From owner-freebsd-hackers Wed May 6 08:34:22 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id IAA15794 for freebsd-hackers-outgoing; Wed, 6 May 1998 08:34:22 -0700 (PDT) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from oskar.nanoteq.co.za (oskar.nanoteq.co.za [196.37.91.10]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id IAA15691 for ; Wed, 6 May 1998 08:33:56 -0700 (PDT) (envelope-from rbezuide@oskar.nanoteq.co.za) Received: (from rbezuide@localhost) by oskar.nanoteq.co.za (8.8.8/8.8.5) id RAA11420; Wed, 6 May 1998 17:31:46 +0200 (SAT) From: Reinier Bezuidenhout Message-Id: <199805061531.RAA11420@oskar.nanoteq.co.za> Subject: Re: Weird UDP T/P on fxp0/de0 - 2.2.6-RELEASE In-Reply-To: <199805061214.FAA13851@implode.root.com> from David Greenman at "May 6, 98 05:14:52 am" To: dg@root.com Date: Wed, 6 May 1998 17:30:30 +0200 (SAT) Cc: freebsd-hackers@FreeBSD.ORG X-Mailer: ELM [version 2.4ME+ PL28 (25)] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Hi ... > I haven't looked at newer versions of ttcp, but the older version, on the > transmitter side, would do a backoff (sleep) whenever it got ENOBUFS from the > kernel. The sleep is tuned for 10Mbps ethernet, so the result is that the > transmitter runs with wild swings filling and draining the kernel's output So this is the part where I go "Oh great master Greenman" :) First off I just removed the delay completely and YES :) the numbers look much better now .. they even increment sequentially from small to large packets ... This will probaly teach me to have a look in the code before I say anything :) Thanx a lot Reinier To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message