Subject: Re: poor network performance on de0's on 21164's.
To: Andrew Gillham <gillhaa@ghost.whirlpool.com>
From: Paul H. Anderson <pha@pdq.com>
List: port-alpha
Date: 07/11/1999 23:27:43
On Sun, 11 Jul 1999, Andrew Gillham wrote:
> I wish I had this setup.. :) Have you tried to use ttcp for this testing?
> >From a NetBSD/i386 (Celeron) to a NetBSD/i386 (PPro200) I get great
> full duplex performance.
I'd be happy for anything over 100KB/second in any duplex. We do get
1MB/second or so when we use 10baseT cards.
> > we've got 10 164LX rackmount boxes that we are trying to use as a
> > supercompter cluster - they all show the same behavior very consistently.
> > This makes our cluster worth approximately nothing to us, and it is
> > getting extremely frustrating.
>
> Bummer, nice hardware though. :-) The PCI DMA bug mentioned might be
> worth looking into.
Where we can start? Would Jason have ideas? It would also be real nice
if someone else running similar hardware could duplicate the problem.
> > Again, any suggestions what we might try would be greatly welcome. If it
> > comes down to it, I'll ship some of these mothers somewhere if that will
> > help (or work with someone remotely). Their next stop is pretty much the
> > dumpster.
>
> Uhmm, #define dumpster ( Andrew's Truck << From SouthWest Michigan)
> :=)
I'm more likely, actually, to dump the motherboards, and see if I can find
intel dual processor boards that can work with slow memory. I spent more
than $30K buying 1GB apiece for these critters, which is the bulk of my
investment.
> Have you tried any (ahem) other OSes? If would be interesting to know
> if this is a NetBSD issue. (e.g. other OSes workaround a hardware bug?)
We're trying RH Linux 6.0 now, and due to some interesting installation
problems, have yet tested it. Hopefully we will tomorrow morning (right
mike?) We'll also re-install Digital Unix, True Unix, or whatever it is
called today. I may even install winblows NT and see what it does.
Thanks for the advice, gang... still need to see if someone else is able
to replicate the problem.
Paul
+------------------------------------------------------+
| Paul Anderson Public Data Queries, Inc. |
| pha@pdq.com 734-213-4964(W) 994-3734(H) |
+------------------------------------------------------+