From owner-freebsd-hackers@FreeBSD.ORG  Mon Sep  4 08:42:49 2006
Return-Path: <owner-freebsd-hackers@FreeBSD.ORG>
X-Original-To: freebsd-hackers@freebsd.org
Delivered-To: freebsd-hackers@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id 817FC16A59C
	for <freebsd-hackers@freebsd.org>; Mon,  4 Sep 2006 08:42:49 +0000 (UTC)
	(envelope-from m.ehinger@ltur.de)
Received: from postx.gateway-inter.net (postx.gateway-inter.net
	[213.144.19.80])
	by mx1.FreeBSD.org (Postfix) with ESMTP id 63CC443D6A
	for <freebsd-hackers@freebsd.org>; Mon,  4 Sep 2006 08:42:36 +0000 (GMT)
	(envelope-from m.ehinger@ltur.de)
In-Reply-To: <20060903.100108.-108810397.imp@bsdimp.com>
Sensitivity: 
To: "M. Warner Losh" <imp@bsdimp.com>
From: m.ehinger@ltur.de
MIME-Version: 1.0
Message-ID: <OF7D027A05.7456D463-ONC12571DF.002EFB0C-C12571DF.002FD6A8@gateway-inter.net>
Date: Mon, 4 Sep 2006 10:43:12 +0200
Content-type: text/plain; charset=US-ASCII
X-Mailman-Approved-At: Mon, 04 Sep 2006 12:35:32 +0000
Cc: freebsd-hackers@freebsd.org
Subject: Re: dev vs. sysctl
X-BeenThere: freebsd-hackers@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Technical Discussions relating to FreeBSD
	<freebsd-hackers.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-hackers>, 
	<mailto:freebsd-hackers-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-hackers>
List-Post: <mailto:freebsd-hackers@freebsd.org>
List-Help: <mailto:freebsd-hackers-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-hackers>,
	<mailto:freebsd-hackers-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Mon, 04 Sep 2006 08:42:49 -0000



"M. Warner Losh" <imp@bsdimp.com> schrieb am 03.09.2006 18:01:08:


> In the past I did some silly measurements and found that sysctls were
> slower by a small amount.  I never could figure out why, since the
> path to the sysctl seemed like it would be shorter than the path to
> the read.  This was in the 3.x timeframe, so your best bet is to code
> up both and see which one is better today.


OK i did that and it seems to be still the same. "read" seems to be faster then th sysctl call.

I got about 8.7 seconds for 100,000 sysctl reads and 1.8 seconds for 100,000 read calls. Measured on a Thinkpad with 75MHz CPU
frequency.


Thanks

Maik