On Thu, Oct 14, 1999 at 11:17:52PM +0100, Alan Cox wrote:
> > Btw. I tried reproducing the IPI TLB timeout on my system, the way
> > I could usually reliably trigger it (by copying a few GB from one
> > RAID to another while doing CPU intensive stuff), and failed.
> > This was with 2.2.13pre16. I could reliably trigger it under 2.2.7
> > (AFAIR).
>
> We fixed specific cases that could cause problems. Thebig one was a bug in
> the real time signal delivery. This normally showed up running very large
> gimp processes under glibc 2.1
Darn... So the RT signal delivery could cause the IPI TLB timeout ?? I don't
understand that, but then again, I'm probably not meant to ;)
Anyways, good to hear!
But AFAIK the RT signal queue delivery stuff wasn't fixed until pre17, and I
have a perfectly well functioning pre16 here, with the IPI timeout gone.
I guess something went in at sometime between .7 and .13pre16 that fixed
the problem in my case.
Seems like I won't have to boot good'ol .7 again.
................................................................
: [EMAIL PROTECTED] : And I see the elder races, :
:.........................: putrid forms of man :
: Jakob �stergaard : See him rise and claim the earth, :
: OZ9ABN : his downfall is at hand. :
:.........................:............{Konkhra}...............:
-
Linux SMP list: FIRST see FAQ at http://www.irisa.fr/prive/mentre/smp-faq/
To Unsubscribe: send "unsubscribe linux-smp" to [EMAIL PROTECTED]
