How does prefix* globing works?

[Peng Yu]

Hi,

I have a directory with many files and globbing with "prefix*" works
very slowly. I am wondering how prefix* globbing works internally.
Based on the slow behavior, my guess is that there is no optimization
despite the prefix is known.

Does it still iterate all the files and then compare against the
patter prefix* to keep only the matched one so that it will be very
slow when there are many files in a directory? Is there a smart way to
speed up the match based on the fact that the prefix is known so that
not all files need to be iterated? Thanks.

-- 
Regards,
Peng