From: Jens Axboe <jaxboe@fusionio.com>
To: Kent Overstreet <koverstreet@google.com>
Cc: Jack Wang <jack.wang.usish@gmail.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-aio@kvack.org" <linux-aio@kvack.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
"zab@redhat.com" <zab@redhat.com>,
"bcrl@kvack.org" <bcrl@kvack.org>,
"jmoyer@redhat.com" <jmoyer@redhat.com>,
"viro@zeniv.linux.org.uk" <viro@zeniv.linux.org.uk>
Subject: Re: [PATCH 00/26] AIO performance improvements/cleanups, v2
Date: Sat, 15 Dec 2012 14:16:48 +0100 [thread overview]
Message-ID: <50CC7840.4090403@fusionio.com> (raw)
In-Reply-To: <20121215103658.GB10411@moria.home.lan>
On 2012-12-15 11:36, Kent Overstreet wrote:
>> Knock yourself out - I already took a quick look at it, and conversion
>> should be pretty simple. It's the mtip32xx driver, it's in the kernel. I
>> would suggest getting rid of the ->async_callback() (since it's always
>> bio_endio()) since that'll make it cleaner.
>
> Just pushed my conversion - it's untested, but it's pretty
> straightforward.
You forgot a batch_complete_init(). With that, it works. Single device
is ~1050K now, so still slower than jaio without batching (which was
~1220K). But it's an improvement over kaio-dio, which was roughly ~930K
IOPS.
--
Jens Axboe
next prev parent reply other threads:[~2012-12-15 13:16 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-03 20:58 [PATCH 00/26] AIO performance improvements/cleanups, v2 Kent Overstreet
2012-12-03 20:58 ` [PATCH 01/26] mm: remove old aio use_mm() comment Kent Overstreet
2012-12-03 20:58 ` [PATCH 02/26] aio: remove dead code from aio.h Kent Overstreet
2012-12-03 20:58 ` [PATCH 03/26] gadget: remove only user of aio retry Kent Overstreet
2012-12-03 20:58 ` [PATCH 04/26] aio: remove retry-based AIO Kent Overstreet
2012-12-27 10:11 ` Fubo Chen
2012-12-03 20:58 ` [PATCH 05/26] char: add aio_{read,write} to /dev/{null,zero} Kent Overstreet
2012-12-03 20:58 ` [PATCH 06/26] aio: Kill return value of aio_complete() Kent Overstreet
2012-12-03 20:58 ` [PATCH 07/26] aio: kiocb_cancel() Kent Overstreet
2012-12-03 20:58 ` [PATCH 08/26] aio: Move private stuff out of aio.h Kent Overstreet
2012-12-03 20:58 ` [PATCH 09/26] aio: dprintk() -> pr_debug() Kent Overstreet
2012-12-03 20:58 ` [PATCH 10/26] aio: do fget() after aio_get_req() Kent Overstreet
2012-12-03 20:58 ` [PATCH 11/26] aio: Make aio_put_req() lockless Kent Overstreet
2012-12-03 20:58 ` [PATCH 12/26] aio: Refcounting cleanup Kent Overstreet
2012-12-03 20:58 ` [PATCH 13/26] aio: Convert read_events() to hrtimers Kent Overstreet
2012-12-03 20:58 ` [PATCH 14/26] aio: Make aio_read_evt() more efficient Kent Overstreet
2012-12-03 20:58 ` [PATCH 15/26] aio: Use flush_dcache_page() Kent Overstreet
2012-12-03 20:58 ` [PATCH 16/26] aio: Use cancellation list lazily Kent Overstreet
2012-12-03 20:58 ` [PATCH 17/26] aio: Change reqs_active to include unreaped completions Kent Overstreet
2012-12-03 20:58 ` [PATCH 18/26] aio: Kill batch allocation Kent Overstreet
2012-12-03 20:58 ` [PATCH 19/26] aio: Kill struct aio_ring_info Kent Overstreet
2012-12-03 20:58 ` [PATCH 20/26] aio: Give shared kioctx fields their own cachelines Kent Overstreet
2012-12-03 20:58 ` [PATCH 21/26] aio: reqs_active -> reqs_available Kent Overstreet
2012-12-03 20:58 ` [PATCH 22/26] aio: percpu reqs_available Kent Overstreet
2012-12-03 20:58 ` [PATCH 23/26] Generic dynamic per cpu refcounting Kent Overstreet
2012-12-27 13:47 ` Fubo Chen
2012-12-03 20:58 ` [PATCH 24/26] aio: Percpu ioctx refcount Kent Overstreet
2012-12-03 20:58 ` [PATCH 25/26] aio: use xchg() instead of completion_lock Kent Overstreet
2012-12-03 20:58 ` [PATCH 26/26] aio: Don't include aio.h in sched.h Kent Overstreet
2012-12-13 21:18 ` [PATCH 00/26] AIO performance improvements/cleanups, v2 Jens Axboe
2012-12-14 2:26 ` Jack Wang
2012-12-14 7:35 ` Jens Axboe
2012-12-15 9:25 ` Kent Overstreet
2012-12-15 9:46 ` Jens Axboe
2012-12-15 10:36 ` Kent Overstreet
2012-12-15 12:59 ` Jens Axboe
2012-12-15 13:16 ` Jens Axboe [this message]
2012-12-18 19:16 ` Kent Overstreet
2012-12-19 6:45 ` Kent Overstreet
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=50CC7840.4090403@fusionio.com \
--to=jaxboe@fusionio.com \
--cc=bcrl@kvack.org \
--cc=jack.wang.usish@gmail.com \
--cc=jmoyer@redhat.com \
--cc=koverstreet@google.com \
--cc=linux-aio@kvack.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=viro@zeniv.linux.org.uk \
--cc=zab@redhat.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