From owner-freebsd-fs@FreeBSD.ORG Wed Nov 28 15:55:04 2012 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id DBCF1289 for ; Wed, 28 Nov 2012 15:55:04 +0000 (UTC) (envelope-from metindoslu@gmail.com) Received: from mail-qa0-f54.google.com (mail-qa0-f54.google.com [209.85.216.54]) by mx1.freebsd.org (Postfix) with ESMTP id 906D28FC0C for ; Wed, 28 Nov 2012 15:55:04 +0000 (UTC) Received: by mail-qa0-f54.google.com with SMTP id g24so5684770qab.13 for ; Wed, 28 Nov 2012 07:55:03 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type:content-transfer-encoding; bh=VbHXriEGsr/88masLf5fbDS5zMLJOGhmoyF2MWbtTD8=; b=g2dukh1frmXsPP6OAlgcoSR0Z79NiXwJ8eZlQJBI8cTuFgWEfEOj9qteNbOEJenRoV wfR/Qha9DvIH78Annv8MsU6qXkl9a7g5g+QnoqdhigJEqG/bdUhaz/gR5LRRW10YpYMC H5QOfmZ1A6I4YhK8aX/9CI0MDM9E81pjoL4aA5Rilq8v1v1kYysgxgeEXla2GofCThhF c1LWAbqE36hg1y+O9RHWDDvFOgHaEijXL7YVGvy96UC4fr0Hj+WU2gOcCz367z0ArwXW iLyYWBpz2D77TOIGwSTYOJp0DLJZ01r+IEl7ROWKr83ClL30Z1mQKhCgWbhD/42hozrG Yi9A== Received: by 10.49.75.226 with SMTP id f2mr16265101qew.43.1354118102908; Wed, 28 Nov 2012 07:55:02 -0800 (PST) MIME-Version: 1.0 Received: by 10.49.35.242 with HTTP; Wed, 28 Nov 2012 07:54:42 -0800 (PST) In-Reply-To: References: From: =?UTF-8?B?TWV0aW4gRMO2xZ9sw7w=?= Date: Wed, 28 Nov 2012 17:54:42 +0200 Message-ID: Subject: Re: Performance Difference on UFS and ZFS To: Sergey Kandaurov Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@freebsd.org X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 28 Nov 2012 15:55:04 -0000 Hi Sergey, I tested it on a cc1.4xlarge EC2 instance, here is the specs: 23 GiB of memory 33.5 EC2 Compute Units (2 x Intel Xeon X5570, quad-core =E2=80=9CNehalem=E2= =80=9D architecture) 1690 GB of instance storage 64-bit platform I installed PostgreSQL from its port on FreeBSD. I didn't do any tuning for PostgreSQL or FreeBSD. Data access pattern consists of completely from sequential reads such "select count(*) from table_name". I measured performance with PostgreSQL's timing option. As as side note; all queries are served from memory, so there were no disk usage for these tests. Thanks, Metin On Wed, Nov 28, 2012 at 4:49 PM, Sergey Kandaurov wrote= : > On 28 November 2012 12:35, Metin D=C3=B6=C5=9Fl=C3=BC wrote: >> Hi - >> >> I installed PostgreSQL 9.1.6 on FreeBSD 9.0-RELEASE, and compared ZFS >> to UFS. I also made sure all data easily fit into memory, ran some >> sequential scan queries on the database. >> >> Query run times on UFS were 100-200% slower than those of ZFS. This >> was intriguing as all data came from memory. What could be causing >> such a large performance difference? > > Hi Metin D=C3=B6=C5=9Fl=C3=BC! > > That's interesting. Can you please share your settings? > Hardware configuration, system tuning (sysctl, zfs), PostgreSQL settings, > data access pattern (read/write ratio), and how you measure performance > would be a good start. > > -- > wbr, > pluknet --=20 Metin D=C3=B6=C5=9Fl=C3=BC