From owner-freebsd-fs@FreeBSD.ORG Tue Nov 1 21:17:14 2011 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 12C7F1065670 for ; Tue, 1 Nov 2011 21:17:14 +0000 (UTC) (envelope-from tom.hurst@clara.net) Received: from ita.aagh.net (unknown [IPv6:2a03:9800:10:11::2]) by mx1.freebsd.org (Postfix) with ESMTP id A86958FC08 for ; Tue, 1 Nov 2011 21:17:13 +0000 (UTC) Received: from cpc1-hart9-2-0-cust900.11-3.cable.virginmedia.com ([86.30.3.133] helo=voi.aagh.net ident=mailnull) by ita.aagh.net with esmtps (TLSv1:AES256-SHA:256) (Exim 4.76 (FreeBSD)) (envelope-from ) id 1RLLhm-000EZB-P9; Tue, 01 Nov 2011 21:17:10 +0000 Received: from freaky by voi.aagh.net with local (Exim 4.77 (FreeBSD)) (envelope-from ) id 1RLLhm-000DUC-Er; Tue, 01 Nov 2011 21:17:10 +0000 Date: Tue, 1 Nov 2011 21:17:10 +0000 From: Thomas Hurst To: Shivaram Upadhyayula Message-ID: <20111101211710.GA36797@voi.aagh.net> Mail-Followup-To: Thomas Hurst , Shivaram Upadhyayula , Dennis Glatting , freebsd-fs@freebsd.org References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: Organization: Not much. User-Agent: Mutt/1.5.21 (2010-09-15) X-SA-Exim-Connect-IP: 86.30.3.133 X-SA-Exim-Mail-From: tom.hurst@clara.net X-SA-Exim-Scanned: No (on ita.aagh.net); SAEximRunCond expanded to false Cc: freebsd-fs@freebsd.org Subject: Re: ZFS/compression/performance X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 01 Nov 2011 21:17:14 -0000 * Shivaram Upadhyayula (shivaram.u@quadstor.com) wrote: > I have recently started using ZFS and during that time i have tried out > ZFS with lzf (http://oldhome.schmorp.de/marc/liblzf.html) and it seems > to perform much better, both in speed and ratio over lzjb. > > Anyway my point is that, somewhere down the line other compression > algorithms should be evaluated. gzip seems slow and it looks like lzjb > may not be sufficient. For anyone interested, I have attached some of > the tests i had run and the diff for lzf support. No you haven't :) -- Thomas 'Freaky' Hurst http://hur.st/