Re: [tsvwg] [Fwd: Re: Traffic protection as a hard requirement for NQB]

Jonathan Morton <> Mon, 09 September 2019 20:29 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id 945741200B8 for <>; Mon, 9 Sep 2019 13:29:18 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -1.748
X-Spam-Status: No, score=-1.748 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, FREEMAIL_ENVFROM_END_DIGIT=0.25, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=no autolearn_force=no
Authentication-Results: (amavisd-new); dkim=pass (2048-bit key)
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id 1ReWOrrpHN_L for <>; Mon, 9 Sep 2019 13:29:17 -0700 (PDT)
Received: from ( [IPv6:2a00:1450:4864:20::22b]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by (Postfix) with ESMTPS id 00FCB120048 for <>; Mon, 9 Sep 2019 13:29:16 -0700 (PDT)
Received: by with SMTP id j16so14110647ljg.6 for <>; Mon, 09 Sep 2019 13:29:16 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=20161025; h=mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=Byi5/Vh9AYYF9arpCOs7PJWQh+Q07Za8CzTD5Yq2qi8=; b=mFwBS0Ce3wfiKd1tXuZ3TZY2z66U6E/jhXoXS1w+6w2cPtgN/WF1ew5KhN1bvOiSAR p7Ju49WKGLQJxZIRpamtBx5bj1RXeKREii4Sh0qoI2DStM7NH0LJtVz6ZulgE31Q7KCr iadh9UvwBfP3tBhADWJW+4dhOoKxaNR9ZnpyJvo/fglW/uK+8nfY/aw2VNR1GfbwKT5P PL0ijmF9Xn1MxjuN8O27VbzRgxH5SZt/+diyk/XEF4d69efiKaJdqps8WBzO5p5RsH+4 jEUlN+HIsm9N//nX+diisGAVQKorVa7vvR2bHzhYY0dITIdyd01VZ6XBqZ4yCJvyrID4 tqFA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=20161025; h=x-gm-message-state:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=Byi5/Vh9AYYF9arpCOs7PJWQh+Q07Za8CzTD5Yq2qi8=; b=FPWCwF5EMYpCqxfxZqO6JbdX1tUM7HZbVw+K/jD/VMi8HgJF0FEUofzCu+wnycsd69 cw/InloU2TGjasHXrehCVts0FKICUJ9+PA6vdt7+lpd3Xb7fv758b8Ap+McPyLva2on7 SBjzQw7+a9WRwja3PJvjj9V3R0IXrwzVnlhlcZ1JFzdhV5nQZzwy9SfYtLu8rJjQiqRS vSE2FOY2wlpQaFUgDDzDWv5nRfwGHTnSTb3kGYHdXCRn/dFTTRiW/zztJrUyNenoC0E8 MWrclpAeRk+rKgKVJa74qO98hSEMd2ReYJUKHLGu+o1qWsyvF1PWsVa+6DFrqmx2TWli EiTw==
X-Gm-Message-State: APjAAAUNZea54T6D7FTOnwHIKWGjy512b9ojre3rBwPkTOTAavhJjsRy J+qvnoKBev3Twi51Rgbi3ISZm8xYq6A=
X-Google-Smtp-Source: APXvYqyGBf4gQ6U/iN/3IdmPus/ZgO8m971Quu15ikZwZ/isswekbPVudYYJcw9qA8hikUFwWsfgTA==
X-Received: by 2002:a2e:442:: with SMTP id 63mr17510243lje.66.1568060955254; Mon, 09 Sep 2019 13:29:15 -0700 (PDT)
Received: from jonathartonsmbp.lan ( []) by with ESMTPSA id d13sm3652972lfm.21.2019. (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Mon, 09 Sep 2019 13:29:14 -0700 (PDT)
Content-Type: text/plain; charset=us-ascii
Mime-Version: 1.0 (Mac OS X Mail 11.5 \(3445.9.1\))
From: Jonathan Morton <>
In-Reply-To: <>
Date: Mon, 9 Sep 2019 23:29:11 +0300
Cc: "" <>
Content-Transfer-Encoding: quoted-printable
Message-Id: <>
References: <> <>
To: Steven Blake <>
X-Mailer: Apple Mail (2.3445.9.1)
Archived-At: <>
Subject: Re: [tsvwg] [Fwd: Re: Traffic protection as a hard requirement for NQB]
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Transport Area Working Group <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Mon, 09 Sep 2019 20:29:19 -0000

> On 9 Sep, 2019, at 7:31 pm, Steven Blake <> wrote:
> How do you estimate how much NQB traffic there might be? How would you tune this? My assumption is that this whole scheme only survives if the amount of NQB traffic is always so small relative to any link's capacity (< 5%) that you just allocation a small fraction of link capacity to NQB and forget about it. In which case, WRR scheduling doesn't give you good latency because your HOL NQB packet might have to wait for >= 20 MTU/link rate to get serviced.

I think we are also dancing around a more general problem here.  If we are having to use straw-man implementations to argue about the merits of the PHB, that implies that we don't have a real implementation to experiment with.

I would advise the authors to come up with a real implementation that has the behaviour they want and adequate robustness, and then we can re-open the discussion with "running code" to work from.

 - Jonathan Morton