HA分布式集群配置三 spark集群配置

（一）HA下配置spark

1，spark版本型号：spark-2.1.0-bin-hadoop2.7

2，解压，修改配置环境变量

tar -zxvf spark-2.1.0-bin-hadoop2.7.tgz
mv spark-2.1.0-bin-hadoop2.7 /usr/spark-2.1.0

vim /etc/profile
export JAVA_HOME=/usr/java
export SCALA_HOME=/usr/scala
export HADOOP_HOME=/usr/hadoop-2.7.3
export ZK_HOME=/usr/zookeeper-3.4.8
export MYSQL_HOME=/usr/local/mysql
export HIVE_HOME=/usr/hive-2.1.1
export SPARK_HOME=/usr/spark-2.1.0
export PATH=$SPARK_HOME/bin:$HIVE_HOME/bin:$MYSQL_HOME/bin:$ZK_HOME/bin:$JAVA_HOME/bin:$SCALA_HOME/bin:$HADOOP_HOME/bin:$PATH 
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar 

3，修改spark-env.sh文件

cd $SPARK_HOME/conf 
vim spark-env.sh
#添加
export JAVA_HOME=/usr/java
export SCALA_HOME=/usr/scala
export SPARK_DAEMON_JAVA_OPTS="-Dspark.deploy.recoveryMode=ZOOKEEPER -Dspark.deploy.zookeeper.url=ha1:2181,ha2:2181,ha3:2181 -Dspark.deploy.zookeeper.dir=/spark"  
export HADOOP_CONF_DIR=/usr/hadoop-2.7.3/conf/etc/hadoop
export SPARK_MASTER_PORT=7077
export SPARK_EXECUTOR_INSTANCES=1
export SPARK_WORKER_INSTANCES=1
export SPARK_WORKER_CORES=1
export SPARK_WORKER_MEMORY=1024M
export SPARK_MASTER_WEBUI_PORT=8080
export SPARK_CONF_DIR=/usr/spark-2.1.0/conf

4，修改slaves文件

vim slaves
#添加
ha2
ha3
ha4

5，分发及启动

cd /usr
scp -r spark-2.1.0 root@ha4:/usr
scp -r spark-2.1.0 root@ha3:/usr
scp -r spark-2.1.0 root@ha2:/usr
scp -r spark-2.1.0 root@ha1:/usr
#在ha1上
./$SPARK_HOME/sbin/start-all.sh
#ha2,ha3上
./$SPARK_HOME/sbin/start-master.sh

各个节点jps情况：

[root@ha1 spark-2.1.0]# jps
2464 NameNode
2880 ResourceManager
2771 DFSZKFailoverController
3699 Jps
2309 QuorumPeerMain
3622 Master
[root@ha2 zookeeper-3.4.8]# jps
2706 NodeManager
3236 Jps
2485 JournalNode
3189 Worker
2375 DataNode
2586 DFSZKFailoverController
2236 QuorumPeerMain
2303 NameNode
3622 Master
[root@ha3 zookeeper-3.4.8]# jps
2258 DataNode
2466 NodeManager
2197 QuorumPeerMain
2920 Jps
2873 Worker
2331 JournalNode
3622 Master
[root@ha4 ~]# jps
2896 Jps
2849 Worker
2307 JournalNode
2443 NodeManager
2237 DataNode

6，关机，快照 sparkok

#启动集群顺序
#ha1,ha2,ha3
cd $ZK_HOME
./bin/zkServer.sh start
#ha1
cd $HADOOP_HOME
./sbin/start-all.sh
cd $SPARK_HOME
./sbin/start-all.sh
#ha2,ha3
./sbin/start-master.sh