Re: [BProc] Fedora Core 2 (2.6.5), bproc-4.0.0pre4 and lam-7.1a1r9667

[Daniel G. <dg...@ti...>]

On Wed, Jun 09, 2004 at 03:23:32PM -0700, Brian Barrett wrote:
> On Jun 9, 2004, at 3:15 PM, Daniel Gruner wrote:
> 
> > I managed to build the latest version, including patches, on my bproc 4
> > cluster.  It is made of Alpha machines, and I configured lam to use the
> > "fort" compiler (the Compaq fortran compiler).  It build without any
> > apparent issues, and installed fine.  Now, when I try to lamboot, it
> > dumps core!
> 
> Yeah, I reused a variable when I shouldn't have (stupid Brian).  Thanks 
> to Kevin Russell for pointing this out to me.  I've attached v2 of the 
> patch and a diff from v1 to v2, which should clean up the segfault.   
> This was on a BProc-4 cluster, correct?
> 

Yes, it is a BProc-4 cluster.  I rebuilt lam with your latest patch, and
while it doesn't dump core anymore, it still doesn't lamboot.  The error
message is:

racaille:dgruner{124}> lamboot bhost

LAM 7.1a1svn/MPI 2 C++/ROMIO/bproc - Indiana University

-----------------------------------------------------------------------------
LAM has detected that one or more nodes specified in the boot schema
are not available, and has aborted.  Bproc is reporting that the
following nodes are not up:

192.168.101.1
192.168.101.100
192.168.101.101
192.168.101.102
192.168.101.103
192.168.101.104
192.168.101.105
-----------------------------------------------------------------------------

I have tried with node names in the bhost file, as well as with numeric 
ip addresses, and got the same message.  The nodes are in fact up, and 
the cluster works properly.

???

Daniel


-- 

Dr. Daniel Gruner                        dg...@ti...
Dept. of Chemistry                       dan...@ut...
University of Toronto                    phone:  (416)-978-8689
80 St. George Street                     fax:    (416)-978-5325
Toronto, ON  M5S 3H6, Canada             finger for PGP public key