From mboxrd@z Thu Jan 1 00:00:00 1970 From: Francois Romieu Subject: Re: reproducible kernel freeze using r8169 in Linux 3.0 Date: Tue, 3 Jan 2012 23:33:54 +0100 Message-ID: <20120103223354.GC8563@electric-eye.fr.zoreil.com> References: <63CE35CA-7DD6-41EC-A745-6BA776D8C5E3@ginzton.net> <20111218083212.GA28286@electric-eye.fr.zoreil.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: nic_swsd@realtek.com, netdev@vger.kernel.org To: Matt Ginzton Return-path: Received: from violet.fr.zoreil.com ([92.243.8.30]:32937 "EHLO violet.fr.zoreil.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932206Ab2ACWm7 (ORCPT ); Tue, 3 Jan 2012 17:42:59 -0500 Content-Disposition: inline In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Matt Ginzton : [...] > Just to follow up on this old thread: Thanks. [...] > I do note that TX performance as measured by pktgen is lower than r8168 -- > with r8169 in 3.2-rc7 I see something like 455MB/sec and with r8168, IIRC, > the number was closer to 800MB/sec. This may be a very artificial statistic, > and isn't something I happen to care about and I'm certainly not going to > use r8168 because of it, but it may be worth looking into? Expect a "remove everything from irq context" patch this week. It should turn things simpler in the (apparently not so-) fast paths. -- Ueimor