Re: 2.0.33 on redhat 4.2

Tad Kollar (tkollar@anduin.lerc.nasa.gov)
Thu, 8 Jan 1998 11:47:13 -0500 (EST)

I don't think its a problem with redhat, I have quad ppro systems running
Debian 1.3.1 and I've had the same error with 2.0.3[123] kernels.
Unfortunately earlier kernels don't seem to be able to support Adaptec
2940W's with the amount of RAM in these systems (1024M). So I use development
kernels, which I would actually prefer except that Xig's CDE 1.1 doesn't run
on them...

-Tad

> I tried brining up 2.0.33 on a quad pentinum pro in SMP mode and
> I got the following error messages early into the booting sequence.
> Somewhere during the run level 5 initializtion sequence.
>
> Attempted flush tlb IPI when not AKP(=1)
> IRQ DEADLOCK DETECTED BY CPU 0
> IRQ DEADLOCK DETECTED BY CPU 1
> IRQ DEADLOCK DETECTED BY CPU 2
>
> Is there some SMP patches I need to add to the kernel in order for
> it to run SMP that redhat supplies? I have not tried the 2.0.32
> kernel as supplied by redhat in the hurricane update area for
> i386. I'm currently running redhat 4.2 and the 2.0.30 kernel
> seems to be stable on the 2 week time scale. The error above
> occures very quickly, as I said while executing the inittab level
> 5 initalizition stuff.
>
> stephen.adler@bnl.gov
> 

-- 
-------------------------------------------------------------------------
Thaddeus J. Kollar                             | 
Sterling Software, Scientific Systems Division | "Evildoers, eat my
NASA Lewis Research Center                     |  justice!!!" - The Tick
Tel: 216-433-5105  Fax: 216-433-8000           |
-------------------------------------------------------------------------