From owner-freebsd-net Wed Apr 21 22:49:15 1999 Delivered-To: freebsd-net@freebsd.org Received: from Meta-Bug.ppp.ucar.edu (ras36.ucar.edu [128.117.68.36]) by hub.freebsd.org (Postfix) with SMTP id B9F4615109 for ; Wed, 21 Apr 1999 22:49:09 -0700 (PDT) (envelope-from rousskov@ircache.net) Received: from localhost (rousskov@localhost) by Meta-Bug.ppp.ucar.edu (950413.SGI.8.6.12/950213.SGI.AUTOCF) via ESMTP id XAA06477; Wed, 21 Apr 1999 23:46:01 -0600 Date: Wed, 21 Apr 1999 23:46:00 -0600 From: Alex Rousskov X-Sender: rousskov@Meta-Bug To: David Greenman Cc: freebsd-net@FreeBSD.ORG Subject: Re: _Some_ acks delayed for 200 msec? In-Reply-To: <199904220524.WAA16883@implode.root.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-net@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Wed, 21 Apr 1999, David Greenman wrote: > I'm not familiar with what your application is doing over the wire, so I > can only speculate. It sounds to me as though TCP_NODELAY wasn't actually > set properly on the socket. Keep in mind that this option is not inherited > in the accept()'ed file descriptor and thus the option must be set on that > descriptor and not on the listen() socket. Oof! I've trusted the accept(2) man page that says: The accept() argument extracts the first connection request on the queue of pending connections, creates a new socket with the same properties of s and allocates a new file descriptor for the socket. Apparently, "same properties" does not include TCP_NODELAY! I will test with [correctly] disabled Nagle on the server side and let you know the result. Thanks, Alex. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message