From owner-freebsd-current@FreeBSD.ORG Mon Jan 23 22:57:24 2006 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D51FB16A4A9; Mon, 23 Jan 2006 22:57:23 +0000 (GMT) (envelope-from des@des.no) Received: from tim.des.no (tim.des.no [194.63.250.121]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9CA5F441EC; Mon, 23 Jan 2006 22:35:49 +0000 (GMT) (envelope-from des@des.no) Received: from tim.des.no (localhost [127.0.0.1]) by spam.des.no (Postfix) with ESMTP id 56B8B2087; Mon, 23 Jan 2006 23:35:42 +0100 (CET) X-Spam-Tests: AWL,BAYES_00,FORGED_RCVD_HELO X-Spam-Learn: ham X-Spam-Score: -3.2/3.0 X-Spam-Checker-Version: SpamAssassin 3.1.0 (2005-09-13) on tim.des.no Received: from xps.des.no (des.no [80.203.243.180]) by tim.des.no (Postfix) with ESMTP id 3DE062086; Mon, 23 Jan 2006 23:35:42 +0100 (CET) Received: by xps.des.no (Postfix, from userid 1001) id 2212B33C1D; Mon, 23 Jan 2006 23:35:42 +0100 (CET) To: Julian Elischer References: <43D05151.5070409@elischer.org> <200601231616.49140.jhb@freebsd.org> <43D55739.80608@elischer.org> From: des@des.no (=?iso-8859-1?q?Dag-Erling_Sm=F8rgrav?=) Date: Mon, 23 Jan 2006 23:35:42 +0100 In-Reply-To: <43D55739.80608@elischer.org> (Julian Elischer's message of "Mon, 23 Jan 2006 14:22:49 -0800") Message-ID: <86lkx6tvwh.fsf@xps.des.no> User-Agent: Gnus/5.110002 (No Gnus v0.2) Emacs/21.3 (berkeley-unix) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-current@freebsd.org Subject: Re: kernel thread as real threads.. X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Jan 2006 22:57:24 -0000 Julian Elischer writes: > However I would like to suggest that we change the way that aio > works.. > > My suggestion is that when a process does AIO, that we "fork a > ksegroup" and attach it to the process, and assign it a (or some) > worker thread to do the aio work. The userland process would be > oblivious of the extra (kernel) threads in that kseg and they would > be independently schedulable. They would however automatically have > full access to the correct address space. Agreed. This would actually greatly simplify the aio code (getting rid of all the vm monkeying), and reduce the likelihood of future security or stability issues with it. DES --=20 Dag-Erling Sm=F8rgrav - des@des.no