There's been lots of turnover on the project recently so the previous experts for checkpoint/restart in MPICH are gone, but from what I can tell, it appears that it might currently be broken. This ticket (https://trac.mpich.org/projects/mpich/ticket/1144) is the only documentation about the subject that I can find, but I think the assumption is that everything has bit rotted and will need to be updated before it works again.

Wesley

On Jul 1, 2013, at 10:19 AM, basma a.azeem <basmaabdelazeem@hotmail.com> wrote:

i created a checkpoint file of the integer sort NPB after 60 sec of running the application , the checkpoint file size is 121.6 MB (121,633,453 bytes).

i have Blcr for checkpoint/restart
when i try to restart from the checkpoint file i had , nothing happened , it just hangs
what i did wrong ?
this is the command i used.


basma@basma-Satellite-A500:~$ mpiexec -ckpointlib blcr \
> -ckpoint-prefix /home/basma/ckpts/app.ckpoint \
> -ckpoint-num 0 -n 4

_______________________________________________
discuss mailing list     discuss@mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss