003.flink源码分析：flink集群启动入口分析

首先查看start-cluster.sh 文件：

bin=`dirname "$0"
bin=`cd "$bin"; pwd`

. "$bin"/config.sh

# Start the JobManager instance(s)
# 打开选项
shopt -s nocasematch
if [[ $HIGH_AVAILABILITY == "zookeeper" ]]; then
    # HA Mode
    readMasters
    #如果ha模式，那么读取所有的master节点，调用jobmanager.sh挨个启动
    echo "Starting HA cluster with ${#MASTERS[@]} masters."

    for ((i=0;i<${#MASTERS[@]};++i)); do
        master=${MASTERS[i]}
        webuiport=${WEBUIPORTS[i]}

        if [ ${MASTERS_ALL_LOCALHOST} = true ] ; then
            "${FLINK_BIN_DIR}"/jobmanager.sh start "${master}" "${webuiport}"
        else
            ssh -n $FLINK_SSH_OPTS $master -- "nohup /bin/bash -l \"${FLINK_BIN_DIR}/jobmanager.sh\" start ${master} ${webuiport} &"
        fi
    done

else
    echo "Starting cluster."

    # Start single JobManager on this machine
    "$FLINK_BIN_DIR"/jobmanager.sh start
fi
shopt -u nocasematch

# Start TaskManager instance(s)
TMSlaves start

可以看到，最终都是调用了jobmanager.sh 这个脚本，传入了 start [可选参数1] [可选参数2]，下面分析jobmanager.sh这个脚本,这里可以看出，两个可选参数为host和port。

USAGE="Usage: jobmanager.sh ((start|start-foreground) [host] [webui-port])|stop|stop-all"

STARTSTOP=$1
HOST=$2 # optional when starting multiple instances
WEBUIPORT=$3 # optional when starting multiple instances
#启动参数判断，只能是start，start-foregroud,stop,stop-all这四种选项
if [[ $STARTSTOP != "start" ]] && [[ $STARTSTOP != "start-foreground" ]] && [[ $STARTSTOP != "stop" ]] && [[ $STARTSTOP != "stop-all" ]]; then
  echo $USAGE
  exit 1
fi

bin=`dirname "$0"`
bin=`cd "$bin"; pwd`

. "$bin"/config.sh

ENTRYPOINT=standalonesession
#如果是启动选项，设置一些jvm参数
if [[ $STARTSTOP == "start" ]] || [[ $STARTSTOP == "start-foreground" ]]; then
    if [ ! -z "${FLINK_JM_HEAP_MB}" ] && [ "${FLINK_JM_HEAP}" == 0 ]; then
	    echo "used deprecated key \`${KEY_JOBM_MEM_MB}\`, please replace with key \`${KEY_JOBM_MEM_SIZE}\`"
    else
	    flink_jm_heap_bytes=$(parseBytes ${FLINK_JM_HEAP})
	    FLINK_JM_HEAP_MB=$(getMebiBytes ${flink_jm_heap_bytes})
    fi

    if [[ ! ${FLINK_JM_HEAP_MB} =~ $IS_NUMBER ]] || [[ "${FLINK_JM_HEAP_MB}" -lt "0" ]]; then
        echo "[ERROR] Configured JobManager memory size is not a valid value. Please set '${KEY_JOBM_MEM_SIZE}' in ${FLINK_CONF_FILE}."
        exit 1
    fi

    if [ "${FLINK_JM_HEAP_MB}" -gt "0" ]; then
        export JVM_ARGS="$JVM_ARGS -Xms"$FLINK_JM_HEAP_MB"m -Xmx"$FLINK_JM_HEAP_MB"m"
    fi

    # Add JobManager-specific JVM options
    export FLINK_ENV_JAVA_OPTS="${FLINK_ENV_JAVA_OPTS} ${FLINK_ENV_JAVA_OPTS_JM}"

    # Startup parameters 设置主机和端口
    args=("--configDir" "${FLINK_CONF_DIR}" "--executionMode" "cluster")
    if [ ! -z $HOST ]; then
        args+=("--host")
        args+=("${HOST}")
    fi

    if [ ! -z $WEBUIPORT ]; then
        args+=("--webui-port")
        args+=("${WEBUIPORT}")
    fi
fi
#如果是前台启动，调用flink-console.sh脚本
if [[ $STARTSTOP == "start-foreground" ]]; then
    exec "${FLINK_BIN_DIR}"/flink-console.sh $ENTRYPOINT "${args[@]}"
else
#这里，调用flink-daemon.sh来启动，这里STARTSTOP一般就是start，
    "${FLINK_BIN_DIR}"/flink-daemon.sh $STARTSTOP $ENTRYPOINT "${args[@]}"
fi

上面脚本最终调用了flink-daemon.sh，在该脚本中，根据不同的参数，选择flink项目中不同的启动类：

...
case $DAEMON in
    (taskexecutor)
        CLASS_TO_RUN=org.apache.flink.runtime.taskexecutor.TaskManagerRunner
    ;;

    (zookeeper)
        CLASS_TO_RUN=org.apache.flink.runtime.zookeeper.FlinkZooKeeperQuorumPeer
    ;;

    (historyserver)
        CLASS_TO_RUN=org.apache.flink.runtime.webmonitor.history.HistoryServer
    ;;
    #这里启动standalone集群
    (standalonesession)
        CLASS_TO_RUN=org.apache.flink.runtime.entrypoint.StandaloneSessionClusterEntrypoint
    ;;

    (standalonejob)
        CLASS_TO_RUN=org.apache.flink.container.entrypoint.StandaloneJobClusterEntryPoint
    ;;

    (*)
        echo "Unknown daemon '${DAEMON}'. $USAGE."
        exit 1
    ;;
esac
...
...
...
echo "Starting $DAEMON daemon on host $HOSTNAME."
        $JAVA_RUN $JVM_ARGS ${FLINK_ENV_JAVA_OPTS} "${log_setting[@]}" -classpath "`manglePathList "$FLINK_TM_CLASSPATH:$INTERNAL_HADOOP_CLASSPATHS"`" ${CLASS_TO_RUN} "${ARGS[@]}" > "$out" 200<&- 2>&1 < /dev/null &

        mypid=$!
...

当我们启动一个standalone集群，启动的是org.apache.flink.runtime.entrypoint.StandaloneSessionClusterEntrypoint这个java类，到此，shell启动入口找到。