From: Goswin von Brederlow Subject: Re: Porting Zfs features to ext2/3 Date: Thu, 07 Aug 2008 14:09:35 +0200 Message-ID: <877iat6n7k.fsf@frosties.localdomain> References: <18674437.post@talk.nabble.com> <1217199281.6992.0.camel@telesto> <20080727233855.GB9378@mit.edu> <20080730012909.GC29748@mit.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Szabolcs Szakacsits , linux-ext4@vger.kernel.org To: Theodore Tso Return-path: Received: from fmmailgate02.web.de ([217.72.192.227]:37933 "EHLO fmmailgate02.web.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755731AbYHGM3L (ORCPT ); Thu, 7 Aug 2008 08:29:11 -0400 In-Reply-To: <20080730012909.GC29748@mit.edu> (Theodore Tso's message of "Tue, 29 Jul 2008 21:29:09 -0400") Sender: linux-ext4-owner@vger.kernel.org List-ID: Theodore Tso writes: > On Tue, Jul 29, 2008 at 10:52:26PM +0000, Szabolcs Szakacsits wrote: >> I did also an in memory test on a T9300@2.5, with disk I/O completely >> eliminated. Results: >> >> tmpfs: 975 MB/sec >> ntfs-3g: 889 MB/sec (note, this FUSE driver is not optimized yet) >> ext3: 675 MB/sec ... > So it's issueing lots of 4k writes, one page at a time, because it > needs to track the completion of each block. This creates a > significant CPU overhead, which dominates in an all-memory test. > Although this is not an issue in real-life today, it will likely > become an issue in real-life solid state disks (SSD's). This already is a major issue for us. We are starting to use SAS raid boxes that deliver >350MB/s write and >600MB/s read performance with lustre, which is ext3 with patches. It is somewhat between ext3 and ext4 in that it has some of its features but not all. > Fortunately, ext4's blktrace when copying a large file looks like > this: That is promising. Once the 64BIT feature becomes usable we plan to port lustre to use ext4 as base filesystem. The current 8TiB limit is a real pain. MfG Goswin