DokuWiki

User Tools

Site Tools

Trace:
cluster:124

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
cluster:124 [2016/03/03 18:58] – hmeij07cluster:124 [2016/03/11 20:14] (current) – hmeij07
Line 159: Line 159:
 # submit via 'bsub < run.serial' # submit via 'bsub < run.serial'
 rm -f *err *out *shell rm -f *err *out *shell
-#BSUB -q mw256+#BSUB -q test
 #BSUB -n 1 #BSUB -n 1
 #BSUB -J test #BSUB -J test
Line 165: Line 165:
 #BSUB -e err #BSUB -e err
  
-export PATH=/share/apps/blcr/0.8.5/mw256/bin:$PATH +export PATH=/share/apps/blcr/0.8.5/test/bin:$PATH 
-export LD_LIBRARY_PATH=/share/apps/blcr/0.8.5/mw256/lib:$LD_LIBRARY_PATH+export LD_LIBRARY_PATH=/share/apps/blcr/0.8.5/test/lib:$LD_LIBRARY_PATH
  
 # checkpoint file is defined in while loop # checkpoint file is defined in while loop
Line 177: Line 177:
 cp -rp ~/blcr/t-20001030-01 . cp -rp ~/blcr/t-20001030-01 .
  
-# start the application and remember the working directory+# on first start of application, remember the working directory
 # save some stuff for checking later and restart # save some stuff for checking later and restart
-cr_run ./t-20001030-01 > context 2>&1 & +#cr_run ./t-20001030-01 > context 2>&1 & 
-process_id=`ps -u hmeij | grep t-20001030-01 | grep -v grep | awk '{print $1}'` +#sleep 60 
-pwd > pwd.$process_id +#process_id=`ps -u hmeij | grep t-20001030-01 | grep -v grep | awk '{print $1}'` 
-cp -p pwd* *.shell *.out *.err ~/blcr/+#pwd > pwd.$process_id 
 +#cp -p pwd* *.shell *.out *.err ~/blcr/
  
 # on restart, give cr_restart some time to set up # on restart, give cr_restart some time to set up
 # WARNING: it will overwrite the checkpoint file, save it # WARNING: it will overwrite the checkpoint file, save it
 # you need to find the process_id and supply it # you need to find the process_id and supply it
-#process_id=9089 +process_id=4711 
-#cp -p ~/blcr/checkpoint.$process_id ~/blcr/checkpoint.$process_id.saved +cp -p ~/blcr/checkpoint.$process_id ~/blcr/checkpoint.$process_id.saved 
-#mv ~/blcr/context  ~/blcr/context.save +mv ~/blcr/context  ~/blcr/context.save 
-#ln -s $MYSANSCRATCH `cat ~/blcr/pwd.$process_id` +ln -s $MYSANSCRATCH `cat ~/blcr/pwd.$process_id` 
-#cr_restart ~/blcr/checkpoint.$process_id > context 2>&1 & +cr_restart ~/blcr/checkpoint.$process_id > context 2>&1 & 
-#sleep 60+sleep 60
  
 +# always uncommented
 echo "process_id=$process_id" echo "process_id=$process_id"
 while [ $process_id -gt 0 ]; do while [ $process_id -gt 0 ]; do
Line 201: Line 203:
         cr_checkpoint -f ~/blcr/checkpoint.$process_id $process_id         cr_checkpoint -f ~/blcr/checkpoint.$process_id $process_id
         cp -p context ~/blcr/         cp -p context ~/blcr/
-        # if the application has crashed, exit+        # if the application has crashed, or finished, exit
         process_id=`ps -u hmeij | grep t-20001030-01 | grep -v grep | awk '{print $1}'`         process_id=`ps -u hmeij | grep t-20001030-01 | grep -v grep | awk '{print $1}'`
         if [ "${process_id}x" = 'x' ]; then         if [ "${process_id}x" = 'x' ]; then
cluster/124.1457031522.txt.gz · Last modified: by hmeij07