From owner-freebsd-fs@freebsd.org Wed Aug 19 12:18:44 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 6D7E89BC1F5 for ; Wed, 19 Aug 2015 12:18:44 +0000 (UTC) (envelope-from daniel@digsys.bg) Received: from smtp-sofia.digsys.bg (smtp-sofia.digsys.bg [193.68.21.123]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (Client CN "smtp-sofia.digsys.bg", Issuer "Digital Systems Operational CA" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id E74D8DAC for ; Wed, 19 Aug 2015 12:18:43 +0000 (UTC) (envelope-from daniel@digsys.bg) Received: from [193.68.6.110] ([193.68.6.110]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.9/8.14.9) with ESMTP id t7JCBnnl022634 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 19 Aug 2015 15:11:49 +0300 (EEST) (envelope-from daniel@digsys.bg) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2104\)) Subject: Re: Optimizing performance with SLOG/L2ARC From: Daniel Kalchev In-Reply-To: Date: Wed, 19 Aug 2015 15:11:49 +0300 Cc: FreeBSD Filesystems Content-Transfer-Encoding: quoted-printable Message-Id: <4BF27882-7BE1-480E-9903-434BDD202BB3@digsys.bg> References: To: javocado X-Mailer: Apple Mail (2.2104) 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: Wed, 19 Aug 2015 12:18:44 -0000 > On 19.08.2015 =D0=B3., at 3:28, javocado wrote: >=20 >=20 > 3. I know it's a good idea to mirror the SLOG (and I have). Do I = understand > correctly that I do not need to mirror the L2ARC since it's just a = read > cache, nothing to lose if the SSD goes down? >=20 There is a little known and grossly underestimated benefit of using = SLOG, even if it is not on SSD: less fragmentation in the pool. This is because, without SLOG ZFS will allocate the intent log records = from blocks in the pool. then free those blocks. These are all small = writes and leave behind a lot of holes. SLOG should be on it=E2=80=99s own drive anyway, normally, it=E2=80=99s = write-only and besides latency, a normal HDD should do as well. Of course, everything needs to be tested against the expected workload. Daniel