Catching NForce2 lockup with NMI watchdog - found?
Quoted 2 lines · Craig Bradney
All the interrupts are the same...except:
0, timer is now IO-APIC-edge.
Same here...
Quoted 1 line
Im not getting any NMI counts.. should I use nmi-watchdog=1?
I got nmi counts with nmi_watchdog=2... I never tested with =1... if you get nmi's 1 lemme know.
Quoted 2 lines
Ian, from looking back, you have an A7N8X-X bios 1007. Interesting that my USB hcis are still sharing IRQs there.
Your? i only see one... But you share it with sound and eth0...
Quoted 1 line
Any idea how I can get them apart, or if I should try.
You could always move eth0 to a different slot. Other than that, you can do manual config for the irq's in the bios, but it shouldn't be needed...
Quoted 2 lines
My system was pretty stable as I've stated.. but the patch has changed things slightly re the timer.
As i stated in my prev email, i had to do 2 full greps at a sizable amount of data to recreate the crash... =P
And, please CC since i'm not on this ml =P
Signature · 1 line
Ian Kumlien <[email protected]>
Quoted 14 lines · Ian Kumlien
Quoted 2 lines · Craig Bradney
All the interrupts are the same...except:
0, timer is now IO-APIC-edge.Same here...
Quoted 1 line
Im not getting any NMI counts.. should I use nmi-watchdog=1?
I got nmi counts with nmi_watchdog=2... I never tested with =1... if you get nmi's 1 lemme know.
Quoted 2 lines
Ian, from looking back, you have an A7N8X-X bios 1007. Interesting that my USB hcis are still sharing IRQs there.
Quoted 7 lines
Your? i only see one... But you share it with sound and eth0...
Quoted 1 line
Any idea how I can get them apart, or if I should try.
You could always move eth0 to a different slot. Other than that, you can do manual config for the irq's in the bios, but it shouldn't be needed...
eth0 is the 3com onboard on the a7n8x deluxe...
Quoted 7 lines
Quoted 2 lines
My system was pretty stable as I've stated.. but the patch has changed things slightly re the timer.
As i stated in my prev email, i had to do 2 full greps at a sizable amount of data to recreate the crash... =P
And, please CC since i'm not on this ml =P
Having finally woken up (me not the pc), uptime here is now 12 hours.. (without the CPU Disconnect athcool run, just the kernel patch). I did run the athcool program to check the result though:
nVIDIA nForce2 (10de 01e0) found
'Halt Disconnect and Stop Grant Disconnect' bit is enabled.
Do others have the same value 10de 01e0 when they run athcool stat? Even with the same motherboard (a7n8x deluxe)?
Im running a grep -R kernel /usr/* and another grep on my 4gb DVD and compiling a Qt 3.2.3 upgrade now.
For me idle time never seemed to be a problem which I guess relates to the CPU Disconnect on low usage/low power issue
Perhaps my motherboard and cpu doesnt have a problem with disconnect and just the IRQ issue, perhaps because its only a few weeks old. It would make sense in some ways given that my system has only one of the problems given the uptime I have been able to reach.
My hangs have always been when I have used the PC.. and often completed a task and then a few seconds later it goes.
Will see in time I guess
Craig
Quoted 5 lines · Craig Bradney
nVIDIA nForce2 (10de 01e0) found
'Halt Disconnect and Stop Grant Disconnect' bit is enabled.Do others have the same value 10de 01e0 when they run athcool stat? Even with the same motherboard (a7n8x deluxe)?
Yes.
0x10de is a PCI VendorID (nVidia).0x01e0 is a PCI DeviceID (nForce2).
;-)
--bart
Quoted 6 lines · Craig Bradney
Quoted 3 lines · Ian Kumlien
You could always move eth0 to a different slot. Other than that, you can do manual config for the irq's in the bios, but it shouldn't be needed...
eth0 is the 3com onboard on the a7n8x deluxe...
I find that so odd... My on board network controller is a realtec phys controlled by a nvidia mac. Same goes for audio.
Quoted 6 lines
Having finally woken up (me not the pc), uptime here is now 12 hours.. (without the CPU Disconnect athcool run, just the kernel patch). I did run the athcool program to check the result though:
nVIDIA nForce2 (10de 01e0) found
'Halt Disconnect and Stop Grant Disconnect' bit is enabled.
nVIDIA nForce2 (10de 01e0) found
'Halt Disconnect and Stop Grant Disconnect' bit is enabled.
Quoted 4 lines
Perhaps my motherboard and cpu doesnt have a problem with disconnect and just the IRQ issue, perhaps because its only a few weeks old. It would make sense in some ways given that my system has only one of the problems given the uptime I have been able to reach.
Mine is 2 weeks old or so..
Quoted 2 lines
My hangs have always been when I have used the PC.. and often completed a task and then a few seconds later it goes.
Mine always seems to hang after a certain amount of time... When id didn't do a grep in the kernel lib.
Btw, i have UDMA100 disks.. 2 disks on primary and 2 cdroms on secondary... I dunno if this could make any difference..
Quoted 1 line
Will see in time I guess
Good luck =)
Signature · 1 line
Ian Kumlien <pomac () vapor ! com> -- http://pomac.netswarm.net
Quoted 10 lines · Ian Kumlien
Quoted 6 lines · Craig Bradney
Quoted 3 lines · Ian Kumlien
You could always move eth0 to a different slot. Other than that, you can do manual config for the irq's in the bios, but it shouldn't be needed...
eth0 is the 3com onboard on the a7n8x deluxe...
I find that so odd... My on board network controller is a realtec phys controlled by a nvidia mac. Same goes for audio.
Yes.. maybe if I was using the onboard nvidia nic it would not share.. Not sure.
Quoted 10 lines
Quoted 7 lines
Having finally woken up (me not the pc), uptime here is now 12 hours.. (without the CPU Disconnect athcool run, just the kernel patch). I did run the athcool program to check the result though:
nVIDIA nForce2 (10de 01e0) found
'Halt Disconnect and Stop Grant Disconnect' bit is enabled.nVIDIA nForce2 (10de 01e0) found
'Halt Disconnect and Stop Grant Disconnect' bit is enabled.
Its a pity that as Bart said, those numbers dont reflect any sort of revision as that might lead to a conclusion about why it happens on some and not others.
Quoted 5 lines
Quoted 4 lines
Perhaps my motherboard and cpu doesnt have a problem with disconnect and just the IRQ issue, perhaps because its only a few weeks old. It would make sense in some ways given that my system has only one of the problems given the uptime I have been able to reach.
Quoted 7 lines
Mine is 2 weeks old or so..
Quoted 2 lines
My hangs have always been when I have used the PC.. and often completed a task and then a few seconds later it goes.
Mine always seems to hang after a certain amount of time... When id didn't do a grep in the kernel lib.
I've just come hom to find my grep -R a /usr/* and my 4gb dvd grep have completed correctly... 14 hours uptime now.
Quoted 2 lines
Btw, i have UDMA100 disks.. 2 disks on primary and 2 cdroms on secondary... I dunno if this could make any difference..
1 ata133 primary master and dvdrw and cdrom on secondary here.
Quoted 3 lines
Quoted 1 line
Will see in time I guess
Good luck =)
You too :)
Craig
Quoted 4 lines · Craig Bradney
On Sat, 2003-12-06 at 15:42, Ian Kumlien wrote:
Its a pity that as Bart said, those numbers dont reflect any sort of revision as that might lead to a conclusion about why it happens on some and not others.
Yeah i saw that aswell...
Quoted 4 lines
Quoted 2 lines
Btw, i have UDMA100 disks.. 2 disks on primary and 2 cdroms on secondary... I dunno if this could make any difference..
1 ata133 primary master and dvdrw and cdrom on secondary here.
I'm just wondering if it could be a relation to the disk aswell or so..
Quoted 3 lines
Quoted 1 line
Good luck =)
You too :)
Heh, thanks =)
Now, about this ACPI powersave thing, wouldn't that be enabled in windows aswell? So wouldn't this workaround be something that $other_os doesn't have to do.
(In general i have always had to hack windows into not crashing when linux worked and doing it the other way around without a real fix dosn't sound that nice in my ears.. =P)
It would be interesting to hear from nvidia about nmi_watchdog... Since nmi_watchdog with the 'not-done-correctly' APIC patch claims that nmi is stalled/locked/doesn't work... If nvidia states that this *should* work, then we have something to go on.
Also, if Allen Martin (nvidia) could go trough the proc/interrupts and tell us if something is wrong, like the XT-PIC on timer. Or just give us a correct listing, since noone had io-apic-edge on timer before afair.
Signature · 1 line
Ian Kumlien <pomac () vapor ! com> -- http://pomac.netswarm.net