From owner-freebsd-questions@FreeBSD.ORG  Wed Nov 14 00:46:16 2012
Return-Path: <owner-freebsd-questions@FreeBSD.ORG>
Delivered-To: freebsd-questions@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52])
 by hub.freebsd.org (Postfix) with ESMTP id C2FB8DA8
 for <freebsd-questions@freebsd.org>; Wed, 14 Nov 2012 00:46:16 +0000 (UTC)
 (envelope-from bonomi@mail.r-bonomi.com)
Received: from mail.r-bonomi.com (mx-out.r-bonomi.com [204.87.227.120])
 by mx1.freebsd.org (Postfix) with ESMTP id 6C3DA8FC08
 for <freebsd-questions@freebsd.org>; Wed, 14 Nov 2012 00:46:15 +0000 (UTC)
Received: (from bonomi@localhost)
 by mail.r-bonomi.com (8.14.4/rdb1) id qAE0kpw0084082;
 Tue, 13 Nov 2012 18:46:51 -0600 (CST)
Date: Tue, 13 Nov 2012 18:46:51 -0600 (CST)
From: Robert Bonomi <bonomi@mail.r-bonomi.com>
Message-Id: <201211140046.qAE0kpw0084082@mail.r-bonomi.com>
To: freebsd-questions@freebsd.org, rfg@tristatelogic.com
Subject: Re: Advanced Format Drive ?
In-Reply-To: <4073.1352844470@tristatelogic.com>
X-BeenThere: freebsd-questions@freebsd.org
X-Mailman-Version: 2.1.14
Precedence: list
List-Id: User questions <freebsd-questions.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/options/freebsd-questions>, 
 <mailto:freebsd-questions-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-questions>
List-Post: <mailto:freebsd-questions@freebsd.org>
List-Help: <mailto:freebsd-questions-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-questions>, 
 <mailto:freebsd-questions-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 14 Nov 2012 00:46:16 -0000


> From: "Ronald F. Guilmette" <rfg@tristatelogic.com>
> Subject: Re: Advanced Format Drive ?
> Date: Tue, 13 Nov 2012 14:07:50 -0800
>
>
> And while we are on the subject... Has anybody ever down any analysis
> (i.e. benchmarking) to find out if -f 4096 is even the best number for
> a modern high(er) capacity drive?  I'm just sort-of wondering if 8192
> or 16384 might be better.

As long as the fragment size is a power-of-two multiple of the media sector
size, there is no significant performance difference.  The only case where
a larger fragment size makes any difference is heavy random i/o on files
where the larger fragment size translates to one less level of indirect
block in the meta-data.

Larger fragment sizes also make for more 'waste' space in the 'used'
part of the disk, assuming random file sizes.

And reduce the space savings gained by _not_ writing 'holes' to disk.

For these reasons, in general, small is better.

> freebsd-questions@freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-questions
> To unsubscribe, send any mail to "freebsd-questions-unsubscribe@freebsd.org"
>