Re: [quicwg/base-drafts] QUIC PTO is too conservative, causing a measurable regression in tail latency (#3526)

mjoras <notifications@github.com> Wed, 27 May 2020 17:33 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 B339D3A0F61 for <quic-issues@ietfa.amsl.com>; Wed, 27 May 2020 10:33:44 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.483
X-Spam-Level:
X-Spam-Status: No, score=-1.483 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, DKIM_VALID_EF=-0.1, HTML_IMAGE_ONLY_24=1.618, HTML_MESSAGE=0.001, MAILING_LIST_MULTI=-1, RCVD_IN_MSPIKE_H2=-0.001, 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 YjCl57ioJvDX for <quic-issues@ietfa.amsl.com>; Wed, 27 May 2020 10:33:43 -0700 (PDT)
Received: from out-28.smtp.github.com (out-28.smtp.github.com [192.30.252.211]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 13CB03A102B for <quic-issues@ietf.org>; Wed, 27 May 2020 10:33:42 -0700 (PDT)
Received: from github-lowworker-1dbcc59.ash1-iad.github.net (github-lowworker-1dbcc59.ash1-iad.github.net [10.56.105.54]) by smtp.github.com (Postfix) with ESMTP id 3E8698C10F5 for <quic-issues@ietf.org>; Wed, 27 May 2020 10:33:40 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=github.com; s=pf2014; t=1590600820; bh=7RzuS1JPGqeN283cjc3GIgrnekYlX769ebH+xGhyFeU=; h=Date:From:Reply-To:To:Cc:In-Reply-To:References:Subject:List-ID: List-Archive:List-Post:List-Unsubscribe:From; b=qDsZlZpqz9m7Mg98C0m2rnESEQlAoa0LSPmKaX5TvGBBMJo1+v6JHa3ubnMln3Pzn E0CS4ro5H6MkJ83FRLSynlg9luIkfyxtFhfxlec+djYCMxIVqFJSX/GbIZK2ECUYx2 HXmbPw1s+oRiwRJDBycKOxThWKSdsl2l6MZueMzM=
Date: Wed, 27 May 2020 10:33:40 -0700
From: mjoras <notifications@github.com>
Reply-To: quicwg/base-drafts <reply+AFTOJK24442PQLJDU5UVUZV43KCXJEVBNHHCFNKKLA@reply.github.com>
To: quicwg/base-drafts <base-drafts@noreply.github.com>
Cc: Subscribed <subscribed@noreply.github.com>
Message-ID: <quicwg/base-drafts/issues/3526/634822736@github.com>
In-Reply-To: <quicwg/base-drafts/issues/3526@github.com>
References: <quicwg/base-drafts/issues/3526@github.com>
Subject: Re: [quicwg/base-drafts] QUIC PTO is too conservative, causing a measurable regression in tail latency (#3526)
Mime-Version: 1.0
Content-Type: multipart/alternative; boundary="--==_mimepart_5ecea4742f3c3_49533fd6414cd964194667"; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: list
X-GitHub-Sender: mjoras
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/MKTUQrPHXmlG5gOfVCJAzrVGNbM>
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, 27 May 2020 17:33:52 -0000

Following up, I ran a test for 4 days on a major country. The results are mostly in line with what @ianswett saw. 

1. Tail response latency (p95) saw a measurable but small decrease of about 1 percent.
2. Various application-level outlier metrics (e.g. time to load images, time to load a feed, etc.) showed slight improvements that also correspond with the change.
3. There were no regressions in any other metrics.

Based on this I think the strategy of arming the first PTO based on max(left_edge + SRTT+4RTTVar, right_edge + 1.5SRTT) is indeed an improvement, but it is not huge.

Based on this I would agree with punting work on this to v2, since we plausibly will have time to come up with different strategies here that may be a larger improvement.

-- 
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/3526#issuecomment-634822736