Did you check if there's actually anything in the checkpoint files? If they're empty, that probably means that you're checkpointing too frequently. On Jun 10, 2013, at 5:17 PM, john donald <[email protected]> wrote:
i raised it to 20 sec but same results sorry i am new to checkpoint restart i am trying this initially on one multicore pc how should it look like if the restart succeed? should it work in the same terminal in which i am running restart command my test app has 5000 iterations , checkpoint is taken at iteration no 300 for example , if i choose to restart from this checkpoint file should it restart near this iteration no 300
2013/6/6 Wesley Bland <[email protected]> Is there actually anything in those checkpoints? With a checkpoint happening every 4 seconds you may be overdoing it.
Wesley
On Jun 5, 2013, at 2:14 PM, Rajeev Thakur <[email protected]> wrote:
I don't know, but see if anything on this page helps: http://wiki.mpich.org/mpich/index.php/Checkpointing
On Jun 5, 2013, at 4:09 PM, john donald wrote:
---------- Forwarded message ---------- From: john donald <[email protected]> Date: 2013/6/3 Subject: ckpoint-num error To: [email protected]
i used mpiexec with checkpoint and created two checkpoint files:
mpiexec -ckpointlib blcr -ckpoint-prefix /home/john/ckpts/app.ckpoint -ckpoint-interval 4 -n 4 /home/john/app/md
context-num0-0-0 context-num1-0-0
i am trying to make a restart mpiexec -ckpointlib blcr -ckpoint-prefix /home/john/ckpts/app.ckpoint -n 4 -ckpoint-num 1
but nothing happened it just hangs i also tried: mpiexec -ckpointlib blcr -ckpoint-prefix /home/john/ckpts/app.ckpoint -n 4 -ckpoint-num 0-0-0 also hangs
_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss
_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss
discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss