Cygwin Filesystem Performance degradation 1.7.5 vs 1.7.7, and methods for improving performance

[Larry Hall (Cygwin Developers)]

On 9/29/2010 1:53 PM, Derry Shribman wrote:
> Hi,
>
> The xstat() is useless for the target of improving performance: it will takes
>  YEARS after Linux kernel will implement it until typical unix applications
> will use it all around their code - just like other 'relativly new' kernel
> APIs like epoll() took years until unix applications started adopting them.
>
> Do we want Cygwin to be slow for another 10 years?!
>
> The env variable is a practical immediate way to improve performance with
> very little effort.

I'm confused by your line of argument here.  Weren't you advocating that
application writers could use the environment variable to get the performance
they wanted from Cygwin?  If so, why wouldn't xstat() be just as useful to
those same developers once it's available in Cygwin?  Let's assume that
Cygwin implements it once the API is settled and that this is measured on
the order of months rather than years.  Cygwin certainly uses Linux as a
guideline for what it supports but it's not bound by that.

-- 
Larry