From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wi0-x230.google.com (mail-wi0-x230.google.com [IPv6:2a00:1450:400c:c05::230]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 5249521F3AD for ; Fri, 24 Apr 2015 06:49:28 -0700 (PDT) Received: by widdi4 with SMTP id di4so22842371wid.0 for ; Fri, 24 Apr 2015 06:49:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=JGfVQoDJxo/TL9f0DHCNwY1mKIGqwPpJneqGZhONHRw=; b=sK23ljgDwavsP9pqmG7MmuivO5jOqBrzJum22a0HasgY5cKcOTzlwc8X3GCd6h6NXT nWcaJTKnV+Q2rLPGfzCY0UzsSEX6Q1N7joCqxKAy9PTmrjX4Yaj5z5JegwTdA1oP+qyt Psb5TtZaGQ1V2caaGWy9euRIJkuMnl2C/2B3G/SSUoMl+3/JBG6DCxf26iVbd3z/n70Y TbC3AHe0kkvEnRERHYW1GAkcW2/m+QNQ3LfbSp4I/t/VOJmAMcQJgTF/ed9ElNotKtDs XFeavF5UQcxaa71kVh3TEXczfgHqKf7v2/2sqOejnViK0542bfpR9i1suP+uKzS+6wtD RUWQ== MIME-Version: 1.0 X-Received: by 10.194.7.97 with SMTP id i1mr16301731wja.107.1429883364664; Fri, 24 Apr 2015 06:49:24 -0700 (PDT) Received: by 10.28.180.87 with HTTP; Fri, 24 Apr 2015 06:49:24 -0700 (PDT) In-Reply-To: References: <87wq18jmak.fsf@toke.dk> <87oamkjfhf.fsf@toke.dk> <87k2x8jcnw.fsf@toke.dk> <0D391BB1-9CA5-4DAF-8FD6-6628AB09C1C5@gmail.com> Date: Fri, 24 Apr 2015 15:49:24 +0200 Message-ID: From: Pedro Tumusok To: Rich Brown Content-Type: multipart/alternative; boundary=047d7b5d86a5056afe051478aaa0 Cc: bloat Subject: Re: [Bloat] DSLReports Speed Test has latency measurement built-in X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 24 Apr 2015 13:50:02 -0000 X-List-Received-Date: Fri, 24 Apr 2015 13:50:02 -0000 X-List-Received-Date: Fri, 24 Apr 2015 13:50:02 -0000 X-List-Received-Date: Fri, 24 Apr 2015 13:50:02 -0000 --047d7b5d86a5056afe051478aaa0 Content-Type: text/plain; charset=UTF-8 On Fri, Apr 24, 2015 at 3:58 AM, Rich Brown wrote: > > On Apr 23, 2015, at 6:22 PM, Dave Taht wrote: > > > > > We had/have a lot of this problem in netperf-wrapper - a lot of data > > tends to accumulate at the end of the test(s) and pollute the last few > > data points in bloated scenarios. You have to wait for the queues to > > drain to get a "clean" test - although this begins to show what > > actually happen when the link is buried in both directions. > > > > Is there any chance to add a simultaneous up+down+ping test at the > conclusion? > > This confuses the "speed test" notion of this site. Since the flow of > ack's can eat up 25% of the bandwidth of a slow, asymmetric link, I am > concerend that people would wonder why their upload bandwidth suddenly went > down dramatically... > > Given that other speed test sites only show upload/download, I would vote > to keep that format here. Perhaps there could be an > option/preference/setting to do up/down/ping . > > But isn't the point to have the best/relevant speed test in the business, how can you innovate or do something new, if you make sure you do not deviate to much from the competition? Most users would likes the new gadget shiny feeling, so if the test does the normal down and then up. And tells you those numbers are the ideal numbers you can get. But in reality this is the closer to the service you are actually getting for your money, then do the down/up+ping test. As for ms thresholds, my $0.02 thinks that there should be some "real world" correlation. Most people know how long 1 second is, but have no idea how it impacts stuff. Especially since most people think 1 second is very quick and most likely negligible. Showing milliseconds, probably does not ring a bell to most people. So putting in pointers like, at this latency (bufferbloat induced or not) VoIP will not work anymore and at this latency online gaming means you have to be psychic to win and at this next level, you probably should think about making a cup of coffee while you wait for your favorite webpage display. Pedro --047d7b5d86a5056afe051478aaa0 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable
On F= ri, Apr 24, 2015 at 3:58 AM, Rich Brown <richb.hanover@gmail.com= > wrote:

On Apr 23, 2015, at 6:22 PM, Dave Taht <dave.taht@gmail.com> wrote:

>
> We had/have a lot of this problem in netperf-wrapper - a lot of= data
> tends to accumulate at the end of the test(s) and pollute the last few=
> data points in bloated scenarios. You have to wait for the queues to > drain to get a "clean" test - although this begins to show w= hat
> actually happen when the link is buried in both directions.
>
> Is there any chance to add a simultaneous up+down+ping test at the con= clusion?

This confuses the "speed test" notion of this site. Since the flo= w of ack's can eat up 25% of the bandwidth of a slow, asymmetric link, = I am concerend that people would wonder why their upload bandwidth suddenly= went down dramatically...

Given that other speed test sites only show upload/download, I would vote t= o keep that format here. Perhaps there could be an option/preference/settin= g to do up/down/ping .



But isn't the po= int to have the best/relevant speed test in the business, how can you innov= ate or do something new, if you make sure you do not deviate to much from t= he competition?

Most users would likes the new= gadget shiny feeling, so if the test does the normal down and then up. And= tells you those numbers are the ideal numbers you can get. But in reality = this is the closer to the service you are actually getting for your money, = then do the down/up+ping test. =C2=A0

As for ms th= resholds, my $0.02 thinks that there should be some "real world" = correlation.=C2=A0 Most people know how long 1 second is, but have no idea = how it impacts stuff. Especially since most people think 1 second is very q= uick and most likely negligible. Showing milliseconds, probably does not ri= ng a bell to most people.

So putting in pointers l= ike, at this latency (bufferbloat induced or not) VoIP will not work anymor= e and at this latency online gaming means you have to be psychic to win and= at this next level, you probably should think about making a cup of coffee= while you wait for your favorite webpage display.

Pedro
--047d7b5d86a5056afe051478aaa0--