I assume you are referring to the message that you posted on the lam-
devel list yesterday with subject "Re: lam-devel Digest, Vol 140,
Issue 1", since this is the same text.
Both Liu and I already replied on the lam-devel list. Please see our
replies there (if you signed up for a digest version of the list, you
may see long delays before you get the actual replies).
http://www.lam-mpi.org/MailArchives/lam-devel/2006/01/0447.php
http://www.lam-mpi.org/MailArchives/lam-devel/2006/01/0449.php
Thanks.
On Jan 10, 2006, at 10:14 AM, Yuan Tang wrote:
> Hi Jeff & Liu,
>
> Would you take a look at my message and give me some hints?
> I downloaded the lam-7.1.2b30 and installed it. But there're 2
> problems:
>
> 1. If the lamd exited after I invoked "cr_checkpoint --term
> ${pid_mpirun}", then the subsequent "cr_restart context.
> {pid_mpirun}" could not
> restart the whole program. That is, the program cannot be restarted
> in a new
> LAM session/universe.
>
> 2. Even the lamd doesnot exit, if I invoke "cr_checkpoint --term
> ${pid_mpirun}" multiple times, the "cr_restart" will always restart
> the
> program from the 1st/earliest checkpoint, which means the subsequent
> checkpoint doesn't take any effect. Especially, it seems I cannot
> checkpoint
> the restarted application, isn't it?
>
> Would you help me?
>
> Thanks!
>
> Yuan
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
--
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/
|
