From owner-cvs-all Fri Jun 16 8:43: 6 2000 Delivered-To: cvs-all@freebsd.org Received: from po3.wam.umd.edu (po3.wam.umd.edu [128.8.10.165]) by hub.freebsd.org (Postfix) with ESMTP id 9947C37BF0C; Fri, 16 Jun 2000 08:42:47 -0700 (PDT) (envelope-from culverk@wam.umd.edu) Received: from rac1.wam.umd.edu (root@rac1.wam.umd.edu [128.8.10.141]) by po3.wam.umd.edu (8.9.3/8.9.3) with ESMTP id LAA27141; Fri, 16 Jun 2000 11:42:24 -0400 (EDT) Received: from rac1.wam.umd.edu (sendmail@localhost [127.0.0.1]) by rac1.wam.umd.edu (8.9.3/8.9.3) with SMTP id LAA25836; Fri, 16 Jun 2000 11:42:25 -0400 (EDT) Received: from localhost (culverk@localhost) by rac1.wam.umd.edu (8.9.3/8.9.3) with ESMTP id LAA25823; Fri, 16 Jun 2000 11:42:25 -0400 (EDT) X-Authentication-Warning: rac1.wam.umd.edu: culverk owned process doing -bs Date: Fri, 16 Jun 2000 11:42:25 -0400 (EDT) From: Kenneth Wayne Culver To: Nate Williams Cc: Bill Fumerola , "Daniel O'Connor" , "Daniel C. Sobral" , cvs-all@FreeBSD.ORG, cvs-committers@FreeBSD.ORG, Alfred Perlstein Subject: Re: cvs commit: src/sys/kern uipc_socket.c uipc_socket2.c src/sy In-Reply-To: <200006161531.JAA00677@nomad.yogotech.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-cvs-all@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > > > Correct. If we want performance, how about removing the difference > > > between kernel and userland. Why have the overhead of the kernel > > > vs. userland change, since it causes us to take a big performance hit. > > > > > > As long as we're at it, we may as well embed all of the video drivers in > > > the kernel, like NT did. X should become an embedded part of the > > > system, since that will also speed up performance again. > > > > > > There are *LOTS* of performance improvments that can be done. Since > > > FreeBSD is used on the internet, let's embed telnet and ftp in the > > > kernel as well. We could certainly blow away all benchmarks that people > > > see. > > > > So basically if you don't have any constructive to contribute to the > > specific case at hand, you can just make broad assinine statements? > > No. I'm saying that blowing your architecture for performance gains > isn't worth it. If performance is your entire goal (as you stated), > there are lots of ways of removing that bottleneck. > > In short, the removal of the userland/kernel switch would make the > original code's reason for existence gone, since the context switch is > so painful. > > Or, will you agree that architecture and consistency has a role in > FreeBSD, and that sometimes performance must take a back seat? > > I know I have no say in this... but as an interested party watching the discussion, I think that certain architectural changes can be made in the intrests of performance as long as the OS remains either as stable as before ... or more stable.. ================================================================= | Kenneth Culver | FreeBSD: The best NT upgrade | | Unix Systems Administrator | ICQ #: 24767726 | | and student at The | AIM: muythaibxr | | The University of Maryland, | Website: (Under Construction) | | College Park. | http://www.wam.umd.edu/~culverk/| ================================================================= To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message