oozie定时调度的配置说明第二篇

这一讲相对上一讲会稍微难点

job.properties 文件 和 coordinato.xml 上一讲已经讲过，本次就不再做过多的赘述了

job.properties

# 集群参数
nameNode=hdfs://master:8020
jobTracker=master:8032
queueName=default

# oozie.coord.application.path=${nameNode}/work/coordinator.xml
# start=2016-12-06T16:00Z
# end=2019-07-30T16:00Z
workflowAppUri=${nameNode}/work/workflow1.xml
# workflow文件在hdfs上的目录
oozie.wf.application.path=${workflowAppUri}
# jar包的路径
jarsDir=/home/work/jars_test
hiveSQLDir=/home/work/HiveSql
# jar包所在机器的host
sshHost=master
sshUser=root
# workflow的名称
workflowName=workflow
# subworkflow
workflow2=workflow2.xml
workflow3=workflow3.xml
# impala
impalaIP=192.168.247.3

coordinator.xml

<coordinator-app name="bdmp_parallel_10_coordinator" frequency="${coord:hours(24)}" start="${start}" end="${end}" timezone="UTC" xmlns="uri:oozie:coordinator:0.2">
  <action>
    <workflow>
      <app-path>${workflowAppUri}</app-path>
      <configuration>
        <property>
          <name>jobTracker</name>
          <value>${jobTracker}</value>
        </property>
        <property>
          <name>nameNode</name>
          <value>${nameNode}</value>
        </property>
        <property>
          <name>queueName</name>
          <value>${queueName}</value>
        </property>
      </configuration>
    </workflow>
  </action>
</coordinator-app>

workflow1.xml

<workflow-app xmlns="uri:oozie:workflow:0.2" name="${workflowName}">
    <start to="work1"/>
    <action name="work1">--执行开始的action
        <ssh xmlns="uri:oozie:ssh-action:0.1">
            <host>${sshUser}@${sshHost}</host>
       <command>hadoop jar</command>
            <args>${jarsDir}/work1.jar</args> 
        </ssh>
        <ok to="work2"/>--work1执行成功以后执行work2
        <error to="fail"/>
    </action>
<action name="work2">
        <ssh xmlns="uri:oozie:ssh-action:0.1">
            <host>${sshUser}@${sshHost}</host>
      <command>hadoop jar</command>
            <args>${jarsDir}/work2.jar</args>
            <args>:oozie:ssh:W=${workflowName}:A=work2:ID=${wf:id()}</args>
        </ssh>
        <ok to="fork_00"/>work2执行成功以后执行fork_00
        <error to="fail"/>
    </action>

   <fork name="fork_00"> --fork标签的意思是并行的执行里面的任务
        <path start="work3"/>
        <path start="work4"/>
    </fork>

<action name="work3">
        <ssh xmlns="uri:oozie:ssh-action:0.1">
            <host>${sshUser}@${sshHost}</host>
            <command>hadoop jar</command>
            <args>${jarsDir}/work3.jar</args>
            <args>:oozie:ssh:W=${workflowName}:A=work3:ID=${wf:id()}</args>
        </ssh>
        <ok to="join_00"/>
        <error to="fail"/>
    </action>
<action name="work4">
        <ssh xmlns="uri:oozie:ssh-action:0.1">
            <host>${sshUser}@${sshHost}</host>
            <command>hadoop jar</command>
            <args>${jarsDir}/work4.jar</args>
            <args>:oozie:ssh:W=${workflowName}:A=work4:ID=${wf:id()}</args>
        </ssh>
        <ok to="join_00"/>
        <error to="fail"/>
    </action>

<join name="join_00" to="work5"/>--join的意思是 只有在 work3 和work4 也就是fork的程序都执行成功以后再执行以下内容

<action name="work5">
        <ssh xmlns="uri:oozie:ssh-action:0.1">
            <host>${sshUser}@${sshHost}</host>
            <command>hadoop jar</command>
            <args>${jarsDir}/work5.jar</args>
            <args>:oozie:ssh:W=${workflowName}:A=work5:ID=${wf:id()}</args>
        </ssh>
        <ok to="subworkflow_part2"/>
        <error to="fail"/>
    </action>

<action name="workflow2">---可以执行另外一个workflow
<sub-workflow>
<app-path>${nameNode}/user/${workflow2}</app-path>
<configuration>
<property>
 <name>nameNode</name>
 <value>${nameNode}</value>
</property>
<property>
 <name>jobTracker</name>
 <value>${jobTracker}</value>
</property>
<property>
 <name>queueName</name>
 <value>${queueName}</value>
</property>
<property>
 <name>jarsDir</name>
 <value>${jarsDir}</value>
</property>
<property>
 <name>hiveSQLDir</name>
 <value>${hiveSQLDir}</value>
</property>
<property>
 <name>sshHost</name>
 <value>${sshHost}</value>
</property>
<property>
 <name>sshUser</name>
 <value>${sshUser}</value>
</property>
<property>
 <name>workflowName</name>
 <value>${workflowName}_subworkflow_part2</value>
</property>
<property>
 <name>subworkflow_part2_xml</name>
 <value>${subworkflow_part2_xml}</value>
</property>
<property>
 <name>subworkflow_part3_xml</name>
 <value>${subworkflow_part3_xml}</value>
</property>
<property>
 <name>impalaIP</name>
 <value>${impalaIP}</value>
</property>
</configuration>
</sub-workflow>
<ok to="end"/>
<error to="fail"/>
</action>

    <kill name="fail">
        <message>Java failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <end name="end"/>
</workflow-app>