Dual Core CPU on Abit NI8-Board

DISCUSSION Frank von Daak 4 participants 10 messages Apr 5, 2006 – Apr 6, 2006 2 messages not in the archive

lore

Share & tools

lore

Frank von Daak

author

2006-04-05 06:28 UTC #0 lore raw

Hello to all!

I hope that this is the right place for me to report my problem - if not, please tell me!

Some days ago I've purchased a new motherboard, cpu and graphics-adapters. The board is called "Abit NI8 SLI" which has a nForce4-Chipset and a socket 775.

http://www.abit-usa.com/products/mb/products.php?categories=1&model=280

The CPU is a Pentium-D 2,8 GHz. And the graphics-adapters are two GeForce7800GTX-Cards...

My problem is, that a "cat /proc/cpuinfo" shows me just one cpu with one core. I've tested this with kernels 2.6.16.1 and 2.6.17-rc1 (x86 and x86_64)

If I add the following line in my lilo.conf to the kernel, I can see both cpu's:
append="pci=noacpi pci=routeirq noapic acpi=off"

After this my cpuinfo looks like this:
http://www.kpage.de/cpuinfo.txt

and dmesg say's this:
http://www.kpage.de/dmesg.txt

But if I do so, the machine is running very unstable and is hanging after a while. The crashes will happen espacialy if I run OpenGL-Applications like "glxgears".

Can someone of you tell me, what I can do to fix this problem? If you need further information, please tell me!

Thank you very much and greetings!
Frank

Signature · 4 lines

Name:	Frank von Daak
eMail:	[email protected]	Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
    Bob Marley"

[email protected]

2006-04-05 06:39 UTC #1 lore raw

Hi Frank:

This sounds suspiciously to me like those kernels don't have SMP support built in. Are those kernels you built yourself or obtained from your distro?

-Phil/CERisE

Quoted 46 lines · Frank von Daak

Hello to all!
I hope that this is the right place for me to report my problem - if not, please tell me!
Some days ago I've purchased a new motherboard, cpu and graphics-adapters. The board is called "Abit NI8 SLI" which has a nForce4-Chipset and a socket 775.
http://www.abit-usa.com/products/mb/products.php?categories=1&model=280
The CPU is a Pentium-D 2,8 GHz. And the graphics-adapters are two GeForce7800GTX-Cards...
My problem is, that a "cat /proc/cpuinfo" shows me just one cpu with one core. I've tested this with kernels 2.6.16.1 and 2.6.17-rc1 (x86 and x86_64)
If I add the following line in my lilo.conf to the kernel, I can see both cpu's:
append="pci=noacpi pci=routeirq noapic acpi=off"
After this my cpuinfo looks like this:
http://www.kpage.de/cpuinfo.txt
and dmesg say's this:
http://www.kpage.de/dmesg.txt
But if I do so, the machine is running very unstable and is hanging after a while. The crashes will happen espacialy if I run OpenGL-Applications like "glxgears".
Can someone of you tell me, what I can do to fix this problem? If you need further information, please tell me!
Thank you very much and greetings!
Frank
Signature · 8 lines
Name:	Frank von Daak
eMail:	[email protected]	Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
    Bob Marley"
-
To unsubscribe from this list: send the line "unsubscribe linux-smp" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Frank von Daak

author

2006-04-05 07:13 UTC #2 lore raw

Hi!

Am Wednesday, 5. April 2006 08:39 schrieb [email protected]:

Quoted 3 lines

This sounds suspiciously to me like those kernels don't have SMP support built in. Are those kernels you built yourself or obtained from your distro?

I've build them myself with smp-support enabled. I've also tried a debian-smp-kernel with the same behaviour...

Quoted 53 lines · Frank von Daak

Quoted 38 lines
Hello to all!
I hope that this is the right place for me to report my problem - if not, please tell me!
Some days ago I've purchased a new motherboard, cpu and graphics-adapters. The board is called "Abit NI8 SLI" which has a nForce4-Chipset and a socket 775.
http://www.abit-usa.com/products/mb/products.php?categories=1&model=280
The CPU is a Pentium-D 2,8 GHz. And the graphics-adapters are two GeForce7800GTX-Cards...
My problem is, that a "cat /proc/cpuinfo" shows me just one cpu with one core. I've tested this with kernels 2.6.16.1 and 2.6.17-rc1 (x86 and x86_64)
If I add the following line in my lilo.conf to the kernel, I can see both cpu's:
append="pci=noacpi pci=routeirq noapic acpi=off"
After this my cpuinfo looks like this:
http://www.kpage.de/cpuinfo.txt
and dmesg say's this:
http://www.kpage.de/dmesg.txt
But if I do so, the machine is running very unstable and is hanging after a while. The crashes will happen espacialy if I run OpenGL-Applications like "glxgears".
Can someone of you tell me, what I can do to fix this problem? If you need further information, please tell me!
Thank you very much and greetings!
Frank
Quoted 9 lines
--
Name: Frank von Daak
eMail: [email protected] Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
Bob Marley"
-
To unsubscribe from this list: send the line "unsubscribe linux-smp" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
-
To unsubscribe from this list: send the line "unsubscribe linux-smp" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

Signature · 3 lines

--
Frank von Daak
[email protected]

[email protected]

2006-04-05 16:57 UTC #3 lore raw

Quoted 3 lines · Frank von Daak

I've build them myself with smp-support enabled. I've also tried a debian-smp-kernel with the same behaviour...

Well, so much for the easy answer 8)

Quoted 7 lines

Quoted 7 lines
Quoted 7 lines
My problem is, that a "cat /proc/cpuinfo" shows me just one cpu with one core. I've tested this with kernels 2.6.16.1 and 2.6.17-rc1 (x86 and x86_64)
If I add the following line in my lilo.conf to the kernel, I can see both cpu's:
append="pci=noacpi pci=routeirq noapic acpi=off"

Probably the best step to take next is to take another pass through a kernel.
It seems like you have a lot of things built in which aren't necessary to boot (your network card, for example). I generally recommend putting as much as possible into modules so that you can boot with the bare minimum of stuff. If it works that way, you can start slowly adding things and figure out with better granularity what's causing it to freeze.
You'll use a little more memory that way (modules load in on page boundaries,
so one could in theory be wasting n * ($PAGE_SIZE - 1) bytes in loading n modules, but the flexibility is very well worth it when figuring out problems like this.
I have a few prejudices to begin with for your short list of what's causing
the box to die. The first is DRI. The second is one of the NFORCE drivers. The fact that glxgears seems to trigger the problem and that I dislike DRI in general sounds like a good place to start ; )

-Phil/CERisE

A message that is not in the archive (sent off-list or not yet received): [email protected]

Frank von Daak

author

2006-04-05 08:39 UTC #5 lore raw

Hi!

Am Wednesday, 5. April 2006 09:11 schrieb Erk:

Quoted 3 lines

The only thing weird in your boot is those lines:
pcie_portdrv_probe->Dev[007e:10de] has invalid IRQ. Check vendor BIOS could you tell us what you see in /proc/interrupts in this case

This is what "cat /proc/interrupts" and "dmesg" says when I boot the kernel with no options: (append="")
http://www.kpage.de/interruptsacpi.txt
http://www.kpage.de/dmesgacpi.txt

Quoted 2 lines

and could you try with: append="pci=noacpi acpi=off" and see if there is major difference in /proc/interrupts.

Sorry, I can't tell you what it say's, because my machine does not boot with this option's. At the moment the machine is hanging after rebooting with this options and I've no more remote access to it. Because I'm at work now, I can go on in 7 hours...
I've tried some of this options yesterday with almost the same result (system is hanging) - I don't get error messages like a segfault on screen - the machine is just hanging...

Greetings
Frank

Quoted 51 lines

2006/4/5, Frank von Daak <[email protected]>:
Quoted 39 lines
Hello to all!
I hope that this is the right place for me to report my problem - if not, please tell me!
Some days ago I've purchased a new motherboard, cpu and graphics-adapters. The board is called "Abit NI8 SLI" which has a nForce4-Chipset and a socket 775.
http://www.abit-usa.com/products/mb/products.php?categories=1&model=280
The CPU is a Pentium-D 2,8 GHz. And the graphics-adapters are two GeForce7800GTX-Cards...
My problem is, that a "cat /proc/cpuinfo" shows me just one cpu with one core. I've tested this with kernels 2.6.16.1 and 2.6.17-rc1 (x86 and x86_64)
If I add the following line in my lilo.conf to the kernel, I can see both cpu's:
append="pci=noacpi pci=routeirq noapic acpi=off"
After this my cpuinfo looks like this:
http://www.kpage.de/cpuinfo.txt
and dmesg say's this:
http://www.kpage.de/dmesg.txt
But if I do so, the machine is running very unstable and is hanging after a while. The crashes will happen espacialy if I run OpenGL-Applications like "glxgears".
Can someone of you tell me, what I can do to fix this problem? If you need further information, please tell me!
Thank you very much and greetings!
Frank
--
Quoted 8 lines
Name:   Frank von Daak
eMail:  [email protected]      Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
Bob Marley"
-
To unsubscribe from this list: send the line "unsubscribe linux-smp" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Erk

Signature · 3 lines

--
Frank von Daak
[email protected]

Frank von Daak

2006-04-05 09:43 UTC #6 lore raw

ok .. after I've found a way to reboot the machine remote [by my mother :-)] I've tried the following append-line:
append="pci=noacpi pci=routeirq noapic acpi=on"

acpi is now on - but just one cpu :-(

And this is what dmesg and /proc/interrupts say:
http://www.kpage.de/dmesgacpi2.txt
http://www.kpage.de/interrputsacpi2.txt

This is the output when I append the following line (append="pci=noacpi pci=routeirq noapic acpi=off")
http://www.kpage.de/dmesgnoacpi.txt
http://www.kpage.de/interruptsnoacpi.txt

The only problem in this case is that the machine is very unstable on 3D-Action...

any more ideas?

Thank you very much!!!

Am Wednesday, 5. April 2006 10:39 schrieb Frank von Daak:

Quoted 77 lines

Hi!
Am Wednesday, 5. April 2006 09:11 schrieb Erk:
Quoted 3 lines
The only thing weird in your boot is those lines:
pcie_portdrv_probe->Dev[007e:10de] has invalid IRQ. Check vendor BIOS could you tell us what you see in /proc/interrupts in this case
This is what "cat /proc/interrupts" and "dmesg" says when I boot the kernel with no options: (append="")
http://www.kpage.de/interruptsacpi.txt
http://www.kpage.de/dmesgacpi.txt
Quoted 2 lines
and could you try with: append="pci=noacpi acpi=off" and see if there is major difference in /proc/interrupts.
Sorry, I can't tell you what it say's, because my machine does not boot with this option's. At the moment the machine is hanging after rebooting with this options and I've no more remote access to it. Because I'm at work now, I can go on in 7 hours...
I've tried some of this options yesterday with almost the same result (system is hanging) - I don't get error messages like a segfault on screen
- the machine is just hanging...
Greetings
Frank
Quoted 51 lines
2006/4/5, Frank von Daak <[email protected]>:
Quoted 39 lines
Hello to all!
I hope that this is the right place for me to report my problem - if not, please tell me!
Some days ago I've purchased a new motherboard, cpu and graphics-adapters. The board is called "Abit NI8 SLI" which has a nForce4-Chipset and a socket 775.
http://www.abit-usa.com/products/mb/products.php?categories=1&model=280
The CPU is a Pentium-D 2,8 GHz. And the graphics-adapters are two GeForce7800GTX-Cards...
My problem is, that a "cat /proc/cpuinfo" shows me just one cpu with one core. I've tested this with kernels 2.6.16.1 and 2.6.17-rc1 (x86 and x86_64)
If I add the following line in my lilo.conf to the kernel, I can see both cpu's:
append="pci=noacpi pci=routeirq noapic acpi=off"
After this my cpuinfo looks like this:
http://www.kpage.de/cpuinfo.txt
and dmesg say's this:
http://www.kpage.de/dmesg.txt
But if I do so, the machine is running very unstable and is hanging after a while. The crashes will happen espacialy if I run OpenGL-Applications like "glxgears".
Can someone of you tell me, what I can do to fix this problem? If you need further information, please tell me!
Thank you very much and greetings!
Frank
--
Quoted 8 lines
Name:   Frank von Daak
eMail:  [email protected]      Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
Bob Marley"
-
To unsubscribe from this list: send the line "unsubscribe linux-smp" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Erk

Signature · 9 lines

frank von daak.leiter.software entwicklung
.
gingco.new media gmbh
kastanienallee 40
38104 braunschweig
www.gingco.net
 
t +49.(0)531.24492-241
f +49.(0)531.24492-29

A message that is not in the archive (sent off-list or not yet received): [email protected]

Frank von Daak

author

2006-04-05 12:05 UTC #8 lore raw

Am Wednesday, 5. April 2006 12:15 schrieben Sie:

Quoted 7 lines

Quoted 3 lines
The only problem in this case is that the machine is very unstable on 3D-Action...
any more ideas?
You get IRQ sharing for you video adpaters in this last case:
7: 5178 0 XT-PIC ohci_hcd:usb3, nvidia, nvidia
Those video cards are on PCI-Express bus?
With the "NVidia SLI" etc...

yes and no :-}
I've attached the two cards in SLI-Mode to the board. This means that I've placed the chip for SLI-Mode (you can see the red chip on this image between the two pcie-slots:
http://www.etech4sale.com/images/0146000_0146999/146929_h.jpg)

This must be done, to run both pcie-slots in 16x mode. If not, only one slot is 16x the other is 1x.
And I've connected both cards with a SLI-bridge - but:
I don't run use the SLI mode in linux!

I'm running a flightsim (x-plane) and have connected three monitors. Because a normal graphics-adapter can handle just 2 monitors there was the need for two graphics-adapters.
And they are running fine, if I don't append anything in my lilo.conf! But I can use just on one cpu-core :-(
I'm not sure if this is realy a problem with the x-server, or?

But I'm really unsure: whats my problem? SMP or Nvidia?

Quoted 1 line

You're welcome since my last message just hang your machine :))

hehe - that's really no problem!!!

Greetings
Frank

Signature · 3 lines

--
Frank von Daak
[email protected]

Frank von Daak

author

2006-04-06 06:27 UTC #9 lore raw

Hi!

I'ld like to sum up, what I've tried to solve my smp(?)-problem:

- I've bootet my vanilla 2.6.17-rc1 kernel with the following options appended in "lilo.conf":
1. noapic
2. pci=noacpi
3. pci=biosirq
4. pci=routeirq
5. pci=conf1
6. acpi=off

and I've tried to combine most of the options together. (very much reboots as you can believe :-})

- I've started my x-server with just one geforce card.
- I've disconnected the SLI-bridge from my card and put the board into normal (not sli)-mode. (In this case the board has one 16xPCIe and one 1XPCIe-Slot. In the other case it hase two 16XPCIe-slots, and the gra.-cards are sharing one irq)
- I've removed PREEMPT from the kernel
- I've tried kernel 2.6.16.1 and installed a 64Bit Debian with 2.6.15
- I've removed the usb-module so that the graphics-adapters don't have to share an irq with usb
- I've upgraded my motherboard-bios to the latest version
- I've tried some different bios-settings (low cpuid for example)
- I've contacted nvidia - they also have not heard about this problem

The result was always the same:
If I start the kernel with ACPI the system is running rock solid, but I have just one cpu-core.
If I start with disabled ACPI the system is hard-crashing after a short while. (Sometimes it is crashing without starting an OpenGL-app!)

So I have no more ideas at the moment...
Should I go and buy a new motherboard?

Greetings
Frank

Signature · 4 lines

Name:	Frank von Daak
eMail:	[email protected]	Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
    Bob Marley"

Frank von Daak

author

2006-04-06 20:39 UTC #10 lore raw

Hi!

After another day of debugging my "smp-problem" I've enabled ACPI-debugging in kernel.
Maybe someone of you can take a look at dmesg's output and interpret the messages:
http://www.kpage.de/dmesg_acpi3.txt

I think the following messages tell something about my problem:
acpi_processor-0495 [06] processor_get_info : Error getting cpuindex for acpiid 0x1

Greetings
Frank

Signature · 4 lines

Name:	Frank von Daak
eMail:	[email protected]	Homepage: http://www.kpage.de
"It takes a revolution, to make a solution!
    Bob Marley"

Randy.Dunlap

2006-04-06 20:58 UTC #11 lore raw

Quoted 11 lines · On Thu, 6 Apr 2006 22:39:04 +0200 Frank von Daak wrote:

Hi!
After another day of debugging my "smp-problem" I've enabled ACPI-debugging in kernel.
Maybe someone of you can take a look at dmesg's output and interpret the messages:
http://www.kpage.de/dmesg_acpi3.txt
I think the following messages tell something about my problem:
acpi_processor-0495 [06] processor_get_info : Error getting cpuindex for acpiid 0x1

I suggest that you ping the acpi development list about this:
[email protected]

You'll probably need to provide the ACPI firmware tables from your computer. Use pmtools (acpidump) to do that. If you don't have them installed already, you can get them here:
http://www.kernel.org/pub/linux/kernel/people/lenb/acpi/utils/
Grab the latest pmtools tarball.

---
~Randy