From owner-freebsd-hackers Thu Jan 28 06:10:51 1999 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id GAA20416 for freebsd-hackers-outgoing; Thu, 28 Jan 1999 06:10:51 -0800 (PST) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from obie.softweyr.com ([204.68.178.33]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id GAA20411 for ; Thu, 28 Jan 1999 06:10:48 -0800 (PST) (envelope-from wes@softweyr.com) Received: from softweyr.com (zaphod.softweyr.com [204.68.178.35]) by obie.softweyr.com (8.8.8/8.8.8) with ESMTP id HAA29931; Thu, 28 Jan 1999 07:10:13 -0700 (MST) (envelope-from wes@softweyr.com) Message-ID: <36B06FC5.1EA65667@softweyr.com> Date: Thu, 28 Jan 1999 07:10:13 -0700 From: Wes Peters Organization: Softweyr llc X-Mailer: Mozilla 4.5 [en] (X11; U; FreeBSD 3.0-RELEASE i386) X-Accept-Language: en MIME-Version: 1.0 To: dyson@iquest.net CC: Matthew Dillon , toasty@home.dragondata.com, hackers@FreeBSD.ORG Subject: Re: High Load cron patches - comments? References: <199901272216.RAA00419@y.dyson.net> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG "John S. Dyson" wrote: > > Matthew Dillon said: > > > > : > > :So this is why pmake drives our system load average up to 8-10 before > > :dropping back down to the assigned limit of 5, huh? Maybe we should > > :fix the load average computations as John suggested. > > : > > :Wes Peters Softweyr LLC > > :http://www.softweyr.com/~softweyr wes@softweyr.com > > > > There's nothing wrong with the load average computation, it's a 1, 5, > > and 15 minute pseudo-average just as advertised. What's wrong are the > > programs that try to use it to regulate themselves. > > > Yep, I didn't really mean that the existing load average calculation be > modified, but develop a better scheme for providing load regulation info > to processes. To me, load average is mostly informational, and long > term trend data. Lots of things can happen within the load average > attack interval. > > I can develop some rather complete and lossless calculations that > provide accurate and useful load indicators. In fact, I think that > a generic load mgmt scheme might be useful. Especially as we start diving more into SMP and threaded applications; which will need some effective means of throttling themselves. The problem with Matt's comment above is he doesn't offer any useful alternative, and couting child processes just isn't an effective means of throttling the overall load on a machine. -- "Where am I, and what am I doing in this handbasket?" Wes Peters Softweyr LLC http://www.softweyr.com/~softweyr wes@softweyr.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message