Hadoop启动脚本全解析,不能再全了![bed]
来源:互联网 发布:淘宝网退机票 编辑:程序博客网 时间:2024/05/01 23:43
转自: http://blog.csdn.net/mrtitan/article/details/9115621
在工作过程中,经常需要调整一些hadoop的参数配置,所以经常会遇到各种各样的问题。比如改了个配置怎么突然namenode起不来啦,加了个jar包怎么让hadoop的jvm加载啊,如何设定log目录啦等等,每次都需要仔细的查一遍启动脚本才能找到原因,费时又费力,因此专门总结了一下以便不时之需。
cloudera的hadoop的启动脚本写的异常复杂和零散,各种shell脚本分散在系统的各个角落,让人很无语。下面以namenode启动的过程为例说明hadoop的启动脚本的调用关系和各个脚本的作用。
hadoop启动的入口脚本是/etc/init.d/hadoop-hdfs-name,下面我们顺着启动namenode的顺序看看hadoop的启动调用过程。
/etc/init.d/hadoop-hdfs-namenode:
#1.加载/etc/default/hadoop /etc/default/hadoop-hdfs-namenode
#2.执行/usr/lib/hadoop/sbin/hadoop-daemon.sh启动namenode
cloudera启动namenode的用户为hdfs,默认的配置目录是/etc/hadoop/conf
- start() {
- [ -x $EXEC_PATH ] || exit $ERROR_PROGRAM_NOT_INSTALLED
- [ -d $CONF_DIR ] || exit $ERROR_PROGRAM_NOT_CONFIGURED
- log_success_msg "Starting ${DESC}: "
- su -s /bin/bash $SVC_USER -c "$EXEC_PATH --config '$CONF_DIR' start $DAEMON_FLAGS"
- # Some processes are slow to start
- sleep $SLEEP_TIME
- checkstatusofproc
- RETVAL=$?
- [ $RETVAL -eq $RETVAL_SUCCESS ] && touch $LOCKFILE
- return $RETVAL
- }
start() { [ -x $EXEC_PATH ] || exit $ERROR_PROGRAM_NOT_INSTALLED [ -d $CONF_DIR ] || exit $ERROR_PROGRAM_NOT_CONFIGURED log_success_msg "Starting ${DESC}: " su -s /bin/bash $SVC_USER -c "$EXEC_PATH --config '$CONF_DIR' start $DAEMON_FLAGS" # Some processes are slow to start sleep $SLEEP_TIME checkstatusofproc RETVAL=$? [ $RETVAL -eq $RETVAL_SUCCESS ] && touch $LOCKFILE return $RETVAL}
/etc/default/hadoop /etc/default/hadoop-hdfs-namenode:
#1.配置logdir,piddir,user
/usr/lib/hadoop/sbin/hadoop-daemon.sh
#1.加载/usr/lib/hadoop/libexec/hadoop-config.sh
- DEFAULT_LIBEXEC_DIR="$bin"/../libexec
- HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
- . $HADOOP_LIBEXEC_DIR/hadoop-config.sh
DEFAULT_LIBEXEC_DIR="$bin"/../libexecHADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}. $HADOOP_LIBEXEC_DIR/hadoop-config.sh
#2.加载hadoop-env.sh
- if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
- . "${HADOOP_CONF_DIR}/hadoop-env.sh"
- fi
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then . "${HADOOP_CONF_DIR}/hadoop-env.sh"fi
#3.指定log目录
- # get log directory
- if [ "$HADOOP_LOG_DIR" = "" ]; then
- export HADOOP_LOG_DIR="$HADOOP_PREFIX/logs"
- fi
# get log directoryif [ "$HADOOP_LOG_DIR" = "" ]; then export HADOOP_LOG_DIR="$HADOOP_PREFIX/logs"fi
#4.补全log目录和log4j的logger等参数
- export HADOOP_LOGFILE=hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.log
- export HADOOP_ROOT_LOGGER=${HADOOP_ROOT_LOGGER:-"INFO,RFA"}
- export HADOOP_SECURITY_LOGGER=${HADOOP_SECURITY_LOGGER:-"INFO,RFAS"}
- export HDFS_AUDIT_LOGGER=${HDFS_AUDIT_LOGGER:-"INFO,NullAppender"}
- log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.out
- pid=$HADOOP_PID_DIR/hadoop-$HADOOP_IDENT_STRING-$command.pid
- HADOOP_STOP_TIMEOUT=${HADOOP_STOP_TIMEOUT:-5}
export HADOOP_LOGFILE=hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.logexport HADOOP_ROOT_LOGGER=${HADOOP_ROOT_LOGGER:-"INFO,RFA"}export HADOOP_SECURITY_LOGGER=${HADOOP_SECURITY_LOGGER:-"INFO,RFAS"}export HDFS_AUDIT_LOGGER=${HDFS_AUDIT_LOGGER:-"INFO,NullAppender"}log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.outpid=$HADOOP_PID_DIR/hadoop-$HADOOP_IDENT_STRING-$command.pidHADOOP_STOP_TIMEOUT=${HADOOP_STOP_TIMEOUT:-5}
#5.调用/usr/lib/hadoop-hdfs/bin/hdfs
- hadoop_rotate_log $log
- echo starting $command, logging to $log
- cd "$HADOOP_PREFIX"
- case $command in
- namenode|secondarynamenode|datanode|journalnode|dfs|dfsadmin|fsck|balancer|zkfc)
- if [ -z "$HADOOP_HDFS_HOME" ]; then
- hdfsScript="$HADOOP_PREFIX"/bin/hdfs
- else
- hdfsScript="$HADOOP_HDFS_HOME"/bin/hdfs
- fi
- nohup nice -n $HADOOP_NICENESS $hdfsScript --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &
- ;;
- (*)
- nohup nice -n $HADOOP_NICENESS $hadoopScript --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null &
- ;;
- esac
- echo $! > $pid
- sleep 1; head "$log"
- sleep 3;
- if ! ps -p $! > /dev/null ; then
- exit 1
- fi
hadoop_rotate_log $logecho starting $command, logging to $logcd "$HADOOP_PREFIX"case $command in namenode|secondarynamenode|datanode|journalnode|dfs|dfsadmin|fsck|balancer|zkfc) if [ -z "$HADOOP_HDFS_HOME" ]; then hdfsScript="$HADOOP_PREFIX"/bin/hdfs else hdfsScript="$HADOOP_HDFS_HOME"/bin/hdfs fi nohup nice -n $HADOOP_NICENESS $hdfsScript --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null & ;; (*) nohup nice -n $HADOOP_NICENESS $hadoopScript --config $HADOOP_CONF_DIR $command "$@" > "$log" 2>&1 < /dev/null & ;;esacecho $! > $pidsleep 1; head "$log"sleep 3;if ! ps -p $! > /dev/null ; then exit 1fi
可以看到namenode的sysout输出到$log中,即log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.out
/usr/lib/hadoop/libexec/hadoop-config.sh
#1.加载/usr/lib/hadoop/libexec/hadoop-layout.sh
hadoop-layout.sh主要描述了hadoop的lib的文件夹结构,主要内容如下
- HADOOP_COMMON_DIR="./"
- HADOOP_COMMON_LIB_JARS_DIR="lib"
- HADOOP_COMMON_LIB_NATIVE_DIR="lib/native"
- HDFS_DIR="./"
- HDFS_LIB_JARS_DIR="lib"
- YARN_DIR="./"
- YARN_LIB_JARS_DIR="lib"
- MAPRED_DIR="./"
- MAPRED_LIB_JARS_DIR="lib"
- HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-"/usr/lib/hadoop/libexec"}
- HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop/conf"}
- HADOOP_COMMON_HOME=${HADOOP_COMMON_HOME:-"/usr/lib/hadoop"}
- HADOOP_HDFS_HOME=${HADOOP_HDFS_HOME:-"/usr/lib/hadoop-hdfs"}
- HADOOP_MAPRED_HOME=${HADOOP_MAPRED_HOME:-"/usr/lib/hadoop-0.20-mapreduce"}
- YARN_HOME=${YARN_HOME:-"/usr/lib/hadoop-yarn"}
HADOOP_COMMON_DIR="./"HADOOP_COMMON_LIB_JARS_DIR="lib"HADOOP_COMMON_LIB_NATIVE_DIR="lib/native"HDFS_DIR="./"HDFS_LIB_JARS_DIR="lib"YARN_DIR="./"YARN_LIB_JARS_DIR="lib"MAPRED_DIR="./"MAPRED_LIB_JARS_DIR="lib"HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-"/usr/lib/hadoop/libexec"}HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop/conf"}HADOOP_COMMON_HOME=${HADOOP_COMMON_HOME:-"/usr/lib/hadoop"}HADOOP_HDFS_HOME=${HADOOP_HDFS_HOME:-"/usr/lib/hadoop-hdfs"}HADOOP_MAPRED_HOME=${HADOOP_MAPRED_HOME:-"/usr/lib/hadoop-0.20-mapreduce"}YARN_HOME=${YARN_HOME:-"/usr/lib/hadoop-yarn"}
#2.指定HDFS和YARN的lib
- HADOOP_COMMON_DIR=${HADOOP_COMMON_DIR:-"share/hadoop/common"}
- HADOOP_COMMON_LIB_JARS_DIR=${HADOOP_COMMON_LIB_JARS_DIR:-"share/hadoop/common/lib"}
- HADOOP_COMMON_LIB_NATIVE_DIR=${HADOOP_COMMON_LIB_NATIVE_DIR:-"lib/native"}
- HDFS_DIR=${HDFS_DIR:-"share/hadoop/hdfs"}
- HDFS_LIB_JARS_DIR=${HDFS_LIB_JARS_DIR:-"share/hadoop/hdfs/lib"}
- YARN_DIR=${YARN_DIR:-"share/hadoop/yarn"}
- YARN_LIB_JARS_DIR=${YARN_LIB_JARS_DIR:-"share/hadoop/yarn/lib"}
- MAPRED_DIR=${MAPRED_DIR:-"share/hadoop/mapreduce"}
- MAPRED_LIB_JARS_DIR=${MAPRED_LIB_JARS_DIR:-"share/hadoop/mapreduce/lib"}
- # the root of the Hadoop installation
- # See HADOOP-6255 for directory structure layout
- HADOOP_DEFAULT_PREFIX=$(cd -P -- "$common_bin"/.. && pwd -P)
- HADOOP_PREFIX=${HADOOP_PREFIX:-$HADOOP_DEFAULT_PREFIX}
- export HADOOP_PREFIX
HADOOP_COMMON_DIR=${HADOOP_COMMON_DIR:-"share/hadoop/common"}HADOOP_COMMON_LIB_JARS_DIR=${HADOOP_COMMON_LIB_JARS_DIR:-"share/hadoop/common/lib"}HADOOP_COMMON_LIB_NATIVE_DIR=${HADOOP_COMMON_LIB_NATIVE_DIR:-"lib/native"}HDFS_DIR=${HDFS_DIR:-"share/hadoop/hdfs"}HDFS_LIB_JARS_DIR=${HDFS_LIB_JARS_DIR:-"share/hadoop/hdfs/lib"}YARN_DIR=${YARN_DIR:-"share/hadoop/yarn"}YARN_LIB_JARS_DIR=${YARN_LIB_JARS_DIR:-"share/hadoop/yarn/lib"}MAPRED_DIR=${MAPRED_DIR:-"share/hadoop/mapreduce"}MAPRED_LIB_JARS_DIR=${MAPRED_LIB_JARS_DIR:-"share/hadoop/mapreduce/lib"}# the root of the Hadoop installation# See HADOOP-6255 for directory structure layoutHADOOP_DEFAULT_PREFIX=$(cd -P -- "$common_bin"/.. && pwd -P)HADOOP_PREFIX=${HADOOP_PREFIX:-$HADOOP_DEFAULT_PREFIX}export HADOOP_PREFIX
#3.对slave文件判断。但cdh的hadoop不是依靠slave来启动集群的,而是要用户自己写集群启动脚本(也许是为了逼用户用他的CloudManager。。。)
#4.再次指定env文件
- if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
- . "${HADOOP_CONF_DIR}/hadoop-env.sh"
- fi
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then . "${HADOOP_CONF_DIR}/hadoop-env.sh"fi
#5.指定java home
- # Attempt to set JAVA_HOME if it is not set
- if [[ -z $JAVA_HOME ]]; then
- # On OSX use java_home (or /Library for older versions)
- if [ "Darwin" == "$(uname -s)" ]; then
- if [ -x /usr/libexec/java_home ]; then
- export JAVA_HOME=($(/usr/libexec/java_home))
- else
- export JAVA_HOME=(/Library/Java/Home)
- fi
- fi
- # Bail if we did not detect it
- if [[ -z $JAVA_HOME ]]; then
- echo "Error: JAVA_HOME is not set and could not be found." 1>&2
- exit 1
- fi
- fi
# Attempt to set JAVA_HOME if it is not setif [[ -z $JAVA_HOME ]]; then # On OSX use java_home (or /Library for older versions) if [ "Darwin" == "$(uname -s)" ]; then if [ -x /usr/libexec/java_home ]; then export JAVA_HOME=($(/usr/libexec/java_home)) else export JAVA_HOME=(/Library/Java/Home) fi fi # Bail if we did not detect it if [[ -z $JAVA_HOME ]]; then echo "Error: JAVA_HOME is not set and could not be found." 1>&2 exit 1 fifi
#6.指定Java程序启动的heapsize,如果用户在hadoop-env.sh中指定了HADOOP_HEAPSIZE字段则会覆盖默认值1000m
- # some Java parameters
- JAVA_HEAP_MAX=-Xmx1000m
- # check envvars which might override default args
- if [ "$HADOOP_HEAPSIZE" != "" ]; then
- #echo "run with heapsize $HADOOP_HEAPSIZE"
- JAVA_HEAP_MAX="-Xmx""$HADOOP_HEAPSIZE""m"
- #echo $JAVA_HEAP_MAX
- fi
# some Java parametersJAVA_HEAP_MAX=-Xmx1000m# check envvars which might override default argsif [ "$HADOOP_HEAPSIZE" != "" ]; then #echo "run with heapsize $HADOOP_HEAPSIZE" JAVA_HEAP_MAX="-Xmx""$HADOOP_HEAPSIZE""m" #echo $JAVA_HEAP_MAXfi
#7.指定程序的classpath,一大串代码,总结下就是
HADOOP_CONF_DIR+HADOOP_CLASSPATH+HADOOP_COMMON_DIR+HADOOP_COMMON_LIB_JARS_DIR+
HADOOP_COMMON_LIB_JARS_DIR+HADOOP_COMMON_LIB_NATIVE_DIR+HDFS_DIR+HDFS_LIB_JARS_DIR
+YARN_DIR+YARN_LIB_JARS_DIR+MAPRED_DIR+MAPRED_LIB_JARS_DIR
有一个要注意的,hadoop比较贴心的提供了HADOOP_USER_CLASSPATH_FIRST属性,如何设置了,
则HADOOP_CLASSPATH(用户自定义classpath)会在hadoop自身的jar包前加载,用来解决用户
想最先加载自定义的jar包情况。
#8.指定HADOOP_OPTS,-Dhadoop.log.dir这些类似参数会在conf下的log4j配置中用到
- HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_LOG_DIR"
- HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_LOGFILE"
- HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.home.dir=$HADOOP_PREFIX"
- HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.id.str=$HADOOP_IDENT_STRING"
- HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_ROOT_LOGGER:-INFO,console}"
- if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
- HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"
- export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$JAVA_LIBRARY_PATH
- fi
- HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.policy.file=$HADOOP_POLICYFILE"
- # Disable ipv6 as it can cause issues
- HADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"
- <SPAN style="FONT-SIZE: 18px">
- </SPAN>
HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.dir=$HADOOP_LOG_DIR"HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.log.file=$HADOOP_LOGFILE"HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.home.dir=$HADOOP_PREFIX"HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.id.str=$HADOOP_IDENT_STRING"HADOOP_OPTS="$HADOOP_OPTS -Dhadoop.root.logger=${HADOOP_ROOT_LOGGER:-INFO,console}"if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH" export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$JAVA_LIBRARY_PATHfiHADOOP_OPTS="$HADOOP_OPTS -Dhadoop.policy.file=$HADOOP_POLICYFILE"# Disable ipv6 as it can cause issuesHADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"
/usr/lib/hadoop-hdfs/bin/hdfs
#1.加载/usr/lib/hadoop/libexec/hdfs-config.sh,但好像没啥作用
#2.根据启动参数指定java的启动mainclass:
- if [ "$COMMAND" = "namenode" ] ; then
- CLASS='org.apache.hadoop.hdfs.server.namenode.NameNode'
- HADOOP_OPTS="$HADOOP_OPTS $HADOOP_NAMENODE_OPTS"
if [ "$COMMAND" = "namenode" ] ; then CLASS='org.apache.hadoop.hdfs.server.namenode.NameNode' HADOOP_OPTS="$HADOOP_OPTS $HADOOP_NAMENODE_OPTS"
- #3.启动Java程序
- exec "$JAVA" -Dproc_$COMMAND $JAVA_HEAP_MAX $HADOOP_OPTS $CLASS "$@"
#3.启动Java程序exec "$JAVA" -Dproc_$COMMAND $JAVA_HEAP_MAX $HADOOP_OPTS $CLASS "$@"
最后介绍几个配置的小例子。
1.如何指定hadoop的log目录:
从启动脚本中看几个配置的优先级排序是hadoop-env.sh>hadoop-config.sh>/etc/default/hadoop,因此我们如果想指定hadoop的log目录只需在hadoop-env.sh中添加一行:
export HADOOP_LOG_DIR=xxxxx
2.如何添加自己的jar包到hadoop中被namenode,datanode使用
export HADOOP_CLASSPATH=xxxxx
3.如何单独设定namenode的java heapsize。
比如想设置namenode10G,datanode1G,这个就有点意思了。如果直接指定HADOOP_HEAPSIZE那么此参数会作用于namenode,datanode,而单独在namenode的参数中指定也会有点小问题哦,不过基本是可以使用的。
总之,由于hadoop的启动脚本极其多而且琐碎,再加上hbase hive的启动脚本都是类似的结构,导致在添加修改一些配置时会产生很多莫名的问题,大家也可以在使用的过程中细细体会啦
- Hadoop启动脚本全解析,不能再全了![bed]
- Hadoop启动脚本全解析,不能再全了![bed]
- Hadoop启动脚本全解析
- Activity启动过程全解析
- Activity启动过程全解析
- Activity启动过程全解析
- Activity启动过程全解析
- Activity 启动过程全解析
- Activity启动过程全解析
- Activity 启动模式全解析
- Activity启动过程全解析
- Activity启动过程全解析
- Struts2的详细讲解,真的不能再全了
- 源码解析:Activity启动过程全解析
- adb 不能正确启动全解决
- adb 不能正确启动全解决
- adb 不能正确启动全解决
- 全志A33添加开机启动脚本
- hadoop hbase metric名全解释
- Android_NDK_c调用java代码
- matlab资料收藏
- VMware vSphere 5.1 学习系列之五:安装 vCenter Server
- Linux 几条强大命令的学习
- Hadoop启动脚本全解析,不能再全了![bed]
- VMware vSphere 5.1 学习系列之六:vCenter Server 主机管理
- 【Android 4.0】conversion to dalvik format failed with error 1
- VMware vSphere 5.1 学习系列之七:虚拟机管理
- 沿着掌纹烙着宿命
- VMware vSphere 5.1 学习系列之八:主机配置文件
- 【算法复习】寻路算法1 - A星 A star
- k-means算法
- 对OJ的一些分析——OJ评判的方法