Re: [quicwg/base-drafts] Pacing when under-utilizing the Congestion Window (#2686)

Gorry Fairhurst <> Fri, 10 May 2019 12:25 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id D50E11200F8 for <>; Fri, 10 May 2019 05:25:31 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -6.392
X-Spam-Status: No, score=-6.392 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HTML_IMAGE_ONLY_24=1.618, HTML_MESSAGE=0.001, MAILING_LIST_MULTI=-1, RCVD_IN_DNSWL_HI=-5, SPF_PASS=-0.001, T_DKIMWL_WL_HIGH=-0.01] autolearn=ham autolearn_force=no
Authentication-Results: (amavisd-new); dkim=pass (1024-bit key)
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id U0p28qooAEmF for <>; Fri, 10 May 2019 05:25:30 -0700 (PDT)
Received: from ( []) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by (Postfix) with ESMTPS id 3AFAB120088 for <>; Fri, 10 May 2019 05:25:30 -0700 (PDT)
Date: Fri, 10 May 2019 05:25:29 -0700
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=pf2014; t=1557491129; bh=QMdp/Y38WhzRAreDpfxINuV7Z1lYgBmcodruoO3oWfA=; h=Date:From:Reply-To:To:Cc:In-Reply-To:References:Subject:List-ID: List-Archive:List-Post:List-Unsubscribe:From; b=cPsp8w/sKlOrr6OWq7Jmn+q4U0LT/qSPnoLKAlmAuAjuWpSVJd9tQl5UW5z6CI6E7 y8ZjTohruDzojvjM2W+KhrqhKofihCG4BkPZKLuf5noEtoa71YOoHt8fXh/vo8CsUs Co4ZN5trkWNadbPjkMPMO4x5Uw3NhDQfTQ5UWayE=
From: Gorry Fairhurst <>
Reply-To: quicwg/base-drafts <>
To: quicwg/base-drafts <>
Cc: Subscribed <>
Message-ID: <quicwg/base-drafts/issues/2686/>
In-Reply-To: <quicwg/base-drafts/issues/>
References: <quicwg/base-drafts/issues/>
Subject: Re: [quicwg/base-drafts] Pacing when under-utilizing the Congestion Window (#2686)
Mime-Version: 1.0
Content-Type: multipart/alternative; boundary="--==_mimepart_5cd56db92ca77_25973fb5c0acd9641035be"; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Precedence: list
X-GitHub-Sender: gorryfair
X-GitHub-Recipient: quic-issues
X-GitHub-Reason: subscribed
X-Auto-Response-Suppress: All
Archived-At: <>
X-Mailman-Version: 2.1.29
List-Id: Notification list for GitHub issues related to the QUIC WG <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Fri, 10 May 2019 12:25:32 -0000

Ah, my reading of the text led me in a different direction - I think we can now talk.

( I know Google shared data on IW10 and also later on other IW proposals. I also think I have seen other analysis that suggested that a larger IW can have an impact - IW10, or larger - can have collateral damage to flows sharing a bottleneck. In this case, because there is no ACK-clocking. )

Could I propose describing limiting the max burst size and enabling pacing for any remaining packets sent above this using the remaining (cwnd-max_burst). My reading is that the current text sets the max_burst size to IW. That is certainly one choice, and could be an upper limit. I am less clear that IW (the startup cwnd) should always be the same as the maximum burst size. Some SCTP implementation uses 4 packets, and I suspect that there could be cases where someone proposed a larger IW, but retained a max_burst that is lower than the increased IW. 

You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub: