jcduell_at_lbl_dot_gov
Date: Thu May 20 2004 - 16:47:33 PDT
On Wed, May 12, 2004 at 11:08:18AM -0700, Thomas Davis wrote:
> 1) how does one subscribe to the mailing list?
Send an email to
Majordomo_at_lbl_dot_gov
with
subscribe checkpoint_at_lbl_dot_gov
I'm not the list admin, but I think that should do it. If not, let me
know and I'll track it down.
> 2) The last version doesn't work right on alvarez.
>
> I can checkpoint some programs, but LAM/MPI seems broken.. I did recompile
> everything, so I'm not sure how to start debugging this.
Are you trying to checkpoint GM- or TCP-based LAM programs? LAM isn't
shipping a version yet where GM-based MPI programs work with
checkpointing. If it's TCP, could you tell me what you see (if
anything) when you try to checkpoint things?
If you give me 'sudo insmod/rmmod' on some node on alvarez, I can look
into this for you.
Thanks,
--
Jason Duell Future Technologies Group
<jcduell_at_lbl_dot_gov> Computational Research Division
Tel: +1-510-495-2354 Lawrence Berkeley National Laboratory