From: "Michael S. Tsirkin" <mst@redhat.com>
To: Stefan Hajnoczi <stefanha@gmail.com>
Cc: linux-aio@kvack.org, kvm@vger.kernel.org,
linux-kernel@vger.kernel.org,
virtualization@lists.linux-foundation.org,
Benjamin LaHaise <bcrl@kvack.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org,
Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: [PATCH 0/5] Add vhost-blk support
Date: Tue, 17 Jul 2012 14:54:50 +0300 [thread overview]
Message-ID: <20120717115450.GA9796__37735.0837261931$1342526070$gmane$org@redhat.com> (raw)
In-Reply-To: <CAJSP0QXPkrVvgA+1fhhwsB5J8oApOObK8D3fk_Lm0Bt3T+Wfuw@mail.gmail.com>
On Tue, Jul 17, 2012 at 12:42:13PM +0100, Stefan Hajnoczi wrote:
> On Tue, Jul 17, 2012 at 12:26 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
> > On Tue, Jul 17, 2012 at 12:11:15PM +0100, Stefan Hajnoczi wrote:
> >> On Tue, Jul 17, 2012 at 10:21 AM, Asias He <asias@redhat.com> wrote:
> >> > On 07/17/2012 04:52 PM, Paolo Bonzini wrote:
> >> >>
> >> >> Il 17/07/2012 10:29, Asias He ha scritto:
> >> >>>
> >> >>> So, vhost-blk at least saves ~6 syscalls for us in each request.
> >> >>
> >> >>
> >> >> Are they really 6? If I/O is coalesced by a factor of 3, for example
> >> >> (i.e. each exit processes 3 requests), it's really 2 syscalls per request.
> >> >
> >> >
> >> > Well. I am counting the number of syscalls in one notify and response
> >> > process. Sure the IO can be coalesced.
> >>
> >> Linux AIO also supports batching in io_submit() and io_getevents().
> >> Depending on the request pattern in the vring when you process it, you
> >> should be able to do better than 1 set of syscalls per host I/O
> >> request.
> >>
> >> Are you taking advantage of that at the moment in your userspace benchmark?
> >>
> >> Stefan
> >
> > Injecting an interrupt directly from kernel bypasses two context switches.
> > Yes some worloads can coalesce interrupts efficiently but others can't.
> > It is not really hard to speculate more.
> >
> > Personally I don't understand where all this speculation leads us.
> > Are you guys disputing the measurements posted? If not would not
> > it be better if discussion focused on the amount of extra code versus
> > measured gain?
>
> 5-15% is nice. But what causes the performance advantage?
Well, check the number of interrupts. If it's high then that is
part of it.
> Knowing the answer to that is important before anyone can say whether
> this approach is good or not.
>
> Stefan
Why is it?
--
MST
next prev parent reply other threads:[~2012-07-17 11:54 UTC|newest]
Thread overview: 81+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-12 15:35 [PATCH 0/5] Add vhost-blk support Asias He
2012-07-12 15:35 ` Asias He
2012-07-12 15:35 ` [PATCH 1/5] aio: Export symbols and struct kiocb_batch for in kernel aio usage Asias He
2012-07-12 15:35 ` Asias He
2012-07-12 17:50 ` James Bottomley
2012-07-13 1:40 ` Asias He
2012-07-13 1:40 ` Asias He
2012-07-13 1:40 ` Asias He
2012-07-12 15:35 ` Asias He
2012-07-12 16:06 ` [PATCH 0/5] Add vhost-blk support Jeff Moyer
2012-07-12 16:06 ` Jeff Moyer
2012-07-13 1:19 ` Asias He
2012-07-13 1:19 ` Asias He
2012-07-13 1:19 ` Asias He
2012-07-12 16:06 ` Jeff Moyer
2012-07-16 11:58 ` Stefan Hajnoczi
2012-07-16 11:58 ` Stefan Hajnoczi
2012-07-17 8:29 ` Asias He
2012-07-17 8:29 ` Asias He
2012-07-17 8:29 ` Asias He
2012-07-17 8:52 ` Paolo Bonzini
2012-07-17 8:52 ` Paolo Bonzini
2012-07-17 8:52 ` Paolo Bonzini
2012-07-17 9:21 ` Asias He
2012-07-17 9:21 ` Asias He
2012-07-17 9:21 ` Asias He
2012-07-17 9:32 ` Paolo Bonzini
2012-07-17 9:32 ` Paolo Bonzini
2012-07-17 9:32 ` Paolo Bonzini
2012-07-17 9:51 ` Michael S. Tsirkin
2012-07-17 9:51 ` Michael S. Tsirkin
2012-07-17 9:51 ` Michael S. Tsirkin
2012-07-17 11:11 ` Stefan Hajnoczi
2012-07-17 11:11 ` Stefan Hajnoczi
2012-07-17 11:11 ` Stefan Hajnoczi
2012-07-17 11:26 ` Michael S. Tsirkin
2012-07-17 11:26 ` Michael S. Tsirkin
2012-07-17 11:42 ` Stefan Hajnoczi
2012-07-17 11:42 ` Stefan Hajnoczi
2012-07-17 11:51 ` Stefan Hajnoczi
2012-07-17 11:51 ` Stefan Hajnoczi
2012-07-17 11:54 ` Michael S. Tsirkin [this message]
2012-07-17 11:54 ` Michael S. Tsirkin
2012-07-17 11:54 ` Michael S. Tsirkin
2012-07-17 12:03 ` Stefan Hajnoczi
2012-07-17 12:03 ` Stefan Hajnoczi
2012-07-17 12:48 ` Michael S. Tsirkin
2012-07-17 12:48 ` Michael S. Tsirkin
2012-07-17 13:02 ` Paolo Bonzini
2012-07-17 13:02 ` Paolo Bonzini
2012-07-17 13:26 ` Michael S. Tsirkin
2012-07-17 13:26 ` Michael S. Tsirkin
2012-07-18 8:47 ` Asias He
2012-07-18 8:47 ` Asias He
2012-07-18 8:47 ` Asias He
2012-07-17 12:48 ` Michael S. Tsirkin
2012-07-17 11:26 ` Michael S. Tsirkin
2012-07-18 8:12 ` Asias He
2012-07-18 8:12 ` Asias He
2012-07-18 8:12 ` Asias He
2012-07-18 8:26 ` Stefan Hajnoczi
2012-07-18 8:26 ` Stefan Hajnoczi
2012-07-18 9:46 ` Ronen Hod
2012-07-18 9:46 ` Ronen Hod
2012-07-18 9:46 ` Ronen Hod
2012-07-17 9:45 ` Michael S. Tsirkin
2012-07-17 9:45 ` Michael S. Tsirkin
2012-07-17 9:45 ` Michael S. Tsirkin
2012-07-17 10:14 ` Paolo Bonzini
2012-07-17 10:14 ` Paolo Bonzini
2012-07-17 10:49 ` Michael S. Tsirkin
2012-07-17 10:49 ` Michael S. Tsirkin
2012-07-17 10:56 ` Paolo Bonzini
2012-07-17 10:56 ` Paolo Bonzini
2012-07-17 11:09 ` Michael S. Tsirkin
2012-07-17 11:09 ` Michael S. Tsirkin
2012-07-17 11:09 ` Michael S. Tsirkin
2012-07-17 11:36 ` Stefan Hajnoczi
2012-07-17 11:36 ` Stefan Hajnoczi
2012-07-17 11:36 ` Stefan Hajnoczi
2012-07-16 11:58 ` Stefan Hajnoczi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to='20120717115450.GA9796__37735.0837261931$1342526070$gmane$org@redhat.com' \
--to=mst@redhat.com \
--cc=bcrl@kvack.org \
--cc=kvm@vger.kernel.org \
--cc=linux-aio@kvack.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=stefanha@gmail.com \
--cc=viro@zeniv.linux.org.uk \
--cc=virtualization@lists.linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.