From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qa0-x234.google.com (mail-qa0-x234.google.com [IPv6:2607:f8b0:400d:c00::234]) (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 A028E201B88 for ; Thu, 30 Jan 2014 09:42:11 -0800 (PST) Received: by mail-qa0-f52.google.com with SMTP id j15so4793284qaq.39 for ; Thu, 30 Jan 2014 09:42:10 -0800 (PST) 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=egzso/PVuL6OEVXdvQfW/qKM8C3BmQ/DfzSzNoKbgn4=; b=z+bWHp3CmvrBAJtiOVG+nUve+s89w6TXSFoTDSpWWXJNC0LKyzy92p0U+DbXBlgOry 3Ju7r1kTbL1PcPvXMfQPJPpUgJ0/cJ+6W1IeyZQtLUY2oNISMgn1VcSEmkWCDTemKV1+ ByCY4YysvMqp+c0k+SSD8gIjJyplX5PhqGEP/h3rEWq5Bq7bOFxdWKfGXf9c2/O+WA9r /PuWfDqD5pJFJ5z0ZTvpHwe2b03FS02g3t3Nw6k6hgGCtJU/7eh3H7W9+dPXTAGL7DWH V3ZB2WyEj5aAp9H6moSrWa8hHVsNsW80wY1h5TSGJMed+z+yEdhjh5RF25L3fx/sDs0/ wLvg== MIME-Version: 1.0 X-Received: by 10.140.81.240 with SMTP id f103mr22952324qgd.104.1391103730328; Thu, 30 Jan 2014 09:42:10 -0800 (PST) Received: by 10.224.42.70 with HTTP; Thu, 30 Jan 2014 09:42:10 -0800 (PST) In-Reply-To: References: Date: Thu, 30 Jan 2014 09:42:10 -0800 Message-ID: From: Dave Taht To: Jeremy Tourville Content-Type: multipart/alternative; boundary=001a11c13b52b145a904f13393ca Cc: "cerowrt-users@lists.bufferbloat.net" Subject: Re: [Cerowrt-users] SQM Setup and Performance X-BeenThere: cerowrt-users@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Support for user problems regarding cerowrt List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 30 Jan 2014 17:42:12 -0000 --001a11c13b52b145a904f13393ca Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On Thu, Jan 30, 2014 at 9:06 AM, Jeremy Tourville wro= te: > Hello, I followed your excellent instructions here - > > http://www.bufferbloat.net/projects/cerowrt/wiki/Setting_up_SQM_for_CeroW= rt_310 > > I am using build 3.10.24-8 > > I am using a DSL line rated at 6 Mbps down and 512kbps up. My real > throughput without SQM enabled is 5.7Mbps down and 450kbps up. > > After enabling SQM my throughput has dropped to approximately 4.5Mbps dow= n > and 350 kbps up. Does this seem like an amount that is expected? (within > norms?) > I recommend tuning, using reasonable benchmarks, like rrul. Generally you can get pretty close to your provider's provided bandwidth, but repeated tuning is something we try really hard to avoid. We know 85% always works. :) Hopefully we'll come up with a tool or approach that works dynamically one day, but we're not there yet. So create a setting, run a benchmark, change a knob, run the benchmark, until you get something satisfying example: http://snapon.lab.bufferbloat.net/~cero2/jimreisert/results.html notes: At the moment nfq_codel is a mildly bigger win than fq_codel is at bandwidths below 1mbit. there was a change to sqm in releases after this ( I think ). It used to allocate a fairly large amount of bandwidth for priority traffic (64kbit I recall), now it does 12 or so. rrul exercises all queues. you might want to fiddle with target a little (target 20ms) > It would seem reasonable that I should expect some performance loss at th= e > expense of better bufferbloat management based on setting 85-95% of actua= l > download/upload speeds. Please correct me if I am wrong. :-) But my > question is, how much is too much? The setting of SQM does fix the > bufferbloat issue as evidenced by ping testing and times for packets. Wi= th > SQM on all packets were 100ms or less. With SQM off the times jumped to > over 500ms or more during the speed testing. > > For reference I have set the parameters as indicated in the screenshots. > I have changed only two variables and tested after each change as indicat= ed > in the grid below. > > Que setup script Per packet overhead test results Test #1 simple.qos > 40 no buffer, less throughput <100ms, 4.5mbps down Test #2 simple.qos 4= 4 no > buffer, less throughput <100ms, 4.5mbps down Test #3 simplest.qos 40 no > buffer, less throughput <100ms, 4.5mbps down Test #4 simplest.qos 44 no > buffer, less throughput <100ms, 4.5mbps down > > whether overhead of 44 or 40 is correct for your provider... > I also read your statement- > >>>"The CeroWrt development team has been working to nail down a > no-brainer set of instructions for eliminating bufferbloat - the > lag/latency that kills voice & video chat, gaming, and overall network > responsiveness. The hard part is that optimal configuration of the Smart > Queue Management (SQM) link is difficult - there are tons of options an I= SP > can set. Although CeroWrt can adapt to any of them, it's difficult to fin= d > out the exact characteristics of the link you have." > > What info do I need to get from my ISP to best optimize my connection? > Ask 'em to do their own benchmarking with cero & rrul, adopt fq_codel on their dslams and (especially) rate-limiters, and publish their results for each tier they sell? >I also recognize that this could be an issue that requires multiple changes at once. I am curious to know from the experts what your thoughts are on this. Many thanks in advance! I think you can get closer than you got. > > -Jeremy > > _______________________________________________ > Cerowrt-users mailing list > Cerowrt-users@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/cerowrt-users > > --=20 Dave T=E4ht Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html --001a11c13b52b145a904f13393ca Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable



On Thu, Jan 30, 2014 at 9:06 AM, Jeremy Tourville <organ_dr@hot= mail.com> wrote:
Hello, I followed your excellent instructions here -
http://www.bufferbloat.net/projects/cerowrt/wik= i/Setting_up_SQM_for_CeroWrt_310
=A0
I am using build 3.10.24-8
=A0
I am using a DSL line rated at = 6 Mbps down and 512kbps up.=A0 My real throughput without SQM enabled is 5.= 7Mbps down and 450kbps up.

After enabling SQM my throughput has dropped to appro= ximately 4.5Mbps down and=A0350 kbps up.=A0 Does this seem like an amount t= hat is expected? (within norms?)

I recommend tuning, using reasonable benchmarks, like rrul.

General= ly you can get pretty close to your provider's provided bandwidth, but = repeated tuning is something we try really hard to avoid. We know 85% alway= s works. :)

Hopefully we'll come up with a tool or approach that works dynamica= lly one day, but we're not there yet.

So create a set= ting, run a benchmark, change a knob, run the benchmark, until you get some= thing satisfying

example:

http://snapon.lab.bufferbloat.net/~cero2/jimreisert/r= esults.html

notes:

At th= e moment nfq_codel is a mildly bigger win than fq_codel is at bandwidths be= low 1mbit.

there was a change to sqm in releases after this ( I think )= . It used to allocate a fairly large
amount of bandwidth for priority tr= affic (64kbit I recall), now it does 12 or so.=A0 rrul exercises all queues= .

you might want to fiddle with target a little (ta= rget 20ms)
=A0
It would seem reasonable that=A0I should expect some = performance loss at the expense of better bufferbloat management based on s= etting 85-95% of actual download/upload=A0speeds.=A0 Please correct me if I= am wrong. :-)=A0 But my question is, how much is too much?=A0 The setting = of SQM does fix the bufferbloat issue as evidenced by ping testing and time= s for packets.=A0 With SQM on all packets=A0were 100ms or less.=A0 With SQM= off the times jumped to over 500ms or more during the speed testing.=A0 =A0
For reference I have set the parameters as indicated in the screensh= ots.=A0 I have changed only two variables and tested after each change as i= ndicated in the grid below.
=A0
Que setup script Per packet overhead test results
Test #1 simple.qos 40 no buffer, less throughput <100ms, 4.5mbps down
Test #2=A0 simple.qos 44 no buffer, less throughput <100ms, 4.5mbps down
Test #3 simplest.qos 40 no buffer, less throughput <100ms, 4.5mbps down
Test #4 simplest.qos 44 no buffer, less throughput <100ms, 4.5mbps down
=A0

whether= overhead of 44 or 40 is correct for your provider...
=A0
I also read your statement-
>>>"The= CeroWrt development team has been working to nail down a no-brainer set of= instructions for eliminating bufferbloat - the lag/latency that kills voic= e & video chat, gaming, and overall network responsiveness. The hard pa= rt is that optimal configuration of the Smart Queue Management (SQM) link i= s difficult - there are tons of options an ISP can set. Although CeroWrt ca= n adapt to any of them, it's difficult to find out the exact characteri= stics of the link you have."
=A0
What info do I need to get from my ISP to best optimize my connectio= n?

Ask 'em to d= o their own benchmarking with cero & rrul, adopt fq_codel on their dsla= ms and (especially) rate-limiters, and publish their results for each tier = they sell?

>I also recognize that this could be an issue that requires multiple= changes at once.=A0 I am curious to know from the experts what your though= ts are on this.=A0 Many thanks in advance!

I think you can get closer than you= got.
=A0
=A0
-Jeremy

_______________________________________________
Cerowrt-users mailing list
Cerowrt-users@lists.= bufferbloat.net
https://lists.bufferbloat.net/listinfo/cerowrt-users




--
Dave T=E4ht

= Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscrib= e.html=20 --001a11c13b52b145a904f13393ca--