Workflow 10929, Stage 1

Priority	50
Processors	1
Wall seconds	7200
Image	/cvmfs/singularity.opensciencegrid.org/fermilab/fnal-wn-sl7:latest
RSS bytes	1048576000 (1000 MiB)
Max distance for inputs	30.0
Enabled input RSEs	CERN_PDUNE_EOS, DUNE_CA_SFU, DUNE_CERN_EOS, DUNE_ES_PIC, DUNE_FR_CCIN2P3_DISK, DUNE_IN_TIFR, DUNE_IT_INFN_CNAF, DUNE_UK_GLASGOW, DUNE_UK_LANCASTER_CEPH, DUNE_UK_MANCHESTER_CEPH, DUNE_US_BNL_SDCC, DUNE_US_FNAL_DISK_STAGE, FNAL_DCACHE, FNAL_DCACHE_STAGING, FNAL_DCACHE_TEST, MONTECARLO, NIKHEF, PRAGUE, QMUL, RAL-PP, RAL_ECHO, SURFSARA, T3_US_NERSC
Enabled output RSEs	CERN_PDUNE_EOS, DUNE_CA_SFU, DUNE_CERN_EOS, DUNE_ES_PIC, DUNE_FR_CCIN2P3_DISK, DUNE_IN_TIFR, DUNE_IT_INFN_CNAF, DUNE_UK_GLASGOW, DUNE_UK_LANCASTER_CEPH, DUNE_UK_MANCHESTER_CEPH, DUNE_US_BNL_SDCC, DUNE_US_FNAL_DISK_STAGE, FNAL_DCACHE, FNAL_DCACHE_STAGING, FNAL_DCACHE_TEST, NIKHEF, PRAGUE, QMUL, RAL-PP, RAL_ECHO, SURFSARA, T3_US_NERSC
Enabled sites	BR_CBPF, CA_SFU, CA_Victoria, CERN, CH_UNIBE-LHEP, CZ_FZU, ES_CIEMAT, ES_PIC, FR_CCIN2P3, IT_CNAF, NL_NIKHEF, NL_SURFsara, UK_Bristol, UK_Brunel, UK_Durham, UK_Edinburgh, UK_Lancaster, UK_Liverpool, UK_Manchester, UK_Oxford, UK_QMUL, UK_RAL-PPD, UK_RAL-Tier1, UK_Sheffield, US_Colorado, US_FNAL-FermiGrid, US_FNAL-T1, US_Michigan, US_PuertoRico, US_SU-ITS, US_Swan, US_UChicago, US_UConn-HPC, US_UCSD, US_Wisconsin
Scope	usertests
Events for this stage

Output patterns

	Destination	Pattern	Lifetime	For next stage	RSE expression
1	https://fndcadoor.fnal.gov:2880/dune/scratch/users/imawby/kalmanAlg_nu_9/fnal/10929/1	ClusterValidation_WithAlg.root
2	https://fndcadoor.fnal.gov:2880/dune/scratch/users/imawby/kalmanAlg_nu_9/fnal/10929/1	ClusterValidation_WithoutAlg.root

Environment variables

Name	Value
INPUT_TAR_DIR_LOCAL	/cvmfs/fifeuser1.opensciencegrid.org/sw/dune/2eb16b67837199f6df3fa6681d86eb3e0fa401cc
NUM_EVENTS	100

File states

Total files	Finding	Unallocated	Allocated	Outputting	Processed	Not found	Failed
1000	0	0	0	0	960	0	40

Job states

Total	Submitted	Started	Processing	Outputting	Finished	Notused	Aborted	Stalled	Jobscript error	Outputting failed	None processed
2800	0	0	0	0	2391	0	110	83	192	24	0

RSEs used

Name	Inputs	Outputs
DUNE_US_FNAL_DISK_STAGE	887	0
PRAGUE	112	0
SURFSARA	72	0
NIKHEF	65	0
RAL-PP	47	0
RAL_ECHO	40	0
QMUL	39	0
DUNE_FR_CCIN2P3_DISK	7	0
None	0	1920

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
US_UChicago	25	11
CA_Victoria	16	0
US_PuertoRico	11	0
CA_SFU	6	0
US_Michigan	6	1
ES_PIC	3	0
UK_RAL-Tier1	2	0
UK_QMUL	2	1
US_FNAL-FermiGrid	2	2
US_UCSD	1	1
NL_SURFsara	1	0
CZ_FZU	0	1

Jobscript

#!/bin/bash

# FCL file and DUNE software version/qualifier to be used
FCL_FILE=${FCL_FILE:-$INPUT_TAR_DIR_LOCAL/kalmanAlg.fcl}
DUNE_VERSION=${DUNE_VERSION:-v10_08_00d00}
DUNE_QUALIFIER=${DUNE_QUALIFIER:-e26:prof}

# Make sure that we're not beeing greedy with resources...
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}

# setup the DUNE environment
source /cvmfs/dune.opensciencegrid.org/products/dune/setup_dune.sh
source $INPUT_TAR_DIR_LOCAL/setup-grid
setup dunesw "$DUNE_VERSION" -q "$DUNE_QUALIFIER"
mrbslp

export FW_SEARCH_PATH=.:${INPUT_TAR_DIR_LOCAL}:$FW_SEARCH_PATH
export FHICL_FILE_PATH=.:${INPUT_TAR_DIR_LOCAL}:$FHICL_FILE_PATH

# 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"

# 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}'`

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

lar -c $FCL_FILE $events_option "$pfn" > ${fname}_reco_${now}.log 2>&1
)

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

echo '=== Start last 100 lines of lar log file ==='
tail -100 ${fname}_reco_${now}.log
echo '=== End last 100 lines of lar log file ==='

mv ClusterValidation_WithAlg.root ClusterValidation_WithAlg_${fname}.root
mv ClusterValidation_WithoutAlg.root ClusterValidation_WithoutAlg_${fname}.root

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