I interpret this blogpost, which is excellent btw, not as ‘IPv6 is a badly designed protocol’ but rather as ‘we haven’t done a good job at evolving our network design as a hole’.
The author explains that the only real issue with IPv6 itself, is that roaming between wireless routers wasn’t addressed (he calls it ‘mobile IP’) and that it could be properly fixed by using another identifier for sessions (uuid,port instead of sourceIP,sourcePORT,destIP,destPORT). Which would be doable with QUIC over UDP.
I think it was badly designed in that it assumed we’d ditch IPv4 for IPv6. That was an absurdly unrealistic expectation.
Forget all of the rest of the issues. From day one they should have come up with a robust, performant system for bridging between IPv4 and IPv6 addresses. Make it so that EVERY IPv4 address is a valid IPv6 address, and provide a simple, robust way to tunnel traffic aimed at an IPv6 address through an IPv4 network.
That totally would have been possible. Then everyone could have switched to IPv6 with no downside, and switching out middle layers of the system would have been great, welcome optimizations.
As opposed to the reality today, where IPv4 is basically never going to go away, because the long tail of cheap devices and older networks have no incentive to switch.
I interpret this blogpost, which is excellent btw, not as ‘IPv6 is a badly designed protocol’ but rather as ‘we haven’t done a good job at evolving our network design as a hole’.
The author explains that the only real issue with IPv6 itself, is that roaming between wireless routers wasn’t addressed (he calls it ‘mobile IP’) and that it could be properly fixed by using another identifier for sessions (uuid,port instead of sourceIP,sourcePORT,destIP,destPORT). Which would be doable with QUIC over UDP.
I think it was badly designed in that it assumed we’d ditch IPv4 for IPv6. That was an absurdly unrealistic expectation.
Forget all of the rest of the issues. From day one they should have come up with a robust, performant system for bridging between IPv4 and IPv6 addresses. Make it so that EVERY IPv4 address is a valid IPv6 address, and provide a simple, robust way to tunnel traffic aimed at an IPv6 address through an IPv4 network.
That totally would have been possible. Then everyone could have switched to IPv6 with no downside, and switching out middle layers of the system would have been great, welcome optimizations.
As opposed to the reality today, where IPv4 is basically never going to go away, because the long tail of cheap devices and older networks have no incentive to switch.