Workflow 1996, Stage 1

Priority	50
Processors	1
Wall seconds	3600
RSS bytes	4194304000 (4000 MiB)
Max distance for inputs	30.0
Enabled input RSEs
Enabled output RSEs
Enabled sites
Scope	usertests
Events for this stage

Output patterns

	Destination	Pattern	Lifetime	For next stage
0	https://fndcadoor.fnal.gov:2880/dune/scratch/users/ykermaid/01996/1	crp5reco_*.root

Environment variables

Name	Value
INPUT_TAR_DIR_LOCAL	/cvmfs/fifeuser1.opensciencegrid.org/sw/dune/41c2481ebe8255e16f9d490e8c768bc601b226e3
NUM_EVENTS	1

File states

Total files	Finding	Unallocated	Allocated	Outputting	Processed	Not found	Failed
304	0	0	0	0	304	0	0

Job states

Total	Submitted	Started	Processing	Outputting	Finished	Notused	Aborted	Stalled	Jobscript error	Outputting failed	None processed
384	0	0	0	0	371	0	0	0	13	0	0

RSEs used

Name	Inputs	Outputs
CERN_PDUNE_EOS	317	0

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 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=crp4_data_reco.fcl
DUNE_VERSION=${DUNE_VERSION:-v09_89_01d00}
DUNE_QUALIFIER=${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=$INPUT_TAR_DIR_LOCAL:${PRODUCTS}

echo "PRODUCTS: ${PRODUCTS}"

setup dunesw "$DUNE_VERSION" -q "$DUNE_QUALIFIER"

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 DUNERECO_DIR=${INPUT_TAR_DIR_LOCAL}/dunereco/${DUNE_VERSION}
export DUNERECO_LIB=${DUNERECO_DIR}/include
export DUNERECO_FQ_DIR=${DUNERECO_DIR}/slf7.x86_64.e26.prof
export DUNERECO_LIB=${DUNERECO_FQ_DIR}/lib

export WIRECELL_PATH=${DUNE_PARDATA_DIR}/WireCellData
export WIRECELL_PATH=${WIRECELL_DIR}/Linux64bit+3.10-2.17-e26-prof/share/wirecell:${WIRECELL_PATH}
export WIRECELL_PATH=${DUNERECO_DIR}/wire-cell-cfg:${WIRECELL_PATH}

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=${DUNERECO_DIR}/fcl:${FHICL_FILE_PATH}

#echo "DUNESW_DIR: ${DUNESW_DIR}"
#echo "DUNERECO_DIR: ${DUNERECO_DIR}"
#echo "DUNEPROTOTYPES_DIR: ${DUNEPROTOTYPES_DIR}"
#echo "WIRECELL_PATH: ${WIRECELL_PATH}"
#echo "FHICL_FILE_PATH: ${FHICL_FILE_PATH}"


export OMP_NUM_THREADS=${JUSTIN_PROCESSORS} 

# 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}_crp4_data_reco_${now}.root

campaign="justIN.r${JUSTIN_WORKFLOW_ID}s${JUSTIN_STAGE_ID}"

(
# Do the scary preload stuff in a subshell!
export LD_PRELOAD=${XROOTD_LIB}/libXrdPosixPreload.so
echo "$LD_PRELOAD"
lar -c $FCL_FILE $events_option -T $outFile "$pfn" > ${fname}_crp4_data_reco_${now}.log 2>&1
)

# Subshell exits with exit code of last command
larExit=$?
echo "lar exit code $larExit"
echo "$pfn" > 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