From mboxrd@z Thu Jan 1 00:00:00 1970 From: Benny Amorsen Subject: Re: e1000 performance issue in 4 simultaneous links Date: Fri, 11 Jan 2008 12:09:32 +0100 Message-ID: References: <1199981839.8931.35.camel@cafe> <36D9DB17C6DE9E40B059440DB8D95F5204275B04@orsmsx418.amr.corp.intel.com> <20080110.172830.16409182.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii To: netdev@vger.kernel.org Return-path: Received: from main.gmane.org ([80.91.229.2]:55060 "EHLO ciao.gmane.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755458AbYAKLJs (ORCPT ); Fri, 11 Jan 2008 06:09:48 -0500 Received: from list by ciao.gmane.org with local (Exim 4.43) id 1JDHld-0006AQ-3P for netdev@vger.kernel.org; Fri, 11 Jan 2008 11:09:41 +0000 Received: from hd5b9080a.c45-01-12.sta.perspektivbredband.net ([213.185.8.10]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 11 Jan 2008 11:09:41 +0000 Received: from benny+usenet by hd5b9080a.c45-01-12.sta.perspektivbredband.net with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Fri, 11 Jan 2008 11:09:41 +0000 Sender: netdev-owner@vger.kernel.org List-ID: David Miller writes: > No IRQ balancing should be done at all for networking device > interrupts, with zero exceptions. It destroys performance. Does irqbalanced need to be taught about this? And how about the initial balancing, so that each network card gets assigned to one CPU? /Benny