From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1Jys8P-0007dd-Ax for qemu-devel@nongnu.org; Wed, 21 May 2008 13:29:53 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1Jys8M-0007as-AW for qemu-devel@nongnu.org; Wed, 21 May 2008 13:29:52 -0400 Received: from [199.232.76.173] (port=50850 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Jys8M-0007ae-2m for qemu-devel@nongnu.org; Wed, 21 May 2008 13:29:50 -0400 Received: from host36-195-149-62.serverdedicati.aruba.it ([62.149.195.36]:52354 helo=mx.cpushare.com) by monty-python.gnu.org with esmtps (TLS-1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.60) (envelope-from ) id 1Jys8L-0000vz-Ua for qemu-devel@nongnu.org; Wed, 21 May 2008 13:29:50 -0400 Date: Wed, 21 May 2008 19:01:29 +0200 From: Andrea Arcangeli Subject: Re: [Qemu-devel] Re: [PATCH][v2] Align file accesses with cache=off (O_DIRECT) Message-ID: <20080521170129.GF22488@duo.random> References: <48341783.3060204@qumranet.com> <20080521134154.GA15210@shareable.org> <483429EB.7070705@codemonkey.ws> <48342F05.2090603@qumranet.com> <48343106.4070801@codemonkey.ws> <48343844.1050107@qumranet.com> <20080521153454.GB20527@shareable.org> <48344793.2020902@codemonkey.ws> <20080521162406.GA21501@shareable.org> <48345258.9040004@qumranet.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <48345258.9040004@qumranet.com> Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Avi Kivity Cc: Blue Swirl , Laurent Vivier , qemu-devel@nongnu.org, Paul Brook On Wed, May 21, 2008 at 07:48:24PM +0300, Avi Kivity wrote: > Hmm, if remap_file_pages() supports MAP_PRIVATE, that solves all the > problems neatly. > > Andrea, do you know if that combination works? No, it only supports MAP_SHARED. Why would anyone want MAP_PRIVATE for real I/O operations? MAP_PRIVATE is primarily for binaries and things that are readonly on disk and that we may want to update (like for dynamic linking w/o hardlinking). Or is that for -snapshot support, to keep the modifications in anonymous ram? I imagine you want remap_file_pages for zerocopy I/O without using O_DIRECT. If you use O_DIRECT you don't need mmap. However O_DIRECT work best with kernel asyncio for small seeking blocks so all I/O can be submitted at the same time. writev also works better than write for O_DIRECT.