Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753065Ab3EUI3I (ORCPT ); Tue, 21 May 2013 04:29:08 -0400 Received: from mms2.broadcom.com ([216.31.210.18]:1865 "EHLO mms2.broadcom.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752661Ab3EUI3E (ORCPT ); Tue, 21 May 2013 04:29:04 -0400 X-Server-Uuid: 4500596E-606A-40F9-852D-14843D8201B2 Message-ID: <1369124929.29989.0.camel@lb-tlvb-eilong.il.broadcom.com> Subject: Re: [PATCH v3 net-next 3/4] ixgbe: Add support for ndo_ll_poll From: "Eilon Greenstein" Reply-to: eilong@broadcom.com To: "Or Gerlitz" cc: "Eliezer Tamir" , "Dave Miller" , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, "Jesse Brandeburg" , "Don Skidmore" , e1000-devel@lists.sourceforge.net, "Willem de Bruijn" , "Andi Kleen" , HPA , "Eliezer Tamir" Date: Tue, 21 May 2013 11:28:49 +0300 In-Reply-To: References: <20130520101552.14133.45953.stgit@ladj378.jer.intel.com> <20130520101622.14133.21998.stgit@ladj378.jer.intel.com> <519B1A2B.4010909@linux.intel.com> <1369120003.25971.2.camel@lb-tlvb-eilong.il.broadcom.com> Organization: Broadcom X-Mailer: Evolution 3.6.4 (3.6.4-3.fc18) MIME-Version: 1.0 X-WSS-ID: 7D85F1711R018501373-01-01 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1195 Lines: 26 On Tue, 2013-05-21 at 11:21 +0300, Or Gerlitz wrote: > On Tue, May 21, 2013 at 10:06 AM, Eilon Greenstein wrote: > > Or - at least for the bnx2x, it is easy to add support for this new ndo. > > Do you understand what's the equivalent of that mysterious module > param for your driver/HW - or you just copied and pasted that black > magic code? > The module parameter is not the interesting part of this patch. It is clear that unloading the module while this sort of traffic is running is not safe and the alternative of adding a reference count or something similar sounds too costly (after all, this patch is about performance). I just played with it to get a feel of the latency improvement - I did not try unloading the module during traffic so I do not care about the module parameter part right now. I agree that the unload should be looked into - but the general concept is great and it is a very nice improvement. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/