Re: [tsvwg] I-D Action: draft-ietf-tsvwg-udp-options-13.txt

[Paul Vixie <[e-mail]>]

On Sun, Jun 20, 2021 at 09:54:54AM -0700, Joseph Touch wrote:
> ...
> 
> Note that TCP bursts up to 10 packets right now anyway,
> so I don???t see why UDP fragments couldn???t do the same.

if tcp sends more than three before it has any estimate of the congestion
window, then i withdraw my suggestion of "3". however, i ask that some
guidance be offered about not transmitting fragments back to back, if the
number is larger than "2". and i do hope the number will be larger than "2",
due to page/MTU sizes.

vixie

re:

> > On Jun 19, 2021, at 9:33 PM, Paul Vixie <[e-mail]> wrote:
> > 
> > On Sat, Jun 19, 2021 at 12:38:51AM -0700, Joseph Touch wrote:
> >> ...
> >> How many frags MUST be supported 2? 4?
> > 
> > if they'll be transmitted back to back, microburst style, like IP fragments are,
> > then 2. if there's implementation guidance to send the frags isochronously on
> > a schedule of some kind, to give other transmissions an opportunity to enter,
> > then 3. on today-typical MTU 1500 networks, "3" allows a today-typical 4K page
> > to be sent as a fragmented UDP datagram. in future networks we should expect
> > this ratio from then-typical MTU to then-typical page size to be more or less
> > similar.
> > 
> > -- 
> > Paul Vixie
> 

-- 
Paul Vixie