From owner-freebsd-current Wed May 15 07:21:47 1996 Return-Path: owner-current Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id HAA21235 for current-outgoing; Wed, 15 May 1996 07:21:47 -0700 (PDT) Received: from dyson.iquest.net (dyson.iquest.net [198.70.144.127]) by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id HAA21224 for ; Wed, 15 May 1996 07:21:43 -0700 (PDT) Received: (from root@localhost) by dyson.iquest.net (8.7.5/8.6.9) id JAA22146; Wed, 15 May 1996 09:21:34 -0500 (EST) From: "John S. Dyson" Message-Id: <199605151421.JAA22146@dyson.iquest.net> Subject: Re: re joe's questions on vm/mincore/etc. To: rminnich@Sarnoff.COM (Ron G. Minnich) Date: Wed, 15 May 1996 09:21:34 -0500 (EST) Cc: current@freebsd.org In-Reply-To: from "Ron G. Minnich" at May 15, 96 05:50:03 am X-Mailer: ELM [version 2.4 PL24 ME8] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-current@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > something i'd like to have but have not spent time figuring out how to do > is just directly mmap the ptes for a piece of your own address space. > Then you don't have to take the hit that mincore requires: > syscall > walk ptes > copyout() > > So if anyone out there has mmap'ed their own ptes or knows how, i'm > listening. > I like Joe's response, about it being really non portable :-), but in -current as of after this weekend (watch out for another mega-commit), the ptes will be in their own object. It *might* be possible to do a vm_map_find using the pte object. At least we will be closer to being able to do that now (perhaps read-only :-)). After this next commit to the VM system, our fork perf will be about 20% faster, exec will be another 5% faster. John