From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-iw0-f171.google.com (mail-iw0-f171.google.com [209.85.214.171]) (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 4F6C52004FF for ; Fri, 20 May 2011 15:35:26 -0700 (PDT) Received: by iwn8 with SMTP id 8so5322346iwn.16 for ; Fri, 20 May 2011 15:47:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:in-reply-to:references:date :message-id:subject:from:to:cc:content-type; bh=SudxRHi0BtKiDTdKArolcJefKsf8AyQ+1i8NAwVB74Y=; b=QZ2clO68KxyUkrYe1uXXR3q1REp+ggVIE5ERI1d9wVCNwhx04krvE63HjtfVXkK+JP XpvzdBZ1SfdRemSsMgDEwHCQGIs7+i+s7++K6fGLHolc8wEK0bG40pMmCDd1RHvBbmlz JjaY+a5wY1MkmZzGKkGrWmDSsgt18EtVjT3jc= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=bg0mRvqzbKx5F8ECBYMSYoW2SZlteGDxP2rZFxhMRXutxAsMUieN8MMWFbkIMxUa6c RK2DfWe6nt3U96rBza8vGNEuRDLhvp6XnhWrZvF3pTRu21fIkgjHq21GwovJg+G4NiBA FB3k8VGDJTNfQrdyg0gFCbnuZGMZqyBbD0Llo= MIME-Version: 1.0 Received: by 10.42.136.197 with SMTP id v5mr5767064ict.513.1305931628717; Fri, 20 May 2011 15:47:08 -0700 (PDT) Received: by 10.231.19.200 with HTTP; Fri, 20 May 2011 15:47:08 -0700 (PDT) In-Reply-To: References: <9EFCAA58-92E8-45FD-9BE4-F213564264E6@cc.gatech.edu> <5C1FCBFC-B007-4B01-A7BA-6CCD5523DC34@cc.gatech.edu> <048ECF4E-9E70-4957-90B4-ACD3C0D7AD44@cc.gatech.edu> Date: Fri, 20 May 2011 16:47:08 -0600 Message-ID: From: Dave Taht To: Nick Feamster Content-Type: multipart/alternative; boundary=90e6ba61357cd4a7c704a3bce608 Cc: bismark-devel@lists.bufferbloat.net Subject: Re: [Bismark-devel] about ready to do another build X-BeenThere: bismark-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: BISMark related software development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 20 May 2011 22:35:26 -0000 --90e6ba61357cd4a7c704a3bce608 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable A much longer test would be to download this wget -4 http://gw.lab.bufferbloat.net/capetown/capetown-wndr3700v2/OpenWrt-ImageBui= lder-ar71xx-for-Linux-x86_64.tar.bz2 while pinging somewhere fairly close by. Over your wired and wireless connection(s)... Over multiple downloads, too... Sorry to make you work so hard. I am SO OVERJOYED to get some data on this problem, however..... (yes, I'll change it to lab.bismarkproject.net as soon as DNS lands) On Fri, May 20, 2011 at 4:42 PM, Dave Taht wrote: > > > On Fri, May 20, 2011 at 4:35 PM, Nick Feamster wr= ote: > >> >> On May 21, 2011, at 12:28 AM, Dave Taht wrote: >> >> > >> > And btw, what are the results of a speedtest from your location withou= t >> QoS on? >> > >> >> Have run it 2x now. >> >> I see about 850 kbps down and 400 kbps up. >> >> The default upload setting is abusive. >> > > Sorry. Nicaragua typically had 64k-128k up. Took my best guess. > > >> >> > With QoS on, set to up/dl values within a few percentage points of tha= t >> (and the overhead calculation disabled) >> > >> > > And with QoS set to say 840/380, with the overhead calculation disabled? > Should be about 15% below that for a long bulk transfer. Can get closer..= . > > Please note that setting these values on the basis of one datapoint in a > majorish city will result in bad values deeper in the country.... > > Helps to also ping somewhere at the same time of the test to see your > latencies start to go to heck as you get closer to the "edge". You'll see= it > start to jitter... then go wildly late... and at extreme values, tcp/ip w= ill > start to malfunction as per the bufferbloat diagrams... > > I'd LOVE for a few tcpdumps of stuff like this, from where you are..... > > > I can bake a better default into the next build, but I was figuring >> you'd be lucky to be gettting 1000 down.... >> > >> > I want to note that according to your previous study, the first 30 >> seconds of data need to be discarded in order for a speedtest to be vali= d, >> and speedtest.net doesn't do that... >> >> Yep yep... though I don't think PowerBoost is enabled over here. >> Although, we'll find out. :-) >> >> -Nick > > > > > -- > Dave T=E4ht > SKYPE: davetaht > US Tel: 1-239-829-5608 > http://the-edge.blogspot.com > --=20 Dave T=E4ht SKYPE: davetaht US Tel: 1-239-829-5608 http://the-edge.blogspot.com --90e6ba61357cd4a7c704a3bce608 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable A much longer test would be to download this

wget -4 http://gw.lab.bufferblo= at.net/capetown/capetown-wndr3700v2/OpenWrt-ImageBuilder-ar71xx-for-Linux-x= 86_64.tar.bz2

while pinging somewhere fairly close by.

Over your wired and wir= eless connection(s)...

Over multiple downloads, too...

Sorry = to make you work so hard. I am SO OVERJOYED to get some data on this proble= m, however.....

(yes, I'll change it to lab.bismarkproject.net as soon as DNS lands)

<= div class=3D"gmail_quote">On Fri, May 20, 2011 at 4:42 PM, Dave Taht <dave.taht@gmail.com<= /a>> wrote:


On Fri, May 20, 2011 at 4:35 PM, Nick F= eamster <feamster@cc.gatech.edu> wrote:

On May 21, 2011, at 12:28 AM, Dave Taht wrote:

>
> And btw, what are the results of a speedtest from your location withou= t QoS on?
>

Have run it 2x now.

I see about 850 kbps down and 400 kbps up.

The default upload setting is abusive.

Sorry= . Nicaragua typically had 64k-128k up. Took my best guess.
=A0
=

> With QoS on, set to up/dl values within a few percentage points of tha= t (and the overhead calculation disabled)
>

And with QoS set to say 840/380, = with the overhead calculation disabled? Should be about 15% below that for = a long bulk transfer. Can get closer...
=A0
Please note that setting = these values on the basis of one datapoint in a majorish city will result i= n bad values deeper in the country....

Helps to also ping somewhere at the same time of the test to see your l= atencies start to go to heck as you get closer to the "edge". You= 'll see it start to jitter... then go wildly late... and at extreme val= ues, tcp/ip will start to malfunction as per the bufferbloat diagrams...
I'd LOVE for a few tcpdumps of stuff like this, from where you are.= ....

> I can bake a better default into the next build, but I was figuring yo= u'd be lucky to be gettting 1000 down....
>
> I want to note that according to your previous study, the first 30 sec= onds of data need to be discarded in order for a speedtest to be valid, and= speedtest.net doesn= 't do that...

Yep yep... though I don't think PowerBoost is enabled over here. = =A0Although, we'll find out. :-)

-Nick


=

--
Dave T=E4ht
SKYPE: davetaht
US Tel: 1-239-8= 29-5608
http://the-edge.= blogspot.com



--
Dave T=E4ht=
SKYPE: davetaht
US Tel: 1-239-829-5608
http://the-edge.blogspot.com
--90e6ba61357cd4a7c704a3bce608--