Skip to content

Instantly share code, notes, and snippets.

@mp911de

mp911de/hadoop-daemon.diff

Created February 21, 2014 07:41
Show Gist options
  • Save mp911de/9130280 to your computer and use it in GitHub Desktop.
Save mp911de/9130280 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
hadoop-daemon.diff
--- dist/hadoop-0.23.10/sbin/hadoop-daemon.sh 2013-12-03 06:59:44.000000000 +0100
+++ customization/sbin/hadoop-daemon.sh 2014-02-20 09:23:15.000000000 +0100
@@ -108,8 +108,8 @@
# some variables
export HADOOP_LOGFILE=hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.log
-export HADOOP_ROOT_LOGGER="INFO,DRFA"
-export HADOOP_SECURITY_LOGGER="INFO,DRFAS"
+export HADOOP_ROOT_LOGGER=${HADOOP_ROOT_LOGGER:-INFO,DRFA}
+export HADOOP_SECURITY_LOGGER=${HADOOP_ROOT_SECURITY_LOGGER:-INFO,DRFAS}
log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.out
pid=$HADOOP_PID_DIR/hadoop-$HADOOP_IDENT_STRING-$command.pid
Raw
hadoop-daemon.sh
#!/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.
# Runs a Hadoop command as a daemon.
#
# Environment Variables
#
# HADOOP_CONF_DIR Alternate conf dir. Default is ${HADOOP_PREFIX}/conf.
# HADOOP_LOG_DIR Where log files are stored. PWD by default.
# HADOOP_MASTER host:path where hadoop code should be rsync'd from
# HADOOP_PID_DIR The pid files are stored. /tmp by default.
# HADOOP_IDENT_STRING A string representing this instance of hadoop. $USER by default
# HADOOP_NICENESS The scheduling priority for daemons. Defaults to 0.
##
usage="Usage: hadoop-daemon.sh [--config <conf-dir>] [--hosts hostlistfile] [--script script] (start|stop) <hadoop-command> <args...>"
# if no args specified, show usage
if [ $# -le 1 ]; then
echo $usage
exit 1
fi
bin=`dirname "${BASH_SOURCE-$0}"`
bin=`cd "$bin"; pwd`
DEFAULT_LIBEXEC_DIR="$bin"/../libexec
HADOOP_LIBEXEC_DIR=${HADOOP_LIBEXEC_DIR:-$DEFAULT_LIBEXEC_DIR}
. $HADOOP_LIBEXEC_DIR/hadoop-config.sh
# get arguments
#default value
hadoopScript="$HADOOP_PREFIX"/bin/hadoop
if [ "--script" = "$1" ]
then
shift
hadoopScript=$1
shift
fi
startStop=$1
shift
command=$1
shift
hadoop_rotate_log ()
{
log=$1;
num=5;
if [ -n "$2" ]; then
num=$2
fi
if [ -f "$log" ]; then # rotate logs
while [ $num -gt 1 ]; do
prev=`expr $num - 1`
[ -f "$log.$prev" ] && mv "$log.$prev" "$log.$num"
num=$prev
done
mv "$log" "$log.$num";
fi
}
if [ -f "${HADOOP_CONF_DIR}/hadoop-env.sh" ]; then
. "${HADOOP_CONF_DIR}/hadoop-env.sh"
fi
# Determine if we're starting a secure datanode, and if so, redefine appropriate variables
if [ "$command" == "datanode" ] && [ "$EUID" -eq 0 ] && [ -n "$HADOOP_SECURE_DN_USER" ]; then
export HADOOP_PID_DIR=$HADOOP_SECURE_DN_PID_DIR
export HADOOP_LOG_DIR=$HADOOP_SECURE_DN_LOG_DIR
export HADOOP_IDENT_STRING=$HADOOP_SECURE_DN_USER
starting_secure_dn="true"
fi
if [ "$HADOOP_IDENT_STRING" = "" ]; then
export HADOOP_IDENT_STRING="$USER"
fi
# get log directory
if [ "$HADOOP_LOG_DIR" = "" ]; then
export HADOOP_LOG_DIR="$HADOOP_PREFIX/logs"
fi
if [ ! -w "$HADOOP_LOG_DIR" ] ; then
mkdir -p "$HADOOP_LOG_DIR"
chown $HADOOP_IDENT_STRING $HADOOP_LOG_DIR
fi
if [ "$HADOOP_PID_DIR" = "" ]; then
HADOOP_PID_DIR=/tmp
fi
# some variables
export HADOOP_LOGFILE=hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.log
export HADOOP_ROOT_LOGGER=${HADOOP_ROOT_LOGGER:-INFO,DRFA}
export HADOOP_SECURITY_LOGGER=${HADOOP_ROOT_SECURITY_LOGGER:-INFO,DRFAS}
log=$HADOOP_LOG_DIR/hadoop-$HADOOP_IDENT_STRING-$command-$HOSTNAME.out
pid=$HADOOP_PID_DIR/hadoop-$HADOOP_IDENT_STRING-$command.pid
# Set default scheduling priority
if [ "$HADOOP_NICENESS" = "" ]; then
export HADOOP_NICENESS=0
fi
case $startStop in
(start)
[ -w "$HADOOP_PID_DIR" ] || mkdir -p "$HADOOP_PID_DIR"
if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo $command running as process `cat $pid`. Stop it first.
exit 1
fi
fi
if [ "$HADOOP_MASTER" != "" ]; then
echo rsync from $HADOOP_MASTER
rsync -a -e ssh --delete --exclude=.svn --exclude='logs/*' --exclude='contrib/hod/logs/*' $HADOOP_MASTER/ "$HADOOP_PREFIX"
fi
hadoop_rotate_log $log
echo starting $command, logging to $log
cd "$HADOOP_PREFIX"
case $command in
namenode|secondarynamenode|datanode|dfs|dfsadmin|fsck|balancer)
if [ -z "$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"
# capture the ulimit output
if [ "true" = "$starting_secure_dn" ]; then
echo "ulimit -a for secure datanode user $HADOOP_SECURE_DN_USER" >> $log
# capture the ulimit info for the appropriate user
su --shell=/bin/bash $HADOOP_SECURE_DN_USER -c 'ulimit -a' >> $log 2>&1
else
echo "ulimit -a for user $USER" >> $log
ulimit -a >> $log 2>&1
fi
sleep 3;
if ! ps -p $! > /dev/null ; then
exit 1
fi
;;
(stop)
if [ -f $pid ]; then
if kill -0 `cat $pid` > /dev/null 2>&1; then
echo stopping $command
kill `cat $pid`
else
echo no $command to stop
exit 1
fi
else
echo no $command to stop
exit 1
fi
;;
(*)
echo $usage
exit 1
;;
esac
Raw
hadoop-env.sh
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# Set Hadoop-specific environment variables here.
# The only required environment variable is JAVA_HOME. All others are
# optional. When running a distributed configuration it is best to
# set JAVA_HOME in this file, so that it is correctly defined on
# remote nodes.
# The java implementation to use.
export JAVA_HOME=/opt/hadoop/java
export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop"}
# Extra Java CLASSPATH elements. Automatically insert capacity-scheduler.
for f in $HADOOP_HOME/contrib/capacity-scheduler/*.jar; do
if [ "$HADOOP_CLASSPATH" ]; then
export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$f
else
export HADOOP_CLASSPATH=$f
fi
done
# The maximum amount of heap to use, in MB. Default is 1000.
#export HADOOP_HEAPSIZE=
#export HADOOP_NAMENODE_INIT_HEAPSIZE=""
# Extra Java runtime options. Empty by default.
export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true $HADOOP_CLIENT_OPTS"
# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_NAMENODE_OPTS="-Dhadoop.security.logger=INFO,DRFAS,gelf -Dhdfs.audit.logger=INFO,DRFAAUDIT,gelf $HADOOP_NAMENODE_OPTS"
HADOOP_JOBTRACKER_OPTS="-Dhadoop.security.logger=INFO,DRFAS,gelf -Dmapred.audit.logger=INFO,MRAUDIT,gelf -Dmapred.jobsummary.logger=INFO,JSA,gelf $HADOOP_JOBTRACKER_OPTS"
HADOOP_TASKTRACKER_OPTS="-Dhadoop.security.logger=ERROR,console,gelf -Dmapred.audit.logger=ERROR,console,gelf $HADOOP_TASKTRACKER_OPTS"
HADOOP_DATANODE_OPTS="-Dhadoop.security.logger=ERROR,DRFAS,gelf $HADOOP_DATANODE_OPTS"
export HADOOP_SECONDARYNAMENODE_OPTS="-Dhadoop.security.logger=INFO,DRFAS,gelf -Dhdfs.audit.logger=INFO,DRFAAUDIT,gelf $HADOOP_SECONDARYNAMENODE_OPTS"
# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
export HADOOP_CLIENT_OPTS="-Xmx128m $HADOOP_CLIENT_OPTS"
#HADOOP_JAVA_PLATFORM_OPTS="-XX:-UsePerfData $HADOOP_JAVA_PLATFORM_OPTS"
# On secure datanodes, user to run the datanode as after dropping privileges
export HADOOP_SECURE_DN_USER=
# Where log files are stored. $HADOOP_HOME/logs by default.
export HADOOP_LOG_DIR=/opt/hadoop/hadoop/var/log/$USER
# Where log files are stored in the secure data environment.
export HADOOP_SECURE_DN_LOG_DIR=/opt/hadoop/hadoop/var/log/hdfs
# The directory where pid files are stored. /tmp by default.
export HADOOP_PID_DIR=/opt/hadoop/hadoop/var/log
export HADOOP_SECURE_DN_PID_DIR=/opt/hadoop/hadoop/var/log
# A string representing this instance of hadoop. $USER by default.
export HADOOP_IDENT_STRING=$USER
export YARN_LOG_DIR=/opt/hadoop/hadoop/var/log/mr
export YARN_ROOT_LOGGER=INFO,DRFA,gelf
export HADOOP_ROOT_LOGGER=INFO,DRFA,gelf
export HADOOP_JHS_LOGGER=INFO,JSA,gelf
export HADOOP_ROOT_SECURITY_LOGGER=INFO,DRFAS,gelf
Raw
log4j.properties
# 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.
# Define some default values that can be overridden by system properties
hadoop.root.logger=INFO,console,gelf
hadoop.log.dir=.
hadoop.log.file=hadoop.log
# Define the root logger to the system property "hadoop.root.logger".
log4j.rootLogger=${hadoop.root.logger}, EventCounter
# Logging Threshold
log4j.threshold=ALL
# Null Appender
log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
log4j.appender.gelf=biz.paluch.logging.gelf.log4j.GelfLogAppender
log4j.appender.gelf.Threshold=INFO
log4j.appender.gelf.Host=udp:<YOUR LOGSTASH HOST NAME>
log4j.appender.gelf.Port=12201
log4j.appender.gelf.Facility=Hadoop
log4j.appender.gelf.ExtractStackTrace=true
log4j.appender.gelf.FilterStackTrace=true
log4j.appender.gelf.MdcProfiling=true
log4j.appender.gelf.TimestampPattern=yyyy-MM-dd HH:mm:ss,SSSS
log4j.appender.gelf.MaximumMessageSize=8192
log4j.appender.gelf.AdditionalFields=Environment=AT
#
# Daily Rolling File Appender
#
log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
# Rollver at midnight
log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
# 30-day backup
#log4j.appender.DRFA.MaxBackupIndex=30
log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
# Pattern format: Date LogLevel LoggerName LogMessage
log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
# Debugging Pattern format
#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
#
# console
# Add "console" to rootlogger above if you want to use this
#
log4j.appender.console=org.apache.log4j.ConsoleAppender
log4j.appender.console.target=System.err
log4j.appender.console.layout=org.apache.log4j.PatternLayout
log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
#
# TaskLog Appender
#
#Default values
hadoop.tasklog.taskid=null
hadoop.tasklog.iscleanup=false
hadoop.tasklog.noKeepSplits=4
hadoop.tasklog.totalLogFileSize=100
hadoop.tasklog.purgeLogSplits=true
hadoop.tasklog.logsRetainHours=12
log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
log4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}
log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
#
#Security appender
#
hadoop.security.logger=INFO,console,gelf
log4j.category.SecurityLogger=${hadoop.security.logger}
hadoop.security.log.file=SecurityAuth.audit
log4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
log4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout
log4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
log4j.appender.DRFAS.DatePattern=.yyyy-MM-dd
#
# hdfs audit logging
#
hdfs.audit.logger=INFO,console,gelf
log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}
log4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false
log4j.appender.DRFAAUDIT=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log
log4j.appender.DRFAAUDIT.layout=org.apache.log4j.PatternLayout
log4j.appender.DRFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
log4j.appender.DRFAAUDIT.DatePattern=.yyyy-MM-dd
#
# mapred audit logging
#
mapred.audit.logger=INFO,console,gelf
log4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}
log4j.additivity.org.apache.hadoop.mapred.AuditLogger=false
log4j.appender.MRAUDIT=org.apache.log4j.DailyRollingFileAppender
log4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log
log4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout
log4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
log4j.appender.MRAUDIT.DatePattern=.yyyy-MM-dd
#
# Rolling File Appender
#
#log4j.appender.RFA=org.apache.log4j.RollingFileAppender
#log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
# Logfile size and and 30-day backups
#log4j.appender.RFA.MaxFileSize=1MB
#log4j.appender.RFA.MaxBackupIndex=30
#log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} - %m%n
#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
# Custom Logging levels
#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
#log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=DEBUG
# Jets3t library
log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
#
# Event Counter Appender
# Sends counts of logging messages at different severity levels to Hadoop Metrics.
#
log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
#
# Job Summary Appender
#
# Use following logger to send summary to separate file defined by
# hadoop.mapreduce.jobsummary.log.file rolled daily:
# hadoop.mapreduce.jobsummary.logger=INFO,JSA
#
hadoop.mapreduce.jobsummary.logger=${hadoop.root.logger}
hadoop.mapreduce.jobsummary.log.file=hadoop-mapreduce.jobsummary.log
log4j.appender.JSA=org.apache.log4j.DailyRollingFileAppender
log4j.appender.JSA.File=${hadoop.log.dir}/${hadoop.mapreduce.jobsummary.log.file}
log4j.appender.JSA.layout=org.apache.log4j.PatternLayout
log4j.appender.JSA.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
log4j.appender.JSA.DatePattern=.yyyy-MM-dd
log4j.logger.org.apache.hadoop.mapred.JobInProgress$JobSummary=${hadoop.mapreduce.jobsummary.logger}
log4j.additivity.org.apache.hadoop.mapred.JobInProgress$JobSummary=false
#
# Yarn ResourceManager Application Summary Log
#
# Set the ResourceManager summary log filename
#yarn.server.resourcemanager.appsummary.log.file=rm-appsummary.log
# Set the ResourceManager summary log level and appender
#yarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY
# Appender for ResourceManager Application Summary Log - rolled daily
# Requires the following properties to be set
# - hadoop.log.dir (Hadoop Log directory)
# - yarn.server.resourcemanager.appsummary.log.file (resource manager app summary log filename)
# - yarn.server.resourcemanager.appsummary.logger (resource manager app summary log level and appender)
#log4j.logger.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=${yarn.server.resourcemanager.appsummary.logger}
#log4j.additivity.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=false
#log4j.appender.RMSUMMARY=org.apache.log4j.DailyRollingFileAppender
#log4j.appender.RMSUMMARY.File=${hadoop.log.dir}/${yarn.server.resourcemanager.appsummary.log.file}
#log4j.appender.RMSUMMARY.layout=org.apache.log4j.PatternLayout
#log4j.appender.RMSUMMARY.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
#log4j.appender.RMSUMMARY.DatePattern=.yyyy-MM-dd
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment