Re: Differences between iQUIC and gQUIC

Matt Joras <> Mon, 18 October 2021 21:55 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id 332813A0E2D for <>; Mon, 18 Oct 2021 14:55:20 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -2.097
X-Spam-Status: No, score=-2.097 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, FREEMAIL_FROM=0.001, RCVD_IN_DNSWL_BLOCKED=0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=ham autolearn_force=no
Authentication-Results: (amavisd-new); dkim=pass (2048-bit key)
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id W_0nKUQf2TA9 for <>; Mon, 18 Oct 2021 14:55:15 -0700 (PDT)
Received: from ( [IPv6:2a00:1450:4864:20::132]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by (Postfix) with ESMTPS id 61A5A3A0E23 for <>; Mon, 18 Oct 2021 14:55:15 -0700 (PDT)
Received: by with SMTP id x27so2777165lfa.9 for <>; Mon, 18 Oct 2021 14:55:15 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=20210112; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc:content-transfer-encoding; bh=rt9mt68SHtKcxIyulg9JdrK03nf1ISy2yF5UScLjODQ=; b=NMgWtT2o/gJPpxVETyid091ApWmuq4RSxx2mglydlO6wflgJM3j2bzWUdpwdZuPtd4 J3LG0Puh1sUHk70XZPOa1uTZvUxL9D1jLV28hXCEgeg9BjBmiD6/ETx4eVSamjHUeU4W mKHE2xxKpZ/hKSjRoxYs+sHRZqHhgTjxeGouYqeNaoiZKjHlu5YpeUvKyWa/ZMEUuTkS lZeOJUytEbBorhjDgOUMIOS4lVFs6E1f3/WG9jNCaMwUlC/iD32bdAcl6YHYJGSuu3L3 gLCQhXvuHAdIlqKaSanGdvPlR9ApmsnDeCFLfOB08RG/WkqCh/jEcvJaPhEUxDP5ZPIB sdxQ==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=20210112; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc:content-transfer-encoding; bh=rt9mt68SHtKcxIyulg9JdrK03nf1ISy2yF5UScLjODQ=; b=hR4k1MCUOzJRfV9LyQrGZbQRbo1fyXo0v2eMp8e7eFnoh6Cv/Er6PQ0nFvtDh+tPgH wScAgrm7bYYqWxr0bXMyGBX+oIHcy0B8TdN99kBdClp7m1I9SUhHGgwmECmG1KJKVHmm RXaWqNdcHweC3F+vpi4kN1mU8ZZI2/evmAW94MG9fhxbaKw7X2u+c5Y83oOJrscBXJ2R 4oqbeluddcmC8CHRj1l15KgswuAp6VMz+eXEo8m9uXbWtgbke7Qm0aBXV9mhwWLJ0uvk YO/O2hgSCbnkDK58nXRcEIu7T+d5dNcjXYtGhKd5qjuWxlAT0xJ2FxVBaeLe2SrPMkxr WNiQ==
X-Gm-Message-State: AOAM530JIS0pIIIRY1Fo5XB8NUW29RlBlSDFM4Q94hF1S4IznAurLAgX ArpHNAe7OklV1tvr/2R2oeeCzi10uGp+RRGDhl9WJhzMURk=
X-Google-Smtp-Source: ABdhPJwe9cSHZ1vv5dgKsWVXz98CI7n5N3cgl7pVPOW/oqtOG6wQjA+w9X/0gUhYjCEZ3ocVYSxpBlhDhcA1IyIXf9Y=
X-Received: by 2002:a05:6512:3e27:: with SMTP id i39mr2285965lfv.10.1634594113256; Mon, 18 Oct 2021 14:55:13 -0700 (PDT)
MIME-Version: 1.0
References: <>
In-Reply-To: <>
From: Matt Joras <>
Date: Mon, 18 Oct 2021 14:55:02 -0700
Message-ID: <>
Subject: Re: Differences between iQUIC and gQUIC
To: "Feltgen, Eric" <>
Cc: "" <>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Archived-At: <>
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Main mailing list of the IETF QUIC working group <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Mon, 18 Oct 2021 21:55:21 -0000

Hi Eric,

In general I would advise not assuming the findings for studies
focused on Google QUIC will apply to IETF QUIC. While many findings
may apply, they are different protocols with different designs, and
any research done on Google QUIC most likely focused on a single
implementation (the Chromium implementation). Even within a single
standard (IETF QUIC), we expect there are going to be different
experimental results depending on implementations studied [1]. As such
I would say right now it's best to rely on research conducted on IETF
QUIC, rather than trying to transform results previously obtained for
Google QUIC.

All the best,
Matt Joras


On Mon, Oct 18, 2021 at 2:43 PM Feltgen, Eric
<> wrote:
> Dear QUIC working group,
> I am a CS student at RWTH Aachen University currently researching papers on the performance of QUIC in the context of a seminar. In the past years, there have been many papers on this topic testing many different versions of Google's QUIC. Over the years, many changes have been made to the protocol and the implementation at Google.
> In order to understand which results are comparable to the standardized version of QUIC (RFC 9000), it would be helpful to which changes have been made in the last years of the Google version and how the last QUIC versions by Google compare to the QUIC standard. In my research so far, I found out that forward error correction has been removed from the Google version a couple of years ago. So my question is whether there are any breaking changes that have been made in the development of the IETF standard which could result in different behaviour.
> Thank you in advance for any response! It would help a lot to understand the development stop of the QUIC standard within the last years.
> Best regards,
> Eric Feltgen