Stats of processed input files as CSV or JSON, and of uploaded output files as CSV or JSON (up to 10000 files included)
Jobscript
#!/bin/bash
:<<'EOF'
Use this jobscript to process files from the dataset fardet-hd:fardet-hd__hit-reconstructed__v09_91_04d00__reco1_supernova_dune10kt_1x2x6__prodmarley_nue_cc_flat_radiological_decay0_dune10kt_1x2x6_centralAPA__out1__v1_official
data and put the output in the $USER namespace (MetaCat) and saves the output in /scratch
Use this script by doing
source hd_1x2x6_centralAPA.sh
(use source fdhdcentral_test.sh first to test it locally - also a good idea to remove the folder created in /tmp afterwards).
This example uses a custom dune repository that is provided via a tar file.
I recommend sending the tar to cvmfs in advance, just to avoid any problem, with this command
INPUT_TAR_DIR_LOCAL=`justin-cvmfs-upload larsoft_v10_05_00.tar.gz`
The following optional environment variables can be set when creating the
workflow/stage: FCL_FILE, NUM_EVENTS, DUNE_VERSION, DUNE_QUALIFIER
EOF
# fcl file and DUNE software version/qualifier to be used
FCL_FILE=${FCL_FILE:-solar_ana_marley_flash_radiological_decay0_dune10kt_1x2x6_centralAPA}
DUNE_VERSION=${DUNE_VERSION:-v10_05_00d00}
DUNE_QUALIFIER=${DUNE_QUALIFIER:-e26:prof}
# number of events to process from the input file
if [ "$NUM_EVENTS" != "" ] ; then
events_option="-n $NUM_EVENTS"
fi
# First get an unprocessed file from this stage
did_pfn_rse=`$JUSTIN_PATH/justin-get-file`
if [ "$did_pfn_rse" = "" ] ; then
echo "Nothing to process - exit jobscript"
exit 0
fi
# Keep a record of all input DIDs, for pdjson2meta file -> DID mapping
echo "$did_pfn_rse" | cut -f1 -d' ' >>all-input-dids.txt
# pfn is also needed when creating justin-processed-pfns.txt
pfn=`echo $did_pfn_rse | cut -f2 -d' '`
echo "Input PFN = $pfn"
# Setup DUNE environment
source /cvmfs/dune.opensciencegrid.org/products/dune/setup_dune.sh
export PRODUCTS="${INPUT_TAR_DIR_LOCAL}/localProducts_larsoft_v10_05_00_e26_prof/:$PRODUCTS"
# Then we can set up our local products
setup dunesw "$DUNE_VERSION" -q "$DUNE_QUALIFIER"
# Construct outFile from input $pfn
now=$(date -u +"%Y-%m-%dT_%H%M%SZ")
Ffname=`echo $pfn | awk -F/ '{print $NF}'`
fname=`echo $Ffname | awk -F. '{print $1}'`
outFile=fdhd_ana_${now}.root
outHistFile=fdhd_ana_${now}_hist.root
campaign="justIN.w${JUSTIN_WORKFLOW_ID}s${JUSTIN_STAGE_ID}"
# Here is where the LArSoft command is call it
(
# Do the scary preload stuff in a subshell!
export LD_PRELOAD=${XROOTD_LIB}/libXrdPosixPreload.so
echo "$LD_PRELOAD"
lar -c $FCL_FILE $events_option -o $outFile -T $outHistFile "$pfn" > fdhd_ana_${now}.log 2>&1
)
echo '=== Start last 100 lines of lar log file ==='
tail -100 fdhd_ana_${now}.log
echo '=== End last 100 lines of lar log file ==='
# Subshell exits with exit code of last command
larExit=$?
echo "lar exit code $larExit"
if [ $larExit -eq 0 ] ; then
# Success !
echo "$pfn" > justin-processed-pfns.txt
jobscriptExit=0
else
# Oh :(
jobscriptExit=1
fi
# Create compressed tar file with all log files
#tar zcf `echo "$JUSTIN_JOBSUB_ID.logs.tgz" | sed 's/@/_/g'` *.log
exit $jobscriptExit
justIN time: 2025-05-22 23:06:23 UTC justIN version: 01.03.01
