From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from sj-iport-1.cisco.com (sj-iport-1-in.cisco.com [171.71.176.70]) by ozlabs.org (Postfix) with ESMTP id EEEB3679E9 for ; Tue, 22 Aug 2006 10:29:10 +1000 (EST) To: David Miller Subject: Re: [RFC] HOWTO use NAPI to reduce TX interrupts References: <44E7BB7F.7030204@osdl.org> <200608191325.19557.arnd@arndb.de> <20060821235244.GJ5427@austin.ibm.com> <20060821.165616.107936004.davem@davemloft.net> From: Roland Dreier Date: Mon, 21 Aug 2006 17:29:05 -0700 In-Reply-To: <20060821.165616.107936004.davem@davemloft.net> (David Miller's message of "Mon, 21 Aug 2006 16:56:16 -0700 (PDT)") Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: akpm@osdl.org, arnd@arndb.de, netdev@vger.kernel.org, jklewis@us.ibm.com, linux-kernel@vger.kernel.org, linuxppc-dev@ozlabs.org, Jens.Osterkamp@de.ibm.com, jgarzik@pobox.com, shemminger@osdl.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , David> Don't touch interrupts until both RX and TX queue work is David> fullydepleted. You seem to have this notion that RX and TX David> interrupts are seperate. They aren't, even if your device David> can generate those events individually. Whatever interrupt David> you get, you shut down all interrupt sources and schedule David> the ->poll(). Then ->poll() does something like: This is a digression from spidernet, but what if a device is able to generate separate MSIs for TX and RX? Some people from IBM have suggested that it is beneficial for throughput to handle TX work and RX work for IP-over-InfiniBand in parallel on separate CPUs, and handling everything through the ->poll() method would defeat this. - R.