From owner-freebsd-net Fri Mar 23 14:34:14 2001 Delivered-To: freebsd-net@freebsd.org Received: from antigonus.hosting.swbell.net (antigonus.hosting.swbell.net [216.100.98.4]) by hub.freebsd.org (Postfix) with ESMTP id 4C23537B71E for ; Fri, 23 Mar 2001 14:34:08 -0800 (PST) (envelope-from alc@imimic.com) Received: from imimic.com ([63.141.155.195]) by antigonus.hosting.swbell.net id RAA00817; Fri, 23 Mar 2001 17:33:59 -0500 (EST) [ConcentricHost SMTP Relay 1.7] Message-ID: <3ABBCF55.E4B99274@imimic.com> Date: Fri, 23 Mar 2001 16:33:57 -0600 From: "Alan L. Cox" Organization: iMimic Networking, Inc. X-Mailer: Mozilla 4.75 [en] (X11; U; FreeBSD 4.2-STABLE i386) X-Accept-Language: en MIME-Version: 1.0 To: Jonathan Graehl Cc: Freebsd-Net Subject: Re: Linux Vs. FreeBSD Networking Performance References: Content-Type: text/plain; charset=iso-8859-15 Content-Transfer-Encoding: 7bit Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Jonathan Graehl wrote: > > What would it take to get Linus to give the nod to an implementation conforming > to the kqueue API? I remember him saying that he only wanted it to work for > file descriptors, and to only allow one kqueue per process - neither of which I > agree with. The abstraction penalty for the capability of multiple filter types > and kqueue-as-selectable-fd is as minimal as a table lookup and a pointer > indirection. If the kqueue API is overengineered, well, then, so is the > Berkeley Sockets API. > You should ask the "other" Alan Cox. I'm the one with the FreeBSD commit bit as opposed to the Linux commit bit. :-) In general, I agree with your statements in regards to kqueue(). It's not overengineered. The capabilities beyond simple poll/select functionality are quite useful in practice. In fact, I contributed the current API by which AIO can signal I/O completion through kevent(). Alan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message