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'
To use this jobscript to process 5 files from the dataset fardet-hd__fd_mc_2023a_reco2__full-reconstructed__v09_81_00d02__standard_reco2_dune10kt_nu_1x2x6__prodgenie_nu_dune10kt_1x2x6__out1__validation
data and put the output in the $USER namespace (MetaCat) and saves the output in /scratch
Use this command to create the workflow:
justin simple-workflow \
--mql \
"files from fardet-hd:fardet-hd__fd_mc_2023a__hit-reconstructed__v09_78_01d01__standard_reco1_dune10kt_1x2x6__prodgenie_nu_dune10kt_1x2x6__out1__v1_official limit 1 limit 5 ordered"\
--jobscript submit_ana.jobscript --rss-mb 4000 \
--scope higuera --output-pattern '*_myreco2_*.root:$FNALURL/$USERF'
The following optional environment variables can be set when creating the
workflow/stage: FCL_FILE, NUM_EVENTS, DUNE_VERSION, DUNE_QUALIFIER
EOF
# fcl file and DUNE software version/qualifier to be used
#FCL_FILE=${FCL_FILE:-$INPUT_TAR_DIR_LOCAL/srcs/protoduneana/protoduneana/singlephase/mucap/muoncapturejob.fcl}
FCL_GEN=${FCL_GEN:-$INPUT_TAR_DIR_LOCAL/srcs/dunereco/dunereco/BlipRecoDUNE/job/gen_protodunevd_mu_and_pi_cap_1GeV.fcl}
FCL_G4STAGE1=${FCL_G4STAGE1:-protodunevd_refactored_g4_stage1.fcl}
FCL_G4STAGE2=${FCL_G4STAGE2:-protodunevd_refactored_g4_stage2.fcl}
FCL_DETSIM=${FCL_DETSIM:-$INPUT_TAR_DIR_LOCAL/srcs/dunereco/dunereco/BlipRecoDUNE/job/protodunevd_refactored_detsim_keepall.fcl}
FCL_RECO=${FCL_RECO:-protodunevd_reco.fcl}
FCL_ANA=${FCL_ANA:-$INPUT_TAR_DIR_LOCAL/srcs/dunereco/dunereco/BlipRecoDUNE/job/run_pdvd_blipana.fcl}
DUNE_VERSION=${DUNE_VERSION:-v09_91_03d00}
DUNE_QUALIFIER=${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_v09_91_03d00_e26_prof/:$PRODUCTS" #working
setup dunesw "$DUNE_VERSION" -q "$DUNE_QUALIFIER"
mrbslp
#export PRODUCTS="${INPUT_TAR_DIR_LOCAL}/localProducts_larsoft_v09_91_03d00_e26_prof/setup:$PRODUCTS" #not working
#source $INPUT_TAR_DIR_LOCAL/localProducts_larsoft_v09_91_03d00_e26_prof/setup #not working
#setup protoduneana "$DUNE_VERSION" -q "$DUNE_QUALIFIER" # working
# 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 $1}'`
#outFile=${fname}_reco2_${now}.root
outFile_GEN=${fname}_gen_${now}.root
outFile_G4Stage1=${fname}_g4_stage1_${now}.root
outFile_G4Stage2=${fname}_g4_stage2_${now}.root
outFile_Detsim=${fname}_detsim_${now}.root
outFile_reco=${fname}_reco_${now}.root
outFile_ana=${fname}_ana_${now}.root
outFile_ana_hist=${fname}_ana_hist_${now}.root
campaign="justIN.w${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_GEN -n 100 -o $outFile_GEN -T /dev/null > ${fname}_gen_${now}.log 2>&1
lar -c $FCL_G4STAGE1 -n -1 -s $outFile_GEN -o $outFile_G4Stage1 -T /dev/null > ${fname}_g4stage1_${now}.log 2>&1
lar -c $FCL_G4STAGE2 -n -1 -s $outFile_G4Stage1 -o $outFile_G4Stage2 -T /dev/null > ${fname}_g4stage2_${now}.log 2>&1
lar -c $FCL_DETSIM -n -1 -s $outFile_G4Stage2 -o $outFile_Detsim -T /dev/null > ${fname}_detsim_${now}.log 2>&1
lar -c $FCL_RECO -n -1 -s $outFile_Detsim -o $outFile_reco -T /dev/null > ${fname}_reco_${now}.log 2>&1
lar -c $FCL_ANA -n -1 -s $outFile_reco -o $outFile_ana -T $outFile_ana_hist > ${fname}_ana_${now}.log 2>&1
#lar -c $FCL_FILE $events_option -o $outFile "$pfn" > ${fname}_myreco2_${now}.log 2>&1
#lar -c $FCL_FILE $events_option -T ${outRecoFile}.root -o ${fname}_crpcb_bottom_reco.root $pfn > ${outRecoFile}.log 2>&1
#lar -c $ANA_FILE $events_option -T ${outAnaFile}_hist.root -o ${outAnaFile}.root ${fname}_crpcb_bottom_reco.root > ${fname}_myana_${now}.log 2>&1
)
echo '=== Start last 100 lines of lar log file ==='
tail -100 ${fname}_ana_${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: 2024-11-23 22:50:00 UTC justIN version: 01.01.09
