[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [RRG] A data point on transit MTU size
>From: Dino Farinacci [mailto:email@example.com]
>Sent: Tuesday, September 23, 2008 2:53 PM
>To: Brian E Carpenter
>Cc: Templin, Fred L; RRG
>Subject: Re: [RRG] A data point on transit MTU size
>> Yes, we agree that sub-optimal implementations are a bad idea.
>> We also agree, I trust, that writing perfect reassembly code
>> hard (although I speak from 20 year old experience).
>> In particular the RFC 4459 and 4963 issues have to be handled.
>> I don't have an opinion whether SEAL is necessary for that,
>> LISP can just rely on basic frag.
>The code for reassembly isn't hard, it's allocating the
>buffers to store the arrived fragments. That's nearly
>impossible in hardware.
Then, consider any link with linkMTU < ~2KB as "marginal"
and in need of replacement. As long as the ITR can detect
that there is a marginal link in the path, it can still
push packets through using SEAL reassembly at the ETR
while a trouble ticket is called in on the link.
Once all of the < ~2KB links are eradicated, there will
be no more reassembly required at ETRs. Then, the same
approach can be reiterated for more robust definitions
of "marginal", and eventually everything smaller than ~9KB
will be weeded out and we will converge on a jumbo-clean
Sound like a plan?
to unsubscribe send a message to firstname.lastname@example.org 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