From owner-freebsd-arch@FreeBSD.ORG  Sun Jul 22 16:53:59 2012
Return-Path: <owner-freebsd-arch@FreeBSD.ORG>
Delivered-To: freebsd-arch@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52])
	by hub.freebsd.org (Postfix) with ESMTP id 72868106566C
	for <freebsd-arch@freebsd.org>; Sun, 22 Jul 2012 16:53:59 +0000 (UTC)
	(envelope-from rwatson@FreeBSD.org)
Received: from cyrus.watson.org (cyrus.watson.org [65.122.17.42])
	by mx1.freebsd.org (Postfix) with ESMTP id 4A9738FC08
	for <freebsd-arch@freebsd.org>; Sun, 22 Jul 2012 16:53:59 +0000 (UTC)
Received: from fledge.watson.org (fledge.watson.org [65.122.17.41])
	by cyrus.watson.org (Postfix) with ESMTPS id 9C48146B17;
	Sun, 22 Jul 2012 12:53:58 -0400 (EDT)
Date: Sun, 22 Jul 2012 17:53:58 +0100 (BST)
From: Robert Watson <rwatson@FreeBSD.org>
X-X-Sender: robert@fledge.watson.org
To: Matthew Jacob <mj@feral.com>
In-Reply-To: <500752CD.9030107@feral.com>
Message-ID: <alpine.BSF.2.00.1207221752310.83786@fledge.watson.org>
References: <3CE55F29-A5B2-44A7-8854-1ED38BAE6F16@FreeBSD.org>
	<50075072.5050906@gmail.com> <500752CD.9030107@feral.com>
User-Agent: Alpine 2.00 (BSF 1167 2008-08-23)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed
Cc: freebsd-arch@freebsd.org
Subject: Re: aio in GENERIC?
X-BeenThere: freebsd-arch@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Discussion related to FreeBSD architecture <freebsd-arch.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-arch>,
	<mailto:freebsd-arch-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-arch>
List-Post: <mailto:freebsd-arch@freebsd.org>
List-Help: <mailto:freebsd-arch-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-arch>,
	<mailto:freebsd-arch-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Sun, 22 Jul 2012 16:53:59 -0000


On Wed, 18 Jul 2012, Matthew Jacob wrote:

> What practically does aio offer that is not achieved via pthreads other than 
> slightly simpler code?

Although the VFS side of the AIO code blocks kernel threads during in-progress 
I/O, the socket side is able to do fully asynchronous I/O down the stack 
without committing a kernel thread to it.  As such, it probably is actually 
significantly more scalable, allowing larger numbers of simultaneous 
outstanding I/Os in the network layer, and more efficiently than simply using 
threads.

Robert