From owner-freebsd-fs@freebsd.org  Wed Aug 19 16:29:59 2015
Return-Path: <owner-freebsd-fs@freebsd.org>
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 A0B019BEE0D
 for <freebsd-fs@mailman.ysv.freebsd.org>; Wed, 19 Aug 2015 16:29:59 +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 36B541695
 for <freebsd-fs@freebsd.org>; Wed, 19 Aug 2015 16:29:58 +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 t7JGTsGB001101
 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO);
 Wed, 19 Aug 2015 19:29:55 +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 <daniel@digsys.bg>
In-Reply-To: <3FE10173-656C-4744-AB2D-32148A34CB46@pk1048.com>
Date: Wed, 19 Aug 2015 19:29:54 +0300
Cc: FreeBSD Filesystems <freebsd-fs@freebsd.org>, javocado <javocado@gmail.com>
Content-Transfer-Encoding: quoted-printable
Message-Id: <6EAEF15E-03B0-4C75-B252-FE56DEA38DA2@digsys.bg>
References: <CAP1HOmTidC3+G4XfhvkQxieo+SYMq-JWiXF9Cs4FSW2VqkktWA@mail.gmail.com>
 <023F881D-CCC5-4FCA-B09D-EB92C3BFBC03@pk1048.com>
 <CALeZrrRex43B6N7GkTtaP36v5q7mQF8U9V1bU2W1+2uh8fhhiQ@mail.gmail.com>
 <3FE10173-656C-4744-AB2D-32148A34CB46@pk1048.com>
To: PK1048 <paul@pk1048.com>
X-Mailer: Apple Mail (2.2104)
X-BeenThere: freebsd-fs@freebsd.org
X-Mailman-Version: 2.1.20
Precedence: list
List-Id: Filesystems <freebsd-fs.freebsd.org>
List-Unsubscribe: <https://lists.freebsd.org/mailman/options/freebsd-fs>,
 <mailto:freebsd-fs-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-fs/>
List-Post: <mailto:freebsd-fs@freebsd.org>
List-Help: <mailto:freebsd-fs-request@freebsd.org?subject=help>
List-Subscribe: <https://lists.freebsd.org/mailman/listinfo/freebsd-fs>,
 <mailto:freebsd-fs-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 19 Aug 2015 16:29:59 -0000


> On 19.08.2015 =D0=B3., at 19:10, PK1048 <paul@pk1048.com> wrote:
>=20
> On Aug 19, 2015, at 12:02, Schweiss, Chip <chip@innovates.com> wrote:
>=20
>>  ZFS doesn't play well with the
>> ZIL on the pool with SSDs.   Even an SSD of the same type as the pool
>> devices as the log device will fix the latency problem and throughput
>> problems.
>=20
> If your load is sync writes then you decidedly want a LOG device, even =
if it is the same type as the devices in the pool. For the reasons =
others have posted.
>=20

This is because of the reason I mentioned earlier. When you don=E2=80=99t =
have separate SLOG, ZFS will allocate the ZIL record from the pool =
blocks, then when the blocks are at their intended location, delete that =
ZIL record from the pool. This plays bad with SSDs. You also get much =
fragmentation.

When you have SLOG, ZFS will write the ZIL record to the SLOG, then =
(batch) write the blocks to their intended place, then forget about the =
SLOG (it=E2=80=99s not freed, just overwritten). This plays much better =
with SSDs.

You should get much better performance, with pure-SSD pool, if you =
allocate small portion of the same SSD for SLOG. I know it sounds =
counderintuitive. :)
Of course, much better performance with separate SSD for the SLOG.

Daniel