AMBARI-18936. DataNode JVM heap settings should include CMSInitiatingOccupancy (Arpit Agarwal via smohanty)

ambari-server/src/main/resources/stacks/HDP/2.4/services/HDFS/configuration/hadoop-env.xml

@@ -0,0 +1,176 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+/**
+ * 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.
+ */
+-->
+<configuration supports_adding_forbidden="true">
+  <!-- hadoop-env.sh -->
+  <property>
+    <name>content</name>
+    <display-name>hadoop-env template</display-name>
+    <description>This is the jinja template for hadoop-env.sh file</description>
+    <value>
+# 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={{java_home}}
+export HADOOP_HOME_WARN_SUPPRESS=1
+
+# Hadoop home directory
+export HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}
+
+# Hadoop Configuration Directory
+
+{# this is different for HDP1 #}
+# Path to jsvc required by secure HDP 2.0 datanode
+export JSVC_HOME={{jsvc_path}}
+
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+export HADOOP_HEAPSIZE="{{hadoop_heapsize}}"
+
+export HADOOP_NAMENODE_INIT_HEAPSIZE="-Xms{{namenode_heapsize}}"
+
+# Extra Java runtime options.  Empty by default.
+export HADOOP_OPTS="-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}"
+
+# Command specific options appended to HADOOP_OPTS when specified
+HADOOP_JOBTRACKER_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{jtnode_opt_newsize}} -XX:MaxNewSize={{jtnode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xmx{{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{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}"
+
+{% if java_version &lt; 8 %}
+SHARED_HADOOP_NAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -XX:PermSize={{namenode_opt_permsize}} -XX:MaxPermSize={{namenode_opt_maxpermsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -XX:CMSInitiatingOccupancyFraction=70 -XX:+UseCMSInitiatingOccupancyOnly -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT"
+export HADOOP_NAMENODE_OPTS="${SHARED_HADOOP_NAMENODE_OPTS} -XX:OnOutOfMemoryError=\"/usr/hdp/current/hadoop-hdfs-namenode/bin/kill-name-node\" -Dorg.mortbay.jetty.Request.maxFormContentSize=-1 ${HADOOP_NAMENODE_OPTS}"
+export HADOOP_DATANODE_OPTS="-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -XX:PermSize=128m -XX:MaxPermSize=256m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS} -XX:CMSInitiatingOccupancyFraction=70 -XX:+UseCMSInitiatingOccupancyOnly"
+
+export HADOOP_SECONDARYNAMENODE_OPTS="${SHARED_HADOOP_NAMENODE_OPTS} -XX:OnOutOfMemoryError=\"/usr/hdp/current/hadoop-hdfs-secondarynamenode/bin/kill-secondary-name-node\" ${HADOOP_SECONDARYNAMENODE_OPTS}"
+
+# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+export HADOOP_CLIENT_OPTS="-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS"
+
+{% else %}
+SHARED_HADOOP_NAMENODE_OPTS="-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$USER/hs_err_pid%p.log -XX:NewSize={{namenode_opt_newsize}} -XX:MaxNewSize={{namenode_opt_maxnewsize}} -Xloggc:{{hdfs_log_dir_prefix}}/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -XX:CMSInitiatingOccupancyFraction=70 -XX:+UseCMSInitiatingOccupancyOnly -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT"
+export HADOOP_NAMENODE_OPTS="${SHARED_HADOOP_NAMENODE_OPTS} -XX:OnOutOfMemoryError=\"/usr/hdp/current/hadoop-hdfs-namenode/bin/kill-name-node\" -Dorg.mortbay.jetty.Request.maxFormContentSize=-1 ${HADOOP_NAMENODE_OPTS}"
+export HADOOP_DATANODE_OPTS="-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$USER/hs_err_pid%p.log -XX:NewSize=200m -XX:MaxNewSize=200m -Xloggc:/var/log/hadoop/$USER/gc.log-`date +'%Y%m%d%H%M'` -verbose:gc -XX:+PrintGCDetails -XX:+PrintGCTimeStamps -XX:+PrintGCDateStamps -Xms{{dtnode_heapsize}} -Xmx{{dtnode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_DATANODE_OPTS} -XX:CMSInitiatingOccupancyFraction=70 -XX:+UseCMSInitiatingOccupancyOnly"
+
+export HADOOP_SECONDARYNAMENODE_OPTS="${SHARED_HADOOP_NAMENODE_OPTS} -XX:OnOutOfMemoryError=\"/usr/hdp/current/hadoop-hdfs-secondarynamenode/bin/kill-secondary-name-node\" ${HADOOP_SECONDARYNAMENODE_OPTS}"
+
+# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+export HADOOP_CLIENT_OPTS="-Xmx${HADOOP_HEAPSIZE}m $HADOOP_CLIENT_OPTS"
+{% endif %}
+
+HADOOP_NFS3_OPTS="-Xmx{{nfsgateway_heapsize}}m -Dhadoop.security.logger=ERROR,DRFAS ${HADOOP_NFS3_OPTS}"
+HADOOP_BALANCER_OPTS="-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_OPTS}"
+
+
+# On secure datanodes, user to run the datanode as after dropping privileges
+export HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}
+
+# Extra ssh options.  Empty by default.
+export HADOOP_SSH_OPTS="-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR"
+
+# Where log files are stored.  $HADOOP_HOME/logs by default.
+export HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER
+
+# History server logs
+export HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER
+
+# Where log files are stored in the secure data environment.
+export HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$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/$USER/src/hadoop
+
+# Seconds to sleep between slave commands.  Unset by default.  This
+# can be useful in large clusters, where, e.g., slave rsyncs can
+# otherwise arrive faster than the master can service them.
+# export HADOOP_SLAVE_SLEEP=0.1
+
+# The directory where pid files are stored. /tmp by default.
+export HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER
+export HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER
+
+# History server pid
+export HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER
+
+YARN_RESOURCEMANAGER_OPTS="-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY"
+
+# 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
+
+# Add database libraries
+JAVA_JDBC_LIBS=""
+if [ -d "/usr/share/java" ]; then
+  for jarFile in `ls /usr/share/java | grep -E "(mysql|ojdbc|postgresql|sqljdbc)" 2&gt;/dev/null`
+  do
+    JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile
+  done
+fi
+
+# Add libraries to the hadoop classpath - some may not need a colon as they already include it
+export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}
+
+# Setting path to hdfs command line
+export HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}
+
+# Mostly required for hadoop 2.0
+export JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}
+
+export HADOOP_OPTS="-Dhdp.version=$HDP_VERSION $HADOOP_OPTS"
+
+
+# Fix temporary bug, when ulimit from conf files is not picked up, without full relogin. 
+# Makes sense to fix only when runing DN as root 
+if [ "$command" == "datanode" ] &amp;&amp; [ "$EUID" -eq 0 ] &amp;&amp; [ -n "$HADOOP_SECURE_DN_USER" ]; then
+  {% if is_datanode_max_locked_memory_set %}
+  ulimit -l {{datanode_max_locked_memory}}
+  {% endif %}
+  ulimit -n {{hdfs_user_nofile_limit}}
+fi
+    </value>
+    <value-attributes>
+      <type>content</type>
+    </value-attributes>
+    <on-ambari-upgrade add="true"/>
+  </property>
+  <property>
+    <name>nfsgateway_heapsize</name>
+    <display-name>NFSGateway maximum Java heap size</display-name>
+    <value>1024</value>
+    <description>Maximum Java heap size for NFSGateway (Java option -Xmx)</description>
+    <value-attributes>
+      <type>int</type>
+      <unit>MB</unit>
+    </value-attributes>
+    <on-ambari-upgrade add="true"/>
+  </property>
+</configuration>