From owner-freebsd-geom@FreeBSD.ORG  Thu Mar  5 09:46:35 2009
Return-Path: <owner-freebsd-geom@FreeBSD.ORG>
Delivered-To: freebsd-geom@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id 4B49C1065672
	for <freebsd-geom@freebsd.org>; Thu,  5 Mar 2009 09:46:35 +0000 (UTC)
	(envelope-from jespasac@minibofh.org)
Received: from smtp02.cdmon.com (smtp02.cdmon.com [212.36.74.229])
	by mx1.freebsd.org (Postfix) with ESMTP id 0DCF58FC1C
	for <freebsd-geom@freebsd.org>; Thu,  5 Mar 2009 09:46:34 +0000 (UTC)
	(envelope-from jespasac@minibofh.org)
Received: from jespasac.cdmon.com (62.Red-217-126-43.staticIP.rima-tde.net
	[217.126.43.62])
	by smtp02.cdmon.com (Postfix) with ESMTP id 0AFC8496A4;
	Thu,  5 Mar 2009 10:30:58 +0100 (CET)
Message-ID: <49AF9B6C.8090908@minibofh.org>
Date: Thu, 05 Mar 2009 10:29:16 +0100
From: Jordi Espasa Clofent <jespasac@minibofh.org>
User-Agent: Thunderbird 2.0.0.19 (X11/20090107)
MIME-Version: 1.0
To: freebsd-geom@freebsd.org
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 8bit
Subject: gmirror(8): round-robin vs. load algorithm
X-BeenThere: freebsd-geom@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: GEOM-specific discussions and implementations
	<freebsd-geom.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-geom>,
	<mailto:freebsd-geom-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-geom>
List-Post: <mailto:freebsd-geom@freebsd.org>
List-Help: <mailto:freebsd-geom-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-geom>,
	<mailto:freebsd-geom-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Thu, 05 Mar 2009 09:46:35 -0000

Hi all,

It's supposed that 'round-robin' algorithm has the best performance in 
gmirror(8).

However, looking directly at code (1) I see that the only difference 
between 'round-robin' and 'load' algorithm is:

[...]
	binuptime(&curtime);
	/*
	 * Find a disk which the smallest load.
	 */
	disk = NULL;
	LIST_FOREACH(dp, &sc->sc_disks, d_next) {
		if (dp->d_state != G_MIRROR_DISK_STATE_ACTIVE)
			continue;
		/* If disk wasn't used for more than 2 sec, use it. */
		if (curtime.sec - dp->d_last_used.sec >= 2) {
			disk = dp;
			break;
		}
		if (disk == NULL ||
		    bintime_cmp(&dp->d_delay, &disk->d_delay) < 0) {
			disk = dp;
		}
	}
[...]

The key is in "/* If disk wasn't used for more than 2 sec, use it. */", 
but, for the rest, 'load' algorithm implementation seems the same as 
round-robin. If I'm right, my question is

¿where is the use of 'load' recommended?

I understand that 'load' will be good in servers with a lot of disk 
activity (large disk I/O could provoque that gmirror expulses a mirror 
member or even reboot or panics the system) because it try always the 
low-loaded disk.

(1) 
http://www.freebsd.org/cgi/cvsweb.cgi/~checkout~/src/sys/geom/mirror/g_mirror.c?rev=1.93.6.1;content-type=text%2Fplain

-- 
Thanks,
Jordi Espasa Clofent