From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp145.dfw.emailsrvr.com (smtp145.dfw.emailsrvr.com [67.192.241.145]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 91A2D21F2AF for ; Fri, 12 Sep 2014 17:19:28 -0700 (PDT) Received: from localhost (localhost.localdomain [127.0.0.1]) by smtp15.relay.dfw1a.emailsrvr.com (SMTP Server) with ESMTP id EF1AF380104; Fri, 12 Sep 2014 20:19:26 -0400 (EDT) X-Virus-Scanned: OK Received: by smtp15.relay.dfw1a.emailsrvr.com (Authenticated sender: dpreed-AT-reed.com) with ESMTPSA id 9D5C4380140; Fri, 12 Sep 2014 20:19:25 -0400 (EDT) X-Sender-Id: dpreed@reed.com Received: from [10.170.39.252] (68.sub-70-192-8.myvzw.com [70.192.8.68]) (using TLSv1 with cipher DHE-RSA-AES256-SHA) by 0.0.0.0:465 (trex/5.2.10); Sat, 13 Sep 2014 00:19:26 GMT User-Agent: K-@ Mail for Android X-Priority: 3 In-Reply-To: <5413104A.4070104@hp.com> References: <1410482143.8059509@apps.rackspace.com> <45F70DEB-F0FE-45EA-8D27-EEF7C523476B@gmail.com> <5413104A.4070104@hp.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----Y9BKT6F5BJMGG3IQGPWF89ZVJIZSCP" Content-Transfer-Encoding: 7bit From: "David P. Reed" Date: Fri, 12 Sep 2014 20:19:21 -0400 To: Rick Jones , Rich Brown , Jonathan Morton Message-ID: Cc: Wes Felter , =?UTF-8?Q?Joel_Wir=C4=81mu_Pauling?= , "cerowrt-devel@lists.bufferbloat.net" , bloat Subject: Re: [Cerowrt-devel] [Bloat] Fixing bufferbloat: How about an open letter to the web benchmarkers? 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: Sat, 13 Sep 2014 00:19:57 -0000 ------Y9BKT6F5BJMGG3IQGPWF89ZVJIZSCP Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable I have a working ping-over-http mobile browser app at alt=2Ereed=2Ecom=2E = feel free to try it and look at the underlying packet stream with wireshark= =2E I did a prototype of a RRUL test using Web sockets and a modified nginx= websocket module as a server that could be commanded to generate precise= traffic and server end measurements =2E=2E=2E it showed this can work up t= o a few 10 s of Mb/s=2E It's slightly tricky and requires a good understan= ding of the Web sockets protocol stack=2E On Sep 12, 2014, Rick Jones wrote: >On 09/11/2014 06:48 PM, Rich Brown wrote: >> = Jonathan, >> >>> Could we make use of the existing test servers (running ne= tperf) for >that demonstration? How hard is the protocol to fake in Javasc= ript? >> >> Not having coded a stitch of this, I *think* it would require t= he >following: >> >> - Web page on netperf-xxx=2Ebufferbloat=2Enet that ser= ved out the >javascript (required to get around cross-domain protections wi= thin the >browser) >> >> - Javascript function to connect back to that host= on port 12865 and >fake out the netserver with TCP_STREAM or TCP_MAERTS re= quest >> >> - Javascript that's efficient enough to source/swallow full-rat= e data >stream >> >> - Cloning the code from https://github=2Ecom/apenwarr/= blip to make fake >pings from TCP requests >> >> Anyone know more than I do= about this? > >Not about the javascript stuff, but your high level descrip= tion of the >netperf side sounds plausible=2E There are a few control mes= sages >netperf >will exchange with netserver that if you want to leverage = a remote >netserver will need to be included=2E You can run a netperf com= mand with > >a higher debug level to see them=2E > >rick jones -- Sent fro= m my Android device with K-@ Mail=2E Please excuse my brevity=2E ------Y9BKT6F5BJMGG3IQGPWF89ZVJIZSCP Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable I have a working ping-over-http mobile browser app= at  alt=2Ereed=2Ecom=2E feel = free to try it and look at the underlying packet stream with wireshark=2E I= did a prototype of a RRUL test using Web sockets and a modified nginx webs= ocket   module as a server that could be commanded to generate pr= ecise traffic and server end measurements =2E=2E=2E it showed this can work= up to a few 10 s of Mb/s=2E

It's sl= ightly tricky and requires a good understanding of the Web sockets protocol= stack=2E


On Sep 12, 2014, Rick Jones <rick=2Ejones2@hp=2Ecom&= gt; wrote:
On 09/11/2014 06:48 PM, Rich Brown wrote:
Jonathan,

Could we make use of the existing test servers (running netperf) for = that demonstration? How hard is the protocol to fake in Javascript?
Not having coded a stitch of this, I *think* it wo= uld require the following:

- Web page = on netper= f-xxx=2Ebufferbloat=2Enet that served out the javascript (required to g= et around cross-domain protections within the browser)
- Javascript function to connect back to that host on port= 12865 and fake out the netserver with TCP_STREAM or TCP_MAERTS request

- Javascript that's efficient enough to s= ource/swallow full-rate data stream

- = Cloning the code from https://github=2Ecom/apenwarr/blip to make fake pings from TCP= requests

Anyone know more than I do a= bout this?

Not about the javascript stuff, b= ut your high level description of the
netperf side sound= s plausible=2E There are a few control messages netperf
will exchange with netserver that if you want to leverage a remote
netserver will need to be included=2E You can run a netperf co= mmand with
a higher debug level to see them=2E

rick jones

-- Sent from my Android device with K-@ Mail=2E Please excuse my brevity=2E ------Y9BKT6F5BJMGG3IQGPWF89ZVJIZSCP--