本节主要内容
- spark-shell
- spark-submit
- spark-sql
- spark-class
- 总结
1. spark-shell
spark-shell脚本文件内容如下：
#!/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
export FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
export _SPARK_CMD_USAGE="Usage: ./bin/spark-shell [options]"
# SPARK-4161: scala does not assume use of the java classpath,
# so we need to add the "-Dscala.usejavacp=true" flag manually. We
# do this specifically for the Spark shell because the scala REPL
# has its own class loader, and any additional classpath specified
# through spark.driver.extraClassPath is not automatically propagated.
SPARK_SUBMIT_OPTS="$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"
#调用spark-submit脚本，传入class org.apache.spark.repl.Main类
#、spark程序名称"Spark shell"及所有传入该脚本的参数
"$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
stty icanon echo > /dev/null 2>&1
else
export SPARK_SUBMIT_OPTS
"$FWDIR"/bin/spark-submit --class org.apache.spark.repl.Main --name "Spark shell" "$@"
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=$?
onExit
2. spark-sql
spark-sql脚本内容如下：
#!/usr/bin/env bash
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
export FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
export _SPARK_CMD_USAGE="Usage: ./bin/spark-sql [options] [cli option]"
#同样，通过spark-submit脚本提交任务
#只不过传入的类是SparkSQLCLIDriver
exec "$FWDIR"/bin/spark-submit --class org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver "$@"3. spark-submit
spark-submit脚本内容如下：
#!/usr/bin/env bash
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
# disable randomized hash for string in Python 3.3+
export PYTHONHASHSEED=0
#spark-submit最终调用的是spark-class脚本
#传入的类是org.apache.spark.deploy.SparkSubmit
#及其它传入的参数
exec "$SPARK_HOME"/bin/spark-class org.apache.spark.deploy.SparkSubmit "$@"4. spark-class
spark-class脚本内容如下：
#!/usr/bin/env bash
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# Figure out where Spark is installed
#定位SAPRK_HOME目录
export SPARK_HOME="$(cd "`dirname "$0"`"/..; pwd)"
#加载load-spark-env.sh，运行环境相关信息
#例如配置文件conf下的spark-env.sh等
. "$SPARK_HOME"/bin/load-spark-env.sh
# Find the java binary
# 定位JAVA_HOME目录
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
#定位spark-assembly-1.5.0-hadoop2.4.0.jar文件（以spark1.5.0为例）
#这意味着任务提交时无需将该JAR文件打包
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
num_jars="$(ls -1 "$ASSEMBLY_DIR" | grep "^spark-assembly.*hadoop.*\.jar$" | wc -l)"
if [ "$num_jars" -eq "0" -a -z "$SPARK_ASSEMBLY_JAR" ]; then
echo "Failed to find Spark assembly in $ASSEMBLY_DIR." 1>&2
echo "You need to build Spark before running this program." 1>&2
exit 1
fi
ASSEMBLY_JARS="$(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
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"
# 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.
#执行org.apache.spark.launcher.Main作为Spark应用程序的主入口
CMD=()
while IFS= read -d '' -r ARG; do
CMD+=("$ARG")
done < <("$RUNNER" -cp "$LAUNCH_CLASSPATH" org.apache.spark.launcher.Main "$@")
exec "${CMD[@]}"5. 总结
通过上述脚本的源码可以看到 spark-shell、spark-sql实现方式都是通过调用spark-submit脚本来实现的，而spark-submit又是通过spark-class脚本来实现的，spark-class脚本最终执行org.apache.spark.launcher.Main，作为整个Spark程序的主入口
