Consistently use PageGetExactFreeSpace() in pgstattuple.
Previously this code used PageGetHeapFreeSpace on heap pages,
and usually used PageGetFreeSpace on index pages (though for some
reason GetHashPageStats used PageGetExactFreeSpace instead).
The difference is that those functions subtract off the size of
a line pointer, and PageGetHeapFreeSpace has some additional
rules about returning zero if adding another line pointer would
require exceeding MaxHeapTuplesPerPage. Those things make sense
when testing to see if a new tuple can be put on the page, but
they seem pretty strange for pure statistics collection.
Additionally, statapprox_heap had a special rule about counting
a "new" page as being fully available space. This also seems
strange, because it's not actually usable until VACUUM or some
such process initializes the page. Moreover, it's inconsistent
with what pgstat_heap does, which is to count such a page as
having zero free space. So make it work like pgstat_heap, which
as of this patch unconditionally calls PageGetExactFreeSpace.
This is more of a definitional change than a bug fix, so no
back-patch. The module's documentation doesn't define exactly
what "free space" means either, so we left that as-is.
Frédéric Yhuel, reviewed by Rafia Sabih and Andreas Karlsson.
Discussion: https://postgr.es/m/3a18f843-76f6-4a84-8cca-49537fefa15d@dalibo.com
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/de239d01e7ccf7648e964d7a38c0f1c36bde8346
Modified Files
--------------
contrib/pgstattuple/pgstatapprox.c | 9 +--------
contrib/pgstattuple/pgstatindex.c | 2 +-
contrib/pgstattuple/pgstattuple.c | 6 +++---
3 files changed, 5 insertions(+), 12 deletions(-)
