From owner-freebsd-current@FreeBSD.ORG Tue May 18 00:50:25 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2B46E16A4CE; Tue, 18 May 2004 00:50:25 -0700 (PDT) Received: from ioskeha.hittite.isp.9tel.net (ioskeha.hittite.isp.9tel.net [62.62.156.27]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8C36C43D1D; Tue, 18 May 2004 00:50:24 -0700 (PDT) (envelope-from clefevre-lists@9online.fr) Received: from pc2k (unknown [81.185.56.16]) by ioskeha.hittite.isp.9tel.net (Postfix) with SMTP id 4C66517B499; Tue, 18 May 2004 09:51:13 +0200 (CEST) Message-ID: <021c01c43cac$c6b4b6b0$7890a8c0@dyndns.org> From: "Cyrille Lefevre" To: "Scott Long" , "Dan Nelson" References: <20040515220258.H920@ganymede.hub.org><20040515233728.Q30269@ganymede.hub.org><20040516163039.GE29158@dan.emsphone.com> <40A79A54.3090703@freebsd.org> Date: Tue, 18 May 2004 09:50:23 +0200 Organization: ACME MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1409 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1409 cc: freebsd-current@freebsd.org cc: Michael Hamburg Subject: Re: fsck in -current X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 18 May 2004 07:50:25 -0000 "Scott Long" wrote: > Dan Nelson wrote: [snip] > > Fsck takes very little CPU; it's almost all disk I/O, and bgfsck tries > > to throttle its load if it thinks that there's too much disk load. > > Actually, bgfsck unconditionally inserts a delay into every 8th i/o > operation to try to keep from saturating the disks. Unfortunately > this isn't terribly sophisticated and it results in bgfsck taking > an eternity whether the system is idle, loaded, or reniced. doesn't the delay be related to the load average or to ki_pctcpu (sys/user.h) ? say, allow bgfsck to eat up to 5 or 10 % of CPU usage ? see getpcpu() in bin/ps/print.c for details. Cyrille Lefevre. -- home: mailto:cyrille.lefevre@laposte.net