From mboxrd@z Thu Jan 1 00:00:00 1970 From: jamal Subject: Re: [PATCH v2] tg3: Tx availability fix Date: Fri, 06 Jul 2007 09:14:40 -0400 Message-ID: <1183727680.5155.12.camel@localhost> References: <1183681399.24582.68.camel@teletran1> <1183683561.24582.76.camel@teletran1> Reply-To: hadi@cyberus.ca Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: Robert Olsson , Evgeniy Polyakov , Krishna Kumar2 , Gagan Arneja , netdev@vger.kernel.org, Rick Jones , Sridhar Samudrala , David Miller , Jeff Garzik , Michael Chan To: Matt Carlson Return-path: Received: from wx-out-0506.google.com ([66.249.82.239]:23549 "EHLO wx-out-0506.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751373AbXGFNOo (ORCPT ); Fri, 6 Jul 2007 09:14:44 -0400 Received: by wx-out-0506.google.com with SMTP id h31so181423wxd for ; Fri, 06 Jul 2007 06:14:43 -0700 (PDT) In-Reply-To: <1183683561.24582.76.camel@teletran1> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Matt, I have applied both changes (and updated the git tree) with a small caveat on the second patch: On Thu, 2007-05-07 at 17:59 -0700, Matt Carlson wrote: > The last change makes sure that new xmit_win values, as assigned by the > transmit queue wake code, will not be drastically larger than the value > set during initialization. I have left out the above change i.e i kept it as dev->xmit_win = tp->tx_pending If you dont mind lets keep it that way for now so we dont introduce any new variables. i.e. thats how i have been testing and collecting results. If you run some tests and come up with better results by using a /4 i would be more than happy to add it back. Thanks very much for all your efforts - Broadcom rocks. cheers, jamal