From mboxrd@z Thu Jan 1 00:00:00 1970 From: jamal Subject: Re: NAPI: netif_rx_reschedule() ?? Date: Thu, 31 Aug 2006 17:50:55 -0400 Message-ID: <1157061055.5297.56.camel@jzny2> References: <20060830161219.7878bada@localhost.localdomain> <20060831142910.427f64fa@localhost.localdomain> Reply-To: hadi@cyberus.ca Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: Roland Dreier , netdev@vger.kernel.org Return-path: Received: from mx03.cybersurf.com ([209.197.145.106]:37042 "EHLO mx03.cybersurf.com") by vger.kernel.org with ESMTP id S932456AbWHaVvL (ORCPT ); Thu, 31 Aug 2006 17:51:11 -0400 Received: from mail.cyberus.ca ([209.197.145.21]) by mx03.cybersurf.com with esmtp (Exim 4.30) id 1GIuRD-0003kW-A7 for netdev@vger.kernel.org; Thu, 31 Aug 2006 17:51:03 -0400 To: Stephen Hemminger In-Reply-To: <20060831142910.427f64fa@localhost.localdomain> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Thu, 2006-31-08 at 14:29 -0700, Stephen Hemminger wrote: > On Wed, 30 Aug 2006 16:39:14 -0700 > Roland Dreier wrote: > > > Roland> makes sense -- especially since the caller probably also > > Roland> deducted N from *budget, and netif_rx_reschedule() doesn't > > Roland> touch that. > > > > Actually, why does undoing the change to quota make sense? Presumably > > I passed N packets to netif_receive_skb() -- why shouldn't I deduct N > > from quota and *budget? > > > > - R. > > This was probably a preventive thing to avoid scheduling when quota remaining was zero? I am reading backwards, so i may be incoherent ;-> I suppose if you dont trust the driver to tell you the truth it could be done in the core code such as netif_receive_skb(). Should be noted however, your quota does get refilled by the NAPI core governed by DRR scheduling rules. cheers, jamal