NForce2 pseudoscience stability testing (2.6.0-test11)
Sorry, should've sent this CC'd to list first time (time to make some more coffee :)
-------- Original Message --------
Subject: Re: NForce2 pseudoscience stability testing (2.6.0-test11)
Date: Thu, 04 Dec 2003 12:38:21 +0000
From: Dan Creswell <[email protected]>
To: [email protected]
References: <[email protected]>
Quoted 4 lines · [email protected] wrote:
Dan Creswell wrote:
Thanks for the input, I'll pass it to the list.
You're welcome.
Quoted 3 lines
Most of these Athlon victims are UP users, in fact, I believe they are exclusively UP. Does MPS 1.1/1.4 play a role in a UP system ever? I dont think the NForce2 chipset,
No, MPS shouldn't matter on a UP system.
Quoted 7 lines
where we are seeing these hard hangs (no ping, no screen, no blinking cursor, no toggling the caps lock, nothing) is capable of SMP operation.
Now whats interesting is you finger the IDE as a potential culprit and think its very low level. Interesting.
Well, I actually finger heavy duty disk access - my system locks under *SCSI* load (via a PCI-card - the motherboard doesn't have built in SCSI), I've not had it happen with my CDROM which is on the IDE subsystem. This leads me to my conclusion in respect of interrupt load. It seems to be an issue with simultaneous interrupts from another source but that's subjective......
Quoted 4 lines
By the way, I've had trouble with SMP on a Tyan board with an i840 chipset with Linux before - I was never able to resolve the issue and had to return the board.
Interesting - I've had a number of Tyan boards and this is the first one I've had any issues with. What bugs me more is that 2.4 seems fine (caveat 2.4.23-rc5 - wondering if the ACPI changes here are back-ported from 2.6) whilst 2.6 is horrid. This is the only thing changing in the system which implies that something different goes on in 2.6 from 2.4 and that it break's things. Now it could be 2.6 is using some additional features - but the problem (once located) would be simply removed by providing an "off" switch to stop usage of those features.
Quoted 5 lines
I've beaten on an Intel SR1300 and SR2300 dual Xeon (aka Micron's Netframe 1610/2610 aka Sun 60x / 65x) and never run into these hangs with kernels up to 2.4.22. The motherboard is an Intel SE7501WV2 .
Okay - well my Tyan also runs on kernels up to 2.4.22 no problem - useful information though.
Thanks,
Dan.