A new data_delivery mechanism called 'relay' has been added.
It bypasses stream handlers (and the buffering in cowboy_stream_h)
and sends the data directly to the process implementing
Websocket (and should work for other similar protocols
like HTTP/2 WebTransport).

Flow control in HTTP/2 is maintained in a simpler way,
via a configured flow value that is used to maintain
the window to a reasonable value when data is received.

The 'relay' data_delivery has been implemented for both
HTTP/2 and HTTP/3. It has not been implemented for HTTP/1.1
since switching protocol there overrides the connection process.

HTTP/2 Websocket is now better tested.

A bug was fixed with the 'stream_handlers' data_delivery
where active mode would not be reenabled if it was disabled
at some point.

The Websocket performance suite has been updated to
include tests that do not use Gun. Websocket modules
used by the performance suite use the 'relay' data_delivery
now. Performance is improved significantly with 'relay',
between 10% and 20% faster. HTTP/2 Websocket performance
is not on par with HTTP/1.1 still, but the remaining
difference is thought to be from the HTTP/2 overhead and
flow control.

This is meant to be used with clients such as Gun to simplify
proxying and similar operations. The set-cookie header must
not be set this way so there is still some extra processing
to be done to fully translate a Gun response into a Cowboy
response.

Over cleartext TCP the `protocols` option lists the enabled
protocols. The default is to allow both HTTP/1.1 and HTTP/2.

Over TLS the default protocol to use when ALPN is not used
can now be configured via the `alpn_default_protocol` option.

Performing an HTTP/1.1 upgrade to HTTP/2 over TLS is now
rejected with an error as connecting to HTTP/2 over TLS
requires the use of ALPN (or that HTTP/2 be the default
when connecting over TLS).

When idle_timeout is configured we do not need a separate
timer to detect inactivity. Disabling idle_timeout is not
recommended and should not be necessary.

When enabled the connection process will automatically hibernate.
Because hibernation triggers GC, this can be used as a way to
keep memory usage lower, at the cost of performance.

There's not a big performance difference between 8192 and 1024
so let's use less memory at the start of the connection.