Return to BSD News archive
Newsgroups: comp.unix.bsd.freebsd.misc Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!newshost.telstra.net!act.news.telstra.net!psgrain!iafrica.com!pipex-sa.net!plug.news.pipex.net!pipex!weld.news.pipex.net!pipex!tank.news.pipex.net!pipex!newsfeed.internetmci.com!in1.uu.net!twwells!bill From: bill@twwells.com (T. William Wells) Subject: Re: Poor performance with INN and FreeBSD. Organization: None, Mt. Laurel, NJ Message-ID: <DnqyIL.H0E@twwells.com> References: <311F8C62.4BC4@pluto.njcc.com> <4gqvs8$7u@uriah.heep.sax.de> <DnFM1F.4FG@twwells.com> <4ha75a$af@uriah.heep.sax.de> Date: Mon, 4 Mar 1996 14:20:44 GMT Lines: 19 In article <4ha75a$af@uriah.heep.sax.de>, J Wunsch <joerg_wunsch@uriah.heep.sax.de> wrote: : bill@twwells.com (T. William Wells) writes: : : > : ``large'' overhead is certainly an overstatement, unless you're going : > : to put your news server on a 386sx/16. : > : > I measured the amount of time spent in a regular NNTP feed spent : > in namei. It's 69% of the time needed to process an article. : : Wall clock or CPU time? Wall clock. Specifically, in ktrace output, from the namei call to the next event, vs. the time between select calls which contain namei calls. I am not even slightly surprised at this result; as I said in my earlier message, each namei call reads on average 44K of data and little of it is cached.