大数据项目实战数仓4——常用脚本

0、xsync：分发脚本

#!/bin/bash
#1. 判断参数个数
if [ $# -lt 1 ]
then
    echo Not Enough Arguement!
    exit;
fi
#2. 遍历集群所有机器
for host in hadoop102 hadoop103 hadoop104
do
    echo ==================== $host ====================
    #3. 遍历所有目录，挨个发送
    for file in $@
    do
        #4. 判断文件是否存在
        if [ -e $file ]
            then
                #5. 获取父目录
                pdir=$(cd -P $(dirname $file); pwd)

                #6. 获取当前文件的名称
                fname=$(basename $file)
                ssh $host "mkdir -p $pdir"
                rsync -av $pdir/$fname $host:$pdir
            else
                echo $file does not exists!
        fi
    done
done

1、xcall.sh：查看相关进程

#! /bin/bash
 
for i in hadoop102 hadoop103 hadoop104
do
    echo --------- $i ----------
    ssh $i "$*"
done

2、hdp.sh：hadoop集群群起

#!/bin/bash
if [ $# -lt 1 ]
then
    echo "No Args Input..."
    exit ;
fi
case $1 in
"start")
        echo " =================== 启动 hadoop集群 ==================="

        echo " --------------- 启动 hdfs ---------------"
        ssh hadoop102 "/opt/module/hadoop-3.1.3/sbin/start-dfs.sh"
        echo " --------------- 启动 yarn ---------------"
        ssh hadoop103 "/opt/module/hadoop-3.1.3/sbin/start-yarn.sh"
        echo " --------------- 启动 historyserver ---------------"
        ssh hadoop102 "/opt/module/hadoop-3.1.3/bin/mapred --daemon start historyserver"
;;
"stop")
        echo " =================== 关闭 hadoop集群 ==================="

        echo " --------------- 关闭 historyserver ---------------"
        ssh hadoop102 "/opt/module/hadoop-3.1.3/bin/mapred --daemon stop historyserver"
        echo " --------------- 关闭 yarn ---------------"
        ssh hadoop103 "/opt/module/hadoop-3.1.3/sbin/stop-yarn.sh"
        echo " --------------- 关闭 hdfs ---------------"
        ssh hadoop102 "/opt/module/hadoop-3.1.3/sbin/stop-dfs.sh"
;;
*)
    echo "Input Args Error..."
;;
esac

3、zk.sh：zookeeper集群群起

#!/bin/bash
case $1 in
"start"){
	for i in hadoop102 hadoop103 hadoop104
	do
        echo ---------- zookeeper $i 启动 ------------
		ssh $i "/opt/module/zookeeper-3.5.7/bin/zkServer.sh start"
	done
};;
"stop"){
	for i in hadoop102 hadoop103 hadoop104
	do
        echo ---------- zookeeper $i 停止 ------------    
		ssh $i "/opt/module/zookeeper-3.5.7/bin/zkServer.sh stop"
	done
};;
"status"){
	for i in hadoop102 hadoop103 hadoop104
	do
        echo ---------- zookeeper $i 状态 ------------    
		ssh $i "/opt/module/zookeeper-3.5.7/bin/zkServer.sh status"
	done
};;
esac

4、kf.sh：kafka集群群起

#! /bin/bash

case $1 in
"start"){
    for i in hadoop102 hadoop103 hadoop104
    do
        echo " --------启动 $i Kafka-------"
        ssh $i "/opt/module/kafka/bin/kafka-server-start.sh -daemon /opt/module/kafka/config/server.properties"
    done
};;
"stop"){
    for i in hadoop102 hadoop103 hadoop104
    do
        echo " --------停止 $i Kafka-------"
        ssh $i "/opt/module/kafka/bin/kafka-server-stop.sh stop"
    done
};;
esac

5、file-flume-kafka.conf：文件通过flume输送到kafka配置

#为各组件命名
a1.sources = r1
a1.channels = c1

#描述source
a1.sources.r1.type = TAILDIR
a1.sources.r1.filegroups = f1
a1.sources.r1.filegroups.f1 = /opt/module/applog/log/app.*
a1.sources.r1.positionFile = /opt/module/flume/taildir_position.json
a1.sources.r1.interceptors =  i1
a1.sources.r1.interceptors.i1.type = com.yingzi.flume.interceptor.ETLInterceptor$Builder

#描述channel
a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
a1.channels.c1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092
a1.channels.c1.kafka.topic = topic_log
a1.channels.c1.parseAsFlumeEvent = false

#绑定source和channel以及sink和channel的关系
a1.sources.r1.channels = c1

6、f1.sh：日志采集Flume启动

#! /bin/bash
case $1 in
"start"){
        for i in hadoop102 hadoop103
        do
                echo " --------启动 $i 采集flume-------"
                ssh $i "nohup /opt/module/flume/bin/flume-ng agent --conf-file /opt/module/flume/conf/file-flume-kafka.conf --name a1 -Dflume.root.logger=INFO,LOGFILE >/opt/module/flume/log1.txt 2>&1  &"
        done
};;	
"stop"){
        for i in hadoop102 hadoop103
        do
                echo " --------停止 $i 采集flume-------"
                ssh $i "ps -ef | grep file-flume-kafka | grep -v grep |awk  '{print \$2}' | xargs -n1 kill -9 "
        done

};;
esac

7、kafka-flume-hdfs.conf：消费者Fllume配置

## 组件
a1.sources=r1
a1.channels=c1
a1.sinks=k1

## source1
a1.sources.r1.type = org.apache.flume.source.kafka.KafkaSource
a1.sources.r1.batchSize = 5000
a1.sources.r1.batchDurationMillis = 2000
a1.sources.r1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sources.r1.kafka.topics=topic_log
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = com.yingzi.flume.interceptor.TimeStampInterceptor$Builder

## channel1
a1.channels.c1.type = file
a1.channels.c1.checkpointDir = /opt/module/flume/checkpoint/behavior1
a1.channels.c1.dataDirs = /opt/module/flume/data/behavior1/


## sink1
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /origin_data/gmall/log/topic_log/%Y-%m-%d
a1.sinks.k1.hdfs.filePrefix = log-
a1.sinks.k1.hdfs.round = false

#控制生成的小文件
a1.sinks.k1.hdfs.rollInterval = 10
a1.sinks.k1.hdfs.rollSize = 134217728
a1.sinks.k1.hdfs.rollCount = 0

## 控制输出文件是原生文件。
a1.sinks.k1.hdfs.fileType = CompressedStream
a1.sinks.k1.hdfs.codeC = lzop

## 拼装
a1.sources.r1.channels = c1
a1.sinks.k1.channel= c1

8、f2.sh：消费者Flume

## 组件
a1.sources=r1
a1.channels=c1
a1.sinks=k1

## source1
a1.sources.r1.type = org.apache.flume.source.kafka.KafkaSource
a1.sources.r1.batchSize = 5000
a1.sources.r1.batchDurationMillis = 2000
a1.sources.r1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
a1.sources.r1.kafka.topics=topic_log
a1.sources.r1.interceptors = i1
a1.sources.r1.interceptors.i1.type = com.atguigu.flume.interceptor.TimeStampInterceptor$Builder

## channel1
a1.channels.c1.type = file
a1.channels.c1.checkpointDir = /opt/module/flume/checkpoint/behavior1
a1.channels.c1.dataDirs = /opt/module/flume/data/behavior1/


## sink1
a1.sinks.k1.type = hdfs
a1.sinks.k1.hdfs.path = /origin_data/gmall/log/topic_log/%Y-%m-%d
a1.sinks.k1.hdfs.filePrefix = log-
a1.sinks.k1.hdfs.round = false

#控制生成的小文件
a1.sinks.k1.hdfs.rollInterval = 10
a1.sinks.k1.hdfs.rollSize = 134217728
a1.sinks.k1.hdfs.rollCount = 0

## 控制输出文件是原生文件。
a1.sinks.k1.hdfs.fileType = CompressedStream
a1.sinks.k1.hdfs.codeC = lzop

## 拼装
a1.sources.r1.channels = c1
a1.sinks.k1.channel= c1

cluster.sh：采集通道

#!/bin/bash

case $1 in
"start"){
        echo ================== 启动 集群 ==================

        #启动 Zookeeper集群
        zk.sh start

        #启动 Hadoop集群
        hdp.sh start

        #启动 Kafka采集集群
        kf.sh start

        #启动 Flume采集集群
        f1.sh start

        #启动 Flume消费集群
        f2.sh start

        };;
"stop"){
        echo ================== 停止 集群 ==================

        #停止 Flume消费集群
        f2.sh stop

        #停止 Flume采集集群
        f1.sh stop

        #停止 Kafka采集集群
        kf.sh stop

        #停止 Hadoop集群
        hdp.sh stop

        #停止 Zookeeper集群
        zk.sh stop

};;
esac