"Diehl, Jeffrey" <jdiehl@sandia.gov> writes:
> Brick* implies 1334 tables
Hmm ... I wonder if the query is somehow holding onto a buffer pin for
the last block of each successively-accessed table? Will look into it.
What -B (# of shared buffers) setting are you running the postmaster
with? Try setting it to 1500 or more, if it's not already.
regards, tom lane