Return-Path: <vasilvv@google.com>
X-Original-To: moq@mail2.ietf.org
Delivered-To: moq@mail2.ietf.org
Received: from localhost (localhost [127.0.0.1])
	by mail2.ietf.org (Postfix) with ESMTP id 72B06DEA7D88
	for <moq@mail2.ietf.org>; Fri, 17 Apr 2026 18:44:07 -0700 (PDT)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=ietf.org; s=ietf1;
	t=1776476647; bh=EsYS/Cx+EJfjTBXGyd5DdiAk7ZD8bZwcgFCdT8Rn1oE=;
	h=References:In-Reply-To:From:Date:Subject:To:Cc;
	b=bbGEoL8A8k63QZW2I0y/zPeb7WnLbvKihGLh6vADdm2ze8hq4jsnBDP3wOz8ei383
	 N9NQOj5M9L2Xvon35SrW9mDDtCGlWkMC9bcRA6s2PPzIFFjTsZ7OY+sYcDOIknpETR
	 x1bKQ/6eMUF+I3AtZOabgsaEE9ASkIj0XWqC7nXg=
X-Virus-Scanned: amavisd-new at ietf.org
X-Spam-Flag: NO
X-Spam-Score: -17.489
X-Spam-Level: 
X-Spam-Status: No, score=-17.489 tagged_above=-999 required=5
	tests=[BAYES_00=-1.9, DKIMWL_WL_MED=-0.001, DKIM_SIGNED=0.1,
	DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,
	ENV_AND_HDR_SPF_MATCH=-0.5, HTML_FONT_LOW_CONTRAST=0.001,
	HTML_MESSAGE=0.001, HTTPS_HTTP_MISMATCH=0.1,
	RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001,
	T_KAM_HTML_FONT_INVALID=0.01, USER_IN_DEF_DKIM_WL=-7.5,
	USER_IN_DEF_SPF_WL=-7.5] autolearn=ham autolearn_force=no
Authentication-Results: mail2.ietf.org (amavisd-new); dkim=pass (2048-bit key)
	header.d=google.com
Received: from mail2.ietf.org ([166.84.6.31])
	by localhost (mail2.ietf.org [127.0.0.1]) (amavisd-new, port 10024)
	with ESMTP id hBUA-c271nkz for <moq@mail2.ietf.org>;
	Fri, 17 Apr 2026 18:44:06 -0700 (PDT)
Received: from mail-dl1-x1233.google.com (mail-dl1-x1233.google.com
 [IPv6:2607:f8b0:4864:20::1233])
	(using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits)
	 key-exchange X25519 server-signature ECDSA (P-256) server-digest SHA256)
	(No client certificate requested)
	by mail2.ietf.org (Postfix) with ESMTPS id 7C460DEA7D7B
	for <moq@ietf.org>; Fri, 17 Apr 2026 18:44:06 -0700 (PDT)
Received: by mail-dl1-x1233.google.com with SMTP id
 a92af1059eb24-126ea4e9697so2281c88.1
        for <moq@ietf.org>; Fri, 17 Apr 2026 18:44:06 -0700 (PDT)
ARC-Seal: i=1; a=rsa-sha256; t=1776476645; cv=none;
        d=google.com; s=arc-20240605;
        b=F6sQhUBSy7Qc+grZMQv3c3ltvkoAAZSiuDkuxOGBjusq54H7UrRCHj/5RdQg1BAOAg
         +b8tSWjnAO1N0k8XPoiZCwCCq0S41eq72GVVSy0mQtRFW6YdITiCFURGM7JFkdVD+V+u
         bLJ6FHmhZkPRwbsLEyG8/dULpFSO2SsjgGmTi3sGs+gi10kZ1PqslSnjuBucBglwkQUH
         5eKKFV3mBGJInWuxqtAdkBbEza5+T69S+rC1fiFYjD+9iWCu3Fux+TJwe79AspOmO6Rm
         hOHDdtT5lhEKtdDt/0fPBjguo71Qes3jHkqeQsmedfJ5bDXFSuC0lZRNicb3dBxUhyj2
         O1DA==
ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com;
 s=arc-20240605;
        h=cc:to:subject:message-id:date:from:in-reply-to:references
         :mime-version:dkim-signature;
        bh=lihORZ8Ikh/jMeYhcUPKwHYpyCiuPc2xutsMobfhXC0=;
        fh=WwjrIVzajg5jSKHrBbNftqQ2ex/YMzTfwqCw3SAQjzQ=;
        b=ht4zpkD1sG2Fr67rNsTkLgR/iw0puZtIu86JbUtlGm2A7Gmy1GrKZV7n5oKDPdTxok
         8gp+BxtMUbGW4Wof5QPbLjlUvI+7E84XB7zPTYdXwlRDYhyy00jM1RjTPrcbl8r2LLLF
         6rL3DsbJQAOFDOWV3EcSXKViBNfc3H4KWBvL5DBx60LEgt5Xgm50inNM9WZB0BhODL7Q
         nXG6wCMTIHAqPjFGBPtkjdEdnkjfTzQrPr++U+Tgw6VS16O7XG3SoeYFfgEkut68N677
         BGQ8kBndlGurrPHYC+LxwqvzvYKfrNy6zrWP72UftWBpLvow2pyQNz4i1HUQFZuDcqmt
         mpdA==;
        darn=ietf.org
ARC-Authentication-Results: i=1; mx.google.com; arc=none
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=google.com; s=20251104; t=1776476645; x=1777081445; darn=ietf.org;
        h=cc:to:subject:message-id:date:from:in-reply-to:references
         :mime-version:from:to:cc:subject:date:message-id:reply-to;
        bh=lihORZ8Ikh/jMeYhcUPKwHYpyCiuPc2xutsMobfhXC0=;
        b=dt1fas5KkYoyKCDCZgXce7JlyZEOrxSF0I3n20UeFpeOlcbYglnKZ2YdIW3/1XXxge
         uRAcv9zwywcP7bqNjxk7nhv3Hdve3rqucvifa+G7+qr0HjOpjhL61ecNZZ8hjfmXHoNl
         14er/CfAZ6UowmmOGHhSk1RXuTL6emk6vjArI+OmhmMOSouKBGpKEYkRk2F44bmQMjRH
         TXbx+tBsw6RTLZT6NcN2pKqmHwBBvjyIzWCIslGlND+6xGmGIblsxziAklYTG5eoG1T0
         FQ3h9XFCUURF6mmUzKrl/uXVtMtzbOzVmDmIYSyQ82JWB/fuDJ4Ijhp2Pa+7EhY23XjC
         SREQ==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20251104; t=1776476645; x=1777081445;
        h=cc:to:subject:message-id:date:from:in-reply-to:references
         :mime-version:x-gm-gg:x-gm-message-state:from:to:cc:subject:date
         :message-id:reply-to;
        bh=lihORZ8Ikh/jMeYhcUPKwHYpyCiuPc2xutsMobfhXC0=;
        b=cuAoMqKhdBu36w+gCQxZz4QOUV4gKGxTwBdZi9NeuCSLXKOf/MyRKyRDSyS+ooPnr3
         N1zqAi41NdPuguV3cG4H9NLrSUU9adVEk4gjNKrdKNKKSUa3+chmJnwqJRe2YzTU5rJQ
         fogrKE9LJ4TjnD1YnpriGnp4ai4rw9+/O/FsTRIF9JSkeLkM341nVGA/vvNUgpKIyxqn
         tMyvPbdfIlC3BVwd6w07IcDXQoZC6dPxEMG+2FZLb/txVU0Cko8TeS+VaQmGP3lOQStD
         bEHUmguzT+r7CkaWbqhzD67SeYquV/9z3ruFVS/FX/bJAOaaP106T4fNYQ3azQWJBlEq
         f4Jw==
X-Forwarded-Encrypted: i=1;
 AFNElJ8xeR91BrmAW76xWfozjYaT4UF0wVXuDm6SRHfQQZC527CW+qiQUOPndPtqEc8TuoEQT80=@ietf.org
X-Gm-Message-State: AOJu0YxzVaVwwen3J246VhUQOrVNffqNKEfrF+vPQ5JSdiyb4UCBCxmC
	pKKzr01EIKFc76+zO5jIVWj1IOOvReqxXGSb8f0AImZG+/kbS8NIbxXawPNyEHomNF0wPdmDoyB
	lXrZ2E3bluISUTOzACs19jscsy5sVlPomm+i/MWVJV3cxC4CLaCwFso/4oVE=
X-Gm-Gg: AeBDiesYHuwb7saVvZh7rHUikJUFa8mZ8v+aPjBJYe+k/U9DGPysZk9wFyscnMeon8r
	wgO38QJZp8jnsHQt9QhmmDtkhNgH26veIYE44llzei1Mjl0CeklQ2uho9YLnafNdvx/Zbfs1FV9
	inHFth6Wp3NXqb9deZRcNbCFF0QRYzmFavp8/jQZetXihrvsNlt7JH6gXo0cSVLfC/suK4b+1/p
	2OgVkp1g/lFj63dYIfe+QFx1QX01/m++UOksfrhEQubpK+46LmDYqEwiJY/HyfjPaxSUNgY7l2X
	G4VJGOQqDf2JsZHS7xDDPaRYGA==
X-Received: by 2002:a05:7022:6b9d:b0:12c:61fe:fb37 with SMTP id
 a92af1059eb24-12c7b258b49mr35019c88.17.1776476644695; Fri, 17 Apr 2026
 18:44:04 -0700 (PDT)
MIME-Version: 1.0
References: 
 <FRWPR07MB106241BC102275483F114857195232@FRWPR07MB10624.eurprd07.prod.outlook.com>
 <CANPAELtivGca3ApT94B01uzsgDk1zTQY7wd7HxpaxWxAKVB0Gg@mail.gmail.com>
 <CAHVo=ZnSk6_NMJVnAqY+JrMQGNK+yjAtb4gPUdr7T8EzAa9iEw@mail.gmail.com>
In-Reply-To: 
 <CAHVo=ZnSk6_NMJVnAqY+JrMQGNK+yjAtb4gPUdr7T8EzAa9iEw@mail.gmail.com>
From: Victor Vasiliev <vasilvv@google.com>
Date: Fri, 17 Apr 2026 21:43:52 -0400
X-Gm-Features: AQROBzAz6TPSvA7H3ATA83rJ8iAQw65uh5L5oZ9qqIqMAMdRe4Yxb4uBNSpejV4
Message-ID: 
 <CAAZdMacGBX-NndZaUFqMqrJNcbcx-_qM=AqVEUDd92Lov1gnjA@mail.gmail.com>
To: Luke Curley <kixelated@gmail.com>
Content-Type: multipart/alternative; boundary="0000000000005cd42a064fb2339a"
Message-ID-Hash: DTXRTYZACOLHI65MYXG6QPZY6DVZJOBS
X-Message-ID-Hash: DTXRTYZACOLHI65MYXG6QPZY6DVZJOBS
X-MailFrom: vasilvv@google.com
X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency;
 loop; banned-address; member-moderation; nonmember-moderation; administrivia;
 implicit-dest; max-recipients; max-size; news-moderation; no-subject;
 digests; suspicious-header
CC: Alan Frindell <afrind=40meta.com@dmarc.ietf.org>,
 Magnus Westerlund <magnus.westerlund=40ericsson.com@dmarc.ietf.org>,
 MOQ Mailing List <moq@ietf.org>
X-Mailman-Version: 3.3.9rc6
Precedence: list
Subject: =?utf-8?q?=5BMoq=5D_Re=3A_Consensus_call_on_way_forward_on_REWIND?=
List-Id: Media over QUIC <moq.ietf.org>
Archived-At: 
 <https://mailarchive.ietf.org/arch/msg/moq/q8Vxe5NGEX-KWgqnChyA3LnMUDE>
List-Archive: <https://mailarchive.ietf.org/arch/browse/moq>
List-Help: <mailto:moq-request@ietf.org?subject=help>
List-Owner: <mailto:moq-owner@ietf.org>
List-Post: <mailto:moq@ietf.org>
List-Subscribe: <mailto:moq-join@ietf.org>
List-Unsubscribe: <mailto:moq-leave@ietf.org>

--0000000000005cd42a064fb2339a
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

The first group within a subscription is always special (at least if you
aim for low latency).

That said, I don't hate the LargestGroup idea.  Wrote up a version of this
that I think will work: <https://github.com/moq-wg/moq-transport/pull/1607>=
.

On Fri, Apr 17, 2026 at 7:10=E2=80=AFPM Luke Curley <kixelated@gmail.com> w=
rote:

> IMO the root problem with SUBSCRIBE + JOINING FETCH is that subscribers
> want "live semantics". However, the first half, of the first group uses
> "vod semantics".
>
>
> *live semantics*- Each sub-group is delivered via independent streams.
> - Either side may reset a sub-group stream, for any reason, to skip any
> remaining objects.
> - Objects within a sub-group are delivered reliably and in order, until
> reset/fin.
>
> *vod semantics*
> - Objects are delivered over a single stream.
> - Objects are delivered in ID order, regardless of the sub-group.
> - Objects cannot be skipped (authoritative).
>
>
> Yes, it's possible to emulate "live semantics" using "vod semantics". The
> end subscriber *could* issue multiple, sequentially prioritized, JOINING
> FETCH requests for each specific groups/sub-group, merging each aligned
> JOINING FETCH and SUBSCRIBE stream. Just for the first group of course!
>
> It's a gross hack. A complicated set of instructions. Just to command
> the relay to serve the latest group *mostly* via "live semantics".
>
> We should add a LargestGroup filter for SUBSCRIBE instead. It is the
> intended behavior 99% of the time and deserves a flag, not an incantation=
.
> The first group within a subscription would no longer be special.
>
> While REWIND is undoubtedly an improvement over LargestGroup, we should
> make incremental progress. Does anyone object to a LargestGroup filter?
>
> On Fri, Apr 17, 2026 at 12:31=E2=80=AFPM Alan Frindell <afrind=3D
> 40meta.com@dmarc.ietf.org> wrote:
>
>> The working group should do nothing with this document at this time.
>>
>> I appreciate the effort Martin and others put in, however, now that
>> FILL_TIMEOUT=3D0 has landed in the Editors=E2=80=99 Copy, the unique cap=
abilities
>> provided by REWIND to avoid HOL blocking are reduced.
>>
>> Specifically we=E2=80=99ve eliminated cases where the subscriber=E2=80=
=99s joining FETCH
>> is blocked by cache misses =E2=80=93 set FILL_TIMEOUT=3D0 (JFFT0).  So t=
he following
>> cases are no longer problematic:
>>
>> 1) Cache Hole in low-pri subgroup blocks hi-pri cached object
>>
>> Object ID:    0   1   2   _   4
>>
>> Subgroup:   0   1   0   1   0
>>
>> 3 is low priority and in flight.  JFFT0 skips over it and delivers the
>> current cache state.  Object 3 can come later via SUBSCRIBE, assuming we
>> allow a range filter (for new objects) to start at the current group.
>>
>> 2) Datagram or stream-per-object track with a cache hole:
>>
>> 0   1   2   3   _    5
>>
>> Cached objects all get delivered with no HOLB.
>>
>> 3) Old group has been evicted:
>>
>> Groups in Cache:   _   98   99   100
>>
>> Current Group: 100
>>
>> JFFT0, Relative -3
>>
>> The FETCH response begins immediately at 98, with previous marked
>> =E2=80=9CUNKNOWN=E2=80=9D.
>>
>>
>> There=E2=80=99s one remaining case where REWIND provides a HOLB advantag=
e: when
>> lower priority data *IS* in the cache, but you don=E2=80=99t want to HOL=
 block
>> on it.
>>
>> This can be addressed by adding a subgroup and/or priority filter to
>> FETCH, which is a small subset of PR #1518.
>>
>> In the happy-cache case, REWIND also serves as a =E2=80=9Csingle wire me=
ssage=E2=80=9D,
>> and saves the subscriber from stitching together the current group from
>> multiple streams, but the working group identified HOLB as the problem t=
o
>> solve.  I got the feeling that the non-deterministic nature of REWIND le=
ft
>> others feeling unsatisfied.  But if you want determinism, you are
>> acknowledging that some head-of-line blocking on cache fill is a feature
>> and not a bug.
>>
>> The lively discussion in Boulder and at the recent interim indicates tha=
t
>> despite all our efforts, there=E2=80=99s some friction in MOQT around SU=
BSCRIBE,
>> FETCH and joining an ongoing Track.  The lack of clear consensus around =
a
>> different direction forward indicates we=E2=80=99re probably close to th=
e best we
>> can achieve in the V1 timeframe.  We should stabilize around the core we
>> have, and let innovation take place in extensions.  If there=E2=80=99s a=
 better
>> solution, it will emerge and it can be codified in a V2. Thanks
>>
>>
>> -Alan
>>
>>
>> On Thu, Apr 16, 2026 at 6:58=E2=80=AFAM Magnus Westerlund <magnus.wester=
lund=3D
>> 40ericsson.com@dmarc.ietf.org> wrote:
>>
>>> WG, We spent Monday's interim talking about https: //github.
>>> com/martinduke/draft-duke-moq-subscribe-rewind/tree/main. There was a l=
ot
>>> of interest to do something in this space but little agreement on the k=
ey
>>> properties of a solution. This document
>>> WG,
>>>
>>> We spent Monday's interim talking about
>>> https://github.com/martinduke/draft-duke-moq-subscribe-rewind/tree/main=
.
>>> There was a lot of interest to do something in this space but little
>>> agreement on the key properties of a solution.
>>>
>>> This document is meant to resolve several issues and PRs related to
>>> Joining Fetch :
>>> #861, #1039, #1358, #1362, #1386
>>> https://github.com/moq-wg/moq-transport/issues
>>>
>>>
>>> As well as the conclusion of the Joining Fetch discussion in Boulder,
>>> which is that people did not like head-of-line blocking in Joining Fetc=
h.
>>> https://datatracker.ietf.org/doc/minutes-interim-2026-moq-06-2026021020=
30/#comparing-proposals
>>> <https://urldefense.com/v3/__https://datatracker.ietf.org/doc/minutes-i=
nterim-2026-moq-06-202602102030/*comparing-proposals__;Iw!!Bt8RZUm9aw!9HjM-=
Wgy-GAgW3ZCAeC4PBs135QHiMVv8dSYg32FL2OX3d0-sOfFvlXnIZ5LJ09o55MjHmm57vCeD2CA=
e4llqDNtCw$>
>>>
>>>
>>> This is a consensus call for the disposition of this document. Please
>>> state your preference.
>>> 1) The working group does nothing with this document, at least until
>>> MOQT is published
>>> 2) The working group adopts this draft as the basis for an MOQT extensi=
on
>>> 3) The working group uses the draft as basis for a PR to be merged into
>>> MOQT when the Editors feel the PR is ready.
>>>
>>> Please provide your input no later than Friday the first of May
>>> (260501).
>>>
>>> Other proposals in this space are welcome, and subject to the same
>>> consensus requirements.
>>>
>>> Magnus Westerlund
>>> MoQ Chair
>>>
>>> --
>>> Moq mailing list -- moq@ietf.org
>>> To unsubscribe send an email to moq-leave@ietf.org
>>>
>> --
>> Moq mailing list -- moq@ietf.org
>> To unsubscribe send an email to moq-leave@ietf.org
>>
> --
> Moq mailing list -- moq@ietf.org
> To unsubscribe send an email to moq-leave@ietf.org
>

--0000000000005cd42a064fb2339a
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">The first group within a subscription is always special (a=
t least if you aim for low latency).<div><br></div><div>That said, I don&#3=
9;t hate the LargestGroup idea.=C2=A0 Wrote up a version of this that I thi=
nk will work: &lt;<a href=3D"https://github.com/moq-wg/moq-transport/pull/1=
607">https://github.com/moq-wg/moq-transport/pull/1607</a>&gt;.</div></div>=
<br><div class=3D"gmail_quote gmail_quote_container"><div dir=3D"ltr" class=
=3D"gmail_attr">On Fri, Apr 17, 2026 at 7:10=E2=80=AFPM Luke Curley &lt;<a =
href=3D"mailto:kixelated@gmail.com">kixelated@gmail.com</a>&gt; wrote:<br><=
/div><blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;bo=
rder-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir=3D"ltr"><di=
v>IMO the root problem with SUBSCRIBE + JOINING FETCH is that subscribers w=
ant &quot;live semantics&quot;. However, the first half, of the first group=
 uses &quot;vod semantics&quot;.<br></div><div><br></div><b>live semantics<=
br aria-hidden=3D"true"></b>- Each sub-group is delivered via independent s=
treams.<br aria-hidden=3D"true">- Either side may reset a sub-group stream,=
 for any reason, to skip any remaining objects.<br aria-hidden=3D"true">- O=
bjects within a sub-group are delivered reliably and in order, until reset/=
fin.<br><br><b>vod semantics</b><br aria-hidden=3D"true">- Objects are deli=
vered over a single stream. <br aria-hidden=3D"true">- Objects are delivere=
d in ID order, regardless of the sub-group.<br aria-hidden=3D"true">- Objec=
ts cannot be skipped (authoritative).<br><br><br>Yes, it&#39;s possible to =
emulate &quot;live semantics&quot; using &quot;vod semantics&quot;. The end=
 subscriber <i>could</i> issue multiple, sequentially prioritized, JOINING =
FETCH=C2=A0requests for each specific groups/sub-group, merging each aligne=
d JOINING FETCH and SUBSCRIBE stream. Just for the first group of course!<d=
iv><br></div><div>It&#39;s a gross hack. A complicated set of instructions.=
 Just to command the=C2=A0relay to serve the latest group <i>mostly</i> via=
 &quot;live semantics&quot;.=C2=A0</div><div><br></div><div>We should add a=
 LargestGroup filter for SUBSCRIBE instead. It is the intended behavior 99%=
 of the time and deserves a flag, not an incantation. The first group withi=
n a subscription would no longer be special.</div><div><br></div><div>While=
 REWIND is undoubtedly an improvement over LargestGroup, we should make inc=
remental progress. Does anyone object to a LargestGroup filter?</div></div>=
<br><div class=3D"gmail_quote"><div dir=3D"ltr" class=3D"gmail_attr">On Fri=
, Apr 17, 2026 at 12:31=E2=80=AFPM Alan Frindell &lt;afrind=3D<a href=3D"ma=
ilto:40meta.com@dmarc.ietf.org" target=3D"_blank">40meta.com@dmarc.ietf.org=
</a>&gt; wrote:<br></div><blockquote class=3D"gmail_quote" style=3D"margin:=
0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">=
<div dir=3D"ltr"><div class=3D"gmail_default" style=3D"font-size:large"><sp=
an id=3D"m_723413065543402761m_7298175877466483237gmail-docs-internal-guid-=
a1edce2d-7fff-a6d7-f58d-e3c2478c0abf"><p dir=3D"ltr" style=3D"line-height:1=
.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-fa=
mily:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-va=
riant:normal;vertical-align:baseline;white-space:pre-wrap">The working grou=
p should do nothing with this document at this time.</span></p><br><p dir=
=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span =
style=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);backg=
round-color:transparent;font-variant:normal;vertical-align:baseline;white-s=
pace:pre-wrap">I appreciate the effort Martin and others put in, however, n=
ow that FILL_TIMEOUT=3D0 has landed in the Editors=E2=80=99 Copy, the uniqu=
e capabilities provided by REWIND to avoid HOL blocking are reduced.</span>=
</p><br><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin-bott=
om:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans-serif;color:rg=
b(0,0,0);background-color:transparent;font-variant:normal;vertical-align:ba=
seline;white-space:pre-wrap">Specifically we=E2=80=99ve eliminated cases wh=
ere the subscriber=E2=80=99s joining FETCH is blocked by cache misses =E2=
=80=93 set FILL_TIMEOUT=3D0 (JFFT0).=C2=A0 So the following cases are no lo=
nger problematic:</span></p><br><p dir=3D"ltr" style=3D"line-height:1.38;ma=
rgin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-family:A=
rial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-weight:7=
00;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">1) Cac=
he Hole in low-pri subgroup blocks hi-pri cached object</span></p><br><p di=
r=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span=
 style=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);back=
ground-color:transparent;font-variant:normal;vertical-align:baseline;white-=
space:pre-wrap">Object ID:=C2=A0 =C2=A0 0 =C2=A0 1 =C2=A0 2 =C2=A0 _ =C2=A0=
 4</span></p><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin=
-bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans-serif;col=
or:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-ali=
gn:baseline;white-space:pre-wrap">Subgroup: =C2=A0 0 =C2=A0 1 =C2=A0 0 =C2=
=A0 1 =C2=A0 0</span></p><br><p dir=3D"ltr" style=3D"line-height:1.38;margi=
n-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-family:Aria=
l,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant:nor=
mal;vertical-align:baseline;white-space:pre-wrap">3 is low priority and in =
flight.=C2=A0 JFFT0 skips over it and delivers the current cache state.=C2=
=A0 Object 3 can come later via SUBSCRIBE, assuming we allow a range filter=
 (for new objects) to start at the current group.</span></p><br><p dir=3D"l=
tr" style=3D"line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style=
=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background=
-color:transparent;font-weight:700;font-variant:normal;vertical-align:basel=
ine;white-space:pre-wrap">2) Datagram or stream-per-object track with a cac=
he hole:</span></p><br><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:=
0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans=
-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;ve=
rtical-align:baseline;white-space:pre-wrap">0 =C2=A0 1 =C2=A0 2 =C2=A0 3 =
=C2=A0 _=C2=A0 =C2=A0 5</span></p><br><p dir=3D"ltr" style=3D"line-height:1=
.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-fa=
mily:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-va=
riant:normal;vertical-align:baseline;white-space:pre-wrap">Cached objects a=
ll get delivered with no HOLB.</span></p><br><p dir=3D"ltr" style=3D"line-h=
eight:1.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;=
font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;=
font-weight:700;font-variant:normal;vertical-align:baseline;white-space:pre=
-wrap">3) Old group has been evicted:</span></p><br><p dir=3D"ltr" style=3D=
"line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-siz=
e:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:trans=
parent;font-variant:normal;vertical-align:baseline;white-space:pre-wrap">Gr=
oups in Cache: =C2=A0 _ =C2=A0 98 =C2=A0 99 =C2=A0 100</span></p><p dir=3D"=
ltr" style=3D"line-height:1.38;margin-top:0pt;margin-bottom:0pt"><span styl=
e=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);backgroun=
d-color:transparent;font-variant:normal;vertical-align:baseline;white-space=
:pre-wrap">Current Group: 100</span></p><br><p dir=3D"ltr" style=3D"line-he=
ight:1.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;f=
ont-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;f=
ont-variant:normal;vertical-align:baseline;white-space:pre-wrap">JFFT0, Rel=
ative -3</span></p><br><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:=
0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans=
-serif;color:rgb(0,0,0);background-color:transparent;font-variant:normal;ve=
rtical-align:baseline;white-space:pre-wrap">The FETCH response begins immed=
iately at 98, with previous marked =E2=80=9CUNKNOWN=E2=80=9D.</span></p><br=
><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin-bottom:0pt"=
><span style=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0=
);background-color:transparent;font-variant:normal;vertical-align:baseline;=
white-space:pre-wrap"><br></span><span style=3D"font-size:11pt;font-family:=
Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font-variant=
:normal;vertical-align:baseline;white-space:pre-wrap">There=E2=80=99s one r=
emaining case where REWIND provides a HOLB advantage: when lower priority d=
ata <b>IS</b> in the cache, but you don=E2=80=99t want to HOL block on it.<=
/span></p><br><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margi=
n-bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans-serif;co=
lor:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-al=
ign:baseline;white-space:pre-wrap">This can be addressed by adding a subgro=
up and/or priority filter to FETCH, which is a small subset of PR #1518.</s=
pan></p><br><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin-=
bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans-serif;colo=
r:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical-alig=
n:baseline;white-space:pre-wrap">In the happy-cache case, REWIND also serve=
s as a =E2=80=9Csingle wire message=E2=80=9D, and saves the subscriber from=
 stitching together the current group from multiple streams, but the workin=
g group identified HOLB as the problem to solve.=C2=A0 I got the feeling th=
at the non-deterministic nature of REWIND left others feeling unsatisfied.=
=C2=A0 But if you want determinism,  you are acknowledging that </span><spa=
n style=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);bac=
kground-color:transparent;font-style:italic;font-variant:normal;vertical-al=
ign:baseline;white-space:pre-wrap">some</span><span style=3D"font-size:11pt=
;font-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent=
;font-variant:normal;vertical-align:baseline;white-space:pre-wrap"> head-of=
-line blocking on cache fill is a feature and not a bug.</span></p><br><p d=
ir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;margin-bottom:0pt"><spa=
n style=3D"font-size:11pt;font-family:Arial,sans-serif;color:rgb(0,0,0);bac=
kground-color:transparent;font-variant:normal;vertical-align:baseline;white=
-space:pre-wrap">The lively discussion in Boulder and at the recent interim=
 indicates that despite all our efforts, there=E2=80=99s some friction in M=
OQT around SUBSCRIBE, FETCH and joining an ongoing Track.=C2=A0 The lack of=
 clear consensus around a different direction forward indicates we=E2=80=99=
re probably close to the best we can achieve in the V1 timeframe.=C2=A0 We =
should stabilize around the core we have, and let innovation take place in =
extensions.=C2=A0 If there=E2=80=99s a better solution, it will emerge and =
it can be codified in a V2.

Thanks</span></p><p dir=3D"ltr" style=3D"line-height:1.38;margin-top:0pt;ma=
rgin-bottom:0pt"><span style=3D"font-size:11pt;font-family:Arial,sans-serif=
;color:rgb(0,0,0);background-color:transparent;font-variant:normal;vertical=
-align:baseline;white-space:pre-wrap"><br></span></p><p style=3D"line-heigh=
t:1.38;margin-top:0pt;margin-bottom:0pt"><span style=3D"font-size:11pt;font=
-family:Arial,sans-serif;color:rgb(0,0,0);background-color:transparent;font=
-variant:normal;vertical-align:baseline;white-space:pre-wrap">-Alan</span><=
/p></span><br></div></div><br><div class=3D"gmail_quote"><div dir=3D"ltr" c=
lass=3D"gmail_attr">On Thu, Apr 16, 2026 at 6:58=E2=80=AFAM Magnus Westerlu=
nd &lt;magnus.westerlund=3D<a href=3D"mailto:40ericsson.com@dmarc.ietf.org"=
 target=3D"_blank">40ericsson.com@dmarc.ietf.org</a>&gt; wrote:<br></div><b=
lockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-le=
ft:1px solid rgb(204,204,204);padding-left:1ex"><div>

<div style=3D"font-size:1px;color:rgb(255,255,255);line-height:1px;max-heig=
ht:0px;opacity:0;overflow:hidden;display:none">
WG, We spent Monday&#39;s interim talking about https:=E2=80=8A//github.=E2=
=80=8Acom/martinduke/draft-duke-moq-subscribe-rewind/tree/main. There was a=
 lot of interest to do something in this space but little agreement on the =
key properties of a solution. This document</div>



<div style=3D"font-size:1px;color:rgb(255,255,255);line-height:1px;max-heig=
ht:0px;opacity:0;overflow:hidden;display:none"></div>











<div>
<div style=3D"direction:ltr;font-family:Aptos,Arial,Helvetica,sans-serif;fo=
nt-size:12pt;color:rgb(0,0,0)">
WG,</div>
<div style=3D"direction:ltr;font-family:Aptos,Arial,Helvetica,sans-serif;fo=
nt-size:12pt;color:rgb(0,0,0)">
<br>
</div>
<div style=3D"direction:ltr;font-size:12pt"><span style=3D"font-family:Apto=
s;color:rgb(0,0,0);background-color:rgb(255,255,255);text-transform:none">W=
e spent Monday&#39;s interim talking about</span><span style=3D"font-family=
:Aptos,Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,134,240);text-transform=
:none"><a href=3D"https://github.com/martinduke/draft-duke-moq-subscribe-re=
wind/tree/main" title=3D"Original URL:
https://github.com/martinduke/draft-duke-moq-subscribe-rewind/tree/main

Click to follow link." style=3D"color:rgb(0,134,240);text-align:left" targe=
t=3D"_blank">https://github.com/martinduke/draft-duke-moq-subscribe-rewind/=
tree/main</a></span><span style=3D"font-family:Aptos;color:rgb(0,0,0);backg=
round-color:rgb(255,255,255);text-transform:none">.
 There was a lot of interest to do something in this space but little agree=
ment on the key properties of a solution.</span><span style=3D"font-family:=
Aptos,Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
<br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">This document is meant to resolve seve=
ral issues and PRs related to Joining Fetch :</span><span style=3D"font-fam=
ily:Aptos,Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">#861, #1039, #1358, #1362, #1386</span=
></div>
<div style=3D"direction:ltr;font-family:Aptos;font-size:12pt;color:rgb(0,0,=
0)">
<a href=3D"https://github.com/moq-wg/moq-transport/issues" target=3D"_blank=
">https://github.com/moq-wg/moq-transport/issues</a></div>
<div style=3D"direction:ltr;font-size:12pt"><span style=3D"font-family:Apto=
s;color:rgb(0,0,0)"><br>
</span><span style=3D"color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">As well as the conclusion of the Joini=
ng Fetch discussion in Boulder, which is that people did not like head-of-l=
ine blocking in Joining
 Fetch. </span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background=
-color:rgb(255,255,255)"><a href=3D"https://urldefense.com/v3/__https://dat=
atracker.ietf.org/doc/minutes-interim-2026-moq-06-202602102030/*comparing-p=
roposals__;Iw!!Bt8RZUm9aw!9HjM-Wgy-GAgW3ZCAeC4PBs135QHiMVv8dSYg32FL2OX3d0-s=
OfFvlXnIZ5LJ09o55MjHmm57vCeD2CAe4llqDNtCw$" target=3D"_blank">https://datat=
racker.ietf.org/doc/minutes-interim-2026-moq-06-202602102030/#comparing-pro=
posals</a></span></div>
<div style=3D"direction:ltr;font-size:12pt"><span style=3D"font-family:Apto=
s;color:rgb(0,0,0)"><br>
</span><span style=3D"color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">This is a consensus call for the dispo=
sition of this document. Please state your preference.</span><span style=3D=
"font-family:Aptos,Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">1) The working group does nothing with=
 this document, at least until MOQT is published</span><span style=3D"font-=
family:Aptos,Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">2) The working group adopts this draft=
 as the basis for an MOQT extension</span><span style=3D"font-family:Aptos,=
Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">3)
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255)">The working group uses the draft as basis for a PR to be</=
span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:rgb=
(255,255,255);text-transform:none">=C2=A0merged
 into MOQT when the Editors feel the PR is ready.</span><span style=3D"font=
-family:Aptos,Arial,Helvetica,sans-serif;color:rgb(0,0,0)"><br>
<br>
Please provide your input no later than Friday the first of May (260501).=
=C2=A0<br>
<br>
</span><span style=3D"font-family:Aptos;color:rgb(0,0,0);background-color:r=
gb(255,255,255);text-transform:none">Other proposals in this space are welc=
ome, and subject to the same consensus requirements.</span></div>
<div style=3D"direction:ltr;font-family:Aptos;font-size:12pt;color:rgb(0,0,=
0)">
<span style=3D"background-color:rgb(255,255,255);text-transform:none"><br>
</span></div>
<div style=3D"direction:ltr;font-family:Aptos;font-size:12pt;color:rgb(0,0,=
0)">
<span style=3D"background-color:rgb(255,255,255);text-transform:none">Magnu=
s Westerlund</span></div>
<div style=3D"direction:ltr;font-family:Aptos;font-size:12pt;color:rgb(0,0,=
0)">
<span style=3D"background-color:rgb(255,255,255);text-transform:none">MoQ C=
hair</span></div>
<div style=3D"direction:ltr;font-family:Aptos,Arial,Helvetica,sans-serif;fo=
nt-size:12pt;color:rgb(0,0,0)">
<br>
</div>
</div>

-- <br>
Moq mailing list -- <a href=3D"mailto:moq@ietf.org" target=3D"_blank">moq@i=
etf.org</a><br>
To unsubscribe send an email to <a href=3D"mailto:moq-leave@ietf.org" targe=
t=3D"_blank">moq-leave@ietf.org</a><br>
</div></blockquote></div>
-- <br>
Moq mailing list -- <a href=3D"mailto:moq@ietf.org" target=3D"_blank">moq@i=
etf.org</a><br>
To unsubscribe send an email to <a href=3D"mailto:moq-leave@ietf.org" targe=
t=3D"_blank">moq-leave@ietf.org</a><br>
</blockquote></div>
-- <br>
Moq mailing list -- <a href=3D"mailto:moq@ietf.org" target=3D"_blank">moq@i=
etf.org</a><br>
To unsubscribe send an email to <a href=3D"mailto:moq-leave@ietf.org" targe=
t=3D"_blank">moq-leave@ietf.org</a><br>
</blockquote></div>

--0000000000005cd42a064fb2339a--

