21 July 2025: This instance at RAL is read-only. Please do not try submitting new workflows for now.

Workflow 6217, Stage 1

Priority	50
Processors	1
GPU required	Yes
Wall seconds	80000
Image	/cvmfs/singularity.opensciencegrid.org/fermilab/fnal-wn-sl7:latest
RSS bytes	2097152000 (2000 MiB)
Max distance for inputs	100.0
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, ES_CIEMAT, ES_PIC, FR_CCIN2P3, IN_TIFR, IT_CNAF, NL_SURFsara, UK_Bristol, UK_Brunel, UK_Durham, UK_Edinburgh, UK_Glasgow, UK_Imperial, UK_Lancaster, UK_Liverpool, UK_Manchester, UK_Oxford, UK_QMUL, UK_RAL-PPD, UK_RAL-Tier1, UK_Sheffield, US_Caltech, US_Colorado, US_FNAL-FermiGrid, US_FNAL-T1, US_Michigan, US_MIT, US_Nebraska, US_NotreDame, US_PuertoRico, US_SU-ITS, US_Swan, US_UChicago, US_UConn-HPC, US_UCSD, US_Wisconsin
Scope	usertests
Events for this stage

File states

Total files	Finding	Unallocated	Allocated	Outputting	Processed	Not found	Failed
10	0	0	0	0	10	0	0

Job states

Total	Submitted	Started	Processing	Outputting	Finished	Notused	Aborted	Stalled	Jobscript error	Outputting failed	None processed
16	0	0	0	0	10	1	0	3	2	0	0

RSEs used

Name	Inputs	Outputs
MONTECARLO	10	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'

GPU Hello World jobscript for justIN

Submit a workflow like this to run 10 jobs on workers with GPUs:

justin simple-workflow --monte-carlo 10 --gpu \
  --jobscript-git DUNE/dune-justin/testing/hello-gpu.jobscript:01.04.rc1

Or like this to run jobs and put the output file into Rucio-managed storage:

justin simple-workflow \
     --monte-carlo 10 \
     --gpu \
     --jobscript-git DUNE/dune-justin/testing/hello-gpu.jobscript:01.04.rc1 \
     --description 'Hello GPU!!!' \
     --scope usertests \
     --output-pattern 'hello-gpu-*.txt:output-test-01' \
     --lifetime-days 1

EOF

# Check the GPU environment
printenv | grep -i cuda
nvidia-smi

# Try to get an unprocessed file from this stage
did_pfn_rse=`$JUSTIN_PATH/justin-get-file`

if [ "$did_pfn_rse" != "" ] ; then
  did=`echo $did_pfn_rse | cut -f1 -d' '`
  pfn=`echo $did_pfn_rse | cut -f2 -d' '`
  rse=`echo $did_pfn_rse | cut -f3 -d' '`

  # Hello gpu to a txt file
  echo "Hello gpu $pfn" >hello-gpu-`date +%s.%N.txt`

  # Hello gpu to the jobscript log 
  echo "Hello gpu $pfn" 
  if [ $? = 0 ] ; then
    # If echo returns 0, then say we processed the file successfully
    echo "$pfn" > justin-processed-pfns.txt
  fi
fi
exit 0