基于Ansible搭建Hadoop HA

目录

基础步骤

hadoop-conf主要配置文件

core-site.xml 

mapred-site.xml

hdfs-site.xml

yarn-site.xml

hadoop-env.sh

fair-scheduler.xml 

slaves

启动Hadoop HA

查看Hadoop HA 状态

小问题

---

Hadoop HA

Hadoop HA模式参照官网文档应该可以说是各组件的HA,比如HDFS HA, YARN HA 。
其中HDFS HA 又有QJM与NFS方式：
QJM方式采用JournalNode来共享edits文件，而NFS方式则采用NFS远程共享目录来共享edits文件。

NFS的方式的HA的配置与启动，和QJM方式基本上是一样，不同的地方是active namenode和standby namenode共享edits文件的方式。

官网学习地址：http://hadoop.apache.org/docs/r2.7.7/ 
接下来部署HDFS HA(QJM) & Yarn HA

基础步骤

# 将hadoop包分发到需要安装的bdp组下各个节点的/home/hadoop/app/
ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7.tar.gz  dest=/home/hadoop/app owner=hadoop group=hadoop'

# 解压hadoop-2.7.7.tar.gz至指定目录/app/gisbdp/目录下
ansible bdp  -m shell -a 'tar -xzvf /home/hadoop/app/hadoop-2.7.7.tar.gz  -C /app/gisbdp/'

# 创建软链接
ansible bdp -m shell -a 'ln -s /app/gisbdp/hadoop-2.7.7  /app/gisbdp/hadoop'

# 在# ~/.bashrc 中新增hadoop属性
#set hadoop environment
export HADOOP_HOME=/app/gisbdp/hadoop
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native 
export HADOOP_OPTS="-Djava.library.path=$HADOOP_HOME/lib"
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$HADOOP_HOME/lib

# 更新.bashrc
ansible bdp  -m copy -a 'src=/home/hadoop/.bashrc  dest=/home/hadoop/.bashrc'

# 同样为了方便Ansible分发，将/app/gisbdp/hadoop/etc/hadoop/* config配置文件复制一份到/home/hadoop/app/hadoop-2.7.7/etc/hadoop/目录下
# node1 节点 
[hadoop@node1 etc]$ cp -R  /app/gisbdp/hadoop/etc/hadoop  /home/hadoop/app/hadoop-2.7.7/etc/

# 创建目录 
ansible bdp -m file -a 'path=/data state=directory owner=hadoop group=hadoop mode=755 force=yes'

hadoop-conf主要配置文件

# 修改hadoop-conf内容，主要修改$HADOOP_CONF_DIR目录下的以下文件：
yarn-site.xml  mapred-site.xml  hdfs-site.xml  core-site.xml  fair-scheduler.xml  slaves 

# 更新hadoop-conf  
ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/yarn-site.xml  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/mapred-site.xml  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/hdfs-site.xml  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/core-site.xml  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/fair-scheduler.xml  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/slaves  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/hosts.include  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/hosts.exclude  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/rmhosts.include  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/rmhosts.exclude  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

ansible bdp  -m copy -a 'src=/home/hadoop/app/hadoop-2.7.7/etc/hadoop/hadoop-env.sh  dest=/app/gisbdp/hadoop/etc/hadoop owner=hadoop group=hadoop'

core-site.xml 

<configuration>
<!-- 指定hdfs的nameservice为gisbdp -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://gisbdp</value>
</property>

<property>
<name>hadoop.tmp.dir</name>
<value>/data/hdfs/tmp</value>
</property>

<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>node3:2181,node4:2181,node5:2181</value>
</property>

<property>
<name>fs.trash.interval</name>
<value>2880</value>
</property>

<property>
<name>net.topology.script.file.name</name>
<value>/app/hadoop-conf/rack.sh</value>
</property>

<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>

<property>
<name>io.compression.codecs</name>
<value>
org.apache.hadoop.io.compress.SnappyCodec,org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec,org.apache.hadoop.io.compress.Lz4Codec
</value>
</property>

<property>
<name>hadoop.proxyuser.hadoop.hosts</name>
<value>*</value>
</property>

<property>
<name>hadoop.proxyuser.hadoop.groups</name>
<value>*</value>
</property>

<property>
<name>hadoop.proxyuser.hdfs.hosts</name>
<value>*</value>
</property>

<property>
<name>hadoop.proxyuser.hdfs.groups</name>
<value>*</value>
</property>

<property>
<name>hadoop.proxyuser.hive.hosts</name>
<value>*</value>
</property>

<property>
<name>hadoop.proxyuser.hive.groups</name>
<value>*</value>
</property>
</configuration>

mapred-site.xml

<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>

<property>
<name>mapreduce.jobhistory.address</name>
<value>node1:10020</value>
</property>

<property>
<name>mapreduce.jobhistory.admin.address</name>
<value>node1:10033</value>
</property>

<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>node1:19888</value>
</property>