From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.15.15]) (using TLSv1 with cipher DHE-RSA-AES128-SHA (128/128 bits)) (Client CN "mout.gmx.net", Issuer "TeleSec ServerPass DE-1" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 999A221F112 for ; Sat, 21 Dec 2013 02:40:48 -0800 (PST) Received: from [10.17.151.121] ([80.187.96.24]) by mail.gmx.com (mrgmx003) with ESMTPSA (Nemesis) id 0MN1C4-1Vs7412A8G-006gMY for ; Sat, 21 Dec 2013 11:40:45 +0100 User-Agent: K-9 Mail for Android In-Reply-To: <690EEC3B-8E4D-439E-84ED-375104FF2C43@gmail.com> References: <690EEC3B-8E4D-439E-84ED-375104FF2C43@gmail.com> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----AGKPYLV6FVV17Y1EM3RMQ2YS7F8WQT" Content-Transfer-Encoding: 7bit From: Sebastian Moeller Date: Sat, 21 Dec 2013 11:40:38 +0100 To: Rich Brown , Hector Ordorica Message-ID: <328873db-2390-40bd-a2af-ae21d440ada4@email.android.com> X-Provags-ID: V03:K0:F9e341rZcEyfaC7OcJLFHwL+tplyH4EckLCW8bYNfHLXLDL/drG jCMDfS4efFWTZ32o6qmhS9mx0j08Pjr2qPiOgMRCES+EySZT6NIJBCDx2Dvcvpip23pBF4M 9/AXJT3wDxXTT2NbCy+vMbGftgwMWa/Tv7FzFGZ87W5dO8CjaSBcxKwb26mI+YylphFlPWT 2jF3B47AhF0HHQwt0GMYg== Cc: cerowrt-devel@lists.bufferbloat.net Subject: Re: [Cerowrt-devel] Proper AQM settings for my connection? X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 21 Dec 2013 10:40:49 -0000 ------AGKPYLV6FVV17Y1EM3RMQ2YS7F8WQT Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Rich Brown wrote: > >On Dec 20, 2013, at 11:32 PM, Hector Ordorica >wrote: > >> I'm running 3=2E10=2E13-2 on a WNDR3800, and have used the suggested >> settings from the latest draft: >>=20 >> >http://www=2Ebufferbloat=2Enet/projects/cerowrt/wiki/Setting_up_AQM_for_C= eroWrt_310 >>=20 >> I have a 30Mb down / 5Mb upload cable connection=2E >>=20 >> With fq_codel, even undershooting network upload bandwidth by more >> than 95%, I'm seeing 500ms excessive upload buffering warnings from >> netalyzr=2E Download is ok at 130ms=2E I was previously on a 3=2E8 rele= ase >> and the same was true=2E > >I have seen the same thing, although with different CeroWrt firmware=2E >Netalyzr was reporting >> 500 msec buffering in both directions=2E > >However, I was simultaneously running a ping to Google during that >Netalyzr run, and the >ping times started at ~55 msec before I started Netalyzr, and >occasionally they would bump >up to 70 or 80 msec, but never the long times that Netzlyzr reported=2E= =2E=2E > >I also reported this to the Netalyzr mailing list and they didn=E2=80=99t= seem >surprised=2E I=E2=80=99m not sure how to interpret this=2E > >> With pie (and default settings), the buffer warnings go away: >>=20 >> >http://n2=2Enetalyzr=2Eicsi=2Eberkeley=2Eedu/summary/id=3D43ca208a-32182-= 9424fd6e-5c5f-42d7-a9ea >>=20 >> And the connection performs very well while torrenting and gaming=2E >>=20 >> Should I try new code? Or can I tweak some variables and/or delay >> options in scripts for codel? > >A couple thoughts: > >- There have been a bunch of changes between 3=2E10=2E13-2 and the curren= t >version (3=2E10=2E24-5, which seems pretty stable)=2E You might try >upgrading=2E (See the =E2=80=9CRough Notes=E2=80=9D at the bottom of >http://www=2Ebufferbloat=2Enet/projects/cerowrt/wiki/CeroWrt_310_Release_= Notes >for the progression of changes)=2E > >- Have you tried a more aggressive decrease to the link speeds on the >AQM page (say, 85% instead of 95%)? This will not affect the report by netalyzr by much, and it will mos= t likely increase the reported buffering=2E Netalyzr fills fq_codels buffer= and finishes before fq_codel get serious dropping packets to get control o= ver the unruly netalyzr flow=2E > >- Can we get more corroboration from the list about the behavior of >Netalyzer? Yes, several people have stumbled over this issue in the past, prob= ably indicating we should write a FAQ or wiki page about the matter to avoi= d this being rediscovered again and again=2E I really like Dave's proposed = concurrent ping test=2E=2E=2E Best Regards Sebastian > >Rich >_______________________________________________ >Cerowrt-devel mailing list >Cerowrt-devel@lists=2Ebufferbloat=2Enet >https://lists=2Ebufferbloat=2Enet/listinfo/cerowrt-devel Hi Rich, --=20 Sent from my Android phone with K-9 Mail=2E Please excuse my brevity=2E ------AGKPYLV6FVV17Y1EM3RMQ2YS7F8WQT Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable
Rich Brown <richb=2E= hanover@gmail=2Ecom> wrote:

On Dec 20, 2013, at 11:32 PM, Hector Ordorica =
<hechacker1@gmail=2Ecom> wrote:

 I'm running 3=2E10=2E13-2 on a WNDR3800, and have u=
sed the suggested
 settings from the latest draft:
 
 http://www=2Ebufferbloat=2Enet/projects/cerowrt/wiki/Setting=
_up_AQM_for_CeroWrt_310
 
 I have a 30Mb down / 5Mb upload ca=
ble connection=2E
 
 With fq_codel, even undershooting network up=
load bandwidth by more
 than 95%, I'm seeing 500ms excessive upload bu=
ffering warnings from
 netalyzr=2E Download is ok at 130ms=2E I was pr=
eviously on a 3=2E8 release
 and the same was true=2E

I have seen the same thing, although with different CeroWrt firmwar=
e=2E Netalyzr was reporting
 500 msec buffering in both directions=2E

Ho=
wever, I was simultaneously running a ping to Google during that Netalyzr r=
un, and the
ping times started at ~55 msec before I started Netalyzr, =
and occasionally they would bump
up to 70 or 80 msec, but never the lo=
ng times that Netzlyzr reported=2E=2E=2E

I also reported this to=
 the Netalyzr mailing list and they didn=E2=80=99t seem surprised=2E I=E2=
=80=99m not sure how to interpret this=2E

 With pie (and default settings), the buffer war=
nings go away:
 
 http://n2=2En=
etalyzr=2Eicsi=2Eberkeley=2Eedu/summary/id=3D43ca208a-32182-9424fd6e-5c5f-4=
2d7-a9ea
 
 And the connection performs very well while torre=
nting and gaming=2E
 
 Should I try new code? Or can I tweak some=
 variables and/or delay
 options in scripts for codel?

A couple thoughts:

- There have been a bunch of changes=
 between 3=2E10=2E13-2 and the current version (3=2E10=2E24-5, which seems =
pretty stable)=2E You might try upgrading=2E (See the =E2=80=9CRough Notes=
=E2=80=9D at the bottom of http://www=2Ebufferbloat=2Enet/p=
rojects/cerowrt/wiki/CeroWrt_310_Release_Notes for the progression of c=
hanges)=2E

- Have you tried a more aggressive decrease to the li=
nk speeds on the AQM page (say, 85% instead of 95%)?

- Can we ge=
t more corroboration from the list about the behavior of Netalyzer?
Rich

Cerowrt-devel mailing list
Cerowrt-devel@lis=
ts=2Ebufferbloat=2Enet
https://lists=2Ebufferbloat=2Enet/listinfo/cerowrt-de=
vel

Hi Rich,
--
Sent from my Android phone with K-9 Mail=2E Please excuse my brevity=2E ------AGKPYLV6FVV17Y1EM3RMQ2YS7F8WQT--