RE: The values of gettimeofday() jumps.

[Liangchen Zheng]

	The clock drift disappeared after booting the kernel with
"notsc" option.
Thanks a lot.  It seems there is some bug with the TSC support inside
the kernel.
Maybe it is caused by the clock drifts between two TSCs in the both
CPUs, as mentioned by Pádraig Brady in one reply to my previous
question.  
	But I am still wondering why the clock drift can be so huge (a
couple of seconds sometimes) and the drifts occurred so regular (around
every 1 second).
If I have time in future, I will dig into it to figure out what is the
exact reason.
	Thanks a lot for your suggestions.

Regards,
Liangchen

-----Original Message-----
From: Arjan van de Ven [mailto:arjan@xxxxxxxxxxxxx] 
Sent: Sunday, May 29, 2005 12:42 AM
To: Liangchen Zheng
Cc: linux-kernel@xxxxxxxxxxxxxxx
Subject: Re: The values of gettimeofday() jumps.

On Sat, 2005-05-28 at 18:37 -0700, Liangchen Zheng wrote:
> Hello,
> 	We have several SMP machines (Tyan Tiger MPX motherboard, 2
> AthlonMP 1900+ CPU, linux-2.4.21-20.EL).  When running some time
> sensitive programs, I observed that the values of gettimeofday ()
jumped
> sometimes on a couple of machines (other machines are fine), from
> several hundreds milliseconds to a couple of seconds. 

try "notsc" as boot option


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/