "$RUNNER" -Xmx128m -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@"
  printf "%d\0" $?
}
# Turn off posix mode since it does not allow process substitution
set +o posix
CMD=()
while IFS= read -d '' -r ARG; do
  CMD+=("$ARG")
done < <(build_command "$@")
COUNT=${#CMD[@]}
LAST=$((COUNT - 1))
LAUNCHER_EXIT_CODE=${CMD[$LAST]}
# Certain JVM failures result in errors being printed to stdout (instead of stderr), which causes
# the code that parses the output of the launcher to get confused. In those cases, check if the
# exit code is an integer, and if it's not, handle it as a special error case.
if ! [[ $LAUNCHER_EXIT_CODE =~ ^[0-9]+$ ]]; then
  echo "${CMD[@]}" | head -n-1 1>&2
  exit 1
fi
if [ $LAUNCHER_EXIT_CODE != 0 ]; then
  exit $LAUNCHER_EXIT_CODE
fi
CMD=("${CMD[@]:0:$LAST}")
exec "${CMD[@]}"

所以最终启动了

org . apache . spark . repl . Main

org.apache.spark.deploy.SparkSubmit

org . apache . spark . launcher . Main