QUIC

Sounds interesting

>As a result, I expect QUIC to largely displace TCP, even as QUIC provides any/all technology suggestions for incorporation into TCP. TCP is routinely implemented in the kernel, which makes evolutionary steps take 5-15 years (including market penetration!… not to mention battles with middle-boxes), while QUIC can evolve in the course of weeks or months.

t. Google

File: images.jpg (4KB, 150x102px) Image search: [Google]

4KB, 150x102px

>replacing TCP with UDP

>>61870777
Literally just means the packets will have to go super far up the stack just to be rejected if there was an error, whereas if there was an error in tcp, the kernel can catch it and send the appropriate response in nanoseconds.

Also, why would QUIC be faster than TCP other than the TCP slow start mechanism, which is actually beneficial?

File: 0rtt-graphic.png (109KB, 997x536px) Image search: [Google]

109KB, 997x536px

>>61873499
>why would QUIC be faster than TCP

>>61870680
I'd tell you a joke about UDP but you probably wouldn't get it.

>>61873499
>slow-start
>beneficial
For whom? In practice, most HTTP requests and responses, not counting large downloads, are small enough to fit in the buffers across the network without any need for flow control.