From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ia0-x22e.google.com (ia-in-x022e.1e100.net [IPv6:2607:f8b0:4001:c02::22e]) (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 E1D6221F190 for ; Sun, 27 Jan 2013 04:28:47 -0800 (PST) Received: by mail-ia0-f174.google.com with SMTP id o25so2895309iad.19 for ; Sun, 27 Jan 2013 04:28:47 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:x-received:date:message-id:subject:from:to :content-type; bh=vRvD9DG2PALQNfAmP8bKSC2KiRkjVk/eVRixTthb24Q=; b=eLqulLMhf9roauCssCfaH8ILdpWklBDWtU5bnjXDTuXf0cYu3Z/wbwSlP9i2A1zpJP ZW4969ANAXx3I/Vs+CxRo0x/qx1dLPuYON+YU4kd+nD0jO6k8IaZ731vjwQwQHMW6wFW SLnCB+jBSyJbqbPuPmCYoJ4BUhcEh0KExllTvTclMfNVNV2WcAUFznWHw2JVMCKepJh9 4RWLe288C6KmeEi3lNhMWQZCYY6SgZLfDOrvX/VC4/R6n3DFHC5ECih9tL7H/1SWtIfu O8Tkqp6dmmY+b+zbz5l6jQ2hIO01UHrkCU2eZLJznRG0OFVCZ5Nl1vkFHryG574vtnBE qLqA== MIME-Version: 1.0 X-Received: by 10.50.168.102 with SMTP id zv6mr2725434igb.27.1359289727174; Sun, 27 Jan 2013 04:28:47 -0800 (PST) Received: by 10.64.135.39 with HTTP; Sun, 27 Jan 2013 04:28:47 -0800 (PST) Date: Sun, 27 Jan 2013 04:28:47 -0800 Message-ID: From: Dave Taht To: cerowrt-devel@lists.bufferbloat.net Content-Type: multipart/alternative; boundary=e89a8f83ab1955c7a704d4444d7e Subject: [Cerowrt-devel] Fixing simple_qos.sh 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: Sun, 27 Jan 2013 12:28:48 -0000 --e89a8f83ab1955c7a704d4444d7e Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable A couple things: It has long been my plan to integrate simple_qos (call it ceroshaper) into the gui, and have a test run automatically to determine the uplink/downlink bandwidth, and store that in upnp. The gui interface stuff has long defeated me, as well as finding enough servers to be the backend portion of the test. as for the latter portion, I have got a couple linode boxes up and hope to get some more boxes from another resource. as for the gui, I'm just hopeless there. As for the shaper script... One thing I notice right now is that an awful lot of stuff ends up in the background bin for some reason. Similar things are happening on (unshaped) wifi. There's a bug there I think. It's been my hope to finish cake (simple_qos poured into C and made more 32 bit cpu oriented) for a month now. I hope that will fix the background bin thing as it does full diffserv classification - but I don't know when I'll be done, so it would be nice to figure out what's going on. One thing that testing (actually kathie) revealed last week is that 1024 nfq_codel flows may be excessive. 32 works pretty good, actually, and provides a defense indirectly, against bittorrent eating your life. Why that works is that codel works pretty good against one or a few flows in a single bin, and 32 bins limits the amount of delay that can be injected into the system that is unmanagable via codel. I'd been trying for "perfect isolation" between flows, but that meant that in an extreme overload situation with 100s of flows, and low bandwidth, delay could get out of hand. Heck, 16 bins might be enough. Don't know. --=20 Dave T=E4ht Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html --e89a8f83ab1955c7a704d4444d7e Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable A couple things:

It has long been my plan to integrate simple_qos (c= all it ceroshaper) into the gui, and have a test run automatically to deter= mine the uplink/downlink bandwidth, and store that in upnp.

The gui = interface stuff has long defeated me, as well as finding enough servers to = be the backend portion of the test. as for the latter portion, I have got a= couple linode boxes up and hope to get some more boxes from another resour= ce. as for the gui, I'm just hopeless there.

As for the shaper script...

One thing I notice right now is that= an awful lot of stuff ends up in the background bin for some reason.
<= br>Similar things are happening on (unshaped) wifi. There's a bug there= I think.

It's been my hope to finish cake (simple_qos poured i= nto C and made more 32 bit cpu oriented) for a month now. I hope that will = fix the background bin thing as it does full diffserv classification - but = I don't know when I'll be done, so it would be nice to figure out w= hat's going on.

One thing that testing (actually kathie) revealed last week is that 102= 4 nfq_codel flows may be excessive. 32 works pretty good, actually, and pro= vides a defense indirectly, against bittorrent eating your life. Why that w= orks is that codel works pretty good against one or a few flows in a single= bin, and 32 bins limits the amount of delay that can be injected into the = system that is unmanagable via codel. I'd been trying for "perfect= isolation" between flows, but that meant that in an extreme overload = situation with 100s of flows, and low bandwidth, delay could get out of han= d.

Heck, 16 bins might be enough. Don't know.

--
Dave T=E4= ht

Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowr= t/subscribe.html=20 --e89a8f83ab1955c7a704d4444d7e--