RE: [RRG] Perplexing PMTUD and packet length observations Oops: TSO

["Templin, Fred L" <Fred.L.Templin@boeing.com>]

Robin,

Excerpting from what you wrote: 

>Yes, but fragmentation in the network was not included in IPv6 and I
>am keen not to have it in ITRs, ETRs or in the path between them.

Fragmentation in the network in IPv4 is useful as long as it
can be detected and tuned out as earlier as possible. Adding
clarification to what I wrote in a previous message, removing
in-the-network fragmentation from IPv6 was not necessarily a
wrong decision but IMHO defined its domain of application as
being most appropriate for edge networks and end system
addressing.

>> I'll take reliable over fast.
>
>I think RFC 1191 is reliable if PTBs are not filtered.  It is not a
>serious problem if the odd PTB is lost due to congestion.

Loss due to congestion is one dimension; loss due to router
rate limiting of ICMPs is another. Both are exacerbated by
multiplexing thousands of streams over a path that has
recently been rerouted over a restricting link.

Also to be considered is that ICMP PTBs coming from the
Internet are essentially produced by anonymous routers;
they can therefore be sourced by *any* rogue node on the
Internet.

>> Actually, it would be interesting to do some research into the MTU
>> distribution across the internet.
>
>Indeed.

But, that is exactly where the RFC1191 "plateau table" came
from, and AFAICT that has not done us a lot of good. At best,
it can only represent a snapshot in time and cannot address
what is really needed: support for true MTU diversity in the
Internet that works both now and into the future.

Fred
fred.l.templin@boeing.com

--
to unsubscribe send a message to rrg-request@psg.com with the
word 'unsubscribe' in a single line as the message text body.
archive: <http://psg.com/lists/rrg/> & ftp://psg.com/pub/lists/rrg