From owner-freebsd-stable@FreeBSD.ORG Mon Feb 13 06:36:34 2012 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 41E44106564A; Mon, 13 Feb 2012 06:36:34 +0000 (UTC) (envelope-from ml@os2.kiev.ua) Received: from s1.sdv.com.ua (s1.sdv.com.ua [IPv6:2a01:d0:81f8::2]) by mx1.freebsd.org (Postfix) with ESMTP id B1BBF8FC12; Mon, 13 Feb 2012 06:36:33 +0000 (UTC) Received: from [2001:470:6f:26:226:b9ff:fedd:5cf1] by s1.sdv.com.ua with esmtpsa (TLSv1:CAMELLIA256-SHA:256) (Exim 4.77 (FreeBSD)) (envelope-from ) id 1RwpWV-000CAR-74; Mon, 13 Feb 2012 08:36:29 +0200 Message-ID: <4F38AF69.6010506@os2.kiev.ua> Date: Mon, 13 Feb 2012 07:36:25 +0100 From: Alex Samorukov User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:9.0) Gecko/20111229 Thunderbird/9.0 MIME-Version: 1.0 To: Adrian Chadd References: <4F215A99.8020003@os2.kiev.ua> <4F27C04F.7020400@omnilan.de> <4F27C7C7.3060807@os2.kiev.ua> <4F37F81E.7070100@os2.kiev.ua> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-SA-Score: -1.0 Cc: Harald Schmalzbauer , freebsd-stable@freebsd.org Subject: Re: disk devices speed is ugly X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Feb 2012 06:36:34 -0000 On 02/13/2012 06:27 AM, Adrian Chadd wrote: > On 12 February 2012 09:34, Alex Samorukov wrote: > >> Yes. But it will nit fix non-cached access to the disk (raw) devices. And >> this is the main reason why ntfs-3g and exfat are much slower then working >> on Linux. > But _that_ can be fixed with the appropriate application of a sensible > caching layer. With every application? :) Are you know anyone who wants to do this? At least for 3 fuse filesystems. Also, caching in user-land is much slower and more dangerous. There is a libublio utility which is done to provide userland caching (it implements pwrite/pread replacement) and it is in use by this 2 ports. > > So if there are alignment issues, let's fix those up first so > filesystems act sensibly with the block device layer. Then yes, adding > a caching layer that works. I didn't get very good performance with > g_cache when i last tried it. Because its very primitive. Once again - try to compare performance of the exfat or ntfs-3g on Linux and FreeBSD. Raw device speed (i used USB) is pretty the same, but resulting speed is very different, as well as I/O characteristic.