"Heikki Linnakangas" <heikki@enterprisedb.com> writes:
> More precisely, on CVS HEAD it takes between 7.1-7.2%. After extending
> BufferTag with one uint32, it takes 7.4-7.5%. So the effect is
> measurable if you try hard enough, but not anything to get worried about.
And if we adopt the allegedly-faster hash_any that's in the patch
queue, the difference should get smaller yet.
regards, tom lane