dnet-hadoop/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml

300 lines
12 KiB
XML

<workflow-app name="import_infospace_graph" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>hive_db_name</name>
<description>the target hive database name</description>
</property>
<property>
<name>hive_source_db_name</name>
<description>the source hive database name</description>
</property>
<property>
<name>hive_timeout</name>
<description>the time period, in seconds, after which Hive fails a transaction if a Hive client has not sent a hearbeat. The default value is 300 seconds.</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hiveMetastoreUris}</value>
</property>
<property>
<name>hive.txn.timeout</name>
<value>${hive_timeout}</value>
</property>
</configuration>
</global>
<start to="Step1-CreateDB"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="Step1-CreateDB">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step1.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step2"/>
<error to="Kill"/>
</action>
<action name="Step2">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step2.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step3"/>
<error to="Kill"/>
</action>
<action name="Step3">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step3.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step4"/>
<!-- <ok to="End"/> -->
<error to="Kill"/>
</action>
<action name="Step4">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
<property>
<name>hive.variable.substitute</name>
<value>true</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step4.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step5"/>
<error to="Kill"/>
</action>
<action name="Step5">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step5.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step6"/>
<error to="Kill"/>
</action>
<action name="Step6">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step6.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step7"/>
<error to="Kill"/>
</action>
<action name="Step7">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step7.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step8"/>
<error to="Kill"/>
</action>
<action name="Step8">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step8.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step9"/>
<error to="Kill"/>
</action>
<action name="Step9">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step9.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step10"/>
<error to="Kill"/>
</action>
<action name="Step10">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step10.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step11"/>
<error to="Kill"/>
</action>
<action name="Step11">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step11.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step12"/>
<error to="Kill"/>
</action>
<action name="Step12">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step12.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step13"/>
<error to="Kill"/>
</action>
<action name="Step13">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration>
<jdbc-url>${hive_jdbc_url}/${hive_db_name}</jdbc-url>
<script>scripts/step13.sql</script>
<param>hive_db_name=${hive_db_name}</param>
<param>hive_source_db_name=${hive_source_db_name}</param>
</hive2>
<ok to="Step14"/>
<error to="Kill"/>
</action>
<action name="Step14">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<!-- <configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
</configuration> -->
<exec>impala-shell.sh</exec>
<argument>${hive_db_name}</argument>
<argument>impala-stats.sql</argument>
<argument>/user/giorgos.alexiou/graph/oozie_app/impala-stats.sql</argument>
<file>impala-shell.sh</file>
<!-- <param>hive_db_name=${hive_db_name}</param> -->
</shell>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>