Re: [tcpm] [EXTERNAL] Re: Linux doesn’t implement RFC3465

[Yoshifumi Nishida <[e-mail]>]

I don't have a strong opinion on this yet, But, if we *could* move in this
direction, it might be good to think about the IW explanation in RFC5681 as
well?
if we do this, we might not need to discuss promoting RFC6928.
--
Yoshi

On Sat, Aug 7, 2021 at 7:57 AM Neal Cardwell <ncardwell=
[e-mail]> wrote:

> I also agree with Yuchung’s suggestion, for all of the reasons he provided.
>
> best,
> neal
>
>
> On Fri, Aug 6, 2021 at 3:59 PM Vidhi Goel <vidhi_goel=
> [e-mail]> wrote:
>
>> I agree with Yuchung’s suggestion for all the reasons he provided. And
>> its better to have it at one place.
>>
>> Vidhi
>>
>> On Aug 6, 2021, at 12:53 PM, Yuchung Cheng <
>> ycheng=[e-mail]> wrote:
>>
>> Hi WG
>>
>> I have been wondering if we (= IETF) should just update RFC5681 directly,
>> instead of another RFC3465-bis with experimental status.
>>
>> Appropriate byte counting is essential but the RFC5681 of L=1 is
>> detrimental. There are far more people who read RFC5681 to implement the
>> new stack instead of RFC3465. So we should fold the experimental RFC3465
>> updates into RFC5681 directly, and obsolete RFC3465.
>>
>> This is orthogonal to the final value of L :-)
>>
>>
>>
>>
>> On Tue, Aug 3, 2021 at 9:42 AM Yuchung Cheng <[e-mail]> wrote:
>>
>>>
>>>
>>> On Mon, Aug 2, 2021 at 6:12 PM Yuchung Cheng <[e-mail]> wrote:
>>>
>>>>
>>>>
>>>> On Mon, Aug 2, 2021 at 5:53 PM Neal Cardwell <ncardwell=
>>>> [e-mail]> wrote:
>>>>
>>>>>
>>>>>
>>>>> On Mon, Aug 2, 2021 at 8:46 PM Praveen Balasubramanian <pravb=
>>>>> [e-mail]> wrote:
>>>>>
>>>>>> In experiments a few years ago on DC networks, values over L=8
>>>>>> resulted in a noticeable increase in packet drops and retransmissions
>>>>>> (without pacing). Windows TCP has been using L=8 for many years now. If we
>>>>>> do want to specify a fallback L value for implementations that cannot pace,
>>>>>> my suggestion would be to use the value 8.
>>>>>>
>>>>>>
>>>>>>
>>>>>> Neal, are there cases where Linux is or can be deployed with infinite
>>>>>> L and no pacing?
>>>>>>
>>>>>
>>>>> Yes, "infinite L and no pacing" is the default behavior for Linux TCP,
>>>>> starting in 2013 for slow-start and then starting in 2015 for congestion
>>>>> avoidance.
>>>>>
>>>> To be more clear: both fq_pacing and TCP pacing have been disabled by
>>>> default in Linux upstream. We do not know how much Linux senders enable
>>>> them today besides the Google servers.
>>>>
>>>> Regarding L = 8, to avoid another round of why or why not. We could say
>>>> inf-L causes line-rate burst up to the stretched ACK degree so put a
>>>> comfortable L if you prefer, then mention implementation practice like
>>>> yours. At the end of the day it's ad-hoc (or "art") and subject to change.
>>>> It might be sensible to cap at cwnd to disincentivize receivers /
>>>> middle-boxes bunching up 10 rounds of ACKs.
>>>>
>>> Sorry please ignore my previous message about the cwnd cap. It is
>>> completely unnecessary -- since with ack-clocking and appropriate counting,
>>> a correct sender would never release more than a cwnd-worth of data. I was
>>> imagining the multiple application-limited burst could let the receiver
>>> keep holding up ACKs, but that can never exceed a cwnd worth of data.
>>>
>>>
>>>>
>>>>>
>>>>
>>>>> Yuchung pasted the URLs for the exact Linux commits above, which are:
>>>>>
>>>>>
>>>>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=9f9843a751d0a2057f9f3d313886e7e5e6ebaac9
>>>>>
>>>>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=9cd981dcf174d26805a032aefa791436da709bee
>>>>>
>>>>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=c22bdca94782f05b9337d8548bde51b2f38ef17f
>>>>>
>>>>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=814d488c61260521b1b3cc97063700a5a6667c8f
>>>>>
>>>>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e73ebb0881ea5534ce606c1d71b4ac44db5c6930
>>>>>
>>>>> But I understand that not everyone is in a position to read
>>>>> GPL-licensed code. :-)
>>>>>
>>>>> best regards,
>>>>> neal
>>>>>
>>>>>
>>>>>
>>>>>>
>>>>>>
>>>>>> *From:* tcpm <[e-mail]> *On Behalf Of * Neal Cardwell
>>>>>> *Sent:* Monday, August 2, 2021 4:18 PM
>>>>>> *To:* Vidhi Goel <[e-mail]>
>>>>>> *Cc:* Extensions <[e-mail]>; Mark Allman <[e-mail]>
>>>>>> *Subject:* [EXTERNAL] Re: [tcpm] Linux doesn’t implement RFC3465
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>> On Mon, Aug 2, 2021 at 7:02 PM Vidhi Goel <[e-mail]>
>>>>>> wrote:
>>>>>>
>>>>>>
>>>>>>
>>>>>> On Mon, Aug 2, 2021 at 3:37 PM Mark Allman <[e-mail]> wrote:
>>>>>>
>>>>>>
>>>>>> > The fact is that Linux CC has long moved to infinite L since 2031,
>>>>>>
>>>>>> So, if our experience is with L=\infinity and it is demonstrably OK
>>>>>> why don't we say *THAT* instead of "make L=5 or L=10"?  I would
>>>>>> submit that it makes more sense to leverage experience than it does
>>>>>>
>>>>>> to make things up.
>>>>>>
>>>>>> +1
>>>>>>
>>>>>>
>>>>>>
>>>>>> Yes, I agree that would be a great approach to take.
>>>>>>
>>>>>>
>>>>>>
>>>>>> So, we are saying it is fine to ignore L completely and simply
>>>>>> increase cwnd by bytes_acked during slow start? And if this causes large
>>>>>> bursts to be sent out (when an implementation doesn’t do pacing), that is
>>>>>> fine?
>>>>>>
>>>>>>
>>>>>>
>>>>>> Yes, I think that is the proposal on the table, and it sounds good to
>>>>>> me.
>>>>>>
>>>>>>
>>>>>>
>>>>>> A rationale would be:
>>>>>>
>>>>>>
>>>>>>
>>>>>> (1) Implementations SHOULD pace (RFC 7661).
>>>>>>
>>>>>>
>>>>>>
>>>>>> (2) Implementations that don't pace will generally be causing large
>>>>>> bursts for many different reasons anyway (data and/or ACK aggregation in
>>>>>> the network or end hosts), restart from idle,...) so having a constant L
>>>>>> does not provide enough protection from bursts to justify the cost in
>>>>>> reduced performance (in the form of slower slow-start). In support of this,
>>>>>> experience with this as the default behavior in Linux TCP over the
>>>>>> 2013-2021 period suggests this works well enough in practice.
>>>>>>
>>>>>>
>>>>>>
>>>>>> neal
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>> _______________________________________________
>>>>> tcpm mailing list
>>>>> [e-mail]
>>>>> https://www.ietf.org/mailman/listinfo/tcpm
>>>>>
>>>> _______________________________________________
>> tcpm mailing list
>> [e-mail]
>> https://www.ietf.org/mailman/listinfo/tcpm
>>
>>
>> _______________________________________________
> tcpm mailing list
> [e-mail]
> https://www.ietf.org/mailman/listinfo/tcpm
>