From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:59836) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1RbU4f-0000Gp-So for qemu-devel@nongnu.org; Fri, 16 Dec 2011 04:27:31 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1RbU4Z-0001sh-Mw for qemu-devel@nongnu.org; Fri, 16 Dec 2011 04:27:29 -0500 Received: from mail-ee0-f45.google.com ([74.125.83.45]:33948) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1RbU4Z-0001sd-HK for qemu-devel@nongnu.org; Fri, 16 Dec 2011 04:27:23 -0500 Received: by eekb45 with SMTP id b45so3331947eek.4 for ; Fri, 16 Dec 2011 01:27:22 -0800 (PST) Date: Fri, 16 Dec 2011 08:31:03 +0000 From: Stefan Hajnoczi Message-ID: <20111216083103.GA24925@stefanha-thinkpad.localdomain> References: <4EDB98B2.6070408@labri.fr> <20111205082617.GA20569@stefanha-thinkpad.localdomain> <4EDCA13E.3080508@labri.fr> <4EE8B68F.4050003@labri.fr> <20111215080758.GA26425@stefanha-thinkpad.localdomain> <4EEA0CDA.80904@labri.fr> <4EEA25B0.8030705@labri.fr> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EEA25B0.8030705@labri.fr> Subject: Re: [Qemu-devel] [Bug 899140] Re: Problem with Linux Kernel Traffic Control List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Vincent Autefage <899140@bugs.launchpad.net> Cc: qemu-devel@nongnu.org, "Michael S. Tsirkin" On Thu, Dec 15, 2011 at 04:48:13PM -0000, Vincent Autefage wrote: > Here is the problem ! > > The Ubuntu version works only because it not uses an *Intel e1000* but a > *rtl8139*. > Therefore, the problem about the e1000 is present in *all* version > (original or ubuntu ones). > > Thus, the file *e1000.c* must contain some instructions which imply the > bad TC behavior. You are right! Looking back at your QEMU command-line you are not explicitly specifying the NIC model so the default will take effect. Now we're back to square one: e1000.c performs poorly when the tc command you posted is used. We don't know why yet. Michael: Have you ever encountered unexpectedly low throughput when tc is used inside the guest? # tc qdisc add dev eth0 root tbf rate 20mbit burst 20k latency 50ms The observed throughput from iperf is only 100kbit/s, not around 20mbit/s as expected. When tc is not run inside the guest then the NIC saturates 20mbit/s easily. Stefan