最新Hadoop-2.7.2+hbase-1.2.0+zookeeper-3.4.8 HA高可用集群配置安装

Ip	主机名	程序	进程
192.168.128.11	h1	Jdk Hadoop hbase	Namenode DFSZKFailoverController Hamster
192.168.128.12	h2	Jdk Hadoop hbase	Namenode DFSZKFailoverController Hamster
192.168.128.13	h3	Jdk Hadoop	resourceManager
192.168.128.14	h4	Jdk Hadoop	resourceManager
192.168.128.15	h5	Jdk Hadoop Zookeeper Hbase	Datanode nodeManager JournalNode QuorumPeerMain HRegionServer
192.168.128.16	h6	Jdk Hadoop Zookeeper Hbase	Datanode nodeManager JournalNode QuorumPeerMain HRegionServer
192.168.128.17	h7	Jdk Hadoop Zookeeper hbase	Datanode nodeManager JournalNode QuorumPeerMain HRegionServer

关于准备工作 我这里就不一一写出来了，总结一下有主机名，ip，主机名和ip的映射关系，防火墙，ssh免密码，jdk的安装及环境变量的设置。

安装zookeeper到 h5、h6、h7上面

修改 /home/zookeeper-3.4.8/conf的zoo_sample.cfg

cp zoo_sample.cfg zoo.cfg

# The number of milliseconds of each tick

tickTime=2000

# The number of ticks that the initial

# synchronization phase can take

initLimit=10

# The number of ticks that can pass between

# sending a request and getting an acknowledgement

syncLimit=5

# the directory where the snapshot is stored.

# do not use /tmp for storage, /tmp here is just

# example sakes.

dataDir=/home/zookeeper-3.4.8/data

# the port at which the clients will connect

clientPort=2181

# the maximum number of client connections.

# increase this if you need to handle more clients

#maxClientCnxns=60

#

# Be sure to read the maintenance section of the

# administrator guide before turning on autopurge.

#

# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
#

# The number of snapshots to retain in dataDir

#autopurge.snapRetainCount=3

# Purge task interval in hours

# Set to "0" to disable auto purge feature

#autopurge.purgeInterval=1

server.1=h5:2888:3888

server.2=h6:2888:3888

server.3=h7:2888:3888

创建 data文件夹 和在里面 创建文件myid 并写入数字1

touch data/myid

echo 1 > data/myid

拷贝整个zookeeper到另外两个节点上

scp -r /home/zookeeper-3.4.8 h6:/home/

scp -r /home/zookeeper-3.4.8 h7:/home/

其他两个节点的myid 修改为 2 3

安装hadoop

/home/hadoop-2.7.2/etc/Hadoop

hadoop-env.sh：

export JAVA_HOME=/home/jdk

core-site.xml：

<configuration>

<!-- 指定hdfs的nameservice为masters -->

<property>

<name>fs.defaultFS</name>

<value>hdfs://masters</value>

</property>

<!-- 指定hadoop临时目录 -->

<property>

<name>hadoop.tmp.dir</name>

<value>/home/hadoop-2.7.2/tmp</value>

</property>

<!-- 指定zookeeper地址 -->

<property>

<name>ha.zookeeper.quorum</name>

<value>h5:2181,h6:2181,h7:2181</value>

</property>

</configuration>

hdfs-site.xml：

<configuration>

<!--指定hdfs的nameservice为masters，需要和core-site.xml中的保持一致 -->

<property>

<name>dfs.nameservices</name>

<value>masters</value>

</property>

<!-- h1下面有两个NameNode，分别是h1，h2 -->

<property>

<name>dfs.ha.namenodes.masters</name>

<value>h1,h2</value>

</property>

<!-- h1的RPC通信地址 -->

<property>

<name>dfs.namenode.rpc-address.masters.h1</name>

<value>h1:9000</value>

</property>

<!-- h1的http通信地址 -->

<property>

<name>dfs.namenode.http-address.masters.h1</name>

<value>h1:50070</value>

</property>

<!-- h2的RPC通信地址 -->

<property>

<name>dfs.namenode.rpc-address.masters.h2</name>

<value>h2:9000</value>

</property>

<!-- h2的http通信地址 -->

<property>

<name>dfs.namenode.http-address.masters.h2</name>

<value>h2:50070</value>

</property>

<!-- 指定NameNode的元数据在JournalNode上的存放位置 -->

<property>

<name>dfs.namenode.shared.edits.dir</name>

<value>qjournal://h5:8485;h6:8485;h7:8485/masters</value>

</property>

<!-- 指定JournalNode在本地磁盘存放数据的位置 -->

<property>

<name>dfs.journalnode.edits.dir</name>

<value>/home/hadoop-2.7.2/journal</value>

</property>

<!-- 开启NameNode失败自动切换 -->

<property>

<name>dfs.ha.automatic-failover.enabled</name>

<value>true</value>

</property>

<!-- 配置失败自动切换实现方式 -->

<property>

<name>dfs.client.failover.proxy.provider.masters</name>

<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>

</property>

<!-- 配置隔离机制方法，多个机制用换行分割，即每个机制暂用一行-->

<property>

<name>dfs.ha.fencing.methods</name>

<value>

sshfence

shell(/bin/true)

</value>

</property>

<!-- 使用sshfence隔离机制时需要ssh免登陆 -->

<property>

<name>dfs.ha.fencing.ssh.private-key-files</name>

<value>/root/.ssh/id_rsa</value>

</property>

<!-- 配置sshfence隔离机制超时时间 -->

<property>

<name>dfs.ha.fencing.ssh.connect-timeout</name>

<value>30000</value>

</property>

</configuration>

mapred-site.xml：

<configuration>

<!-- 指定mr框架为yarn方式 -->

<property>

<name>mapreduce.framework.name</name>

<value>yarn</value>

</property>

</configuration>

yarn-site.xml：

<configuration>

<!-- 开启RM高可靠 -->

<property>

<name>yarn.resourcemanager.ha.enabled</name>

<value>true</value>

</property>

<!-- 指定RM的cluster id -->

<property>

<name>yarn.resourcemanager.cluster-id</name>

<value>RM_HA_ID</value>

</property>

<!-- 指定RM的名字 -->

<property>

<name>yarn.resourcemanager.ha.rm-ids</name>

<value>rm1,rm2</value>

</property>

<!-- 分别指定RM的地址 -->

<property>

<name>yarn.resourcemanager.hostname.rm1</name>

<value>h3</value>

</property>

<property>

<name>yarn.resourcemanager.hostname.rm2</name>

<value>h4</value>

</property>

<property>

<name>yarn.resourcemanager.recovery.enabled</name>

<value>true</value>

</property>

<property>

<name>yarn.resourcemanager.store.class</name>

<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>

</property>

<!-- 指定zk集群地址 -->

<property>

<name>yarn.resourcemanager.zk-address</name>

<value>h5:2181,h6:2181,h7:2181</value>

</property>

<property>

<name>yarn.nodemanager.aux-services</name>

<value>mapreduce_shuffle</value>

</property>

</configuration>

Slaves：

h5

h6

h7

然后 拷贝到其他节点

scp -r hadoop-2.7.2 h2:/home/ 等等

这个地方说明一下 yarn 的HA 是在 h3和h4 上面

启动顺序

###注意：严格按照下面的步骤

启动zookeeper集群

[root@h6 ~]# cd /home/zookeeper-3.4.8/bin/

[root@h6 bin]# ./zkServer.sh start

H5 h6 h7 都一样

[root@h6 bin]# ./zkServer.sh status

查看状态

启动journalnode

[root@h5 bin]# cd /home/hadoop-2.7.2/sbin/

[root@h5 sbin]# ./hadoop-daemons.sh start journalnode

h5: starting journalnode, logging to /home/hadoop-2.7.2/logs/hadoop-root-journalnode-h5.out

h7: starting journalnode, logging to /home/hadoop-2.7.2/logs/hadoop-root-journalnode-h7.out

h6: starting journalnode, logging to /home/hadoop-2.7.2/logs/hadoop-root-journalnode-h6.out

[root@h5 sbin]# jps

2420 JournalNode

2309 QuorumPeerMain

2461 Jps

[root@h5 sbin]# ^C

格式化HDFS

在h1上执行命令:

hdfs namenode -format

格式化后会在根据core-site.xml中的hadoop.tmp.dir配置生成个文件

拷贝tmp 到 h2

[root@h1 hadoop-2.7.2]# scp -r tmp/ h2:/home/hadoop-2.7.2/

4. 格式化ZK(在h1上执行即可)

[root@h1 hadoop-2.7.2]# hdfs zkfc -formatZK

5. 启动HDFS(在h1上执行)

[root@h1 hadoop-2.7.2]# sbin/start-dfs.sh

16/02/25 05:01:14 WARN hdfs.DFSUtil: Namenode for ns1 remains unresolved for ID null. Check your hdfs-site.xml file to ensure namenodes are configured properly.

16/02/25 05:01:14 WARN hdfs.DFSUtil: Namenode for ns2 remains unresolved for ID null. Check your hdfs-site.xml file to ensure namenodes are configured properly.

16/02/25 05:01:14 WARN hdfs.DFSUtil: Namenode for ns3 remains unresolved for ID null. Check your hdfs-site.xml file to ensure namenodes are configured properly.

Starting namenodes on [h1 h2 masters masters masters]

masters: ssh: Could not resolve hostname masters: Name or service not known

masters: ssh: Could not resolve hostname masters: Name or service not known

masters: ssh: Could not resolve hostname masters: Name or service not known

h2: starting namenode, logging to /home/hadoop-2.7.2/logs/hadoop-root-namenode-h2.out

h1: starting namenode, logging to /home/hadoop-2.7.2/logs/hadoop-root-namenode-h1.out

h5: starting datanode, logging to /home/hadoop-2.7.2/logs/hadoop-root-datanode-h5.out

h7: starting datanode, logging to /home/hadoop-2.7.2/logs/hadoop-root-datanode-h7.out

h6: starting datanode, logging to /home/hadoop-2.7.2/logs/hadoop-root-datanode-h6.out

Starting journal nodes [h5 h6 h7]

h5: journalnode running as process 2420. Stop it first.

h6: journalnode running as process 2885. Stop it first.

h7: journalnode running as process 2896. Stop it first.

Starting ZK Failover Controllers on NN hosts [h1 h2 masters masters masters]

masters: ssh: Could not resolve hostname masters: Name or service not known

masters: ssh: Could not resolve hostname masters: Name or service not known

masters: ssh: Could not resolve hostname masters: Name or service not known

h2: starting zkfc, logging to /home/hadoop-2.7.2/logs/hadoop-root-zkfc-h2.out

h1: starting zkfc, logging to /home/hadoop-2.7.2/logs/hadoop-root-zkfc-h1.out

[root@h1 hadoop-2.7.2]#

6. 启动YARN(是在h3上执行start-yarn.sh，把namenode和resourcemanager分开是因为性能问题，因为他们都要占用大量资源，所以把他们分开了，他们分开了就要分别在不同的机器上启动)

[root@h3 sbin]# ./start-yarn.sh

[root@h4 sbin]# ./yarn-daemons.sh start resourcemanager

验证：
http://192.168.128.11:50070
Overview 'h1:9000' (active)
http://192.168.128.12:50070
Overview 'h2:9000' (standby)

上传文件

[root@h4 bin]# hadoop fs -put /etc/profile /profile

[root@h4 bin]# hadoop fs -ls

ls: `.': No such file or directory

[root@h4 bin]# hadoop fs -ls /

Found 1 items

-rw-r--r-- 3 root supergroup 1814 2016-02-26 19:08 /profile

[root@h4 bin]#

杀死h1

[root@h1 sbin]# jps

2480 NameNode

2868 Jps

2775 DFSZKFailoverController

[root@h1 sbin]# kill -9 2480

[root@h1 sbin]# jps

2880 Jps

2775 DFSZKFailoverController

[root@h1 sbin]# hadoop fs -ls /

Found 1 items

-rw-r--r-- 3 root supergroup 1814 2016-02-26 19:08 /profile

此时 h2 变为active

手动启动 h1的 namenode

[root@h1 sbin]# ./hadoop-daemon.sh start namenode

starting namenode, logging to /home/hadoop-2.7.2/logs/hadoop-root-namenode-h1.out

[root@h1 sbin]# hadoop jar /home/hadoop-2.7.2/s

观察 h1 状态为standby

验证yarn

[root@h1 sbin]# hadoop jar /home/hadoop-2.7.2/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.2.jar wordcount /profile /out

16/02/26 19:14:23 INFO input.FileInputFormat: Total input paths to process : 1

16/02/26 19:14:23 INFO mapreduce.JobSubmitter: number of splits:1

16/02/26 19:14:23 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1456484773347_0001

16/02/26 19:14:24 INFO impl.YarnClientImpl: Submitted application application_1456484773347_0001

16/02/26 19:14:24 INFO mapreduce.Job: The url to track the job: http://h3:8088/proxy/application_1456484773347_0001/
16/02/26 19:14:24 INFO mapreduce.Job: Running job: job_1456484773347_0001

16/02/26 19:14:49 INFO mapreduce.Job: Job job_1456484773347_0001 running in uber mode : false

16/02/26 19:14:49 INFO mapreduce.Job: map 0% reduce 0%

16/02/26 19:15:05 INFO mapreduce.Job: map 100% reduce 0%

16/02/26 19:15:22 INFO mapreduce.Job: map 100% reduce 100%

16/02/26 19:15:23 INFO mapreduce.Job: Job job_1456484773347_0001 completed successfully

16/02/26 19:15:23 INFO mapreduce.Job: Counters: 49

File System Counters

FILE: Number of bytes read=2099

FILE: Number of bytes written=243781

FILE: Number of read operations=0

FILE: Number of large read operations=0

FILE: Number of write operations=0

HDFS: Number of bytes read=1901

HDFS: Number of bytes written=1470

HDFS: Number of read operations=6

HDFS: Number of large read operations=0

HDFS: Number of write operations=2

Job Counters

Launched map tasks=1

Launched reduce tasks=1

Data-local map tasks=1

Total time spent by all maps in occupied slots (ms)=13014

Total time spent by all reduces in occupied slots (ms)=13470

Total time spent by all map tasks (ms)=13014

Total time spent by all reduce tasks (ms)=13470

Total vcore-milliseconds taken by all map tasks=13014

Total vcore-milliseconds taken by all reduce tasks=13470

Total megabyte-milliseconds taken by all map tasks=13326336

Total megabyte-milliseconds taken by all reduce tasks=13793280

Map-Reduce Framework

Map input records=80

Map output records=256

Map output bytes=2588

Map output materialized bytes=2099

Input split bytes=87

Combine input records=256

Combine output records=156

Reduce input groups=156

Reduce shuffle bytes=2099

Reduce input records=156

Reduce output records=156

Spilled Records=312

Shuffled Maps =1

Failed Shuffles=0

Merged Map outputs=1

GC time elapsed (ms)=395

CPU time spent (ms)=4100

Physical memory (bytes) snapshot=298807296

Virtual memory (bytes) snapshot=4201771008

Total committed heap usage (bytes)=138964992

Shuffle Errors

BAD_ID=0

CONNECTION=0

IO_ERROR=0

WRONG_LENGTH=0

WRONG_MAP=0

WRONG_REDUCE=0

File Input Format Counters

Bytes Read=1814

File Output Format Counters

Bytes Written=1470

[root@h1 sbin]# hadoop fs -ls /

Found 3 items

drwxr-xr-x - root supergroup 0 2016-02-26 19:15 /out

-rw-r--r-- 3 root supergroup 1814 2016-02-26 19:08 /profile

drwx------ - root supergroup 0 2016-02-26 19:14 /tmp

[root@h1 sbin]#

Hadoop ha 集群搭建完成

安装hbase

hbase-env.sh：

export JAVA_HOME=/home/jdk

export HBASE_MANAGES_ZK=false

hbase-site.xml：

<configuration>

<property>

<name>hbase.rootdir</name>

<value>hdfs://h1:9000/hbase</value>

</property>

<property>

<name>hbase.cluster.distributed</name>

<value>true</value>

</property>

<property>

<name>hbase.master</name>

<value>h1:60000</value>

</property>

<property>

<name>hbase.master.port</name>

<value>60000</value>

<description>The port master should bind to.</description>

</property>

<property>

<name>hbase.zookeeper.quorum</name>

<value>h5,h6,h7</value>

</property>

<property>

<name>dfs.replication</name>

<value>3</value>

</property>

</configuration>

注意：$HBASE_HOME/conf/hbase-site.xml的hbase.rootdir的主机和端口号与$HADOOP_HOME/conf/core-site.xml的fs.default.name的主机和端口号一致

Regionservers：内容为:

h5

h6

h7

复制到h2 h5,h6,h7上面

整个启动顺序

按照上面启动hadoop ha 的顺序 先启动好

然后在h1，h2上启动hbase

./start-hbase.sh

测试进入 hbase

[root@h1 bin]# hbase shell

SLF4J: Class path contains multiple SLF4J bindings.

SLF4J: Found binding in [jar:file:/home/hbase-1.2.0/lib/slf4j-log4j12-1.7.5.jar!/org/slf4j/impl/StaticLoggerBinder.class]

SLF4J: Found binding in [jar:file:/home/hadoop-2.7.2/share/hadoop/common/lib/slf4j-log4j12-1.7.10.jar!/org/slf4j/impl/StaticLoggerBinder.class]

SLF4J: See http://www.slf4j.org/codes.html#multiple_bindings for an explanation.

SLF4J: Actual binding is of type [org.slf4j.impl.Log4jLoggerFactory]

HBase Shell; enter 'help<RETURN>' for list of supported commands.

Type "exit<RETURN>" to leave the HBase Shell

Version 1.2.0, r25b281972df2f5b15c426c8963cbf77dd853a5ad, Thu Feb 18 23:01:49 CST 2016

hbase(main):001:0> esit

NameError: undefined local variable or method `esit' for #<Object:0x7ad1caa2>

hbase(main):002:0> exit

至此全部结束。