From owner-freebsd-net Tue Dec 15 10:04:02 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id KAA28839 for freebsd-net-outgoing; Tue, 15 Dec 1998 10:04:02 -0800 (PST) (envelope-from owner-freebsd-net@FreeBSD.ORG) Received: from alpha.xerox.com (alpha.Xerox.COM [13.1.64.93]) by hub.freebsd.org (8.8.8/8.8.8) with SMTP id KAA28831; Tue, 15 Dec 1998 10:04:01 -0800 (PST) (envelope-from fenner@parc.xerox.com) Received: from crevenia.parc.xerox.com ([13.2.116.11]) by alpha.xerox.com with SMTP id <55775(1)>; Tue, 15 Dec 1998 10:03:55 PST Received: from localhost by crevenia.parc.xerox.com with SMTP id <177534>; Tue, 15 Dec 1998 10:03:38 -0800 To: Michael Robinson cc: fenner@parc.xerox.com, freebsd-net@FreeBSD.ORG, freebsd-stable@FreeBSD.ORG Subject: Re: MLEN < write length < MINCLSIZE "bug" In-reply-to: Your message of "Tue, 15 Dec 98 17:39:17 PST." <199812160139.BAA02158@netrinsics.com> Date: Tue, 15 Dec 1998 10:03:36 PST From: Bill Fenner Message-Id: <98Dec15.100338pst.177534@crevenia.parc.xerox.com> Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In message <199812160139.BAA02158@netrinsics.com> you write: >After exhaustive testing with the standard X benchmarking utility (xmame), >I've discovered a significant performance improvement for graphics- >intensive X applications. I'm not surprised -- since the "atomic" patch confused X, it was clear that X was in this range of small writes. I think that X sets TCP_NODELAY so it shouldn't be subject to the extra round trip in this case, but it still ends up being less packets. Bill To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message