zoukankan html css js c++ java

oozie捕获标准输出&异常capture-output

对于普通的java-action或者shell-action 都是支持的只要标准输出是"k1=v1"这中格式的就行：

现用test.py进行测试：

 1 ##test.py
 2 #! /opt/anaconda3/bin/python
 3 
 4 import re
 5 import os
 6 import sys
 7 import traceback
 8 
 9 if __name__ == '__main__':
10     try:
11         print("k1=v1")
12         
13         print(aaa) ##这里是个故意设置的错误
14     except Exception as e:
15    
16         print(traceback.format_exc())
17         exit(0)  ##这个地方要特别注意，当异常退出时capture-output将会失效，所以要想获取异常信息，一定要正常退出，然后在decison节点处理错误退出

#workflow.xml
<workflow-app xmlns="uri:oozie:workflow:0.4" name="adaf4df46a6597914b9ff6cd80eff542c6a">
    <start to="python-node"/>
    <action name="python-node">
        <shell xmlns="uri:oozie:shell-action:0.2">
            <job-tracker>108412.server.bigdata.com.cn:8032</job-tracker>
            <name-node>hdfs://108474.server.bigdata.com.cn:8020</name-node>
            <configuration>
                <property>
                    <name>oozie.launcher.mapred.job.queue.name</name>
                    <value>ada.oozielauncher</value>
                </property>
            </configuration>
            <exec>model.py</exec>
            <file>model.py</file>
            <capture-output/>
        </shell>
        <ok to="python-node1"/>
        <error to="fail"/>
    </action>
    <action name="python-node1">
        <shell xmlns="uri:oozie:shell-action:0.2">
            <job-tracker>108412.server.bigdata.com.cn:8032</job-tracker>
            <name-node>hdfs://108474.server.bigdata.com.cn:8020</name-node>
            <configuration>
                <property>
                    <name>oozie.launcher.mapred.job.queue.name</name>
                    <value>ada.oozielauncher</value>
                </property>
            </configuration>
            <exec>echo</exec>
            <argument>k1=${wf:actionData("python-node")["k1"]}</argument>
            <capture-output/>
        </shell>
        <ok to="check-output"/>
        <error to="fail"/>
    </action>
    <decision name="check-output">
        <switch>
            <case to="end">
                ${wf:actionData('python-node1')['k1'] eq 'Hello Oozie'}
            </case>
            <default to="fail"/>
        </switch>
    </decision>
    <kill name="fail">
        <message>Python action failed, error message[${wf:actionData('python-node')['k1']}]</message>
        <!--message>Python action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message-->
    </kill>
    <end name="end"/>
</workflow-app>

 1 #job.properties
 2 oozie.use.system.libpath=True
 3 security_enabled=False
 4 dryrun=False
 5 jobTracker=108412.server.bigdata.com.cn:8032
 6 nameNode=hdfs://108474.server.bigdata.com.cn:8020
 7 user.name=root
 8 queueName=test
 9 
10 #sharelib配置不能配置hive,会报错
11 #oozie.action.sharelib.for.spark=spark,hive  spark-action
12 #oozie.action.sharelib.for.sqoop=sqoop,hbase
13 oozie.wf.application.path=${nameNode}/user/lyy/oozie/test

将以上test.py和workflow.xml放到hdfs的/user/lyy/oozie/test目录下，使用一下命令提交：

oozie job -oozie http://10.8.4.46:11000/oozie -config job.properties -run

另外如果代码中有标准输出，但是格式不是"k=v"类型的，则用el函数wf:actionData无法获取，然而capture-output依旧把标准输出的信息捕获了，存储在oozie元数据表oozie.WF_ACTIONS中data字段存放，这个字段是mediumblob类型不能直接查看，可以通过下面restfulAPI获取json格式的数据，如下：

http://108446.server.bigdata.com.cn:11000/oozie/v1/job/0000106-181129152008300-oozie-oozi-W

{
    "appPath":"hdfs://108474.server.bigdata.com.cn:8020/user/lyy/oozie/3a0c7d3a2ed5468087d93c69db651f3f",
    "acl":null,
    "status":"KILLED",
    "createdTime":"Mon, 10 Dec 2018 03:50:13 GMT",
    "conf":"<configuration>
<property>
<name>user.name</name>
<value>root</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>True</value>
</property>
<property>
<name>mapreduce.job.user.name</name>
<value>root</value>
</property>
<property>
<name>security_enabled</name>
<value>False</value>
</property>
<property>
<name>queueName</name>
<value>ada.spark</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://108474.server.bigdata.com.cn:8020</value>
</property>
<property>
<name>dryrun</name>
<value>False</value>
</property>
<property>
<name>jobTracker</name>
<value>108412.server.bigdata.com.cn:8032</value>
</property>
<property>
<name>oozie.wf.application.path</name>
<value>hdfs://108474.server.bigdata.com.cn:8020/user/lyy/oozie/3a0c7d3a2ed5468087d93c69db651f3f</value>
</property>
</configuration>",
    "lastModTime":"Mon, 10 Dec 2018 03:51:17 GMT",
    "run":0,
    "endTime":"Mon, 10 Dec 2018 03:51:17 GMT",
    "externalId":null,
    "appName":"adaf4df46a6597914b9ff6cd80eff542c6a",
    "id":"0000106-181129152008300-oozie-oozi-W",
    "startTime":"Mon, 10 Dec 2018 03:50:13 GMT",
    "parentId":null,
    "toString":"Workflow id[0000106-181129152008300-oozie-oozi-W] status[KILLED]",
    "group":null,
    "consoleUrl":"http://108446.server.bigdata.com.cn:11000/oozie?job=0000106-181129152008300-oozie-oozi-W",
    "user":"root",
    "actions":[
        {
            "errorMessage":null,
            "status":"OK",
            "stats":null,
            "data":null,
            "transition":"python-node",
            "externalStatus":"OK",
            "cred":"null",
            "conf":"",
            "type":":START:",
            "endTime":"Mon, 10 Dec 2018 03:50:14 GMT",
            "externalId":"-",
            "id":"0000106-181129152008300-oozie-oozi-W@:start:",
            "startTime":"Mon, 10 Dec 2018 03:50:13 GMT",
            "userRetryCount":0,
            "externalChildIDs":null,
            "name":":start:",
            "errorCode":null,
            "trackerUri":"-",
            "retries":0,
            "userRetryInterval":10,
            "toString":"Action name[:start:] status[OK]",
            "consoleUrl":"-",
            "userRetryMax":0
        },
        {
            "errorMessage":null,
            "status":"OK",
            "stats":null,
            "data":"#
#Mon Dec 10 11:50:24 CST 2018
File="./model.py", line 12, in <module>
Traceback=(most recent call last):
print(aaa)=
NameError=name 'aaa' is not defined    ####这个就是出错的栈信息
k1=v1  ##这个是标准输出的信息
",
            "transition":"python-node1",
            "externalStatus":"SUCCEEDED",
            "cred":"null",
            "conf":"<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>108412.server.bigdata.com.cn:8032</job-tracker>
<name-node>hdfs://108474.server.bigdata.com.cn:8020</name-node>
<configuration>
<property xmlns="">
<name>oozie.launcher.mapred.job.queue.name</name>
<value>ada.oozielauncher</value>
<source>programatically</source>
</property>
</configuration>
<exec>model.py</exec>
<file>model.py</file>
<capture-output />
</shell>",
            "type":"shell",
            "endTime":"Mon, 10 Dec 2018 03:50:24 GMT",
            "externalId":"job_1542533868365_0510",
            "id":"0000106-181129152008300-oozie-oozi-W@python-node",
            "startTime":"Mon, 10 Dec 2018 03:50:14 GMT",
            "userRetryCount":0,
            "externalChildIDs":null,
            "name":"python-node",
            "errorCode":null,
            "trackerUri":"108412.server.bigdata.com.cn:8032",
            "retries":0,
            "userRetryInterval":10,
            "toString":"Action name[python-node] status[OK]",
            "consoleUrl":"http://108412.server.bigdata.com.cn:8088/proxy/application_1542533868365_0510/",
            "userRetryMax":0
        },
        {
            "errorMessage":null,
            "status":"OK",
            "stats":null,
            "data":"#
#Mon Dec 10 11:51:16 CST 2018
k1=v1
",
            "transition":"check-output",
            "externalStatus":"SUCCEEDED",
            "cred":"null",
            "conf":"<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>108412.server.bigdata.com.cn:8032</job-tracker>
<name-node>hdfs://108474.server.bigdata.com.cn:8020</name-node>
<configuration>
<property xmlns="">
<name>oozie.launcher.mapred.job.queue.name</name>
<value>ada.oozielauncher</value>
<source>programatically</source>
</property>
</configuration>
<exec>echo</exec>
<argument>k1=v1</argument>   ##这个就是正常的k1=v1标准输出传递到了python-node1节点了
<capture-output />
</shell>",
            "type":"shell",
            "endTime":"Mon, 10 Dec 2018 03:51:16 GMT",
            "externalId":"job_1542533868365_0511",
            "id":"0000106-181129152008300-oozie-oozi-W@python-node1",
            "startTime":"Mon, 10 Dec 2018 03:50:24 GMT",
            "userRetryCount":0,
            "externalChildIDs":null,
            "name":"python-node1",
            "errorCode":null,
            "trackerUri":"108412.server.bigdata.com.cn:8032",
            "retries":0,
            "userRetryInterval":10,
            "toString":"Action name[python-node1] status[OK]",
            "consoleUrl":"http://108412.server.bigdata.com.cn:8088/proxy/application_1542533868365_0511/",
            "userRetryMax":0
        },
        {
            "errorMessage":null,
            "status":"OK",
            "stats":null,
            "data":null,
            "transition":"fail",
            "externalStatus":"fail",
            "cred":"null",
            "conf":"<switch xmlns="uri:oozie:workflow:0.4">
<case to="end">false</case>
<default to="fail" />
</switch>",
            "type":"switch",
            "endTime":"Mon, 10 Dec 2018 03:51:17 GMT",
            "externalId":"-",
            "id":"0000106-181129152008300-oozie-oozi-W@check-output",
            "startTime":"Mon, 10 Dec 2018 03:51:16 GMT",
            "userRetryCount":0,
            "externalChildIDs":null,
            "name":"check-output",
            "errorCode":null,
            "trackerUri":"-",
            "retries":0,
            "userRetryInterval":10,
            "toString":"Action name[check-output] status[OK]",
            "consoleUrl":"-",
            "userRetryMax":0
        },
        {
            "errorMessage":"Python action failed, error message[v1]",
            "status":"OK",
            "stats":null,
            "data":null,
            "transition":null,
            "externalStatus":"OK",
            "cred":"null",
            "conf":"Python action failed, error message[${wf:actionData('python-node')['k1']}]",
            "type":":KILL:",
            "endTime":"Mon, 10 Dec 2018 03:51:17 GMT",
            "externalId":"-",
            "id":"0000106-181129152008300-oozie-oozi-W@fail",
            "startTime":"Mon, 10 Dec 2018 03:51:17 GMT",
            "userRetryCount":0,
            "externalChildIDs":null,
            "name":"fail",
            "errorCode":"E0729",
            "trackerUri":"-",
            "retries":0,
            "userRetryInterval":10,
            "toString":"Action name[fail] status[OK]",
            "consoleUrl":"-",
            "userRetryMax":0
        }
    ]
}

spark使用oozie提交的两种方式的workflow.xml：

#shell-action:
<workflow-app xmlns="uri:oozie:workflow:0.4" name="shell-wf">
    <start to="shell-node"/>
    <action name="shell-node">
        <shell xmlns="uri:oozie:shell-action:0.2">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <configuration>
                <property>
                    <name>mapreduce.job.queue.name</name>
                    <value>${queueName}</value>
                </property>
            </configuration>
            <exec>spark2-submit</exec>
            <argument>--master</argument>
            <argument>yarn</argument>
            <argument>--deploy-mode</argument>
            <argument>cluster</argument>
            <argument>--queue</argument>
            <argument>ada.spark</argument>
            <argument>--name</argument>
            <argument>testYarn</argument>
            <argument>--conf</argument>
            <argument>spark.yarn.appMasterEnv.JAVA_HOME=/usr/java/jdk1.8</argument>
            <argument>--conf</argument>
            <argument>spark.executorEnv.JAVA_HOME=/usr/java/jdk1.8</argument>
            <argument>--jars</argument>
            <argument>hdfs://10.8.18.74:8020/ada/spark/share/tech_component/tc.plat.spark.jar,hdfs://10.8.18.74:8020/ada/spark/share/tech_component/bigdata4i-1.0.jar,hdfs://10.8.18.74:8020/ada/spark/share/tech_component/bigdata-sparklog-1.0.jar</argument>
            <argument>--files</argument>
            <argument>/etc/hive/conf/hive-site.xml</argument>
            <argument>--class</argument>
            <argument>testYarn.test.Ttest</argument>
            <argument>hdfs://10.8.18.74:8020/user/lyy/App/testYarn.test.jar</argument>
            <capture-output/>
        </shell>
        <ok to="end"/>
        <error to="fail"/>
    </action>
    <kill name="fail">
        <message>Shell action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <end name="end"/>
</workflow-app>

##spark-action:
<workflow-app xmlns="uri:oozie:workflow:0.4" name="spark-action">
    <start to="spark-node"/>
    <action name="spark-node">
        <spark xmlns="uri:oozie:spark-action:0.1">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <configuration>
                <property>
                    <name>mapreduce.job.queue.name</name>
                    <value>${queueName}</value>
                </property>
            </configuration>
        <master>yarn</master>
        <mode>cluster</mode>
        <name>Spark-Action</name>
        <class>testYarn.test.Ttest</class>
        <jar>${nameNode}/user/lyy/App/testYarn.test.jar</jar>
            <spark-opts>--conf spark.yarn.appMasterEnv.JAVA_HOME=/usr/java/jdk1.8 --conf spark.executorEnv.JAVA_HOME=/usr/java/jdk1.8 --jars hdfs://10.8.18.74:8020/ada/spark/share/tech_component/tc.plat.spark.jar,hdfs://10.8.18.74:8020/ada/spark/share/tech_component/bigdata4i-1.0.jar, hdfs://10.8.18.74:8020/ada/spark/share/tech_component/bigdata-sparklog-1.0.jar --conf spark.executor.extraJavaOptions=-Dlog4j.configuration=/etc/hadoop/conf/log4j.properties --conf spark.driver.extraJavaOptions=-Dlog4j.configuration=/etc/hadoop/conf/log4j.properties --conf spark.yarn.queue=ada.spark --files /etc/hive/conf/hive-site.xml</spark-opts>
        </spark>
        <ok to="end"/>
        <error to="fail"/>
    </action>
    <kill name="fail">
        <message>Shell action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <end name="end"/>
</workflow-app>

查看全文

相关阅读:
python中list/tuple/dict/set的区别
 jquery修改ajax的header的字段origin方法，均被浏览器拒绝
 js判断上传文件的大小、类型、修改日期等信息
 js调试方法
 sqlmapapi的跨域访问Access-Control-Allow-Origin:*；ajax
flask的文件上传和下载
 flask中的g、add_url_rule、send_from_directory、static_url_path、static_folder的用法
 python读写csv时中文乱码问题解决办法
 css中!important的作用
 项目经验——Sql server 数据库的备份和还原____还原数据库提示“介质集有2个介质簇,但只提供了1个。必须提供所有成员” .

原文地址：https://www.cnblogs.com/lyy-blog/p/10095674.html