amd64 systems hanging with powerd (Re: RELENG 6.1/AMD64 system hangs when SMP enabled)

2006-12-15 Thread Kris Kennaway
On Fri, Dec 15, 2006 at 09:22:32AM +0100, Bram wrote:
> Hi all,
> 
> I turned kernel debuging on and tried the key combinations when the 
> machine was stuck
> but it did not really help because the machine was not responding to this.
> 
> I do think that I might have found the cause of the problem.
> 
> I was running powerd and the cpufreq module was loaded each I had problems.
> 
> I now turned powerd of and did not load the cpufreq module and the 
> machine is now running for 23 days in a row.
> 
> Does anybody know wether this is possible/makes sense ?

The same thing happens on this athlon64 X2.

Kris


pgp3ccqFfrrC4.pgp
Description: PGP signature


Re: RELENG 6.1/AMD64 system hangs when SMP enabled

2006-12-15 Thread Bram

Hi all,

I turned kernel debuging on and tried the key combinations when the 
machine was stuck

but it did not really help because the machine was not responding to this.

I do think that I might have found the cause of the problem.

I was running powerd and the cpufreq module was loaded each I had problems.

I now turned powerd of and did not load the cpufreq module and the 
machine is now running for 23 days in a row.


Does anybody know wether this is possible/makes sense ?

kind regards

Kris Kennaway schreef:

On Fri, Oct 27, 2006 at 09:35:09AM +0200, bram wrote:
  

Hi all,

I'm rather new to freebsd so forgive me if I am saying things that don't 
make sense.


I have a dual opteron server running freebsd 6.1/amd64 updated 4 weeks ago.

Since I moved to 6 I've been having tho following problem.

When I put heavy load on the server (python scripts that take 20 minutes 
to complete) the server sometimes hangs.


I can then not ping it anymore and it does not respond to anything (no 
keyboard power button etc.).
Mostly there are no error messages or anything so I have no clue to what 
the problem is.
One time it did give an error but I did not wrote it down, but as I 
recall it was something like SMP spin lock timed out.


It hangs every three weeks

Please give me some info on how I can get it to give more info or how to 
resolve this problem.



See the chapter on kernel debugging in the develpers handbook

Kris
  


___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


Re: RELENG 6.1/AMD64 system hangs when SMP enabled

2006-10-27 Thread Kris Kennaway
On Fri, Oct 27, 2006 at 09:35:09AM +0200, bram wrote:
> Hi all,
> 
> I'm rather new to freebsd so forgive me if I am saying things that don't 
> make sense.
> 
> I have a dual opteron server running freebsd 6.1/amd64 updated 4 weeks ago.
> 
> Since I moved to 6 I've been having tho following problem.
> 
> When I put heavy load on the server (python scripts that take 20 minutes 
> to complete) the server sometimes hangs.
> 
> I can then not ping it anymore and it does not respond to anything (no 
> keyboard power button etc.).
> Mostly there are no error messages or anything so I have no clue to what 
> the problem is.
> One time it did give an error but I did not wrote it down, but as I 
> recall it was something like SMP spin lock timed out.
> 
> It hangs every three weeks
> 
> Please give me some info on how I can get it to give more info or how to 
> resolve this problem.

See the chapter on kernel debugging in the develpers handbook

Kris


pgpTCTl6KG0GS.pgp
Description: PGP signature


Re: RELENG 6.1/AMD64 system hangs when SMP enabled

2006-10-27 Thread Bill Moran
In response to bram <[EMAIL PROTECTED]>:

> Hi all,
> 
> I'm rather new to freebsd so forgive me if I am saying things that don't 
> make sense.
> 
> I have a dual opteron server running freebsd 6.1/amd64 updated 4 weeks ago.
> 
> Since I moved to 6 I've been having tho following problem.
> 
> When I put heavy load on the server (python scripts that take 20 minutes 
> to complete) the server sometimes hangs.
> 
> I can then not ping it anymore and it does not respond to anything (no 
> keyboard power button etc.).
> Mostly there are no error messages or anything so I have no clue to what 
> the problem is.
> One time it did give an error but I did not wrote it down, but as I 
> recall it was something like SMP spin lock timed out.
> 
> It hangs every three weeks
> 
> Please give me some info on how I can get it to give more info or how to 
> resolve this problem.

I'm no expert, but this is probably where you'll need to start:
http://www.freebsd.org/doc/en_US.ISO8859-1/books/developers-handbook/kerneldebug-online-ddb.html

-- 
Bill Moran
Collaborative Fusion Inc.
___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"


RELENG 6.1/AMD64 system hangs when SMP enabled

2006-10-27 Thread bram

Hi all,

I'm rather new to freebsd so forgive me if I am saying things that don't 
make sense.


I have a dual opteron server running freebsd 6.1/amd64 updated 4 weeks ago.

Since I moved to 6 I've been having tho following problem.

When I put heavy load on the server (python scripts that take 20 minutes 
to complete) the server sometimes hangs.


I can then not ping it anymore and it does not respond to anything (no 
keyboard power button etc.).
Mostly there are no error messages or anything so I have no clue to what 
the problem is.
One time it did give an error but I did not wrote it down, but as I 
recall it was something like SMP spin lock timed out.


It hangs every three weeks

Please give me some info on how I can get it to give more info or how to 
resolve this problem.


thanks in advance

Bram

below are the first lines of dmesg

FreeBSD 6.1-RELEASE-p2 #3: Tue Aug  1 16:30:28 CEST 2006
   [EMAIL PROTECTED]:/usr/obj/usr/src/sys/SIMBA
ACPI APIC Table: 
Timecounter "i8254" frequency 1193182 Hz quality 0
CPU: AMD Opteron(tm) Processor 246 (2004.56-MHz K8-class CPU)
 Origin = "AuthenticAMD"  Id = 0xf5a  Stepping = 10
 
Features=0x78bfbff

 AMD Features=0xe0500800
real memory  = 2147418112 (2047 MB)
avail memory = 2062467072 (1966 MB)
FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs

___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"