Re: [lwip-devel] bug entry #27352 code changes

[Bill Auerbach]

>Is it really true that the benefit of some 32-bit direct comparisons
>(instead of two words, our four bytes) outperforms the extra copy of
>the padded to the unpadded structures on NIOS-2?

I spent months characterizing and optimizing lwIP - I wouldn't have made all
of the suggestions and patches if any of them degraded performance.

>How about other architectures?
>
>In general I have seen a lot of code changes and bug reports that
>related to performance, without any proof of improvement.

We have 3 rock-solid high-performing products that don't require special
Win32 packet filter drivers, TCP/IP stack or NIC hardware that are proof
enough for me (and the people who pay me).  We possibly wouldn't have had 2
of the 3 products without my efforts as we couldn't get data out to the PC
fast enough to meet our goals.  I did have to abandon TCP for a custom UDP
reliable protocol, but almost all of my suggestions helped throughput at a
lower level.

Perhaps the flip side is to show us where and/or why you think any of the
changes are dubious and I'll recheck my work.

Bill