ambari-agent/src/main/puppet/modules/hdp-hadoop/templates/hadoop-env.sh.erb

#/*
# * 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.  Required.
export JAVA_HOME=<%=scope.function_hdp_java_home()%>
export HADOOP_HOME_WARN_SUPPRESS=1

# Hadoop Configuration Directory
#TODO: if env var set that can cause problems
export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-<%=scope.function_hdp_template_var("conf_dir")%>}

# The maximum amount of heap to use, in MB. Default is 1000.
export HADOOP_HEAPSIZE="<%=scope.function_hdp_template_var("hadoop_heapsize")%>"

export HADOOP_NAMENODE_INIT_HEAPSIZE="-Xms<%=scope.function_hdp_template_var("namenode_heapsize")%>"

# Extra Java runtime options.  Empty by default.
export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}"

# Command specific options appended to HADOOP_OPTS when specified
export HADOOP_NAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile=<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER/hs_err_pid%p.log -XX:NewSize=<%=scope.function_hdp_template_var("namenode_opt_newsize")%> -XX:MaxNewSize=<%=scope.function_hdp_template_var("namenode_opt_maxnewsize")%> -Xloggc:<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms<%=scope.function_hdp_template_var("namenode_heapsize")%> -Xmx<%=scope.function_hdp_template_var("namenode_heapsize")%> -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_NAMENODE_OPTS}"
HADOOP_JOBTRACKER_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile=<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER/hs_err_pid%p.log -XX:NewSize=<%=scope.function_hdp_template_var("jtnode_opt_newsize")%> -XX:MaxNewSize=<%=scope.function_hdp_template_var("jtnode_opt_maxnewsize")%> -Xloggc:<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xmx<%=scope.function_hdp_template_var("jtnode_heapsize")%> -Dhadoop.security.logger=INFO,DRFAS -Dmapred.audit.logger=INFO,MRAUDIT -Dhadoop.mapreduce.jobsummary.logger=INFO,JSA ${HADOOP_JOBTRACKER_OPTS}"

HADOOP_TASKTRACKER_OPTS="-server -Xmx<%=scope.function_hdp_template_var("ttnode_heapsize")%> -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}"
HADOOP_DATANODE_OPTS="-Xmx<%=scope.function_hdp_template_var("dtnode_heapsize")%> -Dhadoop.security.logger=ERROR,DRFAS ${HADOOP_DATANODE_OPTS}"
HADOOP_BALANCER_OPTS="-server -Xmx<%=scope.function_hdp_template_var("hadoop_heapsize")%>m ${HADOOP_BALANCER_OPTS}"

export HADOOP_SECONDARYNAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile=<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER/hs_err_pid%p.log -XX:NewSize=<%=scope.function_hdp_template_var("namenode_opt_newsize")%> -XX:MaxNewSize=<%=scope.function_hdp_template_var("namenode_opt_maxnewsize")%> -Xloggc:<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps ${HADOOP_NAMENODE_INIT_HEAPSIZE} -Xmx<%=scope.function_hdp_template_var("namenode_heapsize")%> -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${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=<%=scope.function_hdp_template_var("hdfs_user")%>

# Extra ssh options.  Empty by default.
export HADOOP_SSH_OPTS="-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR"

# Where log files are stored.  $HADOOP_HOME/logs by default.
export HADOOP_LOG_DIR=<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$USER


# Where log files are stored in the secure data environment.
export HADOOP_SECURE_DN_LOG_DIR=<%=scope.function_hdp_template_var("hdfs_log_dir_prefix")%>/$HADOOP_SECURE_DN_USER

# File naming remote slave hosts.  $HADOOP_HOME/conf/slaves by default.
# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves

# host:path where hadoop code should be rsync'd from.  Unset by default.
# export HADOOP_MASTER=master:/home/$USER/src/hadoop

# Seconds to sleep between slave commands.  Unset by default.  This
# can be useful in large clusters, where, e.g., slave rsyncs can
# otherwise arrive faster than the master can service them.
# export HADOOP_SLAVE_SLEEP=0.1

# The directory where pid files are stored. /tmp by default.
export HADOOP_PID_DIR=<%=scope.function_hdp_template_var("hadoop_piddirprefix")%>/$USER
export HADOOP_SECURE_DN_PID_DIR=<%=scope.function_hdp_template_var("hadoop_piddirprefix")%>/$HADOOP_SECURE_DN_USER

# A string representing this instance of hadoop. $USER by default.
export HADOOP_IDENT_STRING=$USER

# The scheduling priority for daemon processes.  See 'man nice'.

# export HADOOP_NICENESS=10