From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ee0-f45.google.com (mail-ee0-f45.google.com [74.125.83.45]) (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 480D121F0B0 for ; Sun, 10 Feb 2013 08:43:06 -0800 (PST) Received: by mail-ee0-f45.google.com with SMTP id b57so2878399eek.32 for ; Sun, 10 Feb 2013 08:43:04 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=x-received:mime-version:sender:in-reply-to:references:from:date :x-google-sender-auth:message-id:subject:to:content-type; bh=Taqox2pgsGM6IgEJh8OF1eKJYJ7vbvOLR5dpZKWFbbg=; b=YdXOxBMv8WvwueMTZy13kr1T2JTbFFpYXf8llk41TEMnq4a9L0ERmGS829DiI6NE9X d74M3Qb4d3XFDTxhlZEaOjOIxPdgu08KvKdbvGfKhsOSSsBZeyRdDtR8i3QPwiWRn3Ws M3/JUYSKCFXjbaCfThx23J/0UqVzKts6V7rPIgVtSdR8m68+Jwoh1CBZVzaAJMKmxZk9 1U+LGf3HvDQg2XtTYVe8Q6G+oupBTkjdlYha7NhhBzoD61uh9kGHWwdYdRwZPdEQzA+l +xTeM8/lyGcm9FIOxiBmQt8mn0uwrVkNA3NR3cI+3bic6TbmXvGyg7fI2huK5pG/Ei+Y 1lSA== X-Received: by 10.14.209.131 with SMTP id s3mr39919094eeo.26.1360514583889; Sun, 10 Feb 2013 08:43:03 -0800 (PST) MIME-Version: 1.0 Sender: jeroen.balduyck@gmail.com Received: by 10.14.209.193 with HTTP; Sun, 10 Feb 2013 08:42:33 -0800 (PST) In-Reply-To: References: From: Forums1000 Date: Sun, 10 Feb 2013 17:42:33 +0100 X-Google-Sender-Auth: 9AQcewhUFowjvJ3lfCOnIpX6nxs Message-ID: To: bloat@lists.bufferbloat.net Content-Type: multipart/alternative; boundary=047d7b603bce7c079304d5617cc8 Subject: [Bloat] I am unable to pinpoint the source of bufferbloat 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: Sun, 10 Feb 2013 16:43:06 -0000 --047d7b603bce7c079304d5617cc8 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Firstly, I can confirm uploading to Google Drive saturates my upload (I checked the outgoing rate in the router) and also tried Dropbox and got the same result. Anyway, performing an upload with Windows 7 and then pinging the remote router with windows XP, added 50ms to the "unbloated" 20ms roundtrip times. So the lowest "most represented" RTT numbers I was getting were around 70ms, the worst well over 100ms. I said "most represented" in the previous sentence, as there was also a significant delay variance ("jitter") in the RTT's. The RTT's regularly dived under 70ms, sometimes even hitting an odd 30ms. The was also a large swing in the other direction with regular ventures to 110-120ms. Needless to say, the balance of those ventures tilted more towards the higher numbers. So Windows 7, being more modern definitely induces more bufferbloat (thanks to TCP window scaling:)). I'll be repeating this when running Wireshark as it slipped my mind to fire it up. As a sidenote to the above: I still don't see how an AQM-algorithm will combat the buffering in drivers and hardware (actually, are the issues pertaining to "drivers" and "hardware' distinct or referring to the same?). I understand that feeding less packets to a device will prevent the hardware buffer from filling up as fast as without AQM, but we cannot actually influence its (the HW buffer) size, can we? If so, it can still introduce a bottleneck that cannot be prevented... ---------------------------------------------------------------------------= ---------------------------------------------------------------------------= ------------------- > On Sat, Feb 9, 2013 at 2:06 PM, Forums1000 wrote: > >> Excellent information. So an AQM-algorithm will sort things on the OS >> level of the router and should make things considerably better. However, >> from reading around on the matter, it seems drivers for the network devi= ce >> and the hardware itself also contain buffers. Since, Dave (and respect f= or >> that) is developing CeroWRT, is there anything that can be done about th= at? >> Do we have any idea on how severe the buffering in drivers and hardware = is? >> >> > In linux, it's got a lot better in the past 2 years. Work continues. > > I have some data on OSX now, and some on windows, but not a lot. > > In APs, routers, and switches, it's not looking very good. > > > However I note that the second biggest place we see the issue is on the > edge home gateways, dslams, cable head-ends, and many of those use softwa= re > rate limiting, which generally has 1 buffer or less native to it, and the > underlying buffering doesn't matter. > > (then on top of the software rate limiters are big fat dumb drop tails > queues. currently. sigh) > > > > >> A little test I just performed using Windows XP now, indeed shows that >> Netalyzr is showing me a worst case scenario: >> >> > Meh. Try something with window scaling. Or, try a netanalyzer test from > some other machine at the same time you do this one. > > >> - a continuous ping (1 ping per second) between 2 routers under my >> control has an RTT of 20ms (give or take). The remote router I'm pinging >> sits pretty much idle and has nothing better to do than answering the pi= ng. >> - uploading a large file to Google drive (thereby saturating my uplink >> bandwidth) adds +-10ms of additional latency. >> > > I think this is an invalid assumption without actually measuring your > transfer rate to the the gdrive. It would not surprise me if their TCP wa= s > pretty sensitive to latency swings, however, they are very on top of the > bufferbloat issue. > > Wouldn't mind a packet capture of that upload while doing the above test. > > > >> Sure it varies a bit between 20 and 30ms and goes to 35ms or even 40ms >> regularly. Moreover, every now and then I get a spike to 70-80ms but tha= t >> spike never lasts more than 3 pings. >> >> All in all considerably lower bloat than the 550ms Netalyzr is >> indicating. In order to mimic the worst case scenario, I'd have to trans= fer >> using UDP then? >> > > Just run a more modern OS.... > > >> >> _______________________________________________ >> Bloat mailing list >> Bloat@lists.bufferbloat.net >> https://lists.bufferbloat.net/listinfo/bloat >> >> > > > -- > Dave T=E4ht > > Fixing bufferbloat with cerowrt: > http://www.teklibre.com/cerowrt/subscribe.html > --047d7b603bce7c079304d5617cc8 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable
Firstly, I can confirm uploading to Google = Drive saturates my upload (I checked the outgoing rate in the router) and= =A0 also tried Dropbox and got the same result.

Anyway, performing = an upload with Windows 7 and then pinging the remote router with windows XP= , added 50ms to the "unbloated" 20ms roundtrip times. So the lowe= st "most represented" RTT numbers I was getting were around 70ms,= the worst well over 100ms.
I said "most represented" in the previous sentence, as there was = also a significant delay variance ("jitter") in the RTT's. Th= e RTT's regularly dived under 70ms, sometimes even hitting an odd 30ms.= The was also a large swing in the other direction with regular ventures to= 110-120ms. Needless to say, the balance of those ventures tilted more towa= rds the higher numbers.

So Windows 7, being more modern definitely induces more bufferbloat (th= anks to TCP window scaling:)). I'll be repeating this when running Wire= shark as it slipped my mind to fire it up.

As a sidenote to the abo= ve:
I still don't see how an AQM-algorithm will combat the buffering in dri= vers and hardware (actually, are the issues pertaining to "drivers&quo= t; and "hardware' distinct or referring to the same?). I understan= d that feeding less packets to a device will prevent the hardware buffer fr= om filling up as fast as without AQM, but we cannot actually influence its = (the HW buffer) size, can we? If so, it can still introduce a bottleneck th= at cannot be prevented...
---------------------------------------------------------------------------= ---------------------------------------------------------------------------= -------------------
On Sat, Feb 9, 2013 at 2:06 PM= , Forums1000 <forums1000@gmail.com> wrote:
Excellent information. So an AQM-algorithm will sort things on th= e OS=20 level of the router and should make things considerably better. However, from reading around on the matter, it seems drivers for the network=20 device and the hardware itself also contain buffers. Since, Dave (and=20 respect for that) is developing CeroWRT, is there anything that can be=20 done about that? Do we have any idea on how severe the buffering in=20 drivers and hardware is?


In linux, it's got a lot be= tter in the past 2 years. Work continues.

I have some data on OSX no= w, and some on windows, but not a lot.

In APs, routers, and switches= , it's not looking very good.


However I note that the second biggest place we see the issue is on= the edge home gateways, dslams, cable head-ends, and many of those use sof= tware rate limiting, which generally has 1 buffer or less native to it, and= the underlying buffering doesn't matter.

(then on top of the software rate limiters are big fat dumb drop tails = queues. currently. sigh)


=A0
A little test I just performed using Windows XP now, indeed shows that= Netalyzr is showing me a worst case scenario:


Meh. Try something with window scaling. Or, try a netana= lyzer test from some other machine at the same time you do this one.
=A0
- a continuous ping (1 ping per second) between 2 routers under my=20 control has an RTT of 20ms (give or take). The remote router I'm pingin= g sits pretty much idle and has nothing better to do than answering the=20 ping.
- uploading a large file to Google drive (thereby saturating my uplink=20 bandwidth) adds +-10ms of additional latency.

I think this is an invalid assumption without actually measuring = your transfer rate to the the gdrive. It would not surprise me if their TCP= was pretty sensitive to latency swings, however, they are very on top of t= he bufferbloat issue.

Wouldn't mind a packet capture of that upload while doing the above= test.

=A0
Sure it varies a bit=20 between 20 and 30ms and goes to 35ms or even 40ms regularly. Moreover,=20 every now and then I get a spike to 70-80ms but that spike never lasts=20 more than 3 pings.

All in all considerably lower bloat than the 550ms Netalyzr is=20 indicating. In order to mimic the worst case scenario, I'd have to=20 transfer using UDP then?

Just run a more modern OS....
= =A0

_________= ______________________________________
Bloat mailing list
Bloat@list= s.bufferbloat.net
= https://lists.bufferbloat.net/listinfo/bloat



--
Dave T=E4ht

Fixing bufferbloat with cerow= rt: http://www.teklibre.com/cerowrt/subscribe.html=20

--047d7b603bce7c079304d5617cc8--