From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37393) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1c7K2X-0005lC-3w for qemu-devel@nongnu.org; Thu, 17 Nov 2016 05:35:33 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1c7K2W-0004i2-Fb for qemu-devel@nongnu.org; Thu, 17 Nov 2016 05:35:33 -0500 Date: Thu, 17 Nov 2016 11:35:23 +0100 From: Kevin Wolf Message-ID: <20161117103523.GA5610@noname.redhat.com> References: <20161116144144.674250d7644ef8f8cc516993@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20161116144144.674250d7644ef8f8cc516993@gmail.com> Subject: Re: [Qemu-devel] your mail List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Christopher Oliver Cc: qemu-devel@nongnu.org, qemu-block@nongnu.org, mreitz@redhat.com Am 16.11.2016 um 20:41 hat Christopher Oliver geschrieben: > This patch (hack?) works around the slowness in SEEK_HOLE for large dense files > on Linux tmpfs. It may improve life elsewhere as well, and the penalty of the checks > should be vanishingly small where it is not needed. > > If I'm subtly (or not so subtly) wrong, please fire back. Can't quote the commit message easily because you put it into an attachment, but I'm not sure if we can make the assumption you're making. Accessing a raw image from multiple VMs sounds valid to me as long as a cluster file system is used. Kevin