All of lore.kernel.org
 help / color / mirror / Atom feed
From: Benjamin LaHaise <bcrl@kvack.org>
To: Suparna Bhattacharya <suparna@in.ibm.com>
Cc: linux-aio@kvack.org, linux-kernel@vger.kernel.org,
	wli@holomorphy.com, zab@zabbo.net, mason@suse.com,
	ysaito@hpl.hp.com
Subject: Re: Pending AIO work/patches
Date: Mon, 20 Jun 2005 14:10:08 -0400	[thread overview]
Message-ID: <20050620181007.GA4031@kvack.org> (raw)
In-Reply-To: <20050620120154.GA4810@in.ibm.com>

On Mon, Jun 20, 2005 at 05:31:54PM +0530, Suparna Bhattacharya wrote:
> (1) Updating AIO to use wait-bit based filtered wakeups (me/wli)
> 	Status: Updated to 2.6.12-rc6, needs review
> (2) Buffered filesystem AIO read/write (me/Ben)
> 	Status: aio write: Updated to 2.6.12-rc6, needs review
> 	Status: aio read : Needs rework against readahead changes in mainline

I've looked over the patches from today and they seem quite sane.  Comments 
pending...

> (3) POSIX AIO support (Bull: Laurent/Sebastian or Oracle: Joel)
> 	Status: Needs review and discussion ?

The latest version incorporates changes from the last round of feedback 
(great work Sebastien!) and updates the library license, so people should 
definately take a closer look.  This includes the necessary changes for 
in-kernel signal support, as well as minimal conversion done on iocbs (the 
layout matches the in-kernel iocb).

A quick reading shows that most of it looks quite good.  I have to stare 
at the cancellation code a bit more closely, though.

> (4) AIO for pipes (Chris Mason)
> 	Status: Needs update to latest kernels

This likely needs a rewrite with whatever the final semaphore operations 
turn out to look like, as it gets very easy to convert down() into 
aio_down() and that minimises the changes to the code.

> (5) Asynchronous semaphore implementation (Ben/Trond?)
> 	Status: Posted - under development & discussion

I got the aio_down() variant working with cancellation now, and should be 
able to post an updated series of patches against 2.6.12 shortly.

> (6) epoll - AIO integration (Zach Brown/Feng Zhou/wli)
> 	Status: Needs resurrection ?

What are folks thoughts in this area?  Zach's patches took the approach of 
making multishot iocbs possible, which helped avoid the overhead of plain 
aio_poll's command setup, which was quite visible in pipetest.  Zach -- did 
you do any benchmarking on your aio-epoll patches?

> (7) Vector AIO (aio readv/writev) (Yasushi Saito)
> 	Status: Needs resurrection ?

Zach also made some noises about this recently...

		-ben
-- 
"Time is what keeps everything from happening all at once." -- John Wheeler

  parent reply	other threads:[~2005-06-20 18:08 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-06-20 12:01 Pending AIO work/patches Suparna Bhattacharya
2005-06-20 13:13 ` Trond Myklebust
2005-06-20 14:32 ` Sébastien Dugué
2005-06-20 16:01 ` [PATCH 0/6] Integrate AIO with wait-bit based filtered wakeups Suparna Bhattacharya
2005-06-20 16:20   ` [PATCH 1/6] Add a wait queue argument to wait_bit action() Suparna Bhattacharya
2005-06-20 16:24   ` [PATCH 2/6] Rename __lock_page to lock_page_slow Suparna Bhattacharya
2005-06-28 16:52     ` Zach Brown
2005-06-29  9:51       ` Suparna Bhattacharya
2005-07-24 22:17     ` Christoph Hellwig
2005-07-24 22:36       ` Christoph Hellwig
2005-07-26  1:10         ` Suparna Bhattacharya
2005-06-20 16:28   ` [PATCH 3/6] Interfaces to initialize and to test a wait_bit key Suparna Bhattacharya
2005-06-20 16:30   ` [PATCH 4/6] Add default io wait bit field in task struct Suparna Bhattacharya
2005-06-20 16:33   ` [PATCH 5/6] AIO wait bit and AIO wake bit for filtered wakeups Suparna Bhattacharya
2005-06-20 16:36   ` [PATCH 6/6] AIO wait page and AIO lock page Suparna Bhattacharya
2005-06-30 15:49   ` [PATCH 0/6] Integrate AIO with wait-bit based filtered wakeups Sébastien Dugué
2005-07-01  7:37     ` Suparna Bhattacharya
2005-06-20 18:10 ` Benjamin LaHaise [this message]
2005-06-20 18:51   ` Pending AIO work/patches Zach Brown
2005-06-21  7:36   ` Sébastien Dugué
2005-06-21 19:03 ` William Lee Irwin III
2005-06-24 10:49 ` [PATCH 0/2] Buffered filesystem AIO read/write Suparna Bhattacharya
2005-06-24 11:21   ` [PATCH 1/2] Filesystem AIO read Suparna Bhattacharya
2005-06-24 11:40   ` [PATCH 2/2] Filesystem AIO write Suparna Bhattacharya
2005-06-24 16:10   ` [PATCH 0/2] Buffered filesystem AIO read/write Jeremy Allison

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=20050620181007.GA4031@kvack.org \
    --to=bcrl@kvack.org \
    --cc=linux-aio@kvack.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mason@suse.com \
    --cc=suparna@in.ibm.com \
    --cc=wli@holomorphy.com \
    --cc=ysaito@hpl.hp.com \
    --cc=zab@zabbo.net \
    /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.