On Mon, Feb 8, 2016 at 6:53 PM, Fernando Gont <fgont@xxxxxxxxxxxxxxx> wrote: > On 02/08/2016 05:44 PM, Phillip Hallam-Baker wrote: > [...] >> The ability to consistently support 64KB packets and thus high >> throughput is potentially one of the main selling points for IPv6. I >> don't believe in trying to persuade people to move to IPv6 through >> differences in function. It will be a decade minimum before I consider >> making use of an IPv6 feature not supported in IPv4 in an application >> protocol. Performance is something else, I will encourage people to >> upgrade to get faster performance. > > You mean >64KB? -- 'cause IPv4 can do 64KB packets... By 'doing' I mean, it actually works in practice with stuff bought off the shelf without any special configuration or expertise or additional software beyond that provided by the platform vendors. I am aware that IPv4 was always theoretically capable of jumbo frames. But practice has been rather different. And one of the biggest problems we still have is that while we talk about IP everywhere, the reality is 'IP atop IEEE link layer' and the IEEE people still insist on supporting non IP protocols. Problem is that most of us have ethernet hubs rather than true IP switches. If we had real IP everywhere we could deprecate MAC addresses.