Re: [quicwg/base-drafts] Limit CWND increase in slow start (#3232)

ianswett <> Wed, 13 November 2019 00:26 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id 4896F1200B5 for <>; Tue, 12 Nov 2019 16:26:31 -0800 (PST)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -6.382
X-Spam-Status: No, score=-6.382 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIMWL_WL_HIGH=-0.001, 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_HELO_NONE=0.001, SPF_PASS=-0.001] 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 Hb9Vz0no7aSQ for <>; Tue, 12 Nov 2019 16:26:29 -0800 (PST)
Received: from ( []) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by (Postfix) with ESMTPS id 94582120044 for <>; Tue, 12 Nov 2019 16:26:29 -0800 (PST)
Date: Tue, 12 Nov 2019 16:26:27 -0800
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=pf2014; t=1573604788; bh=//EmffgqkvQO9mthC30hfu6uLNnphUKLLGN3HxuTico=; h=Date:From:Reply-To:To:Cc:In-Reply-To:References:Subject:List-ID: List-Archive:List-Post:List-Unsubscribe:From; b=Q6LiGXkli3U0XqVvg8NQvMeiNJiz+agzMAMGfeBcIPEa9EtgRhBpcK8wVpmRQNUzW UuNuKI4ERKiEbPB/crxz62oDObOuFWIkEQqFzBySO+t8iVnM2thNFKPtYGSG8ogA6V mZKhTWbY+PampiGoA8Nlse6QqBtTN3Rqj1pIdxUs=
From: ianswett <>
Reply-To: quicwg/base-drafts <>
To: quicwg/base-drafts <>
Cc: Subscribed <>
Message-ID: <quicwg/base-drafts/pull/3232/>
In-Reply-To: <quicwg/base-drafts/pull/>
References: <quicwg/base-drafts/pull/>
Subject: Re: [quicwg/base-drafts] Limit CWND increase in slow start (#3232)
Mime-Version: 1.0
Content-Type: multipart/alternative; boundary="--==_mimepart_5dcb4db3cf232_53443ffbe16cd9601705aa"; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Precedence: list
X-GitHub-Sender: ianswett
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: Wed, 13 Nov 2019 00:26:32 -0000

Thanks for your PR, it's helpful to see this clarified.

I think it's worth a discussion of two issues, maybe in Singapore:
1) Do we need anything in addition to the existing IW burst limit?  A single ACK loss would not cause a burst to exceed the IW10 limit, and multiple consecutive ACK losses in slow start are VERY rare in my experience.
2) Do we need to describe the non-pacing scenarios in the pseudocode, given we recommend pacing?  Using CWND to manipulate sending behavior is an indirect method that feels like a holdover from implementation details of older TCP algorithms to me.

I'm no on both counts currently, but if the WG feels otherwise, I can accept that.

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