Re: iotop: khugepaged at 99.99% (2.6.38.3)

[Lin Ming]

On Wed, Sep 14, 2011 at 8:57 PM, Slawomir Czarko-Wasiutycz
<slawomir.czarko@xxxxxxxxx> wrote:
> On Thursday, April 21, 2011 1:28:18 AM UTC+2, Thomas Sattler wrote:
>> Hi there ...
>>
>> While running firefox (>50 open Tabs), khugepaged jumped to 99.99%
>> (according to 'iotop').  I killed firefox and nearly all running
>> programs but khugepaged was still at 99.99% IO while the system
>> was almost idle. I waited about 10 minutes, no improvement, so
>> I rebooted the machine.
>>
> Hi,
>
> I have a similar problem.
>
> System becomes unresponsive for few seconds up to a minute or so.
>
> In my case the trigger seems to be compiling code in a Linux VM running in VMplayer.
>
> Problem seems to go away if I do:
>
> echo madvise > /sys/kernel/mm/transparent_hugepage/defrag
>
> Kernel used: kernel-PAE-2.6.40.4-5.fc15.i686 SMP CONFIG_PREEMPT=n

(Add Thomas and Andrea)

Hi, Thomas

Do you still see this problem on latest kernel(2.6.31-rc6)?
I try to run firefox (>50 open Tabs), but can't reproduce this on
2.6.31-rc6 kernel.

# cat /proc/`pgrep khugepaged`/io
rchar: 0
wchar: 0
syscr: 0
syscw: 0
read_bytes: 0
write_bytes: 0
cancelled_write_bytes: 0

Andrea,

>From above output, all fields are zero.
Does it mean that transparent huge page was not triggered/used at all?

Regards,
Lin Ming
--
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/