From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.perfora.net (mout.perfora.net [74.208.4.197]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "mout.perfora.net", Issuer "Thawte SSL CA" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 7321F21F304 for ; Mon, 1 Sep 2014 10:23:14 -0700 (PDT) Received: from J4 (c-68-50-226-187.hsd1.md.comcast.net [68.50.226.187]) by mrelay.perfora.net (node=mreueus003) with ESMTP (Nemesis) id 0M6lgg-1YIYNX2Gm4-00wUHJ; Mon, 01 Sep 2014 19:23:12 +0200 From: "Jerry Jongerius" To: Date: Mon, 1 Sep 2014 13:23:11 -0400 Message-ID: <000001cfc609$697feb30$3c7fc190$@duckware.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Outlook 14.0 Thread-Index: Ac/GCHOuvkubRExKQ829gE0e6MRJqw== Content-Language: en-us X-Provags-ID: V02:K0:PhaqnNWuAi5GP/wRSb7Eapo43Eb8AgfZOceYTgGv0le bbn9XpGEVYMoiE8ENOdTAA3bnIv58jg35uMItr5od3vuVYWF/V anNxVrZxw6aZp3gGIhF1uooTqrDhoLL5waszV++HBriKNWtDUs K0KHjYpgu0j/0wE/4PKjSkE5NVIn30edcCB60Q2rT0gB57OEud uSO9l7DQxrkVzhgGzBHQiiE9CBFOwp4fleKylr6G3pGDPPcjPp 02hO2V1PSORLnYztGed/7CMXeracmNjOosCa8B53AhsHmf3mMJ Y3BhsPRJqR1PQQXviOA3RlMN3+kGfIvmv9mwwo7e6aw10kT5Ac curg3AOrFTEz0Crv0MmnU8NkvF4Df6Fh/prftJQmR X-UI-Out-Filterresults: notjunk:1; Subject: [Bloat] What is wrong with Microsoft's receive window auto-tuning? 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: Mon, 01 Sep 2014 17:23:14 -0000 I am noticing (via WireShark traces) at times that Microsoft's (Windows 7) receive window auto-tuning goes horribly wrong, causing significant buffer bloat. And at other times, the tuning appears to work just fine. For example, BDP suggests a receive window of 750k, and most often Windows tunes around 1MB -- but at other times, it will tune to 3.8MB (way more than it should). Is anyone aware of any research either pointing out how their tuning algorithm works, or of known bugs/problems with the algorithm?