From 29cf61ade3f245aa40f427a1d6345287ef77e622 Mon Sep 17 00:00:00 2001 From: Tomas Vondra Date: Mon, 3 Jul 2023 18:55:31 +0200 Subject: [PATCH] Consider fillfactor when estimating relation size When table_block_relation_estimate_size() estimated the number of tuples in a relation without statistics (e.g. right after load), it did not consider fillfactor when calculating density. With non-default fillfactor values, this may result in significant overestimate of the number of tuples - up to 10x with the minimum 10% fillfactor. This may have unexpected consequences, e.g. when creating hash indexes. This considers the current fillfactor value in the "no statistics" code path. If the fillfactor changes after loading data into the table, the estimate may be off. But that seems much less likely than changing the fillfactor before the data load. Reviewed-by: Corey Huinker, Peter Eisentraut Discussion: https://postgr.es/m/cf154ef9-6bac-d268-b735-67a3443debba@enterprisedb.com --- src/backend/access/table/tableam.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c index 771438c8ce..c6bdb7e1c6 100644 --- a/src/backend/access/table/tableam.c +++ b/src/backend/access/table/tableam.c @@ -737,11 +737,19 @@ table_block_relation_estimate_size(Relation rel, int32 *attr_widths, * and (c) different table AMs might use different padding schemes. */ int32 tuple_width; + int fillfactor; + + /* + * Without reltuples/relpages, we also need to consider fillfactor. + * The other branch considers it implicitly by calculating density + * from actual relpages/reltuples statistics. + */ + fillfactor = RelationGetFillFactor(rel, HEAP_DEFAULT_FILLFACTOR); tuple_width = get_rel_data_width(rel, attr_widths); tuple_width += overhead_bytes_per_tuple; /* note: integer division is intentional here */ - density = usable_bytes_per_page / tuple_width; + density = (usable_bytes_per_page * fillfactor / 100) / tuple_width; } *tuples = rint(density * (double) curpages);