Skip to contentSkip to conversation

nmi errors?

DISCUSSION Robert L. Harris 3 participants 6 messages Sep 3, 2003 – Sep 4, 2003

lore
Share & tools
lore
#0 lore raw

Can anyone tell me what this is?

16:00:09 mailserver kernel: Uhhuh. NMI received for unknown reason 31. 16:00:09 mailserver kernel: Dazed and confused, but trying to continue 16:00:09 mailserver kernel: Do you have a strange power saving mode enabled? 16:00:34 mailserver kernel: Uhhuh. NMI received for unknown reason 21. 16:00:34 mailserver kernel: Dazed and confused, but trying to continue

A coworker put a script on a server which loads up quite afew arrays with pre-set values and then compares the values against arrays. As soon as he kicked off the script I got alot of these in my log files. Not much longer and the machine crashed hard.

Quad proc P3-550
16Gigs of RAM
Kernel: 2.4.22-rc2-ac3

CONFIG_HIGHMEM64G=y
CONFIG_HIGHMEM=y

Anyone have any thoughts or know what this means? Do I have a HIGHMEM problem?

:wq!
---------------------------------------------------------------------------
Robert L. Harris | GPG Key ID: E344DA3B

                                         @ x-hkp://pgp.mit.edu

DISCLAIMER:
These are MY OPINIONS ALONE. I speak for no-one else.

Life is not a destination, it's a journey.
Microsoft produces 15 car pileups on the highway.
Don't stop traffic to stand and gawk at the tragedy.

#1 lore raw
Quoted 10 lines · Robert L. Harris

Can anyone tell me what this is?

16:00:09 mailserver kernel: Uhhuh. NMI received for unknown reason 31. 16:00:09 mailserver kernel: Dazed and confused, but trying to continue 16:00:09 mailserver kernel: Do you have a strange power saving mode enabled? 16:00:34 mailserver kernel: Uhhuh. NMI received for unknown reason 21. 16:00:34 mailserver kernel: Dazed and confused, but trying to continue

Quoted 5 lines

A coworker put a script on a server which loads up quite afew arrays with pre-set values and then compares the values against arrays. As soon as he kicked off the script I got alot of these in my log files. Not much longer and the machine crashed hard.

Possible bad RAM.

Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (794.73 BogoMips).
Note 96.31% of all statistics are fiction.

#2 lore raw

We ran "memtest" on the machine over the weekend and it completed 3 times without any problems. Know a better or different test?

Thus spake Richard B. Johnson ([email protected]):

Quoted 18 lines · Robert L. Harris
Quoted 11 lines

Can anyone tell me what this is?

16:00:09 mailserver kernel: Uhhuh. NMI received for unknown reason 31. 16:00:09 mailserver kernel: Dazed and confused, but trying to continue 16:00:09 mailserver kernel: Do you have a strange power saving mode enabled? 16:00:34 mailserver kernel: Uhhuh. NMI received for unknown reason 21. 16:00:34 mailserver kernel: Dazed and confused, but trying to continue

Quoted 5 lines

A coworker put a script on a server which loads up quite afew arrays with pre-set values and then compares the values against arrays. As soon as he kicked off the script I got alot of these in my log files. Not much longer and the machine crashed hard.

Quoted 7 lines

Possible bad RAM.

Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (794.73 BogoMips).
Note 96.31% of all statistics are fiction.

:wq!
---------------------------------------------------------------------------
Robert L. Harris | GPG Key ID: E344DA3B

                                         @ x-hkp://pgp.mit.edu

DISCLAIMER:
These are MY OPINIONS ALONE. I speak for no-one else.

Life is not a destination, it's a journey.
Microsoft produces 15 car pileups on the highway.
Don't stop traffic to stand and gawk at the tragedy.

#3 lore raw
Quoted 6 lines · Robert L. Harris

We ran "memtest" on the machine over the weekend and it completed 3 times without any problems. Know a better or different test?

Write 0x80 out port 0x70, and hope nobody accesses the RTC. This will (should) disable the NMI line. Then see if the error messages go away. If they do, it's a real NMI and you really do have bad RAM somewhere. If they don't, your motherboard is getting glitched either by bad design or something plugged into a slot that doesn't have the correct timing specs.

If everything works, in spite of the NMI, just comment out the kernel printk() and cross your fingers.

Quoted 31 lines

Thus spake Richard B. Johnson ([email protected]):

Quoted 18 lines · Robert L. Harris
Quoted 11 lines

Can anyone tell me what this is?

16:00:09 mailserver kernel: Uhhuh. NMI received for unknown reason 31. 16:00:09 mailserver kernel: Dazed and confused, but trying to continue 16:00:09 mailserver kernel: Do you have a strange power saving mode enabled? 16:00:34 mailserver kernel: Uhhuh. NMI received for unknown reason 21. 16:00:34 mailserver kernel: Dazed and confused, but trying to continue

Quoted 5 lines

A coworker put a script on a server which loads up quite afew arrays with pre-set values and then compares the values against arrays. As soon as he kicked off the script I got alot of these in my log files. Not much longer and the machine crashed hard.

Quoted 7 lines

Possible bad RAM.

Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (794.73 BogoMips).
Note 96.31% of all statistics are fiction.

:wq!
---------------------------------------------------------------------------
Robert L. Harris | GPG Key ID: E344DA3B

Quoted 8 lines
                                         @ x-hkp://pgp.mit.edu

DISCLAIMER:
These are MY OPINIONS ALONE. I speak for no-one else.

Life is not a destination, it's a journey.
Microsoft produces 15 car pileups on the highway.
Don't stop traffic to stand and gawk at the tragedy.

Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (794.73 BogoMips).
Note 96.31% of all statistics are fiction.

#4 lore raw
In reply to Robert L. Harris
Quoted 3 lines · Robert L. Harris

We ran "memtest" on the machine over the weekend and it completed 3 times without any problems. Know a better or different test?

You might try to enable all the tests, addresses and set the cache to be always on in memtest. Typical keys pressed is:

c - 1 - 2 - 2 - 3 - 3 - 3

Another is goldmemory, which is fairly the same in default setup as memtest with above config, but shareware, not gpl.

Quoted 39 lines

Thus spake Richard B. Johnson ([email protected]):

Quoted 18 lines · Robert L. Harris
Quoted 11 lines

Can anyone tell me what this is?

16:00:09 mailserver kernel: Uhhuh. NMI received for unknown reason 31. 16:00:09 mailserver kernel: Dazed and confused, but trying to continue 16:00:09 mailserver kernel: Do you have a strange power saving mode enabled? 16:00:34 mailserver kernel: Uhhuh. NMI received for unknown reason 21. 16:00:34 mailserver kernel: Dazed and confused, but trying to continue

Quoted 5 lines

A coworker put a script on a server which loads up quite afew arrays with pre-set values and then compares the values against arrays. As soon as he kicked off the script I got alot of these in my log files. Not much longer and the machine crashed hard.

Quoted 7 lines

Possible bad RAM.

Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (794.73 BogoMips).
Note 96.31% of all statistics are fiction.

:wq!
---------------------------------------------------------------------------
Robert L. Harris | GPG Key ID: E344DA3B

                                         @ x-hkp://pgp.mit.edu

DISCLAIMER:
These are MY OPINIONS ALONE. I speak for no-one else.

Life is not a destination, it's a journey.
Microsoft produces 15 car pileups on the highway.
Don't stop traffic to stand and gawk at the tragedy.

Signature · 1 line
Martin Schlemmer
#5 lore raw

I ran some tests Richard gave me which said it wasn't bad ram but a bad motherboard. I just upgraded to 2.4.22-bk10 and it ran MUCH better, able to use all 16Gigs happily for quite some time until a couple of the processes started finishing then it gave the NMI's en mass, guess it couldn't shove them off to the log server in time.

I'll try the below just to make sure but this is getting odd.

Thus spake Martin Schlemmer ([email protected]):

Quoted 49 lines · Robert L. Harris
Quoted 3 lines

We ran "memtest" on the machine over the weekend and it completed 3 times without any problems. Know a better or different test?

You might try to enable all the tests, addresses and set the cache to be always on in memtest. Typical keys pressed is:

c - 1 - 2 - 2 - 3 - 3 - 3

Another is goldmemory, which is fairly the same in default setup as memtest with above config, but shareware, not gpl.

Quoted 36 lines

Thus spake Richard B. Johnson ([email protected]):

Quoted 18 lines · Robert L. Harris
Quoted 11 lines

Can anyone tell me what this is?

16:00:09 mailserver kernel: Uhhuh. NMI received for unknown reason 31. 16:00:09 mailserver kernel: Dazed and confused, but trying to continue 16:00:09 mailserver kernel: Do you have a strange power saving mode enabled? 16:00:34 mailserver kernel: Uhhuh. NMI received for unknown reason 21. 16:00:34 mailserver kernel: Dazed and confused, but trying to continue

Quoted 5 lines

A coworker put a script on a server which loads up quite afew arrays with pre-set values and then compares the values against arrays. As soon as he kicked off the script I got alot of these in my log files. Not much longer and the machine crashed hard.

Quoted 7 lines

Possible bad RAM.

Cheers,
Dick Johnson
Penguin : Linux version 2.4.22 on an i686 machine (794.73 BogoMips).
Note 96.31% of all statistics are fiction.

:wq!
---------------------------------------------------------------------------
Robert L. Harris | GPG Key ID: E344DA3B

                                         @ x-hkp://pgp.mit.edu

DISCLAIMER:
These are MY OPINIONS ALONE. I speak for no-one else.

Quoted 6 lines
Quoted 3 lines

Life is not a destination, it's a journey.
Microsoft produces 15 car pileups on the highway.
Don't stop traffic to stand and gawk at the tragedy.

Signature · 1 line
Martin Schlemmer

:wq!
---------------------------------------------------------------------------
Robert L. Harris | GPG Key ID: E344DA3B

                                         @ x-hkp://pgp.mit.edu

DISCLAIMER:
These are MY OPINIONS ALONE. I speak for no-one else.

Life is not a destination, it's a journey.
Microsoft produces 15 car pileups on the highway.
Don't stop traffic to stand and gawk at the tragedy.