From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ie0-x22e.google.com (mail-ie0-x22e.google.com [IPv6:2607:f8b0:4001:c03::22e]) (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 38A2221F221 for ; Sat, 9 May 2015 10:59:08 -0700 (PDT) Received: by iecmd7 with SMTP id md7so6459111iec.3 for ; Sat, 09 May 2015 10:59:06 -0700 (PDT) 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=GRVd0dcpJc1H8PQ3FBRUaHr0h4OArfmnICNYb4+G3B0=; b=0pf+8BxWzWdwf5E0gQCDDeO5sLfhpQXErEoZMXI/jAWpVC0nGuZtE4P+s3S2XSx4/P t7WS5fJwbDVRd7S5vznNubu3ceRfLXbNO4Dg5tsIMj5ZcZGuWNbi4LD7GGv6qEIGtwJI 6i0k94LvRRxo8fvVx2M0OvnGMTyVmJFLVxiLPmpbBB2QI0BwzaXpSjFZTh3lodcbNKMM 18jrOfvyc3EPutiePcv5sSbS0hnYtNaccnPtE8cisBNzJm7I5E8pp24u8GaVe5+58kUt Ur9IcvE1obty/AGn22g6f7XHTdMXXPWoY0FYWyO7saQzmTQa0qBpGEjIfy+fWTrmEQ7n ifWQ== MIME-Version: 1.0 X-Received: by 10.43.169.137 with SMTP id nm9mr3722494icc.82.1431194346376; Sat, 09 May 2015 10:59:06 -0700 (PDT) Received: by 10.36.207.134 with HTTP; Sat, 9 May 2015 10:59:06 -0700 (PDT) Received: by 10.36.207.134 with HTTP; Sat, 9 May 2015 10:59:06 -0700 (PDT) In-Reply-To: References: Date: Sat, 9 May 2015 20:59:06 +0300 Message-ID: From: Jonathan Morton To: Dave Taht Content-Type: multipart/alternative; boundary=001a11c2d1f69ed7a70515a9e66f Cc: cake@lists.bufferbloat.net Subject: Re: [Cake] packet mass, ecn, and a fractional count X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 09 May 2015 17:59:50 -0000 --001a11c2d1f69ed7a70515a9e66f Content-Type: text/plain; charset=UTF-8 I have no idea how Tracy-Widom applies here, or what it would mean if it did. Pure mathematics is not my strong point. If there's a concrete point you're trying to make, I might grasp it better if explained a different way. What I do understand is that fq_codel and cake already provide a higher signalling rate in the presence of multiple flows, when compared to plain codel. Each codel instance signals at a given rate once triggered, and the number of instances scales more or less linearly with the number of flows. Further, the signals are directed specifically to the flows which need them. So I don't see the need to increase that signalling rate still further, in the FQ case. It might be a good idea for plain codel, but that's not the subject of this list. - Jonathan Morton --001a11c2d1f69ed7a70515a9e66f Content-Type: text/html; charset=UTF-8 Content-Transfer-Encoding: quoted-printable

I have no idea how Tracy-Widom applies here, or what it woul= d mean if it did. Pure mathematics is not my strong point. If there's a= concrete point you're trying to make, I might grasp it better if expla= ined a different way.

What I do understand is that fq_codel and cake already provi= de a higher signalling rate in the presence of multiple flows, when compare= d to plain codel. Each codel instance signals at a given rate once triggere= d, and the number of instances scales more or less linearly with the number= of flows. Further, the signals are directed specifically to the flows whic= h need them.

So I don't see the need to increase that signalling rate= still further, in the FQ case. It might be a good idea for plain codel, bu= t that's not the subject of this list.

- Jonathan Morton

--001a11c2d1f69ed7a70515a9e66f--