Re: SMP on SS10 with 2.4
Hi again
I've done some more experiments:
I have two 64meg and two 32meg modules in my ss10.
If I put in only one module, 2.4.20rc2 works fine.
If I put in the two 64meg modules, 2.4.20rc2 works nearly well. First the
modules have to be in the right slots (see sun homepage). Second there are
some moments the system sleeps for about 10 seconds. I could not yet
determine what causes this stops besides the fact, that it is a
memory-related problem (what a surprise ;) )
If I put in all four modules, I get where I was before - nothing works.
Besides this I noticed some strange differences between 2.4.20rc2 and
2.2.21 (both smp):
- With two 64meg modules, 2.2.21 counts about 127meg, 2.4.20rc2 counts
about 124meg. I did not know that the kernel version does have an affect
on the installed memory ;)
- With 2.2.21 the dual hyperSparc at 125Mhz produces about 125bogomips per
cpu, with 2.4.20rc2 it produces about 109bogomips. This decrease in
doing
nothing has been observed before on suse-sparc.
If I calculate 2^100000 with bc, there is no time difference for the two
kernels. This probably does not mean anything, I just wanted to see if I
can prove this in an easy way.
Can someone reproduce similar problems (Hartwig?)?
Is there a sparc-kernel-mailing-list or is lkml the place for such
problems?
Did I something that I should not on sparc? I'm sparc-newbie...
Thanks
Emanuel
On Sat, 23 Nov 2002 03:39:12 +0100
Hartwig.Atrops@t-online.de (Hartwig Atrops) wrote:
> Hi.
>
> Some comments.
>
> On Saturday 23 November 2002 02:46, you wrote:
> > rehi
> >
> > > I use 2.4.18 on my SS20 (2 Ross Hypersparc 125 MHz, 196 MB).
> > > Sometimes (not very often) the machine freezes for a while when X is
> > > starting during the boot process (network alive at that moment). But
> > > overall, it works fine.
> >
> > so cpu and openprom can't be the problem... nice to know
> >
> I startetd my SS20 a few minutues ago. This time it was hanging again
> after most of the startup stuff had been done. Only X was missing -
> network was already up. A simple ping from another machine solved the
> problem.
>
> > > Hmm. I recently baught a VSIMM for the onboard high resolution
> > > graphics. With that module installed, I have the same problem:
> > > everything ok in the beginning, but when init starts ...
> > >
> > > When I remove the module and connect the monitor to the SBUS
> > > graphics, the SS20 works fine again. And when I remove the SBUS card
> > > and install the VSIMM, I get an SBUS error when init should start.
> > >
> > > Which graphics on your SS10? Might that be a hint?
> >
> > there is no graphic in my SS10... serial console is enough ;)
> > and i tried with all sbus cards removed, so they should not be the
> > problem...
> > on the other hand... could it be that a framebuffer solves my problem?
> > got to try that tomorrow...
> >
> Hmm, I don't think so, the problem showed up as I installed the second
> one ...
>
> > thanks for your answer!
> > emanuel
>
> After thinking a little bit more, it seems to me that I mixed up two
> different problems - showing up at different times. The startx hang
> occures quite seldomly, and only since I installed the second CPU (with
> kernel recompile, smp support). The hang at init start is reproducable,
> I only have to plug in the Video SIMM Module.
>
> I have to do a little bit more testing, but I have a problem: at the
> moment, the SS20 is my main workstation at home. If I kill that machine,
> my mail account is down 'till I have another machine up and running.
> Therefor I stopped any experiments with the VSIMM module - at least for
> some weeks.
>
> If you have any information about the problem(s), please keep me
> informed. So will I.
>
> Regards,
>
> Hartwig
>
>
>
Reply to: