Mercurial > hg > cc > cirrus_home
view bin/cdx2sql.sh @ 204:dc397748f4e1
rework w2c.py args
| author | Henry S. Thompson <ht@inf.ed.ac.uk> |
|---|---|
| date | Thu, 23 Apr 2026 10:51:36 +0100 |
| parents | afd7879181c9 |
| children |
line wrap: on
line source
#!/bin/bash # Invoke this as e.g. sbatch -N 4 --ntasks=3 -c 5 masterJob.sh cdx2sql \ # CC-MAIN-2019-35 cdx_db # run cdx2sql.py in parallel, working index files enumerated in cdx2sql/n.c.txt n=$SLURM_NTASKS c=$SLURM_CPUS_PER_TASK node=$SLURMD_NODENAME task=$SLURM_LOCALID node=$SLURM_NODEID cc=$1 resdir=$2 echo $(date) $nodename:$node:$task start export PYTHONPATH=$PYTHONPATH:$HOME/lib/python ld=/dev/shm/ht/$task mkdir -p $ld parallel --will-cite -j $c doC2S.sh $node $task $cc $resdir $ld '{}' < cdx2sql/$node.$task.txt if [ "$ld" ] then cd $ld tar -czf $HOME/results/$cc/$resdir/$node.$task.tar.gz * rm * fi echo $(date) $nodename:$node:$task end
