From owner-freebsd-hackers Wed Oct 25 16: 9:52 2000 Delivered-To: freebsd-hackers@freebsd.org Received: from fw.wintelcom.net (ns1.wintelcom.net [209.1.153.20]) by hub.freebsd.org (Postfix) with ESMTP id BD5CF37B4C5 for ; Wed, 25 Oct 2000 16:09:47 -0700 (PDT) Received: (from bright@localhost) by fw.wintelcom.net (8.10.0/8.10.0) id e9PN9ip00617; Wed, 25 Oct 2000 16:09:44 -0700 (PDT) Date: Wed, 25 Oct 2000 16:09:44 -0700 From: Alfred Perlstein To: Jonathan Lemon Cc: Dan Kegel , hackers@FreeBSD.ORG Subject: Re: kqueue microbenchmark results Message-ID: <20001025160944.C28123@fw.wintelcom.net> References: <20001024225637.A54554@prism.flugsvamp.com> <39F6655A.353FD236@alumni.caltech.edu> <20001025115457.X28123@fw.wintelcom.net> <20001025170117.C87091@prism.flugsvamp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.4i In-Reply-To: <20001025170117.C87091@prism.flugsvamp.com>; from jlemon@flugsvamp.com on Wed, Oct 25, 2000 at 05:01:17PM -0500 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG * Jonathan Lemon [001025 15:02] wrote: > On Wed, Oct 25, 2000 at 11:54:57AM -0700, Alfred Perlstein wrote: > > moved to hackers, dropped linux-kernel and -chat. > > > > * Dan Kegel [001024 21:38] wrote: > > > Johnathan, > > > Thanks for running that test for me! I've added your results > > > (plus a cautionary note about microbenchmarks and a link to > > > your site) to http://www.kegel.com/dkftpbench/Poller_bench.html > > > > > > If you haven't already, you might peek at the discussion on > > > linux-kernel. Linus seems to be on the verge of adding > > > something like kqueue() to Linux, but appears opposed to > > > supporting level-triggering; he likes the simplicity of > > > edge triggering (from the kernel's point of view!). See > > > http://boudicca.tux.org/hypermail/linux-kernel/2000week44/index.html#9 > > > > Jonathan, wouldn't this be a good time to try to push our interface > > on Linux? After all, we have several instances of it working and > > having the Open Source community force a new design feature into > > mainstream UNIX to address scalability would be very cool. > > I'd love to do that, but am not quite sure how I'd go about it. > If you read the l-k mailing list, you'll see Linus calling kqueue > "overengineered", and what he is proposing is something that is > definitely not well thought out. I think that's a good summary and probably what you ought to tell him. > Other than whacking him on the head with a stick, any ideas on > how to get him to turn away from the "NIH" syndrome? Try apealing to his sense of making Linux compatible with other OS's... er... Actually I'm at a loss here. :) If you do mail the linux kernel list, which you _should_ otherwise you'll find yourself implementing thier substandard hack over kqueue for freebsd 5 and a really annoying thing to emulate in the linuxulator. CC me on the mail, I'll back you up. :) -- -Alfred Perlstein - [bright@wintelcom.net|alfred@freebsd.org] "I have the heart of a child; I keep it in a jar on my desk." To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message