From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ie0-x22f.google.com (mail-ie0-x22f.google.com [IPv6:2607:f8b0:4001:c03::22f]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 9FEF721F182; Fri, 7 Jun 2013 09:46:43 -0700 (PDT) Received: by mail-ie0-f175.google.com with SMTP id a14so773450iee.6 for ; Fri, 07 Jun 2013 09:46:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:date:message-id:subject:from:to:content-type; bh=72FQZkftIf0kXDpJ1aSFglYBVFsg0gCUzxyZyngNI+k=; b=K2EiG5Q6Q74Ikij+JpFzf768aqKYPcFkSvcxobR/jTCuAUW/JQg67+45Rq67EYX8Z6 9vW+qru7PnmnOuZilktIBNtasljqtr5Y7oIQFrjUf9tkn4+PEeIaY1UdmGy1ZYaYHU0d /IKl45fAme1VKYJ/yweip3gK/kwdLOfpuctAsk2MhJzkFFFI/8piuqW4dzU/UXF+L9h0 iPXI/kdfiUtSId/gmgOaWteimR6Yj4xiAL/8tOQJLVrIAkh4OSJ9rRAJDdZPX8zKXRkp 3mHb2lDTdMBeg2z9Y7hEAArKsqF4ZCZdqyLfkR7d7WkIYXw4qlbDZFprOxQSpiijdeta AJjA== MIME-Version: 1.0 X-Received: by 10.50.25.2 with SMTP id y2mr1524017igf.86.1370623602432; Fri, 07 Jun 2013 09:46:42 -0700 (PDT) Received: by 10.64.35.44 with HTTP; Fri, 7 Jun 2013 09:46:42 -0700 (PDT) Date: Fri, 7 Jun 2013 09:46:42 -0700 Message-ID: From: Dave Taht To: bloat , cerowrt-devel@lists.bufferbloat.net Content-Type: multipart/alternative; boundary=047d7bd74a22f1a0e304de932cbe Subject: [Cerowrt-devel] rebuilding my lab a bit, testing long rtts, testing pie, etc X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 07 Jun 2013 16:46:43 -0000 --047d7bd74a22f1a0e304de932cbe Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Now that I'm done travelling... I've been building up my lab a bit to (as one example) do far more complete netem delay and loss based testing of web and voip traffic under load, in addition to the rrul work. I am very interested as to suggestions as to what and how to evaluate various loads. I've already added emulations of two of cisco's tests from their pie paper, and have come up with a way to do the rest... Currently I'm stuck: as the atom based motherboard I'd chosen has a totally non-functional GM500 video chip in it. It does have decent e1000e ethernet on board, and a slot where I stuck another e1000e based network card - and I'm trying to create equivalent setups for cerowrt and the atom boxes for comparison. I ran into all sorts of old problems like GRO offloads, etc, but I'm gradually beating the bugs down while I look for another cheap-but-good board to stack 4-6 of in the rack. (suggestions for a good board to use welcomed. I also have some common hardware like raspberri pi, beagleboard black, and smileplug on order, in addition to a couple android devices, and a few new router candidates, all of which will start arriving next week) Anyway, there are some extremely early results up at: http://snapon.lab.bufferbloat.net/~d/delay/ on my conventional 20Mbit/4Mbit down/up model, complete with the ubuntu 13.4 kernel build and kernel patches I used, the shaper code is at https://github.com/dtaht/ceropackages-3.3/tree/master/net/aqm-scripts/files= /usr/lib/aqm(use the debloat script to kill the offloads) and now (darn it) I'm going back to trying to vacation in the hope some more folk will take a look at the kernel, patches, etc, etc. http://snapon.lab.bufferbloat.net/~d/delay/delay100-pie.svg Pie code not thoroughly validated yet. http://snapon.lab.bufferbloat.net/~d/delay/delay100-codel.svg The current linux codel http://snapon.lab.bufferbloat.net/~d/delay/delay100-ns2_codel.svg The advanced ns2 codel model http://snapon.lab.bufferbloat.net/~d/delay/delay100-sfq.svg (this shows that sfq's default buffer depth is too short at these RTTs and speeds) http://snapon.lab.bufferbloat.net/~d/delay/delay100-nfq_codel.svg fq_codel using ns2's model of codel While validating the new hardware I also worked on some direct p2p stuff between two machines at 10 and 100Mbit line rates: http://snapon.lab.bufferbloat.net/~d/pie/10mbit-direct-10-capture/ I would be incredibly hesitant to draw any conclusions from any of the above, much validation (with a fresh brain needed in my case) remains to be done on the hardware and patches. I would welcome more eyeballs on the pie patches in particular. --=20 Dave T=E4ht Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html --047d7bd74a22f1a0e304de932cbe Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Now that I'm done travelling...

=A0I've been building up my = lab a bit to (as one example) do far more complete netem delay and loss bas= ed testing of web and voip traffic under load, in addition to the rrul work= .

I am very interested as to suggestions as to what and how to evaluate v= arious loads. I've already added emulations of two of cisco's tests= from their pie paper, and have come up with a way to do the rest...

Currently I'm stuck: as the atom based motherboard I'd chosen h= as a totally non-functional GM500 video chip in it. It does have decent e10= 00e ethernet on board, and a slot where I stuck another e1000e based networ= k card - and I'm trying to create equivalent setups for cerowrt and the= atom boxes for comparison. I ran into all sorts of old problems like GRO o= ffloads, etc, but I'm gradually beating the bugs down while I look for = another cheap-but-good board to stack 4-6 of in the rack. (suggestions for = a good board to use welcomed. I also have some common hardware like raspber= ri pi, beagleboard black, and smileplug on order, in addition to a couple a= ndroid devices, and a few new router candidates, all of which will start ar= riving next week)

Anyway, there are some extremely early results up at: http://snapon.lab.bufferbloat.net/~d= /delay/

on my conventional 20Mbit/4Mbit down/up model, complete= with the ubuntu 13.4 kernel build and kernel patches I used, the shaper co= de is at https://github.com/dtaht/ceropackages-3.3= /tree/master/net/aqm-scripts/files/usr/lib/aqm (use the debloat script = to kill the offloads)

and now (darn it) I'm going back to trying to vacation in the hope = some more folk will take a look at the kernel, patches, etc, etc.

http:= //snapon.lab.bufferbloat.net/~d/delay/delay100-pie.svg

Pie code not thoroughly validated yet.

http://snapon.lab.bufferbl= oat.net/~d/delay/delay100-codel.svg

The current linux codel

http://snapon.lab.bufferbloat.net/~d/delay/delay100-ns2_codel.svg

The advanced ns2 codel model

http://snapon.lab.bufferbloat.net= /~d/delay/delay100-sfq.svg

(this shows that sfq's default buffer depth is too short at these R= TTs and speeds)

http://snapon.lab.bufferbloat.net/~d/delay/delay1= 00-nfq_codel.svg

fq_codel using ns2's model of codel

While validating the new= hardware I also worked on some direct p2p stuff between two machines at 10= and 100Mbit line rates:

http://snapon.lab.bufferbloat.net/~d/pi= e/10mbit-direct-10-capture/

I would be incredibly hesitant to draw any conclusions from any of the = above, much validation (with a fresh brain needed in my case) remains to be= done on the hardware and patches. I would welcome more eyeballs on the pie= patches in particular.

--
Dave T=E4ht

Fixing bufferbloat with cerowrt: http://www= .teklibre.com/cerowrt/subscribe.html=20 --047d7bd74a22f1a0e304de932cbe--