From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Friesen Subject: Re: r8169 : always copying the rx buffer to new skb Date: Mon, 02 May 2011 13:04:19 -0600 Message-ID: <4DBF0033.2070804@genband.com> References: <4DAC7001.9060800@hotmail.com> <1303147676.2857.20.camel@bwh-desktop> <4DACAC7E.4070400@hotmail.com> <20110420191316.GA18805@electric-eye.fr.zoreil.com> <4DAFA9F9.5080909@hotmail.com> <4DB77D03.9070507@hotmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Francois Romieu , netdev@vger.kernel.org, Ben Hutchings , nic_swsd@realtek.com To: John Lumby Return-path: Received: from exprod7og119.obsmtp.com ([64.18.2.16]:41479 "EHLO exprod7og119.obsmtp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751747Ab1EBTFI (ORCPT ); Mon, 2 May 2011 15:05:08 -0400 In-Reply-To: <4DB77D03.9070507@hotmail.com> Sender: netdev-owner@vger.kernel.org List-ID: On 04/26/2011 08:18 PM, John Lumby wrote: > So - question : > is there any way, when returning from rtl8169_poll, to tell napi > something like : > " finish this interrupt context and let something else run on this CPU > (always CPU0 on my machine) BUT reschedule another napi poll on this > same device at some time after that " Does the hardware support any options for interrupt mitigation? I've used some devices where you can specify a minimum time between interrupts such that even if NAPI re-enabled interrupts and there were packets waiting the hardware would wait a certain time before raising a new interrupt. Chris -- Chris Friesen Software Developer GENBAND chris.friesen@genband.com www.genband.com