From: Avi Kivity <avi@exanet.com>
To: Joel Becker <jlbec@evilplan.org>
Cc: Yasushi Saito <ysaito@hpl.hp.com>,
linux-aio@kvack.org, linux-kernel@vger.kernel.org,
suparna@in.ibm.com, Janet Morgan <janetmor@us.ibm.com>
Subject: Re: [PATCH 1/2] aio: add vectored I/O support
Date: Sat, 16 Oct 2004 07:18:45 +0200 [thread overview]
Message-ID: <4170AF35.7030806@exanet.com> (raw)
In-Reply-To: <20041016031301.GC17142@parcelfarce.linux.theplanet.co.uk>
Joel Becker wrote:
>On Thu, Oct 14, 2004 at 01:10:01PM -0700, Yasushi Saito wrote:
>
>
>>This is a patch against 2.6.9-rc3-mm3 that add supports for vectored
>>async I/O. It adds two additional commands, IO_CMD_PREADV and
>>IO_CMD_PWRITEV to libaio.h. The below is roughly what I did:
>>
>>
>
> How does this differ substantially from lio_listio() of each I/O
>range? Does it have some significant performance win, or is it just
>aiming for a completeness that POSIX doesn't (to my knowledge) specify?
>
>
>
It is a huge performance win, at least on the 2.4-based RHEL kernel.
Large reads (~256K) using 4K iocbs are very slow on a large RAID, while
after I coded a similar patch I got a substantial speedup.
I don't know the cause for the slowdown; maybe request merging only
works for queued requests, and as the RAID has a large TCQ depth,
requests didn't have much of a chance to queue in the kernel.
--
Do not meddle in the internals of kernels, for they are subtle and quick to panic.
next prev parent reply other threads:[~2004-10-16 5:18 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-10-14 20:10 [PATCH 1/2] aio: add vectored I/O support Yasushi Saito
2004-10-16 3:13 ` Joel Becker
2004-10-16 5:18 ` Avi Kivity [this message]
2004-10-16 5:37 ` Joel Becker
2004-10-16 8:43 ` Avi Kivity
2004-10-16 16:28 ` Joel Becker
2004-10-16 17:29 ` Avi Kivity
2004-10-17 0:14 ` Joel Becker
2004-10-17 6:25 ` Avi Kivity
2004-10-16 12:05 ` William Lee Irwin III
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=4170AF35.7030806@exanet.com \
--to=avi@exanet.com \
--cc=janetmor@us.ibm.com \
--cc=jlbec@evilplan.org \
--cc=linux-aio@kvack.org \
--cc=linux-kernel@vger.kernel.org \
--cc=suparna@in.ibm.com \
--cc=ysaito@hpl.hp.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 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.