Native preemption is the culprit [was Re: today's CURRENT lockups]

[Arjan van Leeuwen]

On Mon, 12 Jul 2004 21:07:16 +0200, Ulrich Spoerlein <q at uni.de> wrote:

> On Sat, 10.07.2004 at 15:06:20 +0800, Ariff Abdullah wrote:
>> I'm suspecting bad combination between threaded apps and current
>> native preemption, either the preemption itself, or threads. Running
>> current kernel without any threaded apps turns up nothing suspicious.
>> Once the threaded apps started, it's like sending the entire system to
>> the death row.
>>
>> I'm reverting following files to pre-July 2 to achive solid stability:
>>
>>  sys/sys/interrupt.h          - v1.27
>>  sys/kern/kern_intr.c         - v1.110
>>  sys/i386/i386/intr_machdep.c - v1.6
>>  sys/kern/sched_ule.c         - v1.109
>
> I tried to upgrade my kernel from 5.2.1 to -CURRENT and cvsupped
> post-preemption. Running a UP-Kernel on a UP-Machine with either
> SCHED_ULE or SCHED_BSD froze the machine under heavy load. It doesn't
> survive a buildworld or a medium port-build.

Same here.

>
> I tried the revisions above and the machine no longer freezes under
> load, but does an instant reboot :(
>
> Is the machine expected to crash/freeze when running a -CURRENT kernel
> on a 5.2R userland? I don't wanna installworld unless I get a rock-solid
> kernel, that's in sync with it.

This is with an up-to-date world.

Arjan


-- 
Using Opera's revolutionary e-mail client: http://www.opera.com/m2/