From owner-freebsd-arch@FreeBSD.ORG Thu Aug 26 05:36:33 2004 Return-Path: Delivered-To: freebsd-arch@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D7CCF16A4CE; Thu, 26 Aug 2004 05:36:33 +0000 (GMT) Received: from pooker.samsco.org (pooker.samsco.org [168.103.85.57]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4430D43D54; Thu, 26 Aug 2004 05:36:31 +0000 (GMT) (envelope-from scottl@samsco.org) Received: from [192.168.0.201] ([192.168.0.201]) (authenticated bits=0) by pooker.samsco.org (8.12.11/8.12.10) with ESMTP id i7Q5bj0J003171; Wed, 25 Aug 2004 23:37:46 -0600 (MDT) (envelope-from scottl@samsco.org) Message-ID: <412D7643.9000700@samsco.org> Date: Wed, 25 Aug 2004 23:33:55 -0600 From: Scott Long User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.1) Gecko/20040801 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Poul-Henning Kamp References: <51730.1093498385@critter.freebsd.dk> In-Reply-To: <51730.1093498385@critter.freebsd.dk> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Status: No, hits=0.0 required=3.8 tests=none autolearn=no version=2.63 X-Spam-Checker-Version: SpamAssassin 2.63 (2004-01-11) on pooker.samsco.org cc: Matthew Jacob cc: sos@freebsd.org cc: Scott Long cc: arch@freebsd.org Subject: Re: potential re change for 5.3? X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 Aug 2004 05:36:34 -0000 Poul-Henning Kamp wrote: > In message <412D0868.9060203@freebsd.org>, Scott Long writes: > > >>I'm not suggesting anything different, just making a note of something >>that might be desirable in the future. In a way, I see GEOM as having >>the potential to be like Netgraph where it intercepts operations that it >>wants to process through it's framework and lets ones that it doesn't >>pass directly through without a decoupling through extra kernel threads. >>But that's only one possible strategy. Introducing the concept of a >>I/O scheduler that spawns KSE's to handle individual I/O requests is >>another possibility. > > > Well, the problem here is that requests which cannot be dealt with > due to resource shortages should be queued at the level where they > require least resources. A request queued inside a driver holds > far more resources than a request in the pure bio format at the > entrance to the driver for instance. Not necessarily. It's not hard for a driver to keep a request queued on the bioq and not consume and driver resources at all. > > And spawning KSE's in low memory situations is a recipe for suicide. > Probably true. Scott