[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: reiserfs empirical study (very long)



When I asked if you had tried the system with smp off, I meant, did you
try
it with it off and did the system stop crashing? It was just an idea for
narrowing down the problem (like it might not necessarily be an smp
issue).

Sorry for not being mnore clear on that.

-Cameron

On Thu, 31 May 2001, Peter Cordes wrote:

> On Wed, May 30, 2001 at 04:50:57PM +0000, Cameron Berkenpas wrote:
> > I thought you might find this info relevant.
> > 
> > I'm running a starmax 4000/200 with 80 megs of ram and a 200 mhz 604e.
> > I also run kernel 2.4.4-pre6 and I've been up for 9 days now.
> > Before this, I was up for about 25 days. I rebooted when I rebuilt my
> > kernel to upgrade as well as to add in a feature I wanted. 
> > 
> > So far the 2.4 series has been rather stable for me for pc and ppc (I just
> > have a hard time building a working kernel on ppc). I've never had an
> > unexplained crash
> > (that is, when I can build a 2.4 kernel that boots.). In fact, now that I
> > think about it, I don't think I've ever had a crash, using 2.2 or 2.4..
> 
>  I've seen lots of crashes with SMP.  I think the worst was the most recent
> benh kernel (2.4.5-pre3) I tried the other day.  It hung before the
> filesystem even got mounted read-write!  The benh kernel I tried before that
> was not so unstable.  The most stable SMP kernel I've found yet is
> 2.4.3-pre2 from the bk tree.  It doesn't crash very often (but it does
> crash, especially if I leave it running a distributed.net client on all four
> CPUs).  OTOH, it's been up for at least three days in a row, and I've build
> XFree86 from CVS source on it without a single crash.  maybe dnetc overheats
> it...
> 
>  Anyway, Ben H., if you're listening, your 2.4.5-pre3 crashes a lot more
> than previous kernels (e.g. 2.4.4 from your tree, or 2.4.4-pre1 or -pre3
> from the bk tree) on my quad PPC604 machine.  I haven't had time to do much
> hacking to try to figure out why.  2.4.3-pre2 from the bk tree was more
> stable than most.
> 
>  If gcc has anything to do with it, then I my relatively stable
> 2.95.3-pre3-bk was compiled with gcc 2.95.3 20010219 (prerelease).  Later
> kernel were compiled with the current gcc from debian unstable at the time.
> (but not gcc 3.0)
> 
> > So I don't know why you've had trouble. Have you tried using a 2.4 kernel
> > without smp on?
> 
>  If I have to run without SMP, I might as well leave the machine turned off
> (saving about 200W of power!), and use one of my x86 machines that are
> faster than a single PPC604 @150MHz.  I have tried UP mode briefly, and
> I think it was ok.
> 
> 
> > I'm using ext2fs BTW.
> 
>  Me too.  I think I'll move to ReiserFS, since I'm not going to put much
> valuable data on the machine until it stops crashing all the time.  Andrew's
> point that the rest of the kernel is a lot more unstable than Reiser is good.
> 
> 
> -- 
> #define X(x,y) x##y
> Peter Cordes ;  e-mail: X(peter@llama.nslug. , ns.ca)
> 
> "The gods confound the man who first found out how to distinguish the hours!
>  Confound him, too, who in this place set up a sundial, to cut and hack
>  my day so wretchedly into small pieces!" -- Plautus, 200 BCE
> 
> 
> --  
> To UNSUBSCRIBE, email to debian-powerpc-request@lists.debian.org
> with a subject of "unsubscribe". Trouble? Contact listmaster@lists.debian.org
> 
> 



Reply to: