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 TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 8A7C93B2A0 for ; Wed, 20 Jan 2016 11:09:45 -0500 (EST) Received: from android-2a136033e75488df.home.lan ([217.247.221.45]) by mail.gmx.com (mrgmx001) with ESMTPSA (Nemesis) id 0LuOYx-1aB6Nl17SB-011j9U; Wed, 20 Jan 2016 17:09:42 +0100 User-Agent: K-9 Mail for Android In-Reply-To: References: <893CBD83-58AB-407E-864D-B47F0B8D0334@gmx.de> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable From: Sebastian Moeller Date: Wed, 20 Jan 2016 17:09:39 +0100 To: Brandon Applegate CC: Bloat@lists.bufferbloat.net Message-ID: <3B0CED49-6E18-4D82-B44A-1E4BA0E1F29E@gmx.de> X-Provags-ID: V03:K0:toBnDRUteOMlEqyGGm6mvf+MyYeAIdrvgisFD9ZX4keJidMSd6n 7VXJ5A01uPYY438pJbADwyA/SXbeiuVjfhl7sE36DXECqpB2XDuYWnEIRXt1uXVTu/EBD24 9Zvhh7m+PtHf27PEwgkrl4YwwQ6TmvQUjYsnwCJ+CeBRH6jB1/D2moJvPNIYFHwovfsPV1F JIZnpHRUVskCUPZEu2phQ== X-UI-Out-Filterresults: notjunk:1;V01:K0:sbKreslh7f4=:sGWdxm8bMFRqRgnBVaPJSh wTzv4sR6n4VmrOKGbQAvaqvq2kAS7cwwNkN/aY8jrH+WxipS+HVFZSUDINvIL+sY4ak3fX6HK T/Dvik6JqHqRZvSigHEYHMe73L+NFrz3mC4kyVPmwMc6nHZWplSWA9ePFKoIK4wIbGuSdIS+t wXSiEx0OauLEDoUnarpMt8CL1oIiWpay986WBalujOiX6q3HDMQ7J0m0RbRhvjH68I3/b0ivH rt8bF+/TDlVe+Gij9fuh/S4uh4CN83Ducwo5vMvaXHJsk/qbDFJGWwt5xRRzhvQq3yvtlTkTZ Kh0zvx1EHF9s4gF5enfXL6/WeCqSslgZqzWvpa/RBKMqRz4/wvmF7GdxaiN0qcw/YM4cfisp6 RCKn4RBOIz7AMKjZ4VakLp/bBAWlU3ffILC2wlpP9/s1f/1Hs2q+79kqmYb1qovVUOTnCgSO9 H3hyREKaJFvQY04H7Updkop4v9cUO5ItApOBrksFmm4hGzo3ELBJvu7Ij+mw6h+Xpw5nFI1Fu 306SkgVj2tD4c4bIkj8zax+qGaj8gowM30Y0RVqxMcnzDayFGOT08KLkOcsnO891vBOTPZs0w hKuAycCCZpa7enwpcVmLUapBgy1Br09xRUmIgUexBusnFCUGNVFe8/38c8q1h9YKLGoVzpHZj GJYT/9auUDi5qrhTjXLGWFqeGaYVVuB3dDSIR3SX/NZtm2hlMUsC7I7pC0UoDQOVulfxQf8Af I2yd3ZwGnDjS+C2oyZ8nQwzhSW5WIHT83jxHmJ+HJz+wdv3NzpYnpIA5XTryN/oOaa1iuWnCn hMqlYky Subject: Re: [Bloat] Getting started with sqm-scripts - latency good, bandwidth decimated X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 20 Jan 2016 16:09:45 -0000 Hi Brandon, First, thanks a lot=2E On January 20, 2016 4:30:25 PM GMT+01:00, Brandon Applegate wrote: >I=E2=80=99ll try to tackle what I can for now below inline=2E > >> On Jan 20, 2016, at 6:30 AM, moeller0 wrote: >>=20 >> Hi Brandon, >>=20 >>=20 >>> On Jan 20, 2016, at 00:33 , Brandon Applegate >wrote: >>>=20 >>> Disclaimer: if this is the wrong list for such a question - let me >know=2E This is specifically about the sqm-scripts package=2E=2E=2E >>>=20 >>> Hello, >>>=20 >>> I=E2=80=99ve been reading all I can on the bufferbloat website and als= o >trying to understand the evolution of the various scripts (debloat, >sqm, etc)=2E >>>=20 >>> I managed to get sqm-scripts on my firewall (Ubuntu linux on a PC - >no *wrt etc)=2E Got it built with the =E2=80=98linux=E2=80=99 platform= =2E Since this is >Ubuntu 12=2E04 - I had to cheat a bit and pull down the iproute2 source >from 14=2E04=2E I=E2=80=99ve tweaked the main sqm script to reflect this= for the >tc bindary - this is working=2E I also updated my kernel to a later >version that supports fq_codel=2E >>=20 >> Great, could I convince you to post a quick description of the >required steps somewhere linkeable on the net (in case we actually get >it to work correctly first ;) ) >>=20 >>>=20 >>> My topology is =E2=80=98on a stick=E2=80=99=2E I have one gig interfa= ce to a managed >switch, on which are eth0=2E666 (outside/wan) and eth0=2E10 (inside)=2E >>=20 >> Okay, that is a configuration that has not received much testing in >the past=E2=80=A6 >>=20 >>>=20 >>> I have 30/5 cable service, and have tried both those values as well >as 90% in my /etc/sqm/*conf file=2E >>>=20 >>> I=E2=80=99ve tried both eth0 (raw/parent interface) as well as eth0=2E= 666=2E >>=20 >> Eth0 is not going to work in that situation as you will send and >receive both incoming and outgoing traffic on that interface, so we >really need to configure it correctly on the VLAN interfaces=2E I would >like to propose to start with egress/uplink first and handle ingress >afterwards=2E If you select eth0=2E666 (the superstitious among us would >probably try a different VLAN number ;) ) and only configure the upload >bandwidth but set download to 0, effectively sqm will only try to shape >the egress traffic=2E I would propose to try this first, if that works >let=E2=80=99s tackle download/ingress okay > >I set DOWNLINK to 0 and here are the results (again - using >speedtest=2Edslreports=2Ecom) > >Download: 36 mbit (bufferbloat through the roof) >Upload: Slowly climbed to ~ 4=2E5mbit (bufferbloat good/very low) Okay so it seems the uplink shaping is working as intended=2E Good so it s= eems you are ready to tackle ingress/download next ;) > >>>=20 >>> No matter what I do - my bandwidth is 10% of what it should be=2E >>=20 >> Here a comprehensive list what you actually did might help to form >educated hypothesis what is going on=2E=2E=2E >>=20 >>> I get approx=2E 3/4mbit down + 2/3mbit up on dslreports speedtest=2E= =20 >Bufferbloat looks great though - A+=2E >>=20 >> Mmmh, while I would love to declare success (bufferbloat quashed, >let=E2=80=99s move on) I have a hunch you are not too impressed with that >solution ;) >>=20 >>>=20 >>> Is there something inherent I=E2=80=99m doing wrong ? >>=20 >> No, by all means you are doing the right thing, namely helping us >making sqm robust under more different conditions, thanks=2E >>=20 >>=20 >>> Something to do with my =E2=80=98on a stick=E2=80=99 topology biting m= e ? >>=20 >> Could be, but nobody knows=2E >>=20 >>> Kernel version (Ubuntu=E2=80=99s 3=2E13=2E0-74-generic btw)=2E >>>=20 >>> Thanks in advance for any help or info (or pointer to a more >appropriate list)=2E >>=20 >> We recently taught sqm a whole new level of verbosity, please have a >look at Readme=2Emd on https://github=2Ecom/tohojo/sqm-scripts , I believ= e >under non openwrt systems you might need to set: >> [ -z "$SQM_VERBOSITY" ] && SQM_VERBOSITY=3D$VERBOSITY_DEBUG >> instead of the default: >> [ -z "$SQM_VERBOSITY" ] && SQM_VERBOSITY=3D$VERBOSITY_INFO >> and then issue: >> /usr/bin/sqm/sqm-bin stop >> /usr/bin/sqm/sqm-bin start >> manually to get more verbose output, You could also try setting >SQM_DEBUG unconditionally to 1 in defaults=2Esh (in addition to raising >the default log level to SQM_DEBUG) to get debug logs under: >> /var/run/sqm/eth0=2E666=2Edebug=2Elog >> or similar=2E That ideally will contain all debug output as well as all >calls to the tc and ip and iptables binaries and their output, which >should be plenty information to figure out the root cause of your >issues=2E > >I can=E2=80=99t get it to log anything for the life of me=2E I=E2=80=99v= e tried: > >SQM_DEBUG=3D1 SQM_VERBOSITY=3D8 /etc/init=2Ed/sqm stop ; SQM_DEBUG=3D1 >SQM_VERBOSITY=3D8 /etc/init=2Ed/sqm start I am unsure whether this will work outside of openwrt, as we needed some e= xtra code in run=2Esh to pass these on from the command line=2E > >As well as temporarily mucking around in the defaults=2Esh script=2E It >never writes anything to the /var/run (but the state gets written, so I >don=E2=80=99t think it=E2=80=99s perms)=2E That is sad=2E Maybe we try to solve your real problem first and then mayb= e if you are still patient enough we could try to improve sqm scripts? Best Regards Sebastian --=20 Sent from my Android device with K-9 Mail=2E Please excuse my brevity=2E