From: Rusty Russell <rusty@rustcorp.com.au>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: lguest <lguest@ozlabs.org>,
linux-kernel@vger.kernel.org,
"kvm-devel" <kvm-devel@lists.sourceforge.net>
Subject: Re: [PATCH 2/2] lguest: use get_user_pages_fast() instead of get_user_pages()
Date: Wed, 30 Jul 2008 16:53:09 +1000 [thread overview]
Message-ID: <200807301653.10154.rusty@rustcorp.com.au> (raw)
In-Reply-To: <200807301530.10205.nickpiggin@yahoo.com.au>
On Wednesday 30 July 2008 15:30:10 Nick Piggin wrote:
> On Wednesday 30 July 2008 14:39, Rusty Russell wrote:
> > Before: 5.93 seconds
> > After: 5.40 seconds
> >
> > (Counts of slow vs fastpath in this usage are 6092 and 2852462
> > respectively.)
> >
> > And more importantly for lguest, the code is simpler.
>
> Cool. That's actually a fairly significant straight-line performance
> improvement, given that the lguest processes are running one-at-a-time
> right? (and not contending on the locks or bouncing cachelines too much)
Yep. I mean, the performance is abysmal either way (native for this is about
10x faster), but it would be interesting to see kvm numbers as they have a
more sophisticated shadow page table setup. Not as trivial as lguest since
they seem to use the mm sem to protect other things...
Cheers,
Rusty.
next prev parent reply other threads:[~2008-07-30 6:53 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-30 4:38 [PATCH 1/2] Export get_user_pages_fast Rusty Russell
2008-07-30 4:39 ` [PATCH 2/2] lguest: use get_user_pages_fast() instead of get_user_pages() Rusty Russell
2008-07-30 5:30 ` Nick Piggin
2008-07-30 6:53 ` Rusty Russell [this message]
2008-07-30 5:23 ` [PATCH 1/2] Export get_user_pages_fast Nick Piggin
2008-07-30 10:35 ` Andrew Morton
2008-07-30 15:47 ` Adrian Bunk
2008-07-30 17:03 ` Andrew Morton
2008-07-30 17:09 ` Adrian Bunk
2008-07-30 17:14 ` Andrew Morton
2008-07-30 17:18 ` Adrian Bunk
2008-07-30 17:28 ` Andrew Morton
2008-07-30 17:39 ` Adrian Bunk
2008-07-30 17:50 ` Andrew Morton
2008-07-30 17:23 ` Avi Kivity
2008-07-30 17:29 ` Andrew Morton
2008-07-31 6:43 ` Avi Kivity
2008-07-31 7:02 ` Andrew Morton
2008-07-31 8:10 ` Nick Piggin
2008-07-31 8:21 ` Andrew Morton
2008-07-31 8:32 ` Benjamin Herrenschmidt
2008-07-31 8:48 ` Nick Piggin
2008-07-31 8:52 ` Benjamin Herrenschmidt
2008-07-31 8:56 ` Nick Piggin
2008-08-05 5:47 ` Rusty Russell
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=200807301653.10154.rusty@rustcorp.com.au \
--to=rusty@rustcorp.com.au \
--cc=kvm-devel@lists.sourceforge.net \
--cc=lguest@ozlabs.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox