Stats of processed input files as CSV or JSON, and of uploaded output files as CSV or JSON (up to 10000 files included)
File reset events, by site
Site
Allocated
Outputting
UK_Edinburgh
70
0
UK_RAL-Tier1
10
140
NL_SURFsara
0
150
UK_QMUL
0
140
FR_CCIN2P3
0
20
NL_NIKHEF
0
20
Jobscript
#!/bin/bash
:<<'EOF'
To use this jobscript to process 10 files from the dc4-vd-coldbox-bottom
data and put the output in the usertests namespace (MetaCat) and
scope (Rucio), and in the usertests:output-test-01 dataset in MetaCat and
Rucio, use this command to create the workflow:
justin simple-workflow \
--mql \
"files from dune:all where core.run_type='dc4-vd-coldbox-bottom' and dune.campaign='dc4' limit 10" \
--jobscript dc4-vd-coldbox-bottom.jobscript --max-distance 30 --rss-mb 4000 \
--scope usertests --output-pattern '*_reco_data_*.root:output-test-01'
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=MyrunSingleHit_PDHD.fcl
DUNE_VERSION=${DUNE_VERSION:-v10_00_02d00}
DUNE_QUALIFIER=${DUNE_QUALIFIER:-e26:prof}
# number of events to process from the input file
if [ "$NUM_EVENTS" != "" ] ; then
events_option="-n $NUM_EVENTS"
fi
if [ -z ${JUSTIN_PROCESSORS} ]; then
JUSTIN_PROCESSORS=1
fi
echo "Justin processors: ${JUSTIN_PROCESSORS}"
export TF_NUM_THREADS=${JUSTIN_PROCESSORS}
export OPENBLAS_NUM_THREADS=${JUSTIN_PROCESSORS}
export JULIA_NUM_THREADS=${JUSTIN_PROCESSORS}
export MKL_NUM_THREADS=${JUSTIN_PROCESSORS}
export NUMEXPR_NUM_THREADS=${JUSTIN_PROCESSORS}
export OMP_NUM_THREADS=${JUSTIN_PROCESSORS}
# First get an unprocessed file from this stage
for nf in {1..10}
do
DID_PFN_RSE=`$JUSTIN_PATH/justin-get-file`
##Check that any file was returned
if [ "${DID_PFN_RSE}" == "" ] ; then
echo "Could not get file"
exit 0
#continue
fi
FILE=`echo ${DID_PFN_RSE} | cut -f2 -d' '`
DID=`echo ${DID_PFN_RSE} | cut -f1 -d' '`
echo ${DID} >> did.list
echo ${FILE} >> file.list
done
#did_pfn_rse=`$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:${PRODUCTS}
echo "PRODUCTS: ${PRODUCTS}"
echo "DUNESW_DIR: ${DUNESW_DIR}"
# Properly setup custom code with INPUT_TAR_DIR_LOCAL
export DUNESW_DIR=${INPUT_TAR_DIR_LOCAL}/dunesw/${DUNE_VERSION}
export DUNESW_FQ_DIR=${DUNESW_DIR}/slf7.x86_64.e26.prof
export DUNESW_LIB=${DUNESW_FQ_DIR}/lib
export PROTODUNEANA_DIR=${INPUT_TAR_DIR_LOCAL}/protoduneana/${DUNE_VERSION}
export PROTODUNEANA_LIB=${PROTODUNEANA_DIR}/include
export PROTODUNEANA_FQ_DIR=${PROTODUNEANA_DIR}/slf7.x86_64.e26.prof
export PROTODUNEANA_LIB=${PROTODUNEANA_FQ_DIR}/lib
export DUNEPROTOTYPES_DIR=${INPUT_TAR_DIR_LOCAL}/duneprototypes/${DUNE_VERSION}
export DUNEPROTOTYPES_INC=${DUNEPROTOTYPES_DIR}/include
export DUNEPROTOTYPES_FQ_DIR=${DUNEPROTOTYPES_DIR}/slf7.x86_64.e26.prof
export DUNEPROTOTYPES_LIB=${DUNEPROTOTYPES_FQ_DIR}/lib
export FHICL_FILE_PATH=${DUNESW_DIR}/fcl:${FHICL_FILE_PATH}
export FHICL_FILE_PATH=${DUNEPROTOTYPES_DIR}/fcl:${FHICL_FILE_PATH}
export FHICL_FILE_PATH=${PROTODUNEANA_DIR}/fcl:${FHICL_FILE_PATH}
export FHICL_FILE_PATH=${INPUT_TAR_DIR_LOCAL}/myfcl:${FHICL_FILE_PATH}
echo "DUNESW_DIR: ${DUNESW_DIR}"
echo "PROTODUNEANA_DIR: ${PROTODUNEANA_DIR}"
echo "DUNEPROTOTYPES_DIR: ${DUNEPROTOTYPES_DIR}"
source "${INPUT_TAR_DIR_LOCAL}/localProducts_larsoft_v10_00_02d00_prof_e26/setup2"
setup dunesw "$DUNE_VERSION" -q "$DUNE_QUALIFIER"
echo " VERSION ACTIVE = VERSION ACTIVE = VERSION ACTIVE = "
ups active | grep "dunesw\|duneprototypes"
mrbslp
echo "now run lar on these files"
cat file.list
cat did.list
# 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 $1}'`
outFile=singleHit_output_${now}.root
campaign="justIN.r${JUSTIN_WORKFLOW_ID}s${JUSTIN_STAGE_ID}"
# Do the scary preload stuff in a subshell!
lar -c $events_option ${INPUT_TAR_DIR_LOCAL}/myfcl/$FCL_FILE -T $outFile -S file.list > log_singleHit_${now}.log 2>&1
# Subshell exits with exit code of last command
larExit=$?
echo "lar exit code $larExit"
# echo "$FILE" > justin-processed-pfns.txt
cat file.list > justin-processed-pfns.txt
echo "processed files"
cat justin-processed-pfns.txt
ls -lRS
# Create compressed tar file with all log files
#tar zcf `echo "$JUSTIN_JOBSUB_ID.logs.tgz" | sed 's/@/_/g'` *.log
#exit $jobscriptExit
exit $larExit
justIN time: 2024-11-24 02:11:45 UTC justIN version: 01.01.09