spyros
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Add monitor post step

This commit is contained in:
dimitrispie 2023-02-09 13:44:14 +02:00
parent 35ba8bb328
commit d71f5672d3
4 changed files with 42 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/monitor-post.sh Normal file
View File

@ -0,0 +1,19 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
export SOURCE=$1
export SHADOW=$2
export HIVE_OPTS="-hiveconf mapred.job.queue.name=analytics -hiveconf hive.spark.client.connect.timeout=120000ms -hiveconf hive.spark.client.server.connect.timeout=300000ms -hiveconf spark.executor.memory=19166291558 -hiveconf spark.yarn.executor.memoryOverhead=3225 -hiveconf spark.driver.memory=11596411699 -hiveconf spark.yarn.driver.memoryOverhead=1228"
export HADOOP_USER_NAME="oozie"
echo "Updating shadow database"
hive -e "drop database if exists ${SHADOW} cascade"
hive -e "create database if not exists ${SHADOW}"
hive $HIVE_OPTS --database ${SOURCE} -e "show tables" | grep -v WARN | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" > foo
hive -f foo
echo "Updated shadow database"

1
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/monitor.sh
View File

@ -22,3 +22,4 @@ echo "Creating monitor database"
cat step20-createMonitorDB.sql | sed "s/TARGET/${TARGET}/g" | sed "s/SOURCE/${SOURCE}/g1" > foo
hive $HIVE_OPTS -f foo
echo "Hive shell finished"

13
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-post.sh
View File

@ -7,12 +7,13 @@ then
fi
export SOURCE=$1
export TARGET=$2
export SHADOW=$3
export SHADOW=$2
export HIVE_OPTS="-hiveconf mapred.job.queue.name=analytics -hiveconf hive.spark.client.connect.timeout=120000ms -hiveconf hive.spark.client.server.connect.timeout=300000ms -hiveconf spark.executor.memory=19166291558 -hiveconf spark.yarn.executor.memoryOverhead=3225 -hiveconf spark.driver.memory=11596411699 -hiveconf spark.yarn.driver.memoryOverhead=1228"
export HADOOP_USER_NAME="oozie"
hive $HIVE_OPTS --database ${TARGET} -e "show tables" | grep -v WARN | sed "s/\(.*\)/analyze table ${TARGET}.\1 compute statistics;/" > foo
hive $HIVE_OPTS -f foo
echo "Hive shell finished"
echo "Updating shadow database"
hive -e "drop database if exists ${SHADOW} cascade"
hive -e "create database if not exists ${SHADOW}"
hive $HIVE_OPTS --database ${SOURCE} -e "show tables" | grep -v WARN | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" > foo
hive -f foo
echo "Updated shadow database"

15
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
View File

@ -366,6 +366,20 @@
<argument>${wf:appPath()}/scripts/step20-createMonitorDB.sql</argument>
<file>monitor.sh</file>
</shell>
<ok to="step20-createMonitorDB-post"/>
<error to="Kill"/>
</action>
<action name="step20-createMonitorDB-post">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>monitor-post.sh</exec>
<argument>${monitor_db_name}</argument>
<argument>${monitor_db_shadow_name}</argument>
<argument>${wf:appPath()}/scripts/step20-createMonitorDB.sql</argument>
<file>monitor.sh</file>
</shell>
<ok to="step21-createObservatoryDB-pre"/>
<error to="Kill"/>
</action>
@ -400,7 +414,6 @@
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>observatory-post.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${observatory_db_name}</argument>
<argument>${observatory_db_shadow_name}</argument>
<file>observatory-post.sh</file>