Jeff,
I just realized how the code is not working the first node name is wolf0
which may be throwing the padding off.
Robert LeBlanc
BioAg Computer Support
Brigham Young University
-----Original Message-----
From: lam-bounces_at_[hidden] [mailto:lam-bounces_at_[hidden]] On Behalf Of
Jeff Squyres
Sent: Saturday, July 23, 2005 7:16 AM
To: General LAM/MPI mailing list
Subject: Re: LAM: Slurm boot module woes again
Arrgh. Apparently, I'm incapable of writing simple string-parsing code.
I've committed fixes so this (the code is now a bunch simpler, and does
what it should have been doing from the beginning).
Tomorrow morning's nightly tarball should contain the fix, and I'll
roll another beta right now (I think there were a small number of fixes
not in b22). b23 should be up on the web site in the next few hours.
On Jul 22, 2005, at 5:39 PM, Robert LeBlanc wrote:
>
> Dear experts,
> I’m running into problems again with the hostname section of LAM
> with the SLURM boot SSI. On our big cluster the nodes are named
> beast[01-65] and node beast10 is padded with an extra zero (beast010).
> I’ve installed the nightly tar ball onto a smaller cluster wolf[0-3]
> and all the names are being padded (wolf00). I’m going to look through
> the source again, but I guess I wasn’t as successful as I hoped the
> last time. Anyone familiar with the code like to take a look at it?
>
> Thanks,
> Robert LeBlanc
> BioAg Computer Support
> Brigham Young University
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
--
{+} Jeff Squyres
{+} jsquyres_at_[hidden]
{+} http://www.lam-mpi.org/
_______________________________________________
This list is archived at http://www.lam-mpi.org/MailArchives/lam/
|
