From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tom Herbert Subject: Re: [PATCH v4 1/1] rps: core implementation Date: Fri, 20 Nov 2009 16:12:00 -0800 Message-ID: <65634d660911201612y12a9b5bnb6685da040ad832d@mail.gmail.com> References: <65634d660911201528k5a07135el471b65fff9dd7c9d@mail.gmail.com> <20091120.153913.242783116.davem@davemloft.net> <65634d660911201550v34bc463ao17dcd7b16f62264f@mail.gmail.com> <20091120.160507.110482370.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org To: David Miller Return-path: Received: from smtp-out.google.com ([216.239.33.17]:36037 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753233AbZKUAL7 convert rfc822-to-8bit (ORCPT ); Fri, 20 Nov 2009 19:11:59 -0500 Received: from zps19.corp.google.com (zps19.corp.google.com [172.25.146.19]) by smtp-out.google.com with ESMTP id nAL0C3Ww020426 for ; Sat, 21 Nov 2009 00:12:04 GMT Received: from pxi35 (pxi35.prod.google.com [10.243.27.35]) by zps19.corp.google.com with ESMTP id nAL0C1ro010010 for ; Fri, 20 Nov 2009 16:12:01 -0800 Received: by pxi35 with SMTP id 35so627322pxi.18 for ; Fri, 20 Nov 2009 16:12:01 -0800 (PST) In-Reply-To: <20091120.160507.110482370.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: > I guess my confusion is from the: > > =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0__rais= e_softirq_irqoff(NET_RX_SOFTIRQ); > > you are doing as you set the cpus in rps_remote_softirq_cpus. > > Why do you need to schedule the local RX softirq, when we know we're > in a NAPI poll loop and thus that we're in a softirq, and thus that w= e > will fire off the IPIs at the end of net_rx_action()? > > That's what you're doing, the softirq raising just seems superfluous. > Ah, right. If RPS can't be used non-NAPI case, this line is now superfluous. It can be removed. Thanks