public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* BUG(?): kswapd eating CPU
@ 2001-11-09 11:53 Andrew Church
  0 siblings, 0 replies; 2+ messages in thread
From: Andrew Church @ 2001-11-09 11:53 UTC (permalink / raw)
  To: linux-kernel

     I just had a strange case where kswapd started eating up 100% CPU
time.  I haven't been able to reproduce it, but it seemed to occur when I
did a "dd bs=4096 </dev/fb0 >/scratch/image" in X while writing a CD (4x)
from the same filesystem--the dd took 10-20 times longer than usual, and
kswapd's run time from ps also pointed to the same time.  At the time,
roughly 6MB of real memory was free, but most in-use memory (~800MB) was
cached data; only 3MB or so of swap was used.  The system itself seemed to
remain stable, though I rebooted shortly after I discovered the problem.

     System is as follows: (if more info is desired, please contact me
directly at achurch@achurch.org--I'm not subscribed to the list)

Kernel: 2.4.13 (i686, SMP)
CPU   : Dual Pentium II 400MHz
Memory: 896MB RAM, 576MB swap
IDE   : 1 HD (data, including /scratch, and 512MB swap)
SCSI  : 1 HD (root and 64MB swap), 1 CD-R drive
Video : 3dfx Voodoo 3 (PCI), 16MB VRAM (3dfx framebuffer driver enabled
	for virtual consoles, but X hits the hardware directly)

  --Andrew Church
    achurch@achurch.org
    http://achurch.org/

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: BUG(?): kswapd eating CPU
@ 2001-11-09 13:51 Marcus Grando
  0 siblings, 0 replies; 2+ messages in thread
From: Marcus Grando @ 2001-11-09 13:51 UTC (permalink / raw)
  To: linux-kernel

[-- Attachment #1: Type: text/plain, Size: 810 bytes --]

	Hello all,

	I have this problems too.

	Any sugestions?

Regards
Marcus Grando

> I just had a strange case where kswapd started eating up 100% CPU
>time.  I haven't been able to reproduce it, but it seemed to occur when I
>did a "dd bs=4096 </dev/fb0 >/scratch/image" in X while writing a CD (4x)
>from the same filesystem--the dd took 10-20 times longer than usual, and
>kswapd's run time from ps also pointed to the same time.  At the time,
>roughly 6MB of real memory was free, but most in-use memory (~800MB) was
>cached data; only 3MB or so of swap was used.  The system itself seemed to
>remain stable, though I rebooted shortly after I discovered the problem.
>
>     System is as follows: (if more info is desired, please contact me
>directly at achurch@achurch.org--I'm not subscribed to the list)

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2001-11-09 12:51 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2001-11-09 11:53 BUG(?): kswapd eating CPU Andrew Church
  -- strict thread matches above, loose matches on Subject: below --
2001-11-09 13:51 Marcus Grando

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox