From owner-freebsd-stable Tue Jul 4 5:29:57 2000 Delivered-To: freebsd-stable@freebsd.org Received: from mout0.freenet.de (mout0.freenet.de [194.97.50.131]) by hub.freebsd.org (Postfix) with ESMTP id 645DA37B82D; Tue, 4 Jul 2000 05:29:50 -0700 (PDT) (envelope-from se@freebsd.org) Received: from [194.97.50.136] (helo=mx3.freenet.de) by mout0.freenet.de with esmtp (Exim 3.15 #1) id 139RpV-0003Au-00; Tue, 04 Jul 2000 14:29:33 +0200 Received: from a6b2a.pppool.de ([213.6.107.42] helo=StefanEsser.FreeBSD.org) by mx3.freenet.de with esmtp (Exim 3.14 #3) id 139RpU-0004IP-00; Tue, 04 Jul 2000 14:29:32 +0200 Received: by StefanEsser.FreeBSD.org (Postfix, from userid 200) id 14859D41; Tue, 4 Jul 2000 14:01:32 +0200 (CEST) Date: Tue, 4 Jul 2000 14:01:31 +0200 From: Stefan Esser To: Stephen McKay Cc: Alan Edmonds , Bill Paul , Chris Wasser , freebsd-stable@FreeBSD.ORG, Stefan Esser Subject: Re: Strangeness with 4.0-S Message-ID: <20000704140131.A1734@StefanEsser.FreeBSD.org> Reply-To: Stefan Esser References: <200007030749.RAA13446@dungeon.home> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2i In-Reply-To: <200007030749.RAA13446@dungeon.home>; from mckay@thehub.com.au on Mon, Jul 03, 2000 at 05:49:56PM +1000 Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG On 2000-07-03 17:49 +1000, Stephen McKay wrote: > I appreciate Bill's intent here to inform the public, and I usually code > the same way. But I've come to the conclusion that it just scares people, > and isn't beneficial after the shake out in -current. True! > Still, I have an alternative suggestion to just ripping out the messages. > I believe the most useful option would be to make the default to always > store and forward, and allow an option (config file option, or some ifconfig > command, sysctl, or some such) to enable the start-before-you've-got-the-data > method. Why is that preferential to just ripping out the message ??? Each buffer underrun will cause an Ethernet packet to require retransmission. Nobody will ever notice, except if he puts a sniffer on the wire and triggers on packets with CRC errors. > I don't think any normal user would see the speed difference. No one would > see those messages soon after every boot. And best of all, we wouldn't see > the connection hang for several seconds each time that message rolled by. > It annoyed me so much I hacked my copy to not do any fancy stuff, and just > go store and forward. I still get 10MB/s ftp between boxes. You increase latencies without good reason. This is not much of a problem with TCP, but UDP/RPC/NFS may suffer. You better just suppress the messages and let the system find a setting, which will not lead to underruns ... It is just not necessary to disable the optimization, since it will cost a few retransmissions (and the driver will know that the frame was not successfully sent and can retry immediately with the modified buffer setting). Regards, STefan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message