While looking at Alexander's GiST fastbuild patch, which adds buffers to
internal nodes to avoid random I/O during index build, it occurred to me
that inserting the tuples to the leaf pages one at a time is quite
inefficient too, even if the leaf pages are in cache. There's still the
overhead of locking and WAL-logging each insertion separately. I think
we could get a nice further speedup if we attach a small buffer (one
block or so) to every leaf page we're currently writing tuples to, and
update the leaf page in bulk. Conveniently, the code to insert multiple
tuples to a page already exists in GiST code (because inserting a tuple
sometimes splits the page into more than two parts, so you need to
insert multiple downlinks to the parent), so this requires no changes to
the low-level routines and WAL-logging.
Let's finish off the main fastbuild patch first, but I wanted to get the
idea out there.
-- Heikki Linnakangas EnterpriseDB http://www.enterprisedb.com