From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH RFC]: napi_struct V4 Date: Sat, 28 Jul 2007 22:33:39 -0700 (PDT) Message-ID: <20070728.223339.85409302.davem@davemloft.net> References: <46A8003F.1050208@garzik.org> <20070725.190245.68070169.davem@davemloft.net> <46AB862C.9040507@garzik.org> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: shemminger@linux-foundation.org, netdev@vger.kernel.org, hadi@cyberus.ca, rusty@rustcorp.com.au To: jeff@garzik.org Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:53141 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1752979AbXG2Fdj (ORCPT ); Sun, 29 Jul 2007 01:33:39 -0400 In-Reply-To: <46AB862C.9040507@garzik.org> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org From: Jeff Garzik Date: Sat, 28 Jul 2007 14:08:44 -0400 > That's a performance/parallelization regression from current NAPI :( That's not true since current NAPI will only run on one cpu, the one that the interrupt triggers on. The existing cases that are not guarding the sequence to be atomic are racy, and in a way which is very hard to debug when it triggers and the device just appears dead.