spark-2.4.0-hadoop2.7-安装部署 4.1. Spark安装4.2. 环境变量修改4.3. 配置修改4.4. 分发到其他机器4.5. 启动spark

   该Spark集群安装，但是有一个很大的问题，那就是Master节点存在单点故障，要解决此问题，就要借助zookeeper，并且启动至少两个Master节点来实现高可靠。具体部署下节讲解。

 1 [yun@mini01 software]$ pwd
 2 /app/software
 3 [yun@mini01 software]$ ll
 4 total 238572
 5 -rw-r--r--  1 yun yun 227893062 Nov 19 21:24 spark-2.4.0-bin-hadoop2.7.tgz
 6 [yun@mini01 software]$ tar xf spark-2.4.0-bin-hadoop2.7.tgz  
 7 [yun@mini01 software]$ mv spark-2.4.0-bin-hadoop2.7 /app/  
 8 [yun@mini01 software]$ cd /app/
 9 [yun@mini01 ~]$ ln -s spark-2.4.0-bin-hadoop2.7/ spark  
10 [yun@mini01 ~]$ ll -d spark-*   
11 drwxr-xr-x 13 yun yun 211 Oct 29 14:36 spark-2.4.0-bin-hadoop2.7
12 lrwxrwxrwx  1 yun yun  26 Nov 24 14:23 spark -> spark-2.4.0-bin-hadoop2.7/

1 # 需要root权限去添加环境变量
2 [root@mini01 ~]# tail /etc/profile
3 ………………
4 # spark环境变量
5 export SPARK_HOME="/app/spark"
6 export PATH=$SPARK_HOME/bin:$SPARK_HOME/sbin:$PATH
7 
8 [root@mini01 ~]# logout
9 [yun@mini01 conf]$ source /etc/profile  # 重新加载该环境变量

 1 [yun@mini01 conf]$ pwd
 2 /app/spark/conf
 3 [yun@mini01 conf]$ cp -a spark-env.sh.template spark-env.sh  
 4 [yun@mini01 conf]$ tail spark-env.sh  # 修改环境变量配置
 5 # Options for native BLAS, like Intel MKL, OpenBLAS, and so on.
 6 # You might get better performance to enable these options if using native BLAS (see SPARK-21305).
 7 # - MKL_NUM_THREADS=1        Disable multi-threading of Intel MKL
 8 # - OPENBLAS_NUM_THREADS=1   Disable multi-threading of OpenBLAS
 9 
10 # 添加配置如下
11 # 配置JAVA_HOME
12 export JAVA_HOME=/app/jdk
13 # 设置Master的主机名
14 export SPARK_MASTER_IP=mini01
15 # 每一个Worker最多可以使用的内存，我的虚拟机就2g
16 # 真实服务器如果有128G，你可以设置为100G
17 # 所以这里设置为1024m或1g
18 export SPARK_WORKER_MEMORY=1024m
19 # 每一个Worker最多可以使用的cpu core的个数，我虚拟机就一个...
20 # 真实服务器如果有32个，你可以设置为32个
21 export SPARK_WORKER_CORES=1
22 # 提交Application的端口，默认就是这个，万一要改呢，改这里
23 export SPARK_MASTER_PORT=7077
24 
25 [yun@mini01 conf]$ pwd
26 /app/spark/conf
27 [yun@mini01 conf]$ cp -a slaves.template slaves 
28 [yun@mini01 conf]$ tail slaves  # 修改slaves 配置
29 # distributed under the License is distributed on an "AS IS" BASIS,
30 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
31 # See the License for the specific language governing permissions and
32 # limitations under the License.
33 #
34 
35 # A Spark Worker will be started on each of the machines listed below.
36 mini03
37 mini04
38 mini05

1 [yun@mini01 ~]$ scp -pr spark-2.4.0-bin-hadoop2.7/ yun@mini03:/app  # 拷贝到mini03
2 [yun@mini01 ~]$ scp -pr spark-2.4.0-bin-hadoop2.7/ yun@mini04:/app  # 拷贝到mini04
3 [yun@mini01 ~]$ scp -pr spark-2.4.0-bin-hadoop2.7/ yun@mini05:/app  # 拷贝到mini05

1 [yun@mini04 ~]$ pwd
2 /app
3 [yun@mini04 ~]$ ll -d spark-2.4.0-bin-hadoop2.7
4 drwxr-xr-x 13 yun yun 211 Oct 29 14:36 spark-2.4.0-bin-hadoop2.7
5 [yun@mini04 ~]$ ln -s spark-2.4.0-bin-hadoop2.7/ spark  
6 [yun@mini04 ~]$ ll -d spark-*
7 drwxr-xr-x 13 yun yun 211 Oct 29 14:36 spark-2.4.0-bin-hadoop2.7
8 lrwxrwxrwx  1 yun yun  26 Nov 24 23:39 spark -> spark-2.4.0-bin-hadoop2.7/

 1 [yun@mini01 sbin]$ pwd
 2 /app/spark/sbin
 3 [yun@mini01 sbin]$ ./start-all.sh  # 关闭使用 stop-all.sh 脚本
 4 starting org.apache.spark.deploy.master.Master, logging to /app/spark/logs/spark-yun-org.apache.spark.deploy.master.Master-1-mini01.out
 5 mini03: starting org.apache.spark.deploy.worker.Worker, logging to /app/spark/logs/spark-yun-org.apache.spark.deploy.worker.Worker-1-mini03.out
 6 mini05: starting org.apache.spark.deploy.worker.Worker, logging to /app/spark/logs/spark-yun-org.apache.spark.deploy.worker.Worker-1-mini05.out
 7 mini04: starting org.apache.spark.deploy.worker.Worker, logging to /app/spark/logs/spark-yun-org.apache.spark.deploy.worker.Worker-1-mini04.out
 8 [yun@mini01 ~]$ 
 9 [yun@mini01 ~]$ jps  # 查看进程状态 
10 3103 Master
11 3183 Jps

1 [yun@mini03 ~]$ jps
2 2387 Worker
3 2437 Jps

1 [yun@mini04 ~]$ jps 
2 2183 Jps
3 2125 Worker

1 [yun@mini05 ~]$ jps 
2 2212 Worker
3 2261 Jps

1 http://mini01:8080/