From owner-freebsd-fs@freebsd.org Mon Sep 21 13:57:46 2015 Return-Path: Delivered-To: freebsd-fs@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id ADA5FA06A23 for ; Mon, 21 Sep 2015 13:57:46 +0000 (UTC) (envelope-from quartz@sneakertech.com) Received: from douhisi.pair.com (douhisi.pair.com [209.68.5.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 8DDEF107F for ; Mon, 21 Sep 2015 13:57:46 +0000 (UTC) (envelope-from quartz@sneakertech.com) Received: from [10.2.2.1] (pool-173-48-121-235.bstnma.fios.verizon.net [173.48.121.235]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by douhisi.pair.com (Postfix) with ESMTPSA id 8B4253F7AB for ; Mon, 21 Sep 2015 09:57:44 -0400 (EDT) Message-ID: <56000CD8.4030208@sneakertech.com> Date: Mon, 21 Sep 2015 09:57:44 -0400 From: Quartz MIME-Version: 1.0 To: FreeBSD FS Subject: Re: ZFS cpu requirements, with/out compression and/or dedup References: <55FD9A2B.8060207@sneakertech.com> In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 21 Sep 2015 13:57:46 -0000 > This is completely untrue, there performance issues with dedup are > limited to writes only, as it needs to check the DDT table for every > write to the file system with dedup enabled. Once the data is on the > disk there is no overhead, and in many cases a performance boost as less > data on the disk means less head movement and its also more likely to be > in any available caches. If the write performance does become an issue > you can turn it off on that particular file system. This may cause you > to no longer have enough capacity on the pool, but then pools are easily > extended. It still needs to keep the tables in memory as long as there's still deduped data on disk though, right? Else what keeps track of which blocks are used by which files?