From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp113.iad3a.emailsrvr.com (smtp113.iad3a.emailsrvr.com [173.203.187.113]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 220143B25E for ; Fri, 10 Jun 2016 17:45:31 -0400 (EDT) Received: from smtp7.relay.iad3a.emailsrvr.com (localhost.localdomain [127.0.0.1]) by smtp7.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id E782E1807BF; Fri, 10 Jun 2016 17:45:30 -0400 (EDT) Received: from app9.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by smtp7.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id D3C301807BA; Fri, 10 Jun 2016 17:45:30 -0400 (EDT) X-Sender-Id: dpreed@reed.com Received: from app9.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by 0.0.0.0:25 (trex/5.5.4); Fri, 10 Jun 2016 17:45:30 -0400 Received: from reed.com (localhost [127.0.0.1]) by app9.wa-webapps.iad3a (Postfix) with ESMTP id C5374C1B8A; Fri, 10 Jun 2016 17:45:30 -0400 (EDT) Received: by apps.rackspace.com (Authenticated sender: dpreed@reed.com, from: dpreed@reed.com) with HTTP; Fri, 10 Jun 2016 17:45:30 -0400 (EDT) Date: Fri, 10 Jun 2016 17:45:30 -0400 (EDT) From: dpreed@reed.com To: "Eric Johansson" Cc: cerowrt-devel@lists.bufferbloat.net MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_20160610174530000000_94346" Importance: Normal X-Priority: 3 (Normal) X-Type: html In-Reply-To: References: <55fdf513-9c54-bea9-1f53-fe2c5229d7ba@eggo.org> <871t4as1h9.fsf@toke.dk> <3D32F19B-5DEA-48AD-97E7-D043C4EAEC51@gmail.com> <1465267957.902610235@apps.rackspace.com> <1465268329.938313737@apps.rackspace.com> X-Auth-ID: dpreed@reed.com Message-ID: <1465595130.805432550@apps.rackspace.com> X-Mailer: webmail/12.5.0-RC Subject: Re: [Cerowrt-devel] trying to make sense of what switch vendors say wrt buffer bloat X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.20 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, 10 Jun 2016 21:45:31 -0000 ------=_20160610174530000000_94346 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable =0AJust today I found out that a datacenter my company's engineering group = is expanding into is putting us on Arista 7050's. And our very preliminary = tests of our systems there is showiung what seems to be a latency problem u= nder load. I can't get in the way of the deployment process, but it's inte= resting/worrying that "big buffers" are there in the middle of our system, = which is highly latency sensitive.=0A=0AI may also need a diagnostic test t= hat would detect the potential occurence of bufferbloat within a 10 GigE s= witch, now. Our software layers are not prepared to self-diagnose at the e= thernet layer very well.=0A=0AMy thought is to use an ethernet ping while o= ur system is loaded. (our protocol is at the Ethernet layer, no IP stack).= Anyone have an idea of the simplest way to do that?=0A=0AOn Tuesday, June = 7, 2016 1:51pm, "Eric Johansson" said:=0A=0A=0A=0A =0A=0AOn = 6/6/2016 10:58 PM, [ dpreed@reed.com ]( mailto:dpreed@reed.com ) wrote:=0AE= ven better, it would be fun to get access to an Arista switch and some high= performance TCP sources and sinks, and demonstrate extreme bufferbloat com= pared to a small-buffer switch. Just a demo, not a simulation full of assu= mptions and guesses.=0A I'm in the middle of a server room/company move. I= can make a available a XSM4348S NETGEAR M4300-24X24F, and probably an ari= sta 7050T-52 for a short time frame as part of my "testing". tell me what = you need for a test setup, give me a script I can run and where I should se= nd the results. I really need a cut and paste test because I have no time = to think about anything more than the move.=0A=0A thanks.=0A=0A ------=_20160610174530000000_94346 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

Just= today I found out that a datacenter my company's engineering group is expa= nding into is putting us on Arista 7050's. And our very preliminary te= sts of our systems there is showiung what seems to be a latency proble= m under load.  I can't get in the way of the deployment process, = but it's interesting/worrying that "big buffers" are there in the middle of= our system, which is highly latency sensitive.

I may also = need a diagnostic test that would detect the  potential occurence of b= ufferbloat within a 10 GigE switch, now.  Our software layers are not = prepared to self-diagnose at the ethernet layer very well.

=0A=0A


My thought is to use an ethernet ping while our system is = loaded.  (our protocol is at the Ethernet layer, no IP stack). Anyone = have an idea of the simplest way to do that?

=0A


On Tuesday, June 7, 2016 1:51pm, "Eric Johansson" <esj@e= ggo.org> said:

=0A
=0A

 

=0A
=0A
On 6/6/2016 10:58 PM, dpreed@reed.com wrote:
=0A
=0A

Even better, it would be fu= n to get access to an Arista switch and some high performance TCP sources a= nd sinks, and demonstrate extreme bufferbloat compared to a small-buffer sw= itch.  Just a demo, not a simulation full of assumptions and guesses.<= /p>=0A

=0A
I'm in the middle of a server room/company mov= e.  I can make a available a  XSM4348S NETGEAR M4300-24X24F, and = probably an arista 7050T-52 for a short time frame as part of my "testing".=   tell me what you need for a test setup, give me a script I can run a= nd where I should send the results.  I really need a cut and paste tes= t because I have no time to think about anything more than the move.
<= br /> thanks.

 ------=_20160610174530000000_94346--