From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp115.iad3a.emailsrvr.com (smtp115.iad3a.emailsrvr.com [173.203.187.115]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 652F23BA8E for ; Wed, 29 Nov 2017 17:34:06 -0500 (EST) Received: from smtp39.relay.iad3a.emailsrvr.com (localhost [127.0.0.1]) by smtp39.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id 40EB859C2; Wed, 29 Nov 2017 17:34:06 -0500 (EST) Received: from app6.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by smtp39.relay.iad3a.emailsrvr.com (SMTP Server) with ESMTP id 305505961; Wed, 29 Nov 2017 17:34:06 -0500 (EST) X-Sender-Id: dpreed@reed.com Received: from app6.wa-webapps.iad3a (relay-webapps.rsapps.net [172.27.255.140]) by 0.0.0.0:25 (trex/5.7.12); Wed, 29 Nov 2017 17:34:06 -0500 Received: from reed.com (localhost.localdomain [127.0.0.1]) by app6.wa-webapps.iad3a (Postfix) with ESMTP id 1FB0FE05A1; Wed, 29 Nov 2017 17:34:06 -0500 (EST) Received: by apps.rackspace.com (Authenticated sender: dpreed@reed.com, from: dpreed@reed.com) with HTTP; Wed, 29 Nov 2017 17:34:06 -0500 (EST) X-Auth-ID: dpreed@reed.com Date: Wed, 29 Nov 2017 17:34:06 -0500 (EST) From: dpreed@reed.com To: "Dave Taht" Cc: cake@lists.bufferbloat.net MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_20171129173406000000_58918" Importance: Normal X-Priority: 3 (Normal) X-Type: html In-Reply-To: <87vahuxgt9.fsf@nemesis.taht.net> References: <87vahuxgt9.fsf@nemesis.taht.net> Message-ID: <1511994846.127314610@apps.rackspace.com> X-Mailer: webmail/12.9.9-RC Subject: Re: [Cake] 1Gbit/20Mbit D/L with ack-filtering X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 29 Nov 2017 22:34:06 -0000 ------=_20171129173406000000_58918 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable =0AVery interesting. The aggressive-ack-filter seems to mess throughput up= during "boost phase" compared to ack-filter less agreesive.=0A =0AI should= say that my most common heavy upload/download usage has an RTT of 88 msec.= (Boston - AWS west).=0A =0APersonal heavy upload/download usage is has RTT= of about 24 msec. (github, my two personal cloud servers).=0A =0AI wonder = if 88 and 25 msec RTT are much better in practice. I will be testing cake i= n a week or so (delay due to family converging on me due to my daughter's w= edding).=0A =0ABTW, one annoying thing about flent is that netperf is not a= vailable in fedora, rhel, centos as a package. So I have to install it and = it doesn't just plug in smoothly. That's just my convenience issue. I don'= t use netperf myself on any of my systems. iperf and iperf3 seem to be a lo= t more pervasive these days...=0A=0A=0AOn Tuesday, November 28, 2017 3:57pm= , "Dave Taht" said:=0A=0A=0A=0A> =0A> Wrote up that result = here:=0A> =0A> http://blog.cerowrt.org/post/ack_filtering/=0A> ------=_20171129173406000000_58918 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

Very interesting.&= nbsp; The aggressive-ack-filter seems to mess throughput up during "boost p= hase" compared to ack-filter less agreesive.

=0A

&= nbsp;

=0A

I should say that my most common heavy u= pload/download usage has an RTT of 88 msec. (Boston - AWS west).

=0A

 

=0A

Personal heavy uploa= d/download usage is has RTT of about 24 msec. (github, my two personal clou= d servers).

=0A

 

=0A

 

=0A

BTW, one annoying thing about flent is that netperf is not availa= ble in fedora, rhel, centos as a package. So I have to install it and it do= esn't just plug in smoothly.  That's just my convenience issue. I don'= t use netperf myself on any of my systems. iperf and iperf3 seem to be a lo= t more pervasive these days...

=0A=0A



On Tuesday,= November 28, 2017 3:57pm, "Dave Taht" <dave@taht.net> said:

=0A
=0A

> <= br />> Wrote up that result here:
>
> http://blog.cerow= rt.org/post/ack_filtering/
>

=0A
 ------=_20171129173406000000_58918--