Re: [quicwg/base-drafts] Should we allow ACK-only packets to be declared lost? (#3451)

Kazuho Oku <notifications@github.com> Wed, 12 February 2020 05:34 UTC

Return-Path: <noreply@github.com>
X-Original-To: quic-issues@ietfa.amsl.com
Delivered-To: quic-issues@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id BE7311200E3 for <quic-issues@ietfa.amsl.com>; Tue, 11 Feb 2020 21:34:02 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -7.999
X-Spam-Level:
X-Spam-Status: No, score=-7.999 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_32=0.001, 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: ietfa.amsl.com (amavisd-new); dkim=pass (1024-bit key) header.d=github.com
Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id ja7DpHKFhxbP for <quic-issues@ietfa.amsl.com>; Tue, 11 Feb 2020 21:33:59 -0800 (PST)
Received: from out-17.smtp.github.com (out-17.smtp.github.com [192.30.252.200]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 11DBC12022C for <quic-issues@ietf.org>; Tue, 11 Feb 2020 21:33:59 -0800 (PST)
Date: Tue, 11 Feb 2020 21:33:57 -0800
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=github.com; s=pf2014; t=1581485637; bh=P/YFf58I5YMfLnPVQGNxUbihBXSOtoqboedNoUtXzus=; h=Date:From:Reply-To:To:Cc:In-Reply-To:References:Subject:List-ID: List-Archive:List-Post:List-Unsubscribe:From; b=0VlzVlsRG7fDVlq1y8AtZgCqpIcoIeRSoJgNCoLJpvTsvVpOCVw5k2qOW2Dmr0aj0 o4iHDl4dmr97iT85aeVVxl56wcDYRq40BkzPYBVJpalnI/bOkLMo+oh7pFIkzEmAzt NrVDdwaxlKNUjXnbMxUgEtAF3V8nK+3E8t5Sj6gY=
From: Kazuho Oku <notifications@github.com>
Reply-To: quicwg/base-drafts <reply+AFTOJK6R767EVLMY5FXBDPN4KDAMLEVBNHHCDF6P4Q@reply.github.com>
To: quicwg/base-drafts <base-drafts@noreply.github.com>
Cc: Subscribed <subscribed@noreply.github.com>
Message-ID: <quicwg/base-drafts/issues/3451/585037874@github.com>
In-Reply-To: <quicwg/base-drafts/issues/3451@github.com>
References: <quicwg/base-drafts/issues/3451@github.com>
Subject: Re: [quicwg/base-drafts] Should we allow ACK-only packets to be declared lost? (#3451)
Mime-Version: 1.0
Content-Type: multipart/alternative; boundary="--==_mimepart_5e438e45b7907_5dec3f8fa98cd96c1597d6"; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: list
X-GitHub-Sender: kazuho
X-GitHub-Recipient: quic-issues
X-GitHub-Reason: subscribed
X-Auto-Response-Suppress: All
X-GitHub-Recipient-Address: quic-issues@ietf.org
Archived-At: <https://mailarchive.ietf.org/arch/msg/quic-issues/jexozQNBCdEbfQ-PQW8bsgC41xY>
X-BeenThere: quic-issues@ietf.org
X-Mailman-Version: 2.1.29
List-Id: Notification list for GitHub issues related to the QUIC WG <quic-issues.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/quic-issues>, <mailto:quic-issues-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/quic-issues/>
List-Post: <mailto:quic-issues@ietf.org>
List-Help: <mailto:quic-issues-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/quic-issues>, <mailto:quic-issues-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 12 Feb 2020 05:34:03 -0000

Let my paraphrase.

> There's a simpler one: if sending packets causes congestion such that loss (or ECN-CE marking) occurs, then ignoring that signal means that you will likely create more congestion.

Are you arguing that an endpoint SHOULD throttle the rate in which it sends ACK-only packets, when some of those ACK-only packets are being lost?

I would assume that your answer is no, and that is because send-rate of ACKs are not controlled by the endpoint. It is controlled by the peer that is sending data.

Up until now, CC is per-direction. An endpoint sends data at a rate controlled by ACKs sent by peer in response. The other side does the same thing, individually.

While I do not dispute the fact that *ideally* we should take the loss of ACK-only packets into consideration, my argument is that we are not at that point (yet), because we do not control the send-rate of ACK-only packets.

Using the loss of ACK-only packets without controlling the send-rate of ACK-only packets based on their loss essentially means that we are going to prioritize emission of ACKs above data. This would be a departure from the per-direction CC design that we have now.

As I stated in my previous comment, I am concerned about the negative impacts that the change in design might cause.

-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/quicwg/base-drafts/issues/3451#issuecomment-585037874