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

[Yuchung Cheng <[e-mail]>]

+1 to Yoshifumi's proposal as well.



On Mon, Aug 9, 2021 at 1:33 PM Vidhi Goel <vidhi_goel=
[e-mail]> wrote:

> I also like Yoshi’s suggestion to fold the initial window into RFC5681-bis.
>
> That sounds reasonable to me as well. Although the initial window is a
>> somewhat independent issue that might evolve independently from the
>> congestion algorithm itself, so I can imagine advantages to keeping it
>> separate.
>>
>
> I think Initial Window is not independent from congestion control module,
> because lets say in future with higher BDPs we decide to set IW=1000, then
> the congestion control algorithm should be able to immediately detect
> congestion, if any, even at the start of the connection and for such a high
> initial value, probably requires other ways to detect congestion besides
> packet loss.
> Yes, it is separate from how the algorithm works itself, but still
> deciding the initial value depends a lot on the congestion control
> algorithm.
>
> Thanks,
> Vidhi
>
> On Aug 9, 2021, at 10:07 AM, Yoshifumi Nishida <[e-mail]> wrote:
>
> Yes, that was my intention. Sorry for being unclear.
> I thought updating RFC5681 could be impactful. So, if it would happen, I
> would like to make sure we won't have another update for a long time.
> --
> Yoshi
>
> On Mon, Aug 9, 2021 at 9:53 AM Neal Cardwell <[e-mail]> wrote:
>
>> I think Yoshifumi is suggesting that if the WG re-spins  RFC5681 then in
>> addition to folding in discussion of ABC/RFC3465 the RFC5681bis could also
>> include the IW10 content in RFC6928. That could help save time in avoiding
>> promoting RFC6928 from experimental to proposed standard.
>>
>> That sounds reasonable to me as well. Although the initial window is a
>> somewhat independent issue that might evolve independently from the
>> congestion algorithm itself, so I can imagine advantages to keeping it
>> separate.
>>
>> neal
>>
>>
>> On Mon, Aug 9, 2021 at 12:39 PM Yuchung Cheng <ycheng=
>> [e-mail]> wrote:
>>
>>> Sorry I don't understand your suggestion. Is that related to ABC? could
>>> you explain more
>>>
>>> On Mon, Aug 9, 2021 at 1:41 AM Yoshifumi Nishida <[e-mail]>
>>> wrote:
>>>
>>>> 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
>>>>>
>>>> _______________________________________________
>>>> tcpm mailing list
>>>> [e-mail]
>>>> https://www.ietf.org/mailman/listinfo/tcpm
>>>>
>>>
>