From owner-freebsd-arch@FreeBSD.ORG Mon Jul 23 13:36:44 2012 Return-Path: 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 677C6106566C for ; Mon, 23 Jul 2012 13:36:44 +0000 (UTC) (envelope-from mj@feral.com) Received: from ns1.feral.com (ns1.feral.com [192.67.166.1]) by mx1.freebsd.org (Postfix) with ESMTP id 3B4378FC08 for ; Mon, 23 Jul 2012 13:36:44 +0000 (UTC) Received: from [192.168.135.103] (c-76-126-166-136.hsd1.ca.comcast.net [76.126.166.136]) (authenticated bits=0) by ns1.feral.com (8.14.4/8.14.4) with ESMTP id q6NDabcK037673 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO) for ; Mon, 23 Jul 2012 06:36:38 -0700 (PDT) (envelope-from mj@feral.com) Message-ID: <500D5360.80607@feral.com> Date: Mon, 23 Jul 2012 06:36:32 -0700 From: Matthew Jacob Organization: Feral Software User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20120713 Thunderbird/14.0 MIME-Version: 1.0 CC: freebsd-arch@freebsd.org References: <3CE55F29-A5B2-44A7-8854-1ED38BAE6F16@FreeBSD.org> <50075072.5050906@gmail.com> <500752CD.9030107@feral.com> <500D028F.2040904@freebsd.org> In-Reply-To: <500D028F.2040904@freebsd.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.7 (ns1.feral.com [192.67.166.1]); Mon, 23 Jul 2012 06:36:38 -0700 (PDT) Subject: Re: aio in GENERIC? X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Matt Jacob List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Jul 2012 13:36:44 -0000 Thanks for all of the responses to my simplistic query. I really wanted to know what others thought about this. Way back in the day when I was splitting my programming time between Unix, RT-11 and RSX-11, I was much frustrated with Unix not having asynchronous I/O at the application level. Then when Unix acquired it, it was buggy forever. Then we got multithreaded applications, to a first approximation that seemed good enough. The scalability issue makes sense.