1.hive
conf/hive-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
hive.log.threshold=ALL
hive.root.logger=INFO,DRFA
hive.log.dir=/opt/module/hive/logs
hive.log.file=hive.log
# Define the root logger to the system property "hadoop.root.logger".
log4j.rootLogger=${hive.root.logger}, EventCounter
# Logging Threshold
log4j.threshold=${hive.log.threshold}
#
# Daily Rolling File Appender
#
# Use the PidDailyerRollingFileAppend class instead if you want to use separate log files
# for different CLI session.
#
# log4j.appender.DRFA=org.apache.hadoop.hive.ql.log.PidDailyRollingFileAppender
log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
log4j.appender.DRFA.File=${hive.log.dir}/${hive.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 [%t]: %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} [%t]: %p %c{2}: %m%n
log4j.appender.console.encoding=UTF-8
#custom logging levels
#log4j.logger.xxx=DEBUG
#
# Event Counter Appender
# Sends counts of logging messages at different severity levels to Hadoop Metrics.
#
log4j.appender.EventCounter=org.apache.hadoop.hive.shims.HiveEventCounter
log4j.category.DataNucleus=ERROR,DRFA
log4j.category.Datastore=ERROR,DRFA
log4j.category.Datastore.Schema=ERROR,DRFA
log4j.category.JPOX.Datastore=ERROR,DRFA
log4j.category.JPOX.Plugin=ERROR,DRFA
log4j.category.JPOX.MetaData=ERROR,DRFA
log4j.category.JPOX.Query=ERROR,DRFA
log4j.category.JPOX.General=ERROR,DRFA
log4j.category.JPOX.Enhancer=ERROR,DRFA
# Silence useless ZK logs
log4j.logger.org.apache.zookeeper.server.NIOServerCnxn=WARN,DRFA
log4j.logger.org.apache.zookeeper.ClientCnxnSocketNIO=WARN,DRFA
conf/hive-site.xml(使用mysql5.6)
<?xml version="1.0"?> <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> <configuration> <property> <name>javax.jdo.option.ConnectionURL</name> <value>jdbc:mysql://hadoop102:3306/metastore?createDatabaseIfNotExist=true</value> <description>JDBC connect string for a JDBC metastore</description> </property> <property> <name>javax.jdo.option.ConnectionDriverName</name> <value>com.mysql.jdbc.Driver</value> <description>Driver class name for a JDBC metastore</description> </property> <property> <name>javax.jdo.option.ConnectionUserName</name> <value>root</value> <description>username to use against metastore database</description> </property> <property> <name>javax.jdo.option.ConnectionPassword</name> <value>666666</value> <description>password to use against metastore database</description> </property> <property> <name>hive.metastore.warehouse.dir</name> <value>/hive</value> <description>location of default database for the warehouse</description> </property> <property> <name>hive.cli.print.header</name> <value>true</value> </property> <property> <name>hive.cli.print.current.db</name> <value>true</value> </property> <property> <name>hive.zookeeper.quorum</name> <value>hadoop102,hadoop103,hadoop101</value> <description>The list of ZooKeeper servers to talk to. This is only needed for read/write locks.</description> </property> <property> <name>hive.zookeeper.client.port</name> <value>2181</value> <description>The port of ZooKeeper servers to talk to. This is only needed for read/write locks.</description> </property> </configuration>
2.flume
创建myagents/,此目录放置配置自定义文件
execsource-hdfssink.conf
#a1是agent的名称，a1中定义了一个叫r1的source，如果有多个，使用空格间隔 a1.sources = r1 a1.sinks = k1 a1.channels = c1 #组名名.属性名=属性值 a1.sources.r1.type=exec a1.sources.r1.command=tail -f /opt/module/hive/logs/hive.log #定义chanel a1.channels.c1.type=memory a1.channels.c1.capacity=1000 #定义sink a1.sinks.k1.type = hdfs #一旦路径中含有基于时间的转义序列，要求event的header中必须有timestamp=时间戳，如果没有需要将useLocalTimeStamp = true a1.sinks.k1.hdfs.path = hdfs://hadoop101:9000/flume/%Y%m%d/%H/%M #上传文件的前缀 a1.sinks.k1.hdfs.filePrefix = logs- #以下三个和目录的滚动相关，目录一旦设置了时间转义序列，基于时间戳滚动 #是否将时间戳向下舍 a1.sinks.k1.hdfs.round = true #多少时间单位创建一个新的文件夹 a1.sinks.k1.hdfs.roundValue = 1 #重新定义时间单位 a1.sinks.k1.hdfs.roundUnit = minute #是否使用本地时间戳 a1.sinks.k1.hdfs.useLocalTimeStamp = true #积攒多少个Event才flush到HDFS一次 a1.sinks.k1.hdfs.batchSize = 100 #以下三个和文件的滚动相关，以下三个参数是或的关系！以下三个参数如果值为0都代表禁用！ #60秒滚动生成一个新的文件 a1.sinks.k1.hdfs.rollInterval = 10 #设置每个文件到128M时滚动 a1.sinks.k1.hdfs.rollSize = 134217700 #每写多少个event滚动一次 a1.sinks.k1.hdfs.rollCount = 0 #以不压缩的文本形式保存数据 a1.sinks.k1.hdfs.fileType=DataStream #连接组件 同一个source可以对接多个channel，一个sink只能从一个channel拿数据！ a1.sources.r1.channels=c1 a1.sinks.k1.channel=c1
taildirsource-loggersink.conf
#a1是agent的名称，a1中定义了一个叫r1的source，如果有多个，使用空格间隔 a1.sources = r1 a1.sinks = k1 a1.channels = c1 #组名名.属性名=属性值 a1.sources.r1.type=TAILDIR a1.sources.r1.filegroups=f1 f2 a1.sources.r1.filegroups.f1=/home/layman/hi a1.sources.r1.filegroups.f2=/home/layman/test #定义sink a1.sinks.k1.type=logger a1.sinks.k1.maxBytesToLog=100 #定义chanel a1.channels.c1.type=memory a1.channels.c1.capacity=1000 #连接组件 同一个source可以对接多个channel，一个sink只能从一个channel拿数据！ a1.sources.r1.channels=c1 a1.sinks.k1.channel=c1
spoolingdirsource-hdfsink.conf
#a1是agent的名称，a1中定义了一个叫r1的source，如果有多个，使用空格间隔 a1.sources = r1 a1.sinks = k1 a1.channels = c1 #组名名.属性名=属性值 a1.sources.r1.type=spooldir a1.sources.r1.spoolDir=/home/layman/flume #定义chanel a1.channels.c1.type=memory a1.channels.c1.capacity=1000 #定义sink a1.sinks.k1.type = hdfs #一旦路径中含有基于时间的转义序列，要求event的header中必须有timestamp=时间戳，如果没有需要将useLocalTimeStamp = true a1.sinks.k1.hdfs.path = hdfs://hadoop101:9000/flume/%Y%m%d/%H/%M #上传文件的前缀 a1.sinks.k1.hdfs.filePrefix = logs- #以下三个和目录的滚动相关，目录一旦设置了时间转义序列，基于时间戳滚动 #是否将时间戳向下舍 a1.sinks.k1.hdfs.round = true #多少时间单位创建一个新的文件夹 a1.sinks.k1.hdfs.roundValue = 1 #重新定义时间单位 a1.sinks.k1.hdfs.roundUnit = minute #是否使用本地时间戳 a1.sinks.k1.hdfs.useLocalTimeStamp = true #积攒多少个Event才flush到HDFS一次 a1.sinks.k1.hdfs.batchSize = 100 #以下三个和文件的滚动相关，以下三个参数是或的关系！以下三个参数如果值为0都代表禁用！ #60秒滚动生成一个新的文件 a1.sinks.k1.hdfs.rollInterval = 30 #设置每个文件到128M时滚动 a1.sinks.k1.hdfs.rollSize = 134217700 #每写多少个event滚动一次 a1.sinks.k1.hdfs.rollCount = 0 #以不压缩的文本形式保存数据 a1.sinks.k1.hdfs.fileType=DataStream #连接组件 同一个source可以对接多个channel，一个sink只能从一个channel拿数据！ a1.sources.r1.channels=c1 a1.sinks.k1.channel=c1
avrosource-loggersink.conf
#agent2 #a1是agent的名称，a1中定义了一个叫r1的source，如果有多个，使用空格间隔 a1.sources = r1 a1.sinks = k1 a1.channels = c1 #组名名.属性名=属性值 a1.sources.r1.type=avro a1.sources.r1.bind=hadoop102 a1.sources.r1.port=33333 #定义sink a1.sinks.k1.type=logger #定义chanel a1.channels.c1.type=memory a1.channels.c1.capacity=1000 #连接组件 同一个source可以对接多个channel，一个sink只能从一个channel拿数据！ a1.sources.r1.channels=c1 a1.sinks.k1.channel=c1
netcatsource-avrosink.conf
#agent1 #a1是agent的名称，a1中定义了一个叫r1的source，如果有多个，使用空格间隔 a1.sources = r1 a1.sinks = k1 a1.channels = c1 #组名名.属性名=属性值 a1.sources.r1.type=netcat a1.sources.r1.bind=hadoop101 a1.sources.r1.port=44444 #定义sink a1.sinks.k1.type=avro a1.sinks.k1.hostname=hadoop102 a1.sinks.k1.port=33333 #定义chanel a1.channels.c1.type=memory a1.channels.c1.capacity=1000 #连接组件 同一个source可以对接多个channel，一个sink只能从一个channel拿数据！ a1.sources.r1.channels=c1 a1.sinks.k1.channel=c1
注意上面两个agent的启动顺序
3.kafka
conf/server.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. # see kafka.server.KafkaConfig for additional details and defaults ############################# Server Basics ############################# # The id of the broker. This must be set to a unique integer for each broker. broker.id=102 # Switch to enable topic deletion or not, default value is false delete.topic.enable=true ############################# Socket Server Settings ############################# # The address the socket server listens on. It will get the value returned from # java.net.InetAddress.getCanonicalHostName() if not configured. # FORMAT: # listeners = listener_name://host_name:port # EXAMPLE: # listeners = PLAINTEXT://your.host.name:9092 #listeners=PLAINTEXT://:9092 # Hostname and port the broker will advertise to producers and consumers. If not set, # it uses the value for "listeners" if configured. Otherwise, it will use the value # returned from java.net.InetAddress.getCanonicalHostName(). #advertised.listeners=PLAINTEXT://your.host.name:9092 # Maps listener names to security protocols, the default is for them to be the same. See the config documentation for more details #listener.security.protocol.map=PLAINTEXT:PLAINTEXT,SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,SASL_SSL:SASL_SSL # The number of threads that the server uses for receiving requests from the network and sending responses to the network num.network.threads=3 # The number of threads that the server uses for processing requests, which may include disk I/O num.io.threads=8 # The send buffer (SO_SNDBUF) used by the socket server socket.send.buffer.bytes=102400 # The receive buffer (SO_RCVBUF) used by the socket server socket.receive.buffer.bytes=102400 # The maximum size of a request that the socket server will accept (protection against OOM) socket.request.max.bytes=104857600 ############################# Log Basics ############################# # A comma seperated list of directories under which to store log files log.dirs=/opt/module/kafka/datas # The default number of log partitions per topic. More partitions allow greater # parallelism for consumption, but this will also result in more files across # the brokers. num.partitions=1 # The number of threads per data directory to be used for log recovery at startup and flushing at shutdown. # This value is recommended to be increased for installations with data dirs located in RAID array. num.recovery.threads.per.data.dir=1 ############################# Internal Topic Settings ############################# # The replication factor for the group metadata internal topics "__consumer_offsets" and "__transaction_state" # For anything other than development testing, a value greater than 1 is recommended for to ensure availability such as 3. offsets.topic.replication.factor=1 transaction.state.log.replication.factor=1 transaction.state.log.min.isr=1 ############################# Log Flush Policy ############################# # Messages are immediately written to the filesystem but by default we only fsync() to sync # the OS cache lazily. The following configurations control the flush of data to disk. # There are a few important trade-offs here: # 1. Durability: Unflushed data may be lost if you are not using replication. # 2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush. # 3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks. # The settings below allow one to configure the flush policy to flush data after a period of time or # every N messages (or both). This can be done globally and overridden on a per-topic basis. # The number of messages to accept before forcing a flush of data to disk #log.flush.interval.messages=10000 # The maximum amount of time a message can sit in a log before we force a flush #log.flush.interval.ms=1000 ############################# Log Retention Policy ############################# # The following configurations control the disposal of log segments. The policy can # be set to delete segments after a period of time, or after a given size has accumulated. # A segment will be deleted whenever *either* of these criteria are met. Deletion always happens # from the end of the log. # The minimum age of a log file to be eligible for deletion due to age log.retention.hours=168 # A size-based retention policy for logs. Segments are pruned from the log as long as the remaining # segments don't drop below log.retention.bytes. Functions independently of log.retention.hours. #log.retention.bytes=1073741824 # The maximum size of a log segment file. When this size is reached a new log segment will be created. log.segment.bytes=1073741824 # The interval at which log segments are checked to see if they can be deleted according # to the retention policies log.retention.check.interval.ms=300000 ############################# Zookeeper ############################# # Zookeeper connection string (see zookeeper docs for details). # This is a comma separated host:port pairs, each corresponding to a zk # server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002". # You can also append an optional chroot string to the urls to specify the # root directory for all kafka znodes. zookeeper.connect=hadoop101:2181,hadoop102:2181,hadoop103:2181 # Timeout in ms for connecting to zookeeper zookeeper.connection.timeout.ms=6000 ############################# Group Coordinator Settings ############################# # The following configuration specifies the time, in milliseconds, that the GroupCoordinator will delay the initial consumer rebalance. # The rebalance will be further delayed by the value of group.initial.rebalance.delay.ms as new members join the group, up to a maximum of max.poll.interval.ms. # The default value for this is 3 seconds. # We override this to 0 here as it makes for a better out-of-the-box experience for development and testing. # However, in production environments the default value of 3 seconds is more suitable as this will help to avoid unnecessary, and potentially expensive, rebalances during application startup. group.initial.rebalance.delay.ms=0
zk群起脚本
#!/bin/bash #启动(start)|停止(stop)|查看zk集群状态(status) #检测用户是否传入了参数 if(($#==0)) then echo '请输入start|stop|status' exit; fi #对参数检查，看参数是否复合要求 if [ $1 = start ] || [ $1 = stop ] || [ $1 = status ] then xcall /opt/module/zookeeper-3.4.10/bin/zkServer.sh $1 else echo '只允许输入start|stop|status!' fi
/etc/profile
# /etc/profile # System wide environment and startup programs, for login setup # Functions and aliases go in /etc/bashrc # It's NOT a good idea to change this file unless you know what you # are doing. It's much better to create a custom.sh shell script in # /etc/profile.d/ to make custom changes to your environment, as this # will prevent the need for merging in future updates. pathmunge () { case ":${PATH}:" in *:"$1":*) ;; *) if [ "$2" = "after" ] ; then PATH=$PATH:$1 else PATH=$1:$PATH fi esac } if [ -x /usr/bin/id ]; then if [ -z "$EUID" ]; then # ksh workaround EUID=`id -u` UID=`id -ru` fi USER="`id -un`" LOGNAME=$USER MAIL="/var/spool/mail/$USER" fi # Path manipulation if [ "$EUID" = "0" ]; then pathmunge /sbin pathmunge /usr/sbin pathmunge /usr/local/sbin else pathmunge /usr/local/sbin after pathmunge /usr/sbin after pathmunge /sbin after fi HOSTNAME=`/bin/hostname 2>/dev/null` HISTSIZE=1000 if [ "$HISTCONTROL" = "ignorespace" ] ; then export HISTCONTROL=ignoreboth else export HISTCONTROL=ignoredups fi export PATH USER LOGNAME MAIL HOSTNAME HISTSIZE HISTCONTROL # By default, we want umask to get set. This sets it for login shell # Current threshold for system reserved uid/gids is 200 # You could check uidgid reservation validity in # /usr/share/doc/setup-*/uidgid file if [ $UID -gt 199 ] && [ "`id -gn`" = "`id -un`" ]; then umask 002 else umask 022 fi for i in /etc/profile.d/*.sh ; do if [ -r "$i" ]; then if [ "${-#*i}" != "$-" ]; then . "$i" else . "$i" >/dev/null 2>&1 fi fi done unset i unset -f pathmunge JAVA_HOME=/opt/module/jdk1.8.0_241 HADOOP_HOME=/opt/module/hadoop-2.7.2 HIVE_HOME=/opt/module/hive FLUME_HOME=/opt/module/flume HBASE_HOME=/opt/module/hbase PHOENIX_HOME=/opt/module/phoenix PHOENIX_CLASSPATH=$PHOENIX_HOME ZOOKEEPER_HOME=/opt/module/zookeeper-3.4.10 PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HIVE_HOME/bin:$FLUME_HOME/bin:$HBASE_HOME/bin:$PHOENIX_HOME/bin export JAVA_HOME PATH HADOOP_HOME HIVE_HOME FLUME_HOME HBASE_HOME PHOENIX_HOME PHOENIX_CLASSPATH ZOOKEEPER_HOME
4.hbase
conf/hbase-site.xml
<?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> <property> <name>hbase.rootdir</name> <value>hdfs://hadoop101:9000/HBase</value> </property> <property> <name>hbase.cluster.distributed</name> <value>true</value> </property> <!-- 0.98后的新变动，之前版本没有.port,默认端口为60000 --> <property> <name>hbase.master.port</name> <value>16000</value> </property> <property> <name>hbase.zookeeper.quorum</name> <value>hadoop102,hadoop103,hadoop101</value> </property> <property> <name>hbase.zookeeper.property.dataDir</name> <value>/opt/module/zookeeper-3.4.10/datas</value> </property> <!-- phoenix regionserver 配置参数 --> <property> <name>hbase.regionserver.wal.codec</name> <value>org.apache.hadoop.hbase.regionserver.wal.IndexedWALEditCodec</value> </property> <property> <name>hbase.region.server.rpc.scheduler.factory.class</name> <value>org.apache.hadoop.hbase.ipc.PhoenixRpcSchedulerFactory</value> <description>Factory to create the Phoenix RPC Scheduler that uses separate queues for index and metadata updates</description> </property> <property> <name>hbase.rpc.controllerfactory.class</name> <value>org.apache.hadoop.hbase.ipc.controller.ServerRpcControllerFactory</value> <description>Factory to create the Phoenix RPC Scheduler that uses separate queues for index and metadata updates</description> </property> <!-- phoenix master 配置参数 --> <property> <name>hbase.master.loadbalancer.class</name> <value>org.apache.phoenix.hbase.index.balancer.IndexLoadBalancer</value> </property> <property> <name>hbase.coprocessor.master.classes</name> <value>org.apache.phoenix.hbase.index.master.IndexMasterObserver</value> </property>
conf/regionservers
hadoop101
hadoop102
hadoop103
conf/backup-masters(只能用这个名)
hadoop101
hadoop102
hadoop103
conf/hbase-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 environment variables here. # This script sets variables multiple times over the course of starting an hbase process, # so try to keep things idempotent unless you want to take an even deeper look # into the startup scripts (bin/hbase, etc.) # The java implementation to use. Java 1.7+ required. # export JAVA_HOME=/usr/java/jdk1.6.0/ # Extra Java CLASSPATH elements. Optional. # export HBASE_CLASSPATH= # The maximum amount of heap to use. Default is left to JVM default. # export HBASE_HEAPSIZE=1G # Uncomment below if you intend to use off heap cache. For example, to allocate 8G of # offheap, set the value to "8G". # export HBASE_OFFHEAPSIZE=1G # Extra Java runtime options. # Below are what we set by default. May only work with SUN JVM. # For more on why as well as other possible settings, # see http://wiki.apache.org/hadoop/PerformanceTuning export HBASE_OPTS="-XX:+UseConcMarkSweepGC" # Configure PermSize. Only needed in JDK7. You can safely remove it for JDK8+ #export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m" #export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m" # Uncomment one of the below three options to enable java garbage collection logging for the server-side processes. # This enables basic gc logging to the .out file. # export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps" # This enables basic gc logging to its own file. # If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR . # export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>" # This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+. # If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR . # export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M" # Uncomment one of the below three options to enable java garbage collection logging for the client processes. # This enables basic gc logging to the .out file. # export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps" # This enables basic gc logging to its own file. # If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR . # export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>" # This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+. # If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR . # export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M" # See the package documentation for org.apache.hadoop.hbase.io.hfile for other configurations # needed setting up off-heap block caching. # Uncomment and adjust to enable JMX exporting # See jmxremote.password and jmxremote.access in $JRE_HOME/lib/management to configure remote password access. # More details at: http://java.sun.com/javase/6/docs/technotes/guides/management/agent.html # NOTE: HBase provides an alternative JMX implementation to fix the random ports issue, please see JMX # section in HBase Reference Guide for instructions. # export HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.ssl=false -Dcom.sun.management.jmxremote.authenticate=false" # export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10101" # export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10102" # export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10103" # export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10104" # export HBASE_REST_OPTS="$HBASE_REST_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10105" # File naming hosts on which HRegionServers will run. $HBASE_HOME/conf/regionservers by default. # export HBASE_REGIONSERVERS=${HBASE_HOME}/conf/regionservers # Uncomment and adjust to keep all the Region Server pages mapped to be memory resident #HBASE_REGIONSERVER_MLOCK=true #HBASE_REGIONSERVER_UID="hbase" # File naming hosts on which backup HMaster will run. $HBASE_HOME/conf/backup-masters by default. # export HBASE_BACKUP_MASTERS=${HBASE_HOME}/conf/backup-masters # Extra ssh options. Empty by default. # export HBASE_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HBASE_CONF_DIR" # Where log files are stored. $HBASE_HOME/logs by default. # export HBASE_LOG_DIR=${HBASE_HOME}/logs # Enable remote JDWP debugging of major HBase processes. Meant for Core Developers # export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8070" # export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8071" # export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8072" # export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8073" # A string representing this instance of hbase. $USER by default. # export HBASE_IDENT_STRING=$USER # The scheduling priority for daemon processes. See 'man nice'. # export HBASE_NICENESS=10 # The directory where pid files are stored. /tmp by default. # export HBASE_PID_DIR=/var/hadoop/pids # 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 HBASE_SLAVE_SLEEP=0.1 # Tell HBase whether it should manage it's own instance of Zookeeper or not. export HBASE_MANAGES_ZK=false # The default log rolling policy is RFA, where the log file is rolled as per the size defined for the # RFA appender. Please refer to the log4j.properties file to see more details on this appender. # In case one needs to do log rolling on a date change, one should set the environment property # HBASE_ROOT_LOGGER to "<DESIRED_LOG LEVEL>,DRFA". # For example: # HBASE_ROOT_LOGGER=INFO,DRFA # The reason for changing default to RFA is to avoid the boundary case of filling out disk space as # DRFA doesn't put any cap on the log size. Please refer to HBase-5655 for more context.
5.phoenix
注意继承HBase 的配置,hbase中配置二级索引,zookeeper集群配置的时候端口号省略
6.sqoop
配置相关的HADOOP相关的环境变量,由于etc/profile已经配置全局,因此不需要指定
hadoop,zookeeper,hive,hbase,phoenix,sqoop启动一堆效果