...
| No Format |
|---|
ssh -F ssh_config USERNAME@detsim.fnal.gov |
Setup the Grid Tools
Setup the grid tools in a bash shell.
| No Format |
|---|
source /fnal/ups/grid/setup.sh
|
Setup the grid tools in tcsh or csh.
| No Format |
|---|
source /fnal/ups/grid/setup.csh
|
Session Certificate and quotas
...
| No Format |
|---|
cat > sleep_grid << +EOF universe = grid globusschedulerGridResource = gt2 fngp-osgfnpcosg1.fnal.gov/jobmanager-condor executable = /bin/sleep transfer_output = true transfer_error = true transfer_executable = true log = sleep_grid.log.\$(Cluster).\$(Process) notification = NEVER output = sleep_grid.out.\$(Cluster).\$(Process) error = sleep_grid.err.\$(Cluster).\$(Process) stream_output = false stream_error = false ShouldTransferFiles = YES WhenToTransferOutput = ON_EXIT globusrsl = (jobtype=single)(maxwalltime=999) Arguments = 10 queue 5 +EOF condor_submit sleep_grid |
...
| No Format |
|---|
rm -f env_grid.sh
cat > env_grid.sh << +EOF
#!/bin/sh -f
printenv
pwd
cd \${_CONDOR_SCRATCH_DIR}
pwd
#
# This sets up the environment for osg in case we want to
# use grid services like srmcp
#
. $OSG_GRID/setup.sh
source \${VDT_LOCATION}/setup.sh
printenv
/bin/df
+EOF
chmod +x env_grid.sh
rm -f env_grid.run
cat > env_grid.run << +EOF
universe = grid
globusschedulerGridResource = fngp-osggt2 fnpcosg1.fnal.gov/jobmanager-condor
executable = ./env_grid.sh
transfer_output = true
transfer_error = true
transfer_executable = true
log = env_grid.log.\$(Cluster).\$(Process)
notification = NEVER
output = env_grid.out.\$(Cluster).\$(Process)
error = env_grid.err.\$(Cluster).\$(Process)
stream_output = false
stream_error = false
ShouldTransferFiles = YES
WhenToTransferOutput = ON_EXIT
globusrsl = (jobtype=single)(maxwalltime=999)
queue
+EOF
condor_submit env_grid.run
|
...
| No Format |
|---|
rm -f slic_grid.csh
cat > slic_grid.csh << +EOF
#!/bin/csh
echo start
/bin/date
cd \${_CONDOR_SCRATCH_DIR}
setenv LABELRUN slic_grid-\${ClusterProcess}
setenv TARFILE \${LABELRUN}-results.tar
echo \${TARFILE}
echo start
/bin/date
mkdir results
/grid/app/ilc/sid/SimDist/v2r4p2/SimDist/scripts/slic.sh -r 5 \
-g /grid/app/ilc/detector/SimDist/detectors/sid01/sid01.lcdd \
-i /grid/data/ilc/detector/LDC/stdhep/ZZ_run10.stdhep -o ./results/ZZ_run10\${LABELRUN} >& \
./results/ZZ_run10\${LABELRUN}.lis
ls -lh results
/bin/date
echo "build output tarball: " \${TARFILE}
tar -cf \${TARFILE} results
echo done
+EOF
chmod +x slic_grid.csh
rm -f slic_grid.run
cat > slic_grid.run << +EOF
universe = grid
globusschedulerGridResource = gt2 fngp-osgfnpcosg1.fnal.gov/jobmanager-condor
executable = ./slic_grid.csh
transfer_output = true
transfer_error = true
transfer_executable = true
environment = "ClusterProcess=\$(Cluster)-\$(Process)"
transfer_output_files = slic_grid-\$(Cluster)-\$(Process)-results.tar
log = slic_grid.log.\$(Cluster).\$(Process)
notification = NEVER
output = slic_grid.out.\$(Cluster).\$(Process)
error = slic_grid.err.\$(Cluster).\$(Process)
stream_output = false
stream_error = false
ShouldTransferFiles = YES
WhenToTransferOutput = ON_EXIT
globusrsl = (jobtype=single)(maxwalltime=999)
queue
+EOF
condor_submit slic_grid.run
|
...
| No Format |
|---|
condor_q -submitter <username> |
You can view information about all requests with the following command:
| No Format |
|---|
condor_status -submitters |
To cancel a job type condor_rm followed by the job number:
| No Format |
|---|
condor_rm <job number> |
Condor can put a job into held state when e.g. the proxy expires while the job is running. In that case the job still might be running fine on the worker node but even after successsful completion there will not be any log files etc. copied back. To remedy that situation renew the proxy and then release the jobs.
...