Improve kconfig symbol hashing
While looking for something else I noticed that the symbol hash function used by kconfig is quite poor. It doesn't use any of the standard hash techniques but simply adds up the string and then uses power of two masking, which is both known to perform poorly. The current x86 kconfig has over 7000 symbols. When I instrumented it showed that the minimum hash chain length was 16 and a significant number of them was over 30. It didn't help that the hash table size was only 256 buckets. This patch increases the hash table size to a larger prime and switches to a FNV32 hash. I played around with a couple of hash functions, but that one seemed to perform best with reasonable hash table sizes. Increasing the hash table size even further didn't seem like a good idea, because there are a couple of global walks which walk the complete hash table. I also moved the unnamed bucket to 0. It's still the longest of all the buckets (44 entries), but hopefully it's not often hit except for the global walk which doesn't care. The result is a much nicer distribution: (first column bucket length, second number of buckets with that length) 1: 3505 2: 1236 3: 294 4: 52 5: 3 47: 1 <--- this is the unnamed symbols bucket There are still some 5+ buckets, but increasing the hash table even more would be likely not worth it. This also cleans up the code slightly by removing hard coded magic numbers. I didn't notice a big performance difference either way on my Nehalem system, but I presume it'll help somewhat on slower systems. Signed-off-by: NAndi Kleen <ak@linux.intel.com> Signed-off-by: NMichal Marek <mmarek@suse.cz>
Showing
想要评论请 注册 或 登录