The deck is pretty much self explanatory and only 11 slides. Networks are
Analog but MTU is not
<https://datatracker.ietf.org/meeting/121/materials/slides-121-intarea-analog-blockers-to-wide-employment-of-jumbo-mtus-in-the-production-internet-00>
Key points:
- At L1, Ethernet is really analog
- IEEE specifies waveforms, thresholds, tolerances and testing
methodology
- L1 MTU limit is derived from non-digital parameters, such as clock
stability
- The L2 MTU specification is "owned" by the IEEE
- Overriding the default MTU almost certainly violates parametric
assumptions in the design
- There is not a conformance specification for jumbo, and
interoperability is not guaranteed
- Ad Hoc jumbo testing is not robust because it is subject to "false
pass" test results
- e.g. clocks that are good enough at some temperatures may not
be at other temperatures
- Alarming discovery when PLPMTUD [RFC 4121] was almost done
- we encountered a device (bgic) that ran error free at 1500B, but
showed 1% loss at 4kB
- Workaround text in the top of Section 4 of RFC 4121
All links MUST enforce their MTU: links that might non-deterministically
deliver packets that are larger than their rated MTU MUST consistently
discard such packets.
- This makes sense to computer scientists and protocol engineers, but
it is actually out of scope for the IETF
- Goal is organizing yet another attempt to coax the IEEE to address this
issue.
Thanks,
--MM--
Evil is defined by mortals who think they know "The Truth" and use force to
apply it to others.
-------------------------------------------
Matt Mathis (Email is best)
Home & mobile: 412-654-7529 please leave a message if you must call.
_______________________________________________
Int-area mailing list -- int-area@ietf.org
To unsubscribe send an email to int-area-le...@ietf.org
