From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: [PATCH] e100: expose broadcast_disabled as a module option Date: Fri, 23 Apr 2010 15:02:07 -0700 Message-ID: <20100423150207.7969c9f6@nehalam> References: <20100423135816.23f5861f@nehalam> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Jeff Kirsher , netdev , David Miller , linux-kernel@vger.kernel.org, jesse.brandeburg@intel.com, bruce.w.allan@intel.com, alexander.h.duyck@intel.com, peter.p.waskiewicz.jr@intel.com, john.ronciak@intel.com To: Erwan Velu Return-path: Received: from mail.vyatta.com ([76.74.103.46]:58423 "EHLO mail.vyatta.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754751Ab0DWWC3 (ORCPT ); Fri, 23 Apr 2010 18:02:29 -0400 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Fri, 23 Apr 2010 23:03:59 +0200 Erwan Velu wrote: > I first tried "ifconfig -broadcast" without any success, so I forced > the driver to unset IFF_BROADCAST, the interface didn't showed anymore > the BROADCAST option with ifconfig. But I didn't noticed any reduction > in the amount of context/switches on my host. > > I found the broadcast_disabled far more efficient when considering the > cpu impact. The point is that the driver can look at IFF_BROADCAST rather than having module parameter. Module parameters are device driver specific and should be avoid as much as possible in favor of general mechanism. This is a repeated problem where users and vendors make special hooks that only work with their driver, which makes life hard for other users and distribution providers.