From: Nick Piggin <npiggin@suse.de>
To: Miklos Szeredi <miklos@szeredi.hu>
Cc: linux-fsdevel@vger.kernel.org, mark.fasheh@oracle.com
Subject: Re: 2.6.21-rc6 new aops patchset
Date: Fri, 13 Apr 2007 01:41:22 +0200 [thread overview]
Message-ID: <20070412234122.GD23523@wotan.suse.de> (raw)
In-Reply-To: <E1Hc2jG-0000Gz-00@dorka.pomaz.szeredi.hu>
On Thu, Apr 12, 2007 at 07:05:02PM +0200, Miklos Szeredi wrote:
> > Did some performance testing of the fuse_perform_write implementation.
> > Result with a passthrough filesystem onto a backing tmpfs directory is that
> > bulk (1MB) writes are nearly 4 times faster (256MB/s vs 71MB/s), because
> > FUSE can send larger requests to userspace. Block based filesystems will
> > tend to be less dramatic, but could still be significant if block allocation
> > is batched, for example.
>
> Thanks a bunch, this is great news. Large writes are one of the most
> requested features for fuse. I did have a patch that does this in
> prepare_write/commit_write, but it's rather hackish, and I'm glad
> there will be a better way.
Oh, that's good to know it will actually be useful ;) I didn't actually
instrument request sizes going down, but it that number might be increased
further by increasing the max pages per fuse request.
next prev parent reply other threads:[~2007-04-12 23:41 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-12 4:48 2.6.21-rc6 new aops patchset Nick Piggin
2007-04-12 16:37 ` Badari Pulavarty
2007-04-12 23:25 ` Nick Piggin
2007-04-13 16:42 ` Badari Pulavarty
2007-04-14 0:52 ` Nick Piggin
2007-04-17 18:41 ` Badari Pulavarty
2007-04-18 5:04 ` Nick Piggin
2007-04-12 17:05 ` Miklos Szeredi
2007-04-12 23:41 ` Nick Piggin [this message]
2007-04-12 17:27 ` Mark Fasheh
2007-04-12 23:45 ` Nick Piggin
2007-04-17 0:19 ` Mark Fasheh
2007-04-17 5:59 ` Nick Piggin
2007-04-17 9:33 ` Christoph Hellwig
2007-04-17 9:47 ` Nick Piggin
2007-04-17 9:58 ` Christoph Hellwig
2007-04-17 11:18 ` Nick Piggin
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=20070412234122.GD23523@wotan.suse.de \
--to=npiggin@suse.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=mark.fasheh@oracle.com \
--cc=miklos@szeredi.hu \
/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.