Re: [tcpm] Comments for draft-ietf-tcpm-rfc8312bis-02

[Lars Eggert <[e-mail]>]

Hi,

many thanks for the review!

On 2021-6-1, at 11:35, Yoshifumi Nishida <[e-mail]> wrote:
> 1: While this draft focuses on only TCP,  CUBIC can actually be applied to other transport protocols
>     such as QUIC, SCTP. Do we want to mention it in the draft or is it out of scope?

I've opened https://github.com/NTAP/rfc8312bis/issues/61 for this.

Note that we did discuss CUBIC for QUIC in https://github.com/NTAP/rfc8312bis/issues/45.

> 2: Section 3.1 "After a window reduction in response to a congestion event is
>      detected by duplicate ACKs or Explicit Congestion Notification-Echo
>      (ECN-Echo, ECE) ACKs [
> RFC3168], CUBIC remembers the congestion window..."
> 
>    I think the events detected by RACK (or PTO for QUIC) can also be included here.

I opened https://github.com/NTAP/rfc8312bis/issues/62

> 3: Section 4.1.1
>     It seems that the text version of the draft uses b_cubic and a_aimd, while the pdf version of the
>     draft uses different names. But, I prefer to use the same names in both versions to avoid confusion.

The PDF is actually corrupt, due to a Unicode bug in the datatracker PDF generation. See https://github.com/NTAP/rfc8312bis/issues/46.

> 4: Section 4.2  I personally prefer to refer the equations in the draft as 'Equation' rather than 'Figure'  if there's
>     no strong reason for it.

With kramdown-xml2rfc2629, it's unfortunately not possible to change this. We would need to add an RFC Editor Note instructing them to manually make the change. Opened https://github.com/NTAP/rfc8312bis/issues/63

> 5: Section 4.3  It seems to me that there are two meanings for a_aimd in this section.
>     One is the additive factor for CUBIC and the other is a generic parameter for AIMD() function.
>     This looks a bit confusing to me.

Opened https://github.com/NTAP/rfc8312bis/issues/64

> 6: Section 4.3  The description for P is required for Figure 3.

Opened https://github.com/NTAP/rfc8312bis/issues/65

> 7: Section 4.3  I think The analysis in [FHP00] doesn't include delayed ACK factor. So, the AIMD TCP model here
>    can be a bit aggressive compared to a TCP that doesn't enable ABC and uses delayed ACK.
>   This is fine, but I think it might be good to clarify it.

Opened https://github.com/NTAP/rfc8312bis/issues/66

> 8: Section 4.3  I am not very sure why segments_acked is used rather than byted_acked here. What is the benefit of it?
>     How do we calculate when the acks are split?
>    Also, I think it should be clarified that cwnd is expressed in segments here in this case.

Opened https://github.com/NTAP/rfc8312bis/issues/67

> 9: Section 4.3  "Note that once _W_est_ reaches _W_max_, that is, _W_est_ >= _W_max_, ..."
>    I might miss something, but I'm not sure why  a_aimd can be set to 1 to be compatible with AIMD TCP.
>    Does this mean b_cubic is also updated? If not, why this can be compatible?

Opened https://github.com/NTAP/rfc8312bis/issues/68

> 10: Section 4.5: " The convex profile ensure that the window increases very slowly at the beginning.."
>    I am wondering how much this part is accurate. Because of Principal 2,  even though cwnd is increased
>    through convex profile, I think it will be overridden by linear growth by AIMD.

Opened https://github.com/NTAP/rfc8312bis/issues/69

> 11: Section 4.7: "we update w_max as follows, before the window reduction as described in section 4.6"
>    I am wondering if reducing w_max is the right approach here. Because if we reduce w_max, CUBIC
>    can exit from convex region earlier than the case where fast convergence is not used.
>    It seems to me that keeping w_max and reducing only cwnd (using smaller value than b_cubic)
>    look more conservative.

Opened https://github.com/NTAP/rfc8312bis/issues/70

> 12: Section 5.2 and Section 5.3. Do these results are based on the algorithms and the parameter values
>    described in the draft?  If there're differences, I think it should be described.

Opened https://github.com/NTAP/rfc8312bis/issues/71

Thanks,
Lars