From: Benjamin LaHaise <bcrl@lhnet.ca>
To: Greg KH <greg@kroah.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
Octavian Purdila <opurdila@ixiacom.com>,
netdev@vger.kernel.org, Cosmin Ratiu <cratiu@ixiacom.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/3] sysfs directory scaling: rbtree for dirent name lookups
Date: Tue, 3 Nov 2009 15:01:56 -0500 [thread overview]
Message-ID: <20091103200155.GQ8227@kvack.org> (raw)
In-Reply-To: <20091103035058.GA19515@kroah.com>
On Mon, Nov 02, 2009 at 07:50:58PM -0800, Greg KH wrote:
> On Sun, Nov 01, 2009 at 11:31:30AM -0500, Benjamin LaHaise wrote:
> > Use an rbtree in sysfs_dirent to speed up file lookup times
> >
> > Systems with large numbers (tens of thousands and more) of network
> > interfaces stress the sysfs code in ways that make the linear search for
> > a name match take far too long. Avoid this by using an rbtree.
>
> What kind of speedups are you seeing here? And do these changes cause a
> memory increase due to the structure changes which outweigh the
> speedups?
Depends on the number of interfaces being created. Without the patch,
interface creation time tends to double or worse for every 5,000-10,000
additional network interfaces.
> What kind of test are you doing to reproduce this?
I'm creating 30,000+ network interfaces, with the goal being 100,000.
With other hacks in the tree to get around the sysctl and procfs scaling
issues, as well as disabling things like NetworkManager, the results look
as follows:
Interfaces no-rb rbtree rbtree+list
0-5,000 13.8s 14.0s 13.0s
5,000-10,000 20.0s 17.4s 14.4s
10,000-15,000 27.3s 24.1s 16.9s
15,000-20,000 36.3s 32.2s 19.7s
20,000-25,000 45.2s 40.0s 22.9s
25,000-30,000 54.2s 48.2s 26.6s
30,000-35,000 63.9s 54.9s 30.7s
Thoughts?
-ben
next prev parent reply other threads:[~2009-11-03 20:01 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-11-01 16:31 [PATCH 1/3] sysfs directory scaling: rbtree for dirent name lookups Benjamin LaHaise
2009-11-01 16:32 ` [PATCH 2/3] sysfs directory scaling: doubly linked list for dirents Benjamin LaHaise
2009-11-01 16:33 ` [PATCH 2/3] sysfs directory scaling: count number of children dirs Benjamin LaHaise
2009-11-03 3:50 ` [PATCH 1/3] sysfs directory scaling: rbtree for dirent name lookups Greg KH
2009-11-03 6:14 ` Eric Dumazet
2009-11-03 7:01 ` [PATCH] sysctl: reduce ram usage by 40 % Eric Dumazet
2009-11-03 10:23 ` Eric W. Biederman
2009-11-03 16:07 ` [PATCH 1/3] sysfs directory scaling: rbtree for dirent name lookups Greg KH
2009-11-03 16:38 ` Octavian Purdila
2009-11-03 16:45 ` Benjamin LaHaise
2009-11-03 17:56 ` Greg KH
2009-11-03 22:28 ` Eric W. Biederman
2009-11-03 20:01 ` Benjamin LaHaise [this message]
2009-11-03 21:32 ` Eric W. Biederman
2009-11-03 21:43 ` Eric W. Biederman
2009-11-03 21:56 ` Benjamin LaHaise
2009-11-03 22:06 ` Eric Dumazet
2009-11-03 21:52 ` Benjamin LaHaise
2009-11-03 22:18 ` Eric W. Biederman
2009-11-03 10:41 ` Eric W. Biederman
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=20091103200155.GQ8227@kvack.org \
--to=bcrl@lhnet.ca \
--cc=cratiu@ixiacom.com \
--cc=ebiederm@xmission.com \
--cc=eric.dumazet@gmail.com \
--cc=greg@kroah.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=opurdila@ixiacom.com \
/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;
as well as URLs for NNTP newsgroup(s).