| { |
| "configuration_attributes": { |
| "spark-defaults": {}, |
| "spark-javaopts-properties": {}, |
| "spark-log4j-properties": {}, |
| "spark-env": {}, |
| "core-site": { |
| "final": { |
| "fs.defaultFS": "true" |
| } |
| }, |
| "hadoop-env": {}, |
| "spark-metrics-properties": {}, |
| "cluster-env": {} |
| }, |
| "commandParams": { |
| "service_package_folder": "common-services/SPARK/1.2.0.2.2/package", |
| "script": "scripts/job_history_server.py", |
| "hooks_folder": "HDP/2.0.6/hooks", |
| "version": "2.2.2.0-2538", |
| "command_timeout": "600", |
| "script_type": "PYTHON" |
| }, |
| "roleCommand": "START", |
| "kerberosCommandParams": [], |
| "clusterName": "c1", |
| "hostname": "c6408.ambari.apache.org", |
| "hostLevelParams": { |
| "jdk_location": "http://c6408.ambari.apache.org:8080/resources/", |
| "ambari_db_rca_password": "mapred", |
| "java_home": "/usr/jdk64/jdk1.7.0_67", |
| "java_version": "8", |
| "ambari_db_rca_url": "jdbc:postgresql://c6408.ambari.apache.org/ambarirca", |
| "repo_info": "[{\"baseUrl\":\"http://s3.amazonaws.com/dev.hortonworks.com/HDP/centos6/2.x/BUILDS/2.2.2.0-2538\",\"osType\":\"redhat6\",\"repoId\":\"HDP-2.2\",\"repoName\":\"HDP\",\"defaultBaseUrl\":\"http://public-repo-1.hortonworks.com/HDP/centos6/2.x/GA/2.2.0.0\",\"latestBaseUrl\":\"http://s3.amazonaws.com/dev.hortonworks.com/HDP/centos6/2.x/BUILDS/2.2.2.0-2538\",\"baseSaved\":true},{\"baseUrl\":\"http://public-repo-1.hortonworks.com/HDP-UTILS-1.1.0.20/repos/centos6\",\"osType\":\"redhat6\",\"repoId\":\"HDP-UTILS-1.1.0.20\",\"repoName\":\"HDP-UTILS\",\"defaultBaseUrl\":\"http://public-repo-1.hortonworks.com/HDP-UTILS-1.1.0.20/repos/centos6\",\"latestBaseUrl\":\"http://public-repo-1.hortonworks.com/HDP-UTILS-1.1.0.20/repos/centos6\",\"baseSaved\":true}]", |
| "group_list": "[\"hadoop\",\"users\",\"spark\"]", |
| "package_list": "[{\"name\":\"spark_2_2_*\"},{\"name\":\"spark_2_2_*-python\"}]", |
| "stack_version": "2.2", |
| "stack_name": "HDP", |
| "db_name": "ambari", |
| "user_list": "[\"mapred\",\"ambari-qa\",\"zookeeper\",\"tez\",\"false\",\"hdfs\",\"yarn\",\"spark\"]", |
| "clientsToUpdateConfigs": "[\"*\"]" |
| }, |
| "commandType": "EXECUTION_COMMAND", |
| "roleParams": {}, |
| "serviceName": "SPARK", |
| "role": "SPARK_JOBHISTORYSERVER", |
| "forceRefreshConfigTags": [], |
| "taskId": 70, |
| "public_hostname": "c6408.ambari.apache.org", |
| "configurations": { |
| "spark-defaults": { |
| "spark.yarn.applicationMaster.waitTries": "10", |
| "spark.history.kerberos.keytab": "none", |
| "spark.yarn.preserve.staging.files": "false", |
| "spark.yarn.submit.file.replication": "3", |
| "spark.history.kerberos.principal": "none", |
| "spark.yarn.driver.memoryOverhead": "384", |
| "spark.yarn.queue": "default", |
| "spark.yarn.containerLauncherMaxThreads": "25", |
| "spark.yarn.scheduler.heartbeat.interval-ms": "5000", |
| "spark.history.ui.port": "18080", |
| "spark.yarn.max.executor.failures": "3", |
| "spark.driver.extraJavaOptions": "", |
| "spark.history.provider": "org.apache.spark.deploy.yarn.history.YarnHistoryProvider", |
| "spark.yarn.am.extraJavaOptions": "", |
| "spark.yarn.executor.memoryOverhead": "384" |
| }, |
| "spark-javaopts-properties": { |
| "content": " " |
| }, |
| "spark-log4j-properties": { |
| "content": "\n# Set everything to be logged to the console\nlog4j.rootCategory=INFO, console\nlog4j.appender.console=org.apache.log4j.ConsoleAppender\nlog4j.appender.console.target=System.err\nlog4j.appender.console.layout=org.apache.log4j.PatternLayout\nlog4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n\n\n# Settings to quiet third party logs that are too verbose\nlog4j.logger.org.eclipse.jetty=WARN\nlog4j.logger.org.eclipse.jetty.util.component.AbstractLifeCycle=ERROR\nlog4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO\nlog4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO" |
| }, |
| "spark-env": { |
| "content": "\n#!/usr/bin/env bash\n\n# This file is sourced when running various Spark programs.\n# Copy it as spark-env.sh and edit that to configure Spark for your site.\n\n# Options read in YARN client mode\n#SPARK_EXECUTOR_INSTANCES=\"2\" #Number of workers to start (Default: 2)\n#SPARK_EXECUTOR_CORES=\"1\" #Number of cores for the workers (Default: 1).\n#SPARK_EXECUTOR_MEMORY=\"1G\" #Memory per Worker (e.g. 1000M, 2G) (Default: 1G)\n#SPARK_DRIVER_MEMORY=\"512 Mb\" #Memory for Master (e.g. 1000M, 2G) (Default: 512 Mb)\n#SPARK_YARN_APP_NAME=\"spark\" #The name of your application (Default: Spark)\n#SPARK_YARN_QUEUE=\"~@~Xdefault~@~Y\" #The hadoop queue to use for allocation requests (Default: @~Xdefault~@~Y)\n#SPARK_YARN_DIST_FILES=\"\" #Comma separated list of files to be distributed with the job.\n#SPARK_YARN_DIST_ARCHIVES=\"\" #Comma separated list of archives to be distributed with the job.\n\n# Generic options for the daemons used in the standalone deploy mode\n\n# Alternate conf dir. (Default: ${SPARK_HOME}/conf)\nexport SPARK_CONF_DIR=${SPARK_HOME:-{{spark_home}}}/conf\n\n# Where log files are stored.(Default:${SPARK_HOME}/logs)\n#export SPARK_LOG_DIR=${SPARK_HOME:-{{spark_home}}}/logs\nexport SPARK_LOG_DIR={{spark_log_dir}}\n\n# Where the pid file is stored. (Default: /tmp)\nexport SPARK_PID_DIR={{spark_pid_dir}}\n\n# A string representing this instance of spark.(Default: $USER)\nSPARK_IDENT_STRING=$USER\n\n# The scheduling priority for daemons. (Default: 0)\nSPARK_NICENESS=0\n\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\nexport HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-{{hadoop_conf_dir}}}\n\n# The java implementation to use.\nexport JAVA_HOME={{java_home}}\n\nif [ -d \"/etc/tez/conf/\" ]; then\n export TEZ_CONF_DIR=/etc/tez/conf\nelse\n export TEZ_CONF_DIR=\nfi", |
| "spark_pid_dir": "/var/run/spark", |
| "spark_log_dir": "/var/log/spark", |
| "spark_group": "spark", |
| "spark_user": "spark" |
| }, |
| "hadoop-env": { |
| "dtnode_heapsize": "1024m", |
| "namenode_opt_maxnewsize": "256m", |
| "hdfs_log_dir_prefix": "/var/log/hadoop", |
| "namenode_heapsize": "1024m", |
| "proxyuser_group": "users", |
| "hadoop_pid_dir_prefix": "/var/run/hadoop", |
| "content": "\n# Set Hadoop-specific environment variables here.\n\n# The only required environment variable is JAVA_HOME. All others are\n# optional. When running a distributed configuration it is best to\n# set JAVA_HOME in this file, so that it is correctly defined on\n# remote nodes.\n\n# The java implementation to use. Required.\nexport JAVA_HOME={{java_home}}\nexport HADOOP_HOME_WARN_SUPPRESS=1\n\n# Hadoop home directory\nexport HADOOP_HOME=${HADOOP_HOME:-{{hadoop_home}}}\n\n# Hadoop Configuration Directory\n\n{# this is different for HDP1 #}\n# Path to jsvc required by secure HDP 2.0 datanode\nexport JSVC_HOME={{jsvc_path}}\n\n\n# The maximum amount of heap to use, in MB. Default is 1000.\nexport HADOOP_HEAPSIZE=\"{{hadoop_heapsize}}\"\n\nexport HADOOP_NAMENODE_INIT_HEAPSIZE=\"-Xms{{namenode_heapsize}}\"\n\n# Extra Java runtime options. Empty by default.\nexport HADOOP_OPTS=\"-Djava.net.preferIPv4Stack=true ${HADOOP_OPTS}\"\n\n# Command specific options appended to HADOOP_OPTS when specified\nexport HADOOP_NAMENODE_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$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 -Xms{{namenode_heapsize}} -Xmx{{namenode_heapsize}} -Dhadoop.security.logger=INFO,DRFAS -Dhdfs.audit.logger=INFO,DRFAAUDIT ${HADOOP_NAMENODE_OPTS}\"\nHADOOP_JOBTRACKER_OPTS=\"-server -XX:ParallelGCThreads=8 -XX:+UseConcMarkSweepGC -XX:ErrorFile={{hdfs_log_dir_prefix}}/$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}\"\n\nHADOOP_TASKTRACKER_OPTS=\"-server -Xmx{{ttnode_heapsize}} -Dhadoop.security.logger=ERROR,console -Dmapred.audit.logger=ERROR,console ${HADOOP_TASKTRACKER_OPTS}\"\nexport HADOOP_DATANODE_OPTS=\"-server -XX:ParallelGCThreads=4 -XX:+UseConcMarkSweepGC -XX:ErrorFile=/var/log/hadoop/$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}\"\nHADOOP_BALANCER_OPTS=\"-server -Xmx{{hadoop_heapsize}}m ${HADOOP_BALANCER_OPTS}\"\n\nexport HADOOP_SECONDARYNAMENODE_OPTS=$HADOOP_NAMENODE_OPTS\n\n# The following applies to multiple commands (fs, dfs, fsck, distcp etc)\nexport HADOOP_CLIENT_OPTS=\"-Xmx${HADOOP_HEAPSIZE}m -XX:MaxPermSize=512m $HADOOP_CLIENT_OPTS\"\n\n# On secure datanodes, user to run the datanode as after dropping privileges\nexport HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER:-{{hadoop_secure_dn_user}}}\n\n# Extra ssh options. Empty by default.\nexport HADOOP_SSH_OPTS=\"-o ConnectTimeout=5 -o SendEnv=HADOOP_CONF_DIR\"\n\n# Where log files are stored. $HADOOP_HOME/logs by default.\nexport HADOOP_LOG_DIR={{hdfs_log_dir_prefix}}/$USER\n\n# History server logs\nexport HADOOP_MAPRED_LOG_DIR={{mapred_log_dir_prefix}}/$USER\n\n# Where log files are stored in the secure data environment.\nexport HADOOP_SECURE_DN_LOG_DIR={{hdfs_log_dir_prefix}}/$HADOOP_SECURE_DN_USER\n\n# File naming remote slave hosts. $HADOOP_HOME/conf/slaves by default.\n# export HADOOP_SLAVES=${HADOOP_HOME}/conf/slaves\n\n# host:path where hadoop code should be rsync'd from. Unset by default.\n# export HADOOP_MASTER=master:/home/$USER/src/hadoop\n\n# Seconds to sleep between slave commands. Unset by default. This\n# can be useful in large clusters, where, e.g., slave rsyncs can\n# otherwise arrive faster than the master can service them.\n# export HADOOP_SLAVE_SLEEP=0.1\n\n# The directory where pid files are stored. /tmp by default.\nexport HADOOP_PID_DIR={{hadoop_pid_dir_prefix}}/$USER\nexport HADOOP_SECURE_DN_PID_DIR={{hadoop_pid_dir_prefix}}/$HADOOP_SECURE_DN_USER\n\n# History server pid\nexport HADOOP_MAPRED_PID_DIR={{mapred_pid_dir_prefix}}/$USER\n\nYARN_RESOURCEMANAGER_OPTS=\"-Dyarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY\"\n\n# A string representing this instance of hadoop. $USER by default.\nexport HADOOP_IDENT_STRING=$USER\n\n# The scheduling priority for daemon processes. See 'man nice'.\n\n# export HADOOP_NICENESS=10\n\n# Use libraries from standard classpath\nJAVA_JDBC_LIBS=\"\"\n#Add libraries required by mysql connector\nfor jarFile in `ls /usr/share/java/*mysql* 2>/dev/null`\ndo\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\ndone\n# Add libraries required by oracle connector\nfor jarFile in `ls /usr/share/java/*ojdbc* 2>/dev/null`\ndo\n JAVA_JDBC_LIBS=${JAVA_JDBC_LIBS}:$jarFile\ndone\n# Add libraries required by nodemanager\nMAPREDUCE_LIBS={{mapreduce_libs_path}}\nexport HADOOP_CLASSPATH=${HADOOP_CLASSPATH}${JAVA_JDBC_LIBS}:${MAPREDUCE_LIBS}\n\n# added to the HADOOP_CLASSPATH\nif [ -d \"/usr/hdp/current/tez-client\" ]; then\n if [ -d \"/etc/tez/conf/\" ]; then\n # When using versioned RPMs, the tez-client will be a symlink to the current folder of tez in HDP.\n export HADOOP_CLASSPATH=${HADOOP_CLASSPATH}:/usr/hdp/current/tez-client/*:/usr/hdp/current/tez-client/lib/*:/etc/tez/conf/\n fi\nfi\n\n\n# Setting path to hdfs command line\nexport HADOOP_LIBEXEC_DIR={{hadoop_libexec_dir}}\n\n# Mostly required for hadoop 2.0\nexport JAVA_LIBRARY_PATH=${JAVA_LIBRARY_PATH}\n\nexport HADOOP_OPTS=\"-Dhdp.version=$HDP_VERSION $HADOOP_OPTS\"", |
| "hdfs_user": "hdfs", |
| "namenode_opt_newsize": "256m", |
| "hadoop_root_logger": "INFO,RFA", |
| "hadoop_heapsize": "1024", |
| "namenode_opt_maxpermsize": "256m", |
| "namenode_opt_permsize": "128m" |
| }, |
| "spark-metrics-properties": { |
| "content": "\n# syntax: [instance].sink|source.[name].[options]=[value]\n\n# This file configures Spark's internal metrics system. The metrics system is\n# divided into instances which correspond to internal components.\n# Each instance can be configured to report its metrics to one or more sinks.\n# Accepted values for [instance] are \"master\", \"worker\", \"executor\", \"driver\",\n# and \"applications\". A wild card \"*\" can be used as an instance name, in\n# which case all instances will inherit the supplied property.\n#\n# Within an instance, a \"source\" specifies a particular set of grouped metrics.\n# there are two kinds of sources:\n# 1. Spark internal sources, like MasterSource, WorkerSource, etc, which will\n# collect a Spark component's internal state. Each instance is paired with a\n# Spark source that is added automatically.\n# 2. Common sources, like JvmSource, which will collect low level state.\n# These can be added through configuration options and are then loaded\n# using reflection.\n#\n# A \"sink\" specifies where metrics are delivered to. Each instance can be\n# assigned one or more sinks.\n#\n# The sink|source field specifies whether the property relates to a sink or\n# source.\n#\n# The [name] field specifies the name of source or sink.\n#\n# The [options] field is the specific property of this source or sink. The\n# source or sink is responsible for parsing this property.\n#\n# Notes:\n# 1. To add a new sink, set the \"class\" option to a fully qualified class\n# name (see examples below).\n# 2. Some sinks involve a polling period. The minimum allowed polling period\n# is 1 second.\n# 3. Wild card properties can be overridden by more specific properties.\n# For example, master.sink.console.period takes precedence over\n# *.sink.console.period.\n# 4. A metrics specific configuration\n# \"spark.metrics.conf=${SPARK_HOME}/conf/metrics.properties\" should be\n# added to Java properties using -Dspark.metrics.conf=xxx if you want to\n# customize metrics system. You can also put the file in ${SPARK_HOME}/conf\n# and it will be loaded automatically.\n# 5. MetricsServlet is added by default as a sink in master, worker and client\n# driver, you can send http request \"/metrics/json\" to get a snapshot of all the\n# registered metrics in json format. For master, requests \"/metrics/master/json\" and\n# \"/metrics/applications/json\" can be sent seperately to get metrics snapshot of\n# instance master and applications. MetricsServlet may not be configured by self.\n#\n\n## List of available sinks and their properties.\n\n# org.apache.spark.metrics.sink.ConsoleSink\n# Name: Default: Description:\n# period 10 Poll period\n# unit seconds Units of poll period\n\n# org.apache.spark.metrics.sink.CSVSink\n# Name: Default: Description:\n# period 10 Poll period\n# unit seconds Units of poll period\n# directory /tmp Where to store CSV files\n\n# org.apache.spark.metrics.sink.GangliaSink\n# Name: Default: Description:\n# host NONE Hostname or multicast group of Ganglia server\n# port NONE Port of Ganglia server(s)\n# period 10 Poll period\n# unit seconds Units of poll period\n# ttl 1 TTL of messages sent by Ganglia\n# mode multicast Ganglia network mode ('unicast' or 'multicast')\n\n# org.apache.spark.metrics.sink.JmxSink\n\n# org.apache.spark.metrics.sink.MetricsServlet\n# Name: Default: Description:\n# path VARIES* Path prefix from the web server root\n# sample false Whether to show entire set of samples for histograms ('false' or 'true')\n#\n# * Default path is /metrics/json for all instances except the master. The master has two paths:\n# /metrics/aplications/json # App information\n# /metrics/master/json # Master information\n\n# org.apache.spark.metrics.sink.GraphiteSink\n# Name: Default: Description:\n# host NONE Hostname of Graphite server\n# port NONE Port of Graphite server\n# period 10 Poll period\n# unit seconds Units of poll period\n# prefix EMPTY STRING Prefix to prepend to metric name\n\n## Examples\n# Enable JmxSink for all instances by class name\n#*.sink.jmx.class=org.apache.spark.metrics.sink.JmxSink\n\n# Enable ConsoleSink for all instances by class name\n#*.sink.console.class=org.apache.spark.metrics.sink.ConsoleSink\n\n# Polling period for ConsoleSink\n#*.sink.console.period=10\n\n#*.sink.console.unit=seconds\n\n# Master instance overlap polling period\n#master.sink.console.period=15\n\n#master.sink.console.unit=seconds\n\n# Enable CsvSink for all instances\n#*.sink.csv.class=org.apache.spark.metrics.sink.CsvSink\n\n# Polling period for CsvSink\n#*.sink.csv.period=1\n\n#*.sink.csv.unit=minutes\n\n# Polling directory for CsvSink\n#*.sink.csv.directory=/tmp/\n\n# Worker instance overlap polling period\n#worker.sink.csv.period=10\n\n#worker.sink.csv.unit=minutes\n\n# Enable jvm source for instance master, worker, driver and executor\n#master.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#worker.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#driver.source.jvm.class=org.apache.spark.metrics.source.JvmSource\n\n#executor.source.jvm.class=org.apache.spark.metrics.source.JvmSource" |
| }, |
| "cluster-env": { |
| "security_enabled": "false", |
| "ignore_groupsusers_create": "false", |
| "kerberos_domain": "EXAMPLE.COM", |
| "user_group": "hadoop", |
| "smokeuser": "ambari-qa", |
| "smokeuser_keytab": "/etc/security/keytabs/smokeuser.headless.keytab" |
| } |
| }, |
| "configurationTags": { |
| "spark-defaults": { |
| "tag": "version1425610281212" |
| }, |
| "spark-javaopts-properties": { |
| "tag": "version1425610281212" |
| }, |
| "spark-log4j-properties": { |
| "tag": "version1425610281212" |
| }, |
| "spark-env": { |
| "tag": "version1425610281212" |
| }, |
| "core-site": { |
| "tag": "version1" |
| }, |
| "hadoop-env": { |
| "tag": "version1" |
| }, |
| "spark-metrics-properties": { |
| "tag": "version1425610281212" |
| }, |
| "cluster-env": { |
| "tag": "version1" |
| } |
| }, |
| "commandId": "12-0", |
| "clusterHostInfo": { |
| "all_hosts": [ |
| "c6408.ambari.apache.org", |
| "c6410.ambari.apache.org", |
| "c6409.ambari.apache.org" |
| ], |
| "slave_hosts": [ |
| "c6408.ambari.apache.org", |
| "c6410.ambari.apache.org", |
| "c6409.ambari.apache.org" |
| ], |
| "spark_jobhistoryserver_hosts": [ |
| "c6408.ambari.apache.org" |
| ], |
| "ambari_server_host": [ |
| "c6408.ambari.apache.org" |
| ] |
| } |
| } |
