From: Piet Delaney <piet@bluelane.com>
To: Andi Kleen <ak@suse.de>
Cc: Piet Delaney <piet@bluelane.com>,
"David S. Miller" <davem@davemloft.net>,
torvalds@osdl.org, diegocg@gmail.com,
linux-kernel@vger.kernel.org
Subject: Re: Linux 2.6.17-rc2
Date: Thu, 20 Apr 2006 23:47:10 -0700 [thread overview]
Message-ID: <1145602031.5901.7.camel@piet2.bluelane.com> (raw)
In-Reply-To: <p73bquv3cox.fsf@bragg.suse.de>
On Fri, 2006-04-21 at 04:05 +0200, Andi Kleen wrote:
> Piet Delaney <piet@bluelane.com> writes:
> >
> > FreeBSD folks developed a ZERO_COPY_SOCKET facility that uses COW;
> > code looked great.
>
> Linux had patches many years ago (in 2.3.x), but it was never merged
> because it is inherently unscalable on MP. Classical BSD sockets really
> don't work well for zero copy - you need a new interface (like POSIX aio)
> that allows the kernel/user to tell each other when use of data is
> finished and buffers can be reused.
Right, back when I was working on zero copy for 2.4 I noticed that
2.6 seemed to support aio in the socket code, passing the kiocb
pointer as I recall, and support in the socket code for for sendpage
seemed enhanced. I was also wondering about using 2.6 and aio for zero
copy instead of tokens via sendmsg() and recvmsg() cmsghdr structures.
-piet
>
> -Andi
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
---
piet@bluelane.com
next prev parent reply other threads:[~2006-04-21 6:47 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-04-19 3:27 Linus Torvalds
2006-04-19 7:30 ` [patch, 2.6.17-rc2] dm: fix typo Ingo Molnar
2006-04-19 7:33 ` Ingo Molnar
2006-04-19 18:00 ` Linux 2.6.17-rc2 Diego Calleja
2006-04-19 18:04 ` Hua Zhong
2006-04-19 19:40 ` splice and tee [was Linux 2.6.17-rc2] Jonathan Corbet
2006-04-19 18:44 ` Linux 2.6.17-rc2 Linus Torvalds
2006-04-19 19:20 ` Grzegorz Kulewski
2006-04-19 20:09 ` Linus Torvalds
2006-04-19 21:23 ` Trond Myklebust
2006-04-19 21:49 ` Linus Torvalds
2006-04-19 22:19 ` Peter Naulls
2006-04-20 13:21 ` Diego Calleja
2006-04-20 14:50 ` Jens Axboe
2006-04-20 15:32 ` Linus Torvalds
2006-04-20 19:19 ` Jens Axboe
2006-04-20 18:40 ` Linh Dang
2006-04-20 19:49 ` Jens Axboe
2006-04-20 19:57 ` Linh Dang
2006-04-20 20:02 ` Nick Piggin
2006-04-21 7:53 ` Jens Axboe
2006-04-20 20:08 ` Jens Axboe
2006-04-20 19:26 ` David S. Miller
2006-04-20 19:34 ` Jens Axboe
2006-04-20 19:39 ` David S. Miller
2006-04-20 19:44 ` Jens Axboe
2006-04-20 19:54 ` Nick Piggin
2006-04-20 21:37 ` Piet Delaney
2006-04-20 22:20 ` Linus Torvalds
2006-04-20 23:39 ` Piet Delaney
2006-04-21 0:09 ` Linus Torvalds
2006-04-20 23:26 ` David Lang
2006-04-21 0:49 ` David S. Miller
2006-04-22 4:52 ` Troy Benjegerdes
2006-04-21 0:41 ` David S. Miller
2006-04-21 17:58 ` Linus Torvalds
2006-04-21 18:15 ` Steven Rostedt
2006-04-21 18:42 ` Steven Rostedt
2006-04-21 0:20 ` David S. Miller
2006-04-21 2:05 ` Andi Kleen
2006-04-21 6:47 ` Piet Delaney [this message]
2006-04-20 16:24 ` Ingo Oeser
2006-04-20 19:52 ` splice(), vmsplice() niftiness [was: Re: Linux 2.6.17-rc2] bjd
2006-04-21 10:21 ` Linux 2.6.17-rc2 Alistair John Strachan
2006-04-21 16:40 ` Linus Torvalds
2006-04-21 17:21 ` Stephen Rothwell
2006-04-21 22:02 ` Andi Kleen
2006-04-22 0:53 ` Alistair John Strachan
2006-04-22 1:07 ` Andi Kleen
2006-04-22 13:21 ` Alistair John Strachan
2006-04-21 11:01 ` Linux 2.6.17-rc2 - notifier chain problem? Herbert Poetzl
2006-04-21 21:31 ` Chandra Seetharaman
2006-04-22 0:58 ` Herbert Poetzl
2006-04-24 21:26 ` Chandra Seetharaman
2006-04-24 22:03 ` Andrew Morton
2006-04-24 23:01 ` Chandra Seetharaman
2006-04-24 23:28 ` Andrew Morton
2006-04-25 0:19 ` Chandra Seetharaman
2006-04-26 15:49 ` Alan Stern
2006-04-26 18:18 ` Chandra Seetharaman
2006-04-26 18:43 ` Andrew Morton
2006-04-26 19:29 ` Ashok Raj
2006-04-26 20:21 ` Chandra Seetharaman
2006-04-26 20:26 ` Ashok Raj
2006-04-28 23:12 ` Chandra Seetharaman
2006-04-28 23:23 ` Andrew Morton
2006-04-28 23:33 ` Linus Torvalds
2006-04-28 23:48 ` Chandra Seetharaman
2006-04-28 23:43 ` Chandra Seetharaman
2006-04-29 15:30 ` Alan Stern
2006-04-22 6:40 ` Keith Owens
[not found] <63bym-4wt-3@gated-at.bofh.it>
[not found] ` <64eE4-1gP-15@gated-at.bofh.it>
[not found] ` <64eX5-1RE-13@gated-at.bofh.it>
[not found] ` <64wre-2cg-35@gated-at.bofh.it>
2006-04-24 4:42 ` Linux 2.6.17-rc2 Robert Hancock
2006-04-24 13:08 ` Alistair John Strachan
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=1145602031.5901.7.camel@piet2.bluelane.com \
--to=piet@bluelane.com \
--cc=ak@suse.de \
--cc=davem@davemloft.net \
--cc=diegocg@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@osdl.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®