Re: svn commit: r1333326 - in /subversion/trunk/subversion: include/private/svn_hash_private.h libsvn_fs_fs/temp_serializer.c libsvn_subr/hash.c

stefan2_at_apache.org writes:

> Author: stefan2
> Date: Thu May 3 07:16:11 2012
> New Revision: 1333326
>
> URL: http://svn.apache.org/viewvc?rev=1333326&view=rev
> Log:
> Introduce private API functions that wrap apr_hash_make_custom
> and return hash tables that are 2 to 4 times faster than the APR default.

How do you benchmark something like that? What is 2 to 4 times faster?
Is it the runtime of the function? Does it include or exclude function
call overhead? What sort of data? Is it relatively short data like
paths or much larger data?

On my system the compiled code is 425 bytes, compared to 102 bytes for
the APR code. That means your code pushes over 300 other bytes out
of the cache. Does that mean something else gets slower?

Should this code be in APR rather than Subversion?

-- 
Philip