安装

su - root
https://repo.anaconda.com/archive/
Anaconda3-2021.05-Linux-x86_64.sh
sh ./Anaconda3-2021.05-Linux-x86_64.sh
yes
enter
exit()
exit()
重新登录
su - root

配置成功

(base) [root@node1 ~]# python
Python 3.8.8 (default, Apr 13 2021, 19:58:26)
[GCC 7.3.0] :: Anaconda, Inc. on linux

.condarc

su - root
vim ~/.condarc

channels:
  - http://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
  - http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
  - http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
show_channel_urls: true

pyspark

(base) [root@node1 ~]# pyspark
-bash: pyspark: command not found
(base) [root@node1 ~]# # pyspark
(base) [root@node1 ~]# conda create -n pyspark python=3.9

conda activate pyspark
conda deactivate

conda安装

(base) [root@node1 ~]#  conda activate pyspark
(pyspark) [root@node1 ~]# 

Spark安装

tar -zxvf spark-3.2.0-bin-hadoop3.2.tgz -C /export/server/
ln -s /export/server/spark-3.2.0-bin-hadoop3.2 /export/server/spark

lrwxrwxrwx  1 hadoop hadoop        23 May 24 22:50 spark -> spark-3.4.0-bin-hadoop3

环境变量 /etc/profile

配置Spark由如下5个环境变量需要设置

• SPARK_HOME: 表示Spark安装路径在哪里
• PYSPARK_PYTHON: 表示Spark想运行Python程序, 那么去哪里找python执行器
• JAVA_HOME: 告知Spark Java在哪里
• HADOOP_CONF_DIR: 告知Spark Hadoop的配置文件在哪里
• HADOOP_HOME: 告知Spark Hadoop安装在哪里

vim /etc/profile


## export MAVEN_HOME=/export/server/maven
export HADOOP_HOME=/export/server/hadoop
export SPARK_HOME=/export/server/spark
export PYSPARK_PYTHON=/export/server/anaconda3/envs/pyspark/bin/python3.9
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export PATH=$PATH:/usr/local/python3/bin
export JAVA_HOME=/export/server/jdk
export PATH=$PATH:$JAVA_HOME/bin:$MAVEN_HOME/bin
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

~/.bashrc

(base) [root@node1 ~]# vim ~/.bashrc

export PYSPARK_PYTHON=/export/server/anaconda3/envs/pyspark/bin/python3.9
export JAVA_HOME=/export/server/jdk

spark

drwxr-xr-x 2 hadoop hadoop  4096 Apr  7 10:43 bin    可执行文件
drwxr-xr-x 2 hadoop hadoop  4096 Apr  7 10:43 conf  配置文件
drwxr-xr-x 5 hadoop hadoop  4096 Apr  7 10:43 data  数据
drwxr-xr-x 4 hadoop hadoop  4096 Apr  7 10:43 examples   实例
drwxr-xr-x 2 hadoop hadoop 16384 Apr  7 10:43 jars    spark依赖jar
drwxr-xr-x 4 hadoop hadoop  4096 Apr  7 10:43 kubernetes
-rw-r--r-- 1 hadoop hadoop 22982 Apr  7 10:43 LICENSE
drwxr-xr-x 2 hadoop hadoop  4096 Apr  7 10:43 licenses
-rw-r--r-- 1 hadoop hadoop 57842 Apr  7 10:43 NOTICE
drwxr-xr-x 9 hadoop hadoop  4096 Apr  7 10:43 python  spark的python支持库
drwxr-xr-x 3 hadoop hadoop  4096 Apr  7 10:43 R      spark的R语言支持库
-rw-r--r-- 1 hadoop hadoop  4605 Apr  7 10:43 README.md
-rw-r--r-- 1 hadoop hadoop   165 Apr  7 10:43 RELEASE
drwxr-xr-x 2 hadoop hadoop  4096 Apr  7 10:43 sbin     启动关闭
drwxr-xr-x 2 hadoop hadoop  4096 Apr  7 10:43 yarn     yarn的相关依赖项

进入pyspark解析器环境

cd park/bin
./pyspark
>>> sc.parallelize([1,2,3,4]).map(lambda x:x*10).collect()
[10, 20, 30, 40]

master = local[*]

• 多少个cpu模拟多少个进程
  可以查看一个任务的jvm的监控页面：4040
  
  local进程分配了一系列线程在执行pyspark任务

./spark-shell
scala>

例证spark-submit 举例计算10的圆周率
(pyspark) [root@node1 bin]# ./spark-submit --master local[*] /export/server/spark/examples/src/main/python/pi.py 10

Pi is roughly 3.135200

提交之后，4040端口就关闭了

# local模式运行的原理
以一个独立的进程配合内部的线程来完成spark运行时环境；local模式可以通过：spark-shell/pyspark/spark-submit等来开启

# bin/pyspark是什么程序
交互式的解释器环境可以运行python代码，进行spark计算
# spark的端口
spark的任务运行之后，会在Driver所在机器的绑定4040端口，提供当前任务的监控页面


# standalone架构
![在这里插入图片描述](https://img-blog.csdnimg.cn/31a6962be97e464ba685f8259562a719.png)

![在这里插入图片描述](https://img-blog.csdnimg.cn/402ac1703997439a92e984d2333bc843.png)

## 集群规划
课程中 使用三台Linux虚拟机来组成集群环境, 非别是:
node1\ node2\ node3
node1运行: Spark的Master进程  和 1个Worker进程
node2运行: spark的1个worker进程
node3运行: spark的1个worker进程
整个集群提供: 1个master进程 和 3个worker进程
```linux
配置node2\node3
[hadoop@node1 server]$ scp Anaconda3-2021.05-Linux-x86_64.sh node2:`pwd`/

cd /export/server
chown -R hadoop:hadoop spark*

chown -R hadoop:hadoop anaconda3*
su - hadoop
cd /export/server/spark
cd conf
ll
mv workers.template workers
vim workers
node1
node2
node3

mv spark-env.sh.template spark-env.sh
vim spark-env.sh

JAVA_HOME=/export/server/jdk

HADOOP_CONF_DIR=/export/server/hadoop/etc/hadoop
YARN_CONF_DIR=/export/server/hadoop/etc/hadoop

export SPARK_MASTER_HOST=node1
export SPARK_MASTER_PORT=7077
SPARK_MASTER_WEBUI_PORT=8080

SPARK_WORKER_CORES=1
SPARK_WORKER_MEMORY=1g
SPARK_WORKER_PORT=7078
SPARK_WORKER_WEBUI_PORT=8081

SPARK_HISTORY_OPTS="-Dspark.history.fs.logDirectory=hdfs://node1:8020/sparklog/ -Dspark.history.fs.cleaner.enabled=true"

hadoop fs -mkdir /sparklog
hadoop fs -chmod 777 /sparkog

mv spark-defaults.conf.template spark-defaults.conf
vim spark-defaults.conf

spark.eventLog.enabled			true
spark.eventLog.dir					hdfs://node1:8020/sparklog/
spark.eventLog.compress		true

配置相同的node2,node3

export JAVA_HOME=/export/server/jdk
export PATH=$PATH:$JAVA_HOME/bin
export HADOOP_HOME=/export/server/hadoop
export SPARK_HOME=/export/server/spark
export PYSPARK_PYTHON=/export/server/anaconda3/envs/pyspark/bin/python3.9
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop
export PATH=$PATH:$JAVA_HOME/bin
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

scp -r spark-3.4.0-bin-hadoop3 node2:`pwd`/
scp -r spark-3.4.0-bin-hadoop3 node3:`pwd`/

node2,node3

ln -s spark-3.4.0-bin-hadoop3 spark

启动历史服务

sbin/start-history-server.sh

启动spark的Master和Worker进程

sbin/start-all.sh

sbin/start-master.sh
sbin/start-worker.sh

sbin/stop-all.sh

jps
jobHistoryServer是yarn
historyserver 是spark

连接集群操作

spark/bin ./pyspark --master spark://node1:7077
》》》测试