Oozie使用详解

一、oozie4.3.0调用shell

1. 编写workflow.xml

<!--Workflow-DEF-NAME-->
<workflow-app xmlns='uri:oozie:workflow:0.3' name='shell-wf'>
	<!--shell1: node-name -->
    <start to='shell1' />
    <action name='shell1'>
        <shell xmlns="uri:oozie:shell-action:0.1">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <configuration>
                <property>
                  <name>mapred.job.queue.name</name>
                  <value>${queueName}</value>
                </property>
            </configuration>
            <!--${EXEC}是shell脚本命令，例如；mkdir-->
            <exec>${EXEC}</exec>
            <!--argument标签中是exec中的参数值-->
            <argument>A</argument>
            <argument>B</argument>
            <!--file标签里面放的hdfs上写好的shell脚本，例如：test.sh -->
            <file>${EXEC}#${EXEC}</file> <!--Copy the executable to compute node's current working directory -->
        </shell>
        <!--end和fail都是node-name -->
        <ok to="end" />
        <error to="fail" />
    </action>
    <!--fork与join成对使用的举例start-->
    <fork name="[FORK-NODE-NAME]">
        <path start="[NODE-NAME]" />
        ...
        <path start="[NODE-NAME]" />
    </fork>
    <join name="[JOIN-NODE-NAME]" to="[NODE-NAME]" />
    <!--fork与join成对使用的举例end-->
    <kill name="fail">
        <message>Script failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <end name='end' />
</workflow-app>

2. 编写job.properties

# 这里写的是workflow.xml和job.properties在hdfs的哪个目录下
oozie.wf.application.path=hdfs://localhost:8020/user/kamrul/workflows/script#Execute is expected to be in the Workflow directory.
#Shell Script to run
EXEC=script.sh
#CPP executable. Executable should be binary compatible to the compute node OS.
#EXEC=hello
#Perl script
#EXEC=script.pl

#jobTracker实际上就是resourceManager的地址
jobTracker=localhost:8021
nameNode=hdfs://localhost:8020
queueName=default

3. 提交job

# 注意这个job.properties是本地的
bin/oozie job -oozie http://hadoop102:11000/oozie -config oozie-apps/shell/job.properties -run