Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.mel.connect.com.au!news.syd.connect.com.au!phaedrus.kralizec.net.au!news.mel.aone.net.au!news.netspace.net.au!news.mira.net.au!news.vbc.net!vbcnet-west!samba.rahul.net!rahul.net!a2i!news.pbi.net!news.mathworks.com!uunet!in3.uu.net!205.230.225.2!news.BSDI.COM!usenet From: Tony Sanders <sanders@earth.com> Newsgroups: comp.unix.bsd.bsdi.misc Subject: Re: load average Date: Fri, 21 Mar 1997 13:04:56 -0700 Organization: Berkeley Software Design, Inc. Lines: 19 Message-ID: <3332E9E8.2781E494@earth.com> References: <5f4813$i90@eros.clara.net> <331805CC.19E@dragon.net.au> <5f9mbe$r6f@eros.clara.net> NNTP-Posting-Host: austin.bsdi.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Mailer: Mozilla 3.0Gold (X11; U; BSD/OS 2.0 i386) Xref: euryale.cc.adfa.oz.au comp.unix.bsd.bsdi.misc:6437 Steve Rawlinson wrote: > >to fix it up. Is it just Apache 1.1.1? I don't remember previous ... > It happens on 1.0, 1.1 and 1.2b3 which are the three versions I have > running here. I have a cron job to kill -HUP it but as I say it seems > to be error in the load reporting rather than an actual load problem. > > One suggested explanation I got from Chris was that apache does > something which syncs it with the load-averaging clock which I assume > would artificially raise the load average reported by 1. It only seems > to happen on very low load servers. Yeap, that is what is happening. We've seen it happen here at BSDI even and looked at it to make sure something else wasn't going on. I think that apache is probably over doing the wake-up every second thing and when I get some time I'll probably submit a patch (unless someone else does it in the meantime) but since it isn't hurting anything that all it's not really worth messing with too much :-) --sanders