Re: [hybi] frame length encoding

["Shelby Moore" <[e-mail]>]

> I posted a while back and keep referring to packet-traces of real-world
> apps.  Nobody else has posted any, so all I can go with is the data I
> collected.  That data shows that after compression, not just a lot of
> frames
> will fit in ~126 bytes, but *an overwhelming majority*.

In that case we can go with Option 2 as optimum.

But I think you are missing my point as follows?

Any ends that have a CPU load problem due to multi-core synchronization
overhead, may set their maximum size to 125, if eliminating the
conditional test will improve throughput. The downside is that is a lot of
fragmentation that would not be necessary for the large source frames. 
The CPU load problem improves the larger the maximum frame can be, but
apparently not if there is conditionals in the size. That was the only
reason I proposed Option 1/15-bit, which gives a maximum frame size of
32767 without any conditionals, and the cost is only adds 1 byte to header
for frame sizes smaller than 126, and removes 1 byte for the 2% of frame
sizes between 126 - 32767.

I think that is the most concise I can be on that matter.