==================================================================================
一、基础环境
==================================================================================
1、服务器分布
192.168.10.84 主名字节点
192.168.10.84 备名字节点
192.168.10.83 数据节点1
192.168.10.85 数据节点2
----------------------------------------------------------------------------------
2、HOSTS 设置
在每台服务器的“/etc/hosts”文件
192.168.10.83 192-168-10-83
192.168.10.84 192-168-10-84
192.168.10.85 192-168-10-85
----------------------------------------------------------------------------------
3、SSH 免密码登录
可参考文章:
http://blog.csdn.net/codepeak/article/details/14447627
==================================================================================
二、Hadoop 2.6.2 编译安装【官方提供的二进制版本native java为32位版本,64位环境需重新编译】
==================================================================================
1、JDK 安装
http://download.oracle.com/otn-pub/java/jdk/7u45-b18/jdk-7u45-linux-x64.tar.gz
# tar xvzf jdk-7u45-linux-x64.tar.gz -C /usr/local
# cd /usr/local
# ln -s jdk1.7.0_45 jdk
# vim /etc/profile
export JAVA_HOME=/usr/local/java
export CLASS_PATH=$JAVA_HOME/lib:$JAVA_HOME/jre/lib
export PATH=$PATH:$JAVA_HOME/bin
# source /etc/profile
----------------------------------------------------------------------------------
2、MAVEN 安装
http://mirror.bit.edu.cn/apache/maven/maven-3/3.1.1/binaries/apache-maven-3.1.1-bin.tar.gz
# tar xvzf apache-maven-3.1.1-bin.tar.gz -C /usr/local
# cd /usr/local
# ln -s apache-maven-3.1.1 maven
# vim /etc/profile
export MAVEN_HOME=/usr/local/maven
export PATH=$PATH:$MAVEN_HOME/bin
# source /etc/profile
# mvn -v
3、PROTOBUF 安装
https://protobuf.googlecode.com/files/protobuf-2.5.0.tar.gz
# tar xvzf protobuf-2.5.0.tar.gz
# ./configure --prefix=/usr/local/protobuf
# make && make install
# vim /etc/profile
export PROTO_HOME=/usr/local/protobuf
export PATH=$PATH:$PROTO_HOME/bin
# source /etc/profile
# vim /etc/ld.so.conf
/usr/local/protobuf/lib
# /sbin/ldconfig
4、其他依赖库安装
http://www.cmake.org/files/v2.8/cmake-2.8.12.1.tar.gz
http://ftp.gnu.org/pub/gnu/ncurses/ncurses-5.9.tar.gz
http://www.openssl.org/source/openssl-1.0.1e.tar.gz
# tar xvzf cmake-2.8.12.1.tar.gz
# cd cmake-2.8.12.1
# ./bootstrap --prefix=/usr/local
# gmake && gmake install
# tar xvzf ncurses-5.9.tar.gz
# cd ncurses-5.9
# ./configure --prefix=/usr/local
# make && make install
# tar xvzf openssl-1.0.1e.tar.gz
# cd openssl-1.0.1e
# ./config shared --prefix=/usr/local
# make && make install
# /sbin/ldconfig
----------------------------------------------------------------------------------
5、编译 Hadoop
http://mirrors.hust.edu.cn/apache/hadoop/common/hadoop-2.6.2/hadoop-2.6.2-src.tar.gz
(1)、maven源设置【在<mirrors></mirros>里添加】
# vim /usr/local/maven/conf/settings.xml
<mirror>
<id>nexus-osc</id>
<mirrorOf>*</mirrorOf>
<name>Nexusosc</name>
<url>http://maven.oschina.net/content/groups/public/</url>
</mirror>
(2)、编译Hadoop
# tar xvzf hadoop-2.6.2-src.tar.gz
# cd hadoop-2.6.2-src
# mvn clean install -DskipTests
# mvn package -Pdist,native -DskipTests -Dtar
## 编译成功后,生成的二进制包所在路径
hadoop-dist/target/hadoop-2.6.2
创建hadoop用户
useradd hadoop
# cp -a hadoop-dist/target/hadoop-2.6.2 /home/hadoop/source
# cd /home/hadoop
# ln -s /home/hadoop/source/hadoop-2.6.2 ./hadoop
【注意:编译过程中,可能会失败,需要多尝试几次】
========================================================================================
三、Hadoop YARN 分布式集群配置【注:所有节点都做同样配置】
========================================================================================
1、环境变量设置
# vim /etc/profile 或者 .bash_profile
export HADOOP_DEV_HOME=/home/hadoop/hadoop
export PATH=$PATH:$HADOOP_DEV_HOME/bin
export PATH=$PATH:$HADOOP_DEV_HOME/sbin
export HADOOP_MAPARED_HOME=${HADOOP_DEV_HOME}
export HADOOP_COMMON_HOME=${HADOOP_DEV_HOME}
export HADOOP_HDFS_HOME=${HADOOP_DEV_HOME}
export YARN_HOME=${HADOOP_DEV_HOME}
export HADOOP_CONF_DIR=${HADOOP_DEV_HOME}/etc/hadoop
export HDFS_CONF_DIR=${HADOOP_DEV_HOME}/etc/hadoop
export YARN_CONF_DIR=${HADOOP_DEV_HOME}/etc/hadoop
export SPARK_HOME=/home/hadoop/spark
export PATH=$PATH:$SPARK_HOME/bin
export PATH
# source /etc/profile
3、配置 core-site.xml
# vim /home/hadoop/hadoop/etc/hadoop/core-site.xml
<configuration>
<property>
<name>hadoop.tmp.dir</name>
<value>/hadoop/tmp</value>
<description>A base for other temporary directories.</description>
</property>
<property>
<name>fs.default.name</name>
<value>hdfs://192.168.10.84:9000</value>
</property>
<property>
<name>hadoop.proxyuser.root.hosts</name>
<value>192.168.10.84</value>
</property>
<property>
<name>hadoop.proxyuser.root.groups</name>
<value>*</value>
</property>
</configuration>
4、配置 hdfs-site.xml
# vim /home/hadoop/hadoop/etc/hadoop/hdfs-site.xml
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/hadoop/hdfs/name</value>
<final>true</final>
</property>
<property>
<name>dfs.federation.nameservice.id</name>
<value>ns1</value>
</property>
<property>
<name>dfs.namenode.backup.address.ns1</name>
<value>192.168.10.84:50100</value>
</property>
<property>
<name>dfs.namenode.backup.http-address.ns1</name>
<value>192.168.10.84:50105</value>
</property>
<property>
<name>dfs.federation.nameservices</name>
<value>ns1</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns1</name>
<value>192.168.10.84:9000</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns2</name>
<value>192.168.10.84:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.ns1</name>
<value>192.168.10.84:23001</value>
</property>
<property>
<name>dfs.namenode.http-address.ns2</name>
<value>192.168.10.84:13001</value>
</property>
<property>
<name>dfs.dataname.data.dir</name>
<value>file:/hadoop/hdfs/data</value>
<final>true</final>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns1</name>
<value>192.168.10.84:23002</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns2</name>
<value>192.168.10.84:23002</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns1</name>
<value>192.168.10.84:23003</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns2</name>
<value>192.168.10.84:23003</value>
</property>
------------------------------------------------------------------------------------------------------------------------------------------
6、配置 yarn-site.xml
# vim /home/hadoop/hadoop/etc/hadoop/yarn-site.xml
<property>
<name>yarn.resourcemanager.address</name>
<value>192.168.10.84:18040</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>192.168.10.84:18030</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>192.168.10.84:18088</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>192.168.10.84:18025</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>192.168.10.84:18141</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
7、配置 hadoop-env.sh、mapred-env.sh、yarn-env.sh【在开头添加】
文件路径:
/home/hadoop/hadoop/etc/hadoop/hadoop-env.sh
/home/hadoop/hadoop/etc/hadoop/mapred-env.sh
/home/hadoop/hadoop/etc/hadoop/yarn-env.sh
添加内容:
export JAVA_HOME=/usr/local/java
export CLASS_PATH=$JAVA_HOME/lib:$JAVA_HOME/jre/lib
export HADOOP_HOME=/home/hadoop/hadoop
export HADOOP_PID_DIR=/home/hadoop/data/hadoop/pids
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$HADOOP_HOME/lib/native"
export HADOOP_PREFIX=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export HDFS_CONF_DIR=$HADOOP_HOME/etc/hadoop
export YARN_CONF_DIR=$HADOOP_HOME/etc/hadoop
export JAVA_LIBRARY_PATH=$HADOOP_HOME/lib/native
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
------------------------------------------------------------------------------------------------------------------------------------------
8、数据节点配置
# vim /home/hadoop/hadoop/etc/hadoop/slaves
192.168.10.83
192.168.10.84
192.168.10.85
------------------------------------------------------------------------------------------------------------------------------------------
9、Hadoop 简单测试
# cd /home/hadoop/hadoop
## 首次启动集群时,做如下操作【主名字节点上执行】
# hdfs namenode -format
# sbin/start-dfs.sh
## 检查进程是否正常启动
# jps
主名字节点:
NodeManager
备名字节点:
SecondaryNameNode
数据节点:
DataNode
## hdfs与mapreduce测试
# hdfs dfs -mkdir -p /user/test
# hdfs dfs -put bin/hdfs.cmd /user/test
# hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.0.jar wordcount /user/test /user/out
# hdfs dfs -ls /user/out
## hdfs信息查看
# hdfs dfsadmin -report
# hdfs fsck / -files -blocks
## 集群的后续维护
# sbin/start-all.sh
# sbin/stop-all.sh
## 监控页面URL
http://192.168.10.84:80/
========================================================================================
四、Spark 分布式集群配置【注:所有节点都做同样配置】
========================================================================================
1、Scala 安装
http://www.scala-lang.org/files/archive/scala-2.9.3.tgz
# tar xvzf scala-2.9.3.tgz -C /usr/local
# cd /usr/local
# ln -s scala-2.9.3 scala
# vim /etc/profile
export SCALA_HOME=/usr/local/scala
export PATH=$PATH:$SCALA_HOME/bin
export SPARK_CLASSPATH=/home/hadoop/spark/lib
# source /etc/profile
------------------------------------------------------------------------------------------------------------------------------------------
2、Spark 安装
http://d3kbcqa49mib13.cloudfront.net/spark-1.6.1-incubating-bin-hadoop2.6tgz
# tar xvzf spark-1.6.1-incubating-bin-hadoop2.6.tgz -C /home/hadoop/source
# cd /home/hadoop
# ln -s spark-1.6.1-incubating-bin-hadoop2.6 ./spark
# vim /etc/profile
export SPARK_HOME=/home/hadoop/spark
export PATH=$PATH:$SPARK_HOME/bin
# source /etc/profile
# cd /home/hadoop/spark/conf
# mv spark-env.sh.template spark-env.sh
# vim spark-env.sh
export JAVA_HOME=/usr/local/java
export SCALA_HOME=/usr/local/scala
export HADOOP_HOME=/home/hadoop/hadoop
## worker节点的主机名列表
# vim slaves
192.168.10.83
192.168.10.84
192.168.10.85
# mv log4j.properties.template log4j.properties
## 在Master节点上执行
# .sbin/start-all.sh
## 检查进程是否启动【在master节点上出现“Master”,在slave节点上出现“Worker”】
# jps
Master节点:
Master
Slave节点:
worker
3、相关测试
## 监控页面URL
http://192.168.10.84:8080/
## 先切换到“/home/hadoop/spark”目录
(1)、本地模式
# ./run-example org.apache.spark.examples.SparkPi local
(2)、普通集群模式
# ./run-example org.apache.spark.examples.SparkPi spark://namenode1:7077
# ./run-example org.apache.spark.examples.SparkLR spark://namenode1:7077
# ./run-example org.apache.spark.examples.SparkKMeans spark://namenode1:7077 file:/home/hadoop/spark/kmeans_data.txt 2 1
(3)、结合HDFS的集群模式
# hadoop fs -put README.md .
# MASTER=spark://namenode1:7077 ./spark-shell
scala> val file = sc.textFile("hdfs://namenode1:9000/user/root/README.md")
scala> val count = file.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey(_+_)
scala> count.collect()
scala> :quit
(4)、基于YARN模式
# SPARK_JAR=./assembly/target/scala-2.9.3/spark-assembly-1.6.1-incubating-hadoop2.6.2.jar \
./spark-class org.apache.spark.deploy.yarn.Client \
--jar examples/target/scala-2.9.3/spark-examples-assembly-1.6.1-incubating.jar \
--class org.apache.spark.examples.SparkPi \
--args yarn-standalone \
--num-workers 3 \
--master-memory 4g \
--worker-memory 2g \
--worker-cores 1
执行结果:
/usr/local/hadoop/logs/userlogs/application_*/container*_000001/stdout
(5)、其他一些样例程序
examples/src/main/scala/org/apache/spark/examples/
(6)、问题定位【数据节点上的日志】
/home/hadoop/hadoop/logs
(7)、一些优化
# vim /home/hadoop/spark/conf/spark-env.sh
export SPARK_WORKER_MEMORY=16g 【根据内存大小进行实际配置】
......
(8)、最终的目录结构
一、基础环境
==================================================================================
1、服务器分布
192.168.10.84 主名字节点
192.168.10.84 备名字节点
192.168.10.83 数据节点1
192.168.10.85 数据节点2
----------------------------------------------------------------------------------
2、HOSTS 设置
在每台服务器的“/etc/hosts”文件
192.168.10.83 192-168-10-83
192.168.10.84 192-168-10-84
192.168.10.85 192-168-10-85
----------------------------------------------------------------------------------
3、SSH 免密码登录
可参考文章:
http://blog.csdn.net/codepeak/article/details/14447627
==================================================================================
二、Hadoop 2.6.2 编译安装【官方提供的二进制版本native java为32位版本,64位环境需重新编译】
==================================================================================
1、JDK 安装
http://download.oracle.com/otn-pub/java/jdk/7u45-b18/jdk-7u45-linux-x64.tar.gz
# tar xvzf jdk-7u45-linux-x64.tar.gz -C /usr/local
# cd /usr/local
# ln -s jdk1.7.0_45 jdk
# vim /etc/profile
export JAVA_HOME=/usr/local/java
export CLASS_PATH=$JAVA_HOME/lib:$JAVA_HOME/jre/lib
export PATH=$PATH:$JAVA_HOME/bin
# source /etc/profile
----------------------------------------------------------------------------------
2、MAVEN 安装
http://mirror.bit.edu.cn/apache/maven/maven-3/3.1.1/binaries/apache-maven-3.1.1-bin.tar.gz
# tar xvzf apache-maven-3.1.1-bin.tar.gz -C /usr/local
# cd /usr/local
# ln -s apache-maven-3.1.1 maven
# vim /etc/profile
export MAVEN_HOME=/usr/local/maven
export PATH=$PATH:$MAVEN_HOME/bin
# source /etc/profile
# mvn -v
3、PROTOBUF 安装
https://protobuf.googlecode.com/files/protobuf-2.5.0.tar.gz
# tar xvzf protobuf-2.5.0.tar.gz
# ./configure --prefix=/usr/local/protobuf
# make && make install
# vim /etc/profile
export PROTO_HOME=/usr/local/protobuf
export PATH=$PATH:$PROTO_HOME/bin
# source /etc/profile
# vim /etc/ld.so.conf
/usr/local/protobuf/lib
# /sbin/ldconfig
4、其他依赖库安装
http://www.cmake.org/files/v2.8/cmake-2.8.12.1.tar.gz
http://ftp.gnu.org/pub/gnu/ncurses/ncurses-5.9.tar.gz
http://www.openssl.org/source/openssl-1.0.1e.tar.gz
# tar xvzf cmake-2.8.12.1.tar.gz
# cd cmake-2.8.12.1
# ./bootstrap --prefix=/usr/local
# gmake && gmake install
# tar xvzf ncurses-5.9.tar.gz
# cd ncurses-5.9
# ./configure --prefix=/usr/local
# make && make install
# tar xvzf openssl-1.0.1e.tar.gz
# cd openssl-1.0.1e
# ./config shared --prefix=/usr/local
# make && make install
# /sbin/ldconfig
----------------------------------------------------------------------------------
5、编译 Hadoop
http://mirrors.hust.edu.cn/apache/hadoop/common/hadoop-2.6.2/hadoop-2.6.2-src.tar.gz
(1)、maven源设置【在<mirrors></mirros>里添加】
# vim /usr/local/maven/conf/settings.xml
<mirror>
<id>nexus-osc</id>
<mirrorOf>*</mirrorOf>
<name>Nexusosc</name>
<url>http://maven.oschina.net/content/groups/public/</url>
</mirror>
(2)、编译Hadoop
# tar xvzf hadoop-2.6.2-src.tar.gz
# cd hadoop-2.6.2-src
# mvn clean install -DskipTests
# mvn package -Pdist,native -DskipTests -Dtar
## 编译成功后,生成的二进制包所在路径
hadoop-dist/target/hadoop-2.6.2
创建hadoop用户
useradd hadoop
# cp -a hadoop-dist/target/hadoop-2.6.2 /home/hadoop/source
# cd /home/hadoop
# ln -s /home/hadoop/source/hadoop-2.6.2 ./hadoop
【注意:编译过程中,可能会失败,需要多尝试几次】
========================================================================================
三、Hadoop YARN 分布式集群配置【注:所有节点都做同样配置】
========================================================================================
1、环境变量设置
# vim /etc/profile 或者 .bash_profile
export HADOOP_DEV_HOME=/home/hadoop/hadoop
export PATH=$PATH:$HADOOP_DEV_HOME/bin
export PATH=$PATH:$HADOOP_DEV_HOME/sbin
export HADOOP_MAPARED_HOME=${HADOOP_DEV_HOME}
export HADOOP_COMMON_HOME=${HADOOP_DEV_HOME}
export HADOOP_HDFS_HOME=${HADOOP_DEV_HOME}
export YARN_HOME=${HADOOP_DEV_HOME}
export HADOOP_CONF_DIR=${HADOOP_DEV_HOME}/etc/hadoop
export HDFS_CONF_DIR=${HADOOP_DEV_HOME}/etc/hadoop
export YARN_CONF_DIR=${HADOOP_DEV_HOME}/etc/hadoop
export SPARK_HOME=/home/hadoop/spark
export PATH=$PATH:$SPARK_HOME/bin
export PATH
# source /etc/profile
3、配置 core-site.xml
# vim /home/hadoop/hadoop/etc/hadoop/core-site.xml
<configuration>
<property>
<name>hadoop.tmp.dir</name>
<value>/hadoop/tmp</value>
<description>A base for other temporary directories.</description>
</property>
<property>
<name>fs.default.name</name>
<value>hdfs://192.168.10.84:9000</value>
</property>
<property>
<name>hadoop.proxyuser.root.hosts</name>
<value>192.168.10.84</value>
</property>
<property>
<name>hadoop.proxyuser.root.groups</name>
<value>*</value>
</property>
</configuration>
4、配置 hdfs-site.xml
# vim /home/hadoop/hadoop/etc/hadoop/hdfs-site.xml
<property>
<name>dfs.namenode.name.dir</name>
<value>file:/hadoop/hdfs/name</value>
<final>true</final>
</property>
<property>
<name>dfs.federation.nameservice.id</name>
<value>ns1</value>
</property>
<property>
<name>dfs.namenode.backup.address.ns1</name>
<value>192.168.10.84:50100</value>
</property>
<property>
<name>dfs.namenode.backup.http-address.ns1</name>
<value>192.168.10.84:50105</value>
</property>
<property>
<name>dfs.federation.nameservices</name>
<value>ns1</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns1</name>
<value>192.168.10.84:9000</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns2</name>
<value>192.168.10.84:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.ns1</name>
<value>192.168.10.84:23001</value>
</property>
<property>
<name>dfs.namenode.http-address.ns2</name>
<value>192.168.10.84:13001</value>
</property>
<property>
<name>dfs.dataname.data.dir</name>
<value>file:/hadoop/hdfs/data</value>
<final>true</final>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns1</name>
<value>192.168.10.84:23002</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns2</name>
<value>192.168.10.84:23002</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns1</name>
<value>192.168.10.84:23003</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address.ns2</name>
<value>192.168.10.84:23003</value>
</property>
------------------------------------------------------------------------------------------------------------------------------------------
6、配置 yarn-site.xml
# vim /home/hadoop/hadoop/etc/hadoop/yarn-site.xml
<property>
<name>yarn.resourcemanager.address</name>
<value>192.168.10.84:18040</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>192.168.10.84:18030</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>192.168.10.84:18088</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>192.168.10.84:18025</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>192.168.10.84:18141</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
7、配置 hadoop-env.sh、mapred-env.sh、yarn-env.sh【在开头添加】
文件路径:
/home/hadoop/hadoop/etc/hadoop/hadoop-env.sh
/home/hadoop/hadoop/etc/hadoop/mapred-env.sh
/home/hadoop/hadoop/etc/hadoop/yarn-env.sh
添加内容:
export JAVA_HOME=/usr/local/java
export CLASS_PATH=$JAVA_HOME/lib:$JAVA_HOME/jre/lib
export HADOOP_HOME=/home/hadoop/hadoop
export HADOOP_PID_DIR=/home/hadoop/data/hadoop/pids
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_OPTS="$HADOOP_OPTS -Djava.library.path=$HADOOP_HOME/lib/native"
export HADOOP_PREFIX=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export HDFS_CONF_DIR=$HADOOP_HOME/etc/hadoop
export YARN_CONF_DIR=$HADOOP_HOME/etc/hadoop
export JAVA_LIBRARY_PATH=$HADOOP_HOME/lib/native
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
------------------------------------------------------------------------------------------------------------------------------------------
8、数据节点配置
# vim /home/hadoop/hadoop/etc/hadoop/slaves
192.168.10.83
192.168.10.84
192.168.10.85
------------------------------------------------------------------------------------------------------------------------------------------
9、Hadoop 简单测试
# cd /home/hadoop/hadoop
## 首次启动集群时,做如下操作【主名字节点上执行】
# hdfs namenode -format
# sbin/start-dfs.sh
## 检查进程是否正常启动
# jps
主名字节点:
NodeManager
备名字节点:
SecondaryNameNode
数据节点:
DataNode
## hdfs与mapreduce测试
# hdfs dfs -mkdir -p /user/test
# hdfs dfs -put bin/hdfs.cmd /user/test
# hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.6.0.jar wordcount /user/test /user/out
# hdfs dfs -ls /user/out
## hdfs信息查看
# hdfs dfsadmin -report
# hdfs fsck / -files -blocks
## 集群的后续维护
# sbin/start-all.sh
# sbin/stop-all.sh
## 监控页面URL
http://192.168.10.84:80/
========================================================================================
四、Spark 分布式集群配置【注:所有节点都做同样配置】
========================================================================================
1、Scala 安装
http://www.scala-lang.org/files/archive/scala-2.9.3.tgz
# tar xvzf scala-2.9.3.tgz -C /usr/local
# cd /usr/local
# ln -s scala-2.9.3 scala
# vim /etc/profile
export SCALA_HOME=/usr/local/scala
export PATH=$PATH:$SCALA_HOME/bin
export SPARK_CLASSPATH=/home/hadoop/spark/lib
# source /etc/profile
------------------------------------------------------------------------------------------------------------------------------------------
2、Spark 安装
http://d3kbcqa49mib13.cloudfront.net/spark-1.6.1-incubating-bin-hadoop2.6tgz
# tar xvzf spark-1.6.1-incubating-bin-hadoop2.6.tgz -C /home/hadoop/source
# cd /home/hadoop
# ln -s spark-1.6.1-incubating-bin-hadoop2.6 ./spark
# vim /etc/profile
export SPARK_HOME=/home/hadoop/spark
export PATH=$PATH:$SPARK_HOME/bin
# source /etc/profile
# cd /home/hadoop/spark/conf
# mv spark-env.sh.template spark-env.sh
# vim spark-env.sh
export JAVA_HOME=/usr/local/java
export SCALA_HOME=/usr/local/scala
export HADOOP_HOME=/home/hadoop/hadoop
## worker节点的主机名列表
# vim slaves
192.168.10.83
192.168.10.84
192.168.10.85
# mv log4j.properties.template log4j.properties
## 在Master节点上执行
# .sbin/start-all.sh
## 检查进程是否启动【在master节点上出现“Master”,在slave节点上出现“Worker”】
# jps
Master节点:
Master
Slave节点:
worker
3、相关测试
## 监控页面URL
http://192.168.10.84:8080/
## 先切换到“/home/hadoop/spark”目录
(1)、本地模式
# ./run-example org.apache.spark.examples.SparkPi local
(2)、普通集群模式
# ./run-example org.apache.spark.examples.SparkPi spark://namenode1:7077
# ./run-example org.apache.spark.examples.SparkLR spark://namenode1:7077
# ./run-example org.apache.spark.examples.SparkKMeans spark://namenode1:7077 file:/home/hadoop/spark/kmeans_data.txt 2 1
(3)、结合HDFS的集群模式
# hadoop fs -put README.md .
# MASTER=spark://namenode1:7077 ./spark-shell
scala> val file = sc.textFile("hdfs://namenode1:9000/user/root/README.md")
scala> val count = file.flatMap(line => line.split(" ")).map(word => (word, 1)).reduceByKey(_+_)
scala> count.collect()
scala> :quit
(4)、基于YARN模式
# SPARK_JAR=./assembly/target/scala-2.9.3/spark-assembly-1.6.1-incubating-hadoop2.6.2.jar \
./spark-class org.apache.spark.deploy.yarn.Client \
--jar examples/target/scala-2.9.3/spark-examples-assembly-1.6.1-incubating.jar \
--class org.apache.spark.examples.SparkPi \
--args yarn-standalone \
--num-workers 3 \
--master-memory 4g \
--worker-memory 2g \
--worker-cores 1
执行结果:
/usr/local/hadoop/logs/userlogs/application_*/container*_000001/stdout
(5)、其他一些样例程序
examples/src/main/scala/org/apache/spark/examples/
(6)、问题定位【数据节点上的日志】
/home/hadoop/hadoop/logs
(7)、一些优化
# vim /home/hadoop/spark/conf/spark-env.sh
export SPARK_WORKER_MEMORY=16g 【根据内存大小进行实际配置】
......
(8)、最终的目录结构