High sleep_on_page latency

[Mulyadi Santosa]

Hi Prateek...

On Mon, Jan 16, 2012 at 12:54, Prateek Sharma <prateek3.14 at gmail.com> wrote:
> I am using qemu-kvm 0.15, with KVM.

Hmm, not sure whether it already enables iothreads or not. Sometimes
KVM changes certain things from main Qemu tree.

>   My initial understanding was that sleep_on_page is 'called' by
> __lock_page, which is usually called by file_read .
>    So, i assumed that sleep_on_page is for the page-lock contention.
> My primary confusion is with the interpretation of latencytop output.
> 2 seconds even for I/O to complete seems awfully long.

Apologize, I haven't done complete call trace that leads to
sleep_on_page(), so I can't offer my own personal view.

The thing that cross my mind is to use tool like blktrace to confirm
those numbers.

AFAIK too, sometimes Qemu (or KVM) assume doing synchronized I/O.
Maybe that also explain the numbers you get. Try to read qemu/kvm
manual page and switch to async mode.

NB: are you doing read from journalling filesystem? I guess so...if
yes, which mode do you use i.e ext3 write back etc.


-- 
regards,

Mulyadi Santosa
Freelance Linux trainer and consultant

blog: the-hydra.blogspot.com
training: mulyaditraining.blogspot.com