Re: Big performance slowdown from 11.2 to 13.3

I wrote:
> I think the right fix here is to remove the cap, which will require
> changing get_hash_mem to return double, and then maybe some cascading
> changes --- I've not looked at its callers.

Or, actually, returning size_t would likely make the most sense.
We'd fold the 1024L multiplier in here too instead of doing that
at the callers.

            regards, tom lane