MTU of the Internet?

Robert E. Seastrom rs at bifrost.seastrom.com
Wed Feb 4 18:17:05 UTC 1998


   From: Peter Ford <peterf at microsoft.com>

   The reason for this change cited by many customers is that many ISPs have
   576 MTUs set "inside" their networks and packets get fragmented.

   How prevelant is this fragmentation and how prevelant is this MTU in ISPs?

Unless your ISP uses BBN Butterflies and C30 IMPs in its backbone, I
would discount the odds of running into a link with an MTU of 576.


   Are there statistics that can be shared on how much traffic they see on
   their networks that are IP fragments?

   Why do ISPs set their MTUs to 576 instead of ~1500 or even ~4K?

Setting your MSS to higher than the MTU on any network over which the
packet will be routed will guarantee fragmentation.  That's why people
generally don't set it higher than 1500, which is the MTU on ethernet,
Cisco serial lines, and a lot of other media (most of which can be
attributed to inheritence from Ethernet).  FDDI and HSSI interfaces
are generally set to 4470 unless someone throttles it back.

I have no idea where they came up with this "576 internally" nonsense.
Generally whenever one runs into that number it is as a result of
creaky old software that expects to be running over milnet or arpanet.

Are Microsoft stacks known to be broken in the packet
fragmentation/reassembly department?  Or are just acknowledging
deficiencies in their path mtu discovery code by setting the MSS in
the basement?  I knew they had problems with window length (this from
my friends with long fat pipes)...

                                        ---Rob








More information about the NANOG mailing list