From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-vc0-x230.google.com (mail-vc0-x230.google.com [IPv6:2607:f8b0:400c:c03::230]) (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 700D421F38D for ; Wed, 4 Mar 2015 13:49:39 -0800 (PST) Received: by mail-vc0-f176.google.com with SMTP id kv7so7256845vcb.7 for ; Wed, 04 Mar 2015 13:49:38 -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=vnW9j6dvFLUIw34/ztgDlxEmbjV9rtJhXIwEAtr6ooQ=; b=hBLUf1jt42ksmYUWHeRZQksW78pW0k/7g3iTlFHnDPx3jQA/PbyAItn+Mwggf95Bji qmklusVbY8sHlvASyHYvY1Xc0zfnJAQQrnIRlLgIZi2+db2zXXzw5NXrkbkZ2I5NirOm 9DeQtTiU0QxmMGEpYQIcg3NJG9xogIUhwgS0i/mDb0Z+zGIWD0i7IOOPTaIJcAYnAd13 67Bz5izJr4LLtv6MPoXiG00cwvNE6u1JAzz+zcqzu3Yq5rnEeb6r/VKMh2AikE/4AC7R FMGRf/nvEeJFGrpI4kordqz9nekdql1ki/E0e8EQta45IBKxsUPOD9lGDRZ1d9nxWoSK BQJw== MIME-Version: 1.0 X-Received: by 10.52.92.39 with SMTP id cj7mr9329589vdb.97.1425505778658; Wed, 04 Mar 2015 13:49:38 -0800 (PST) Received: by 10.52.24.79 with HTTP; Wed, 4 Mar 2015 13:49:38 -0800 (PST) Received: by 10.52.24.79 with HTTP; Wed, 4 Mar 2015 13:49:38 -0800 (PST) In-Reply-To: <20150304211758.33DDE406057@ip-64-139-1-69.sjc.megapath.net> References: <20150304211758.33DDE406057@ip-64-139-1-69.sjc.megapath.net> Date: Wed, 4 Mar 2015 23:49:38 +0200 Message-ID: From: Jonathan Morton To: Hal Murray Content-Type: multipart/alternative; boundary=bcaec5015ed18ff17c05107d6d19 Cc: bloat Subject: Re: [Bloat] Really really big buffers 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: Wed, 04 Mar 2015 21:50:08 -0000 --bcaec5015ed18ff17c05107d6d19 Content-Type: text/plain; charset=UTF-8 No, I don't think that's what's happening. The in-flight one, which is the most egregious example, shows the queue gradually draining at the end of the flight, when all the passengers have been told to turn their lap warmers and fondleslabs off. I personally have seen 45 seconds buffering delays with continuous delivery at half a megabit or so, resulting from a market segmentation shaper in a 3G network using a big, drop tail queue. In fact, I could probably reproduce that effect using the hardware in my hands right now. The FireBrick, a custom firmware router made by A&A to go with their services, is reportedly capable of rebooting without losing a packet. But it does so by completing the reboot extremely quickly - a fraction of a second. (It doesn't run Linux.) - Jonathan Morton --bcaec5015ed18ff17c05107d6d19 Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable

No, I don't think that's what's happening.

The in-flight one, which is the most egregious example, show= s the queue gradually draining at the end of the flight, when all the passe= ngers have been told to turn their lap warmers and fondleslabs off.

I personally have seen 45 seconds buffering delays with cont= inuous delivery at half a megabit or so, resulting from a market segmentati= on shaper in a 3G network using a big, drop tail queue. In fact, I could pr= obably reproduce that effect using the hardware in my hands right now.

The FireBrick, a custom firmware router made by A&A to g= o with their services, is reportedly capable of rebooting without losing a = packet. But it does so by completing the reboot extremely quickly - a fract= ion of a second. (It doesn't run Linux.)

- Jonathan Morton

--bcaec5015ed18ff17c05107d6d19--