一、概述
1.实验环境基于以前搭建的Haoop HA；
2.spark HA所需要的Zookeeper环境前文已经配置过，此处不再重复。
4.主机规划
| bd1 bd2 bd3 |
Worker |
| bd4 bd5 |
扫描二维码关注公众号，回复：
2007644 查看本文章
Master、Worker |
二、配置Scala
1.解压并拷贝
[root@bd1 ~]
# tar -zxf scala-2.12.3.tgz
[root@bd1 ~]
# cp -r scala-2.12.3 /usr/local/
2.配置环境变量
[root@bd1 ~]
# vim /etc/profile
export
SCALA_HOME=
/usr/local/scala
export
PATH=:$SCALA_HOME
/bin
:$PATH
[root@bd1 ~]
# source /etc/profile
3.验证
[root@bd1 ~]
# scala -version
Scala code runner version 2.12.3 -- Copyright 2002-2017, LAMP
/EPFL
and Lightbend, Inc.
三、配置Spark
1.解压并拷贝
[root@bd1 ~]
# tar -zxf spark-2.2.0-bin-hadoop2.7.tgz
[root@bd1 ~]
# cp spark-2.2.0-bin-hadoop2.7 /usr/local/spark
2.配置环境变量
[root@bd1 ~]
# vim /etc/profile
export
SCALA_HOME=
/usr/local/scala
export
PATH=:$SCALA_HOME
/bin
:$PATH
[root@bd1 ~]
# source /etc/profile
3.修改spark-env.sh #文件不存在需要拷贝模板
[root@bd1 conf]
# vim spark-env.sh
export
JAVA_HOME=
/usr/local/jdk
export
HADOOP_HOME=
/usr/local/hadoop
export
HADOOP_CONF_DIR=
/usr/local/hadoop/etc/hadoop
export
SCALA_HOME=
/usr/local/scala
export
SPARK_DAEMON_JAVA_OPTS=
"-Dspark.deploy.recoveryMode=ZOOKEEPER -Dspark.deploy.zookeeper.url=bd4:2181,bd5:2181 -Dspark.deploy.zookeeper.dir=/spark"
export
SPARK_WORKER_MEMORY=1g
export
SPARK_WORKER_CORES=2
export
SPARK_WORKER_INSTANCES=1
4.修改spark-defaults.conf #文件不存在需要拷贝模板
[root@bd1 conf]
# vim spark-defaults.conf
spark.master spark:
//master
:7077
spark.eventLog.enabled
true
spark.eventLog.
dir
hdfs:
//master
:
/user/spark/history
spark.serializer org.apache.spark.serializer.KryoSerializer
5.在HDFS文件系统中新建日志文件目录
hdfs dfs -
mkdir
-p
/user/spark/history
hdfs dfs -
chmod
777
/user/spark/history
6.修改slaves
[root@bd1 conf]
# vim slaves
bd1
bd2
bd3
bd4
bd5
四、同步到其他主机
1.使用scp同步Scala到bd2-bd5
scp
-r
/usr/local/scala
root@bd2:
/usr/local/
scp
-r
/usr/local/scala
root@bd3:
/usr/local/
scp
-r
/usr/local/scala
root@bd4:
/usr/local/
scp
-r
/usr/local/scala
root@bd5:
/usr/local/
2.同步Spark到bd2-bd5
scp
-r
/usr/local/spark
root@bd2:
/usr/local/
scp
-r
/usr/local/spark
root@bd3:
/usr/local/
scp
-r
/usr/local/spark
root@bd4:
/usr/local/
scp
-r
/usr/local/spark
root@bd5:
/usr/local/
五、启动集群并测试HA
1.启动顺序为：zookeeper-->hadoop-->spark
2.启动spark
bd4：
[root@bd4 sbin]
# cd /usr/local/spark/sbin/
[root@bd4 sbin]
# ./start-all.sh
starting org.apache.spark.deploy.master.Master, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.master.Master-1-bd4.out
bd4: starting org.apache.spark.deploy.worker.Worker, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.worker.Worker-1-bd4.out
bd2: starting org.apache.spark.deploy.worker.Worker, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.worker.Worker-1-bd2.out
bd3: starting org.apache.spark.deploy.worker.Worker, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.worker.Worker-1-bd3.out
bd5: starting org.apache.spark.deploy.worker.Worker, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.worker.Worker-1-bd5.out
bd1: starting org.apache.spark.deploy.worker.Worker, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.worker.Worker-1-bd1.out
[root@bd4 sbin]
# jps
3153 DataNode
7235 Jps
3046 JournalNode
7017 Master
3290 NodeManager
7116 Worker
2958 QuorumPeerMain
bd5：
[root@bd5 sbin]
# ./start-master.sh
starting org.apache.spark.deploy.master.Master, logging to
/usr/local/spark/logs/spark-root-org
.apache.spark.deploy.master.Master-1-bd5.out
[root@bd5 sbin]
# jps
3584 NodeManager
5602 RunJar
3251 QuorumPeerMain
8564 Master
3447 DataNode
8649 Jps
8474 Worker
3340 JournalNode
3.停掉bd4的Master进程
[root@bd4 sbin]
# kill -9 7017
[root@bd4 sbin]
# jps
3153 DataNode
7282 Jps
3046 JournalNode
3290 NodeManager
7116 Worker
2958 QuorumPeerMain
五、总结
一开始时想把Master放到bd1和bd2上，但是启动Spark后发现两个节点上都是Standby。然后修改配置文件转移到bd4和bd5上，才顺利运行。换言之Spark HA的Master必须位于Zookeeper集群上才能正常运行，即该节点上要有JournalNode这个进程。
更多Spark相关教程见以下内容：