From mboxrd@z Thu Jan 1 00:00:00 1970 From: Christoph Hellwig Subject: Re: [PATCH] ixgbe: Introduce new 10GbE driver for Intel 82598 based PCI Express adapters... Date: Mon, 2 Jul 2007 21:16:36 +0100 Message-ID: <20070702201636.GA5100@infradead.org> References: <4688F512.3030801@garzik.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Jeff Garzik , netdev@vger.kernel.org, "Kok, Auke-jan H" , arjan@linux.intel.com, akpm@linux-foundation.org To: "Veeraiyan, Ayyappan" Return-path: Received: from pentafluge.infradead.org ([213.146.154.40]:51035 "EHLO pentafluge.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753524AbXGBUQy (ORCPT ); Mon, 2 Jul 2007 16:16:54 -0400 Content-Disposition: inline In-Reply-To: Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Mon, Jul 02, 2007 at 12:00:29PM -0700, Veeraiyan, Ayyappan wrote: > Agreed. > Fake netdevs are needed for doing the multiple Rx queues in NAPI mode. > We are thinking to solve in 2 ways. Having netdev pointer in ring > structure or having an array of netdev pointers in ixgbe_adatper struct > which would be visible to all rings. Didn't we have a patchset floating around recently that separates NAPI state from struct netdevice?