qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Qemu-devel] [PATCH v4 0/7] aio: Support epoll by introducing qemu_p


From: Stefan Hajnoczi
Subject: Re: [Qemu-devel] [PATCH v4 0/7] aio: Support epoll by introducing qemu_poll abstraction
Date: Wed, 29 Apr 2015 11:06:17 +0100
User-agent: Mutt/1.5.23 (2014-03-12)

On Wed, Apr 29, 2015 at 11:24:24AM +0800, Fam Zheng wrote:
> v4: Rebase to 2.3 and rerun tests.  timerfd+epoll shows clear improvement over
>     current master when the virtio-console device attaches more fds to the 
> main
>     loop:
> 
>     syscall         high # of fd      low # of fd
>     -------------------------------------------------
>     qemu.git(ppoll) 24                83
>     ppoll+epoll     49                82
>     timerfd+epoll   49                91
>     glib            20                82
> 
>     (In high # of fd case, 3 activated but idle virtio-console devices are
>     attached, which will add us hundereds of fds to poll)

Thanks for posting these numbers.  Nice job on speeding up the Linux
case, I'm looking forward to seeing the results with your new epoll
syscall patches.

It looks like there will be a 15-20% regression for non-Linux hosts with
high # of fds.  But since the low # of fd regression between
qemu.git(ppoll) and glib is small, I think we can merge this now and
optimize later, if necessary.

Reviewed-by: Stefan Hajnoczi <address@hidden>

Attachment: pgp60ih7TeWH6.pgp
Description: PGP signature


reply via email to

[Prev in Thread] Current Thread [Next in Thread]