Re: Stuck TCP sockets in 2.1.1xx SMP
Andi Kleen (ak@muc.de)
Tue, 20 Oct 1998 17:02:59 +0200
On Tue, Oct 20, 1998 at 03:33:29PM +0200, Alex Korobka wrote:
>
> Andi Kleen <ak@muc.de> writes:
> > In article <199810191841.OAA18489@galaxy.ams.sunysb.edu>,
> > Alex Korobka <korobka@galaxy.ams.sunysb.edu> writes:
> > > We have a few dual PII 400 machines (P6DBE boards, eepro100 NICs)
> > > that we'd like to use in a Beowulf-like cluster. However, all recent
> > > kernels have exhibited the same problem, NPB2.3 MPI benchmarks keep
> > > getting stuck waiting for incoming data. This happens only when
> > > there are 2 MPI processes running on the same machine, there are
> > > no problems with one process per machine. This is the output
> > > of netstat -a -t for a job consisting of 8 MPI processes running
> > > on star1, star2, star3, and star4 nodes.
> >
> > Could you define 'all recent kernels'. Was there a version when it started,
> > but in the old one worked?
> >
>
> There was a number of kernels (2.1.3x - 2.1.9x) that didn't boot
> on this hardware. All following releases have had this problem.
> One more thing, three simultaneous NetPIPE processes usually kill
> the machine before the block size gets to 1Mb.
How does this killing look? oops or simple hang? Does the SysRq key still
work? What does Shft-Roll on the console say?
-A.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/