Don't use partial unique indexes for unique proofs in the planner

Here we adjust relation_has_unique_index_for() so that it no longer makes
use of partial unique indexes as uniqueness proofs.  It is incorrect to
use these as the predicates used by check_index_predicates() to set
predOK makes use of not only baserestrictinfo quals as proofs, but also
qual from join conditions.  For relation_has_unique_index_for()'s case, we
need to know the relation is unique for a given set of columns before any
joins are evaluated, so if predOK was only set to true due to some join
qual, then it's unsafe to use such indexes in
relation_has_unique_index_for().  The final plan may not even make use
of that index, which could result in reading tuples that are not as
unique as the planner previously expected them to be.

Bug: #17975
Reported-by: Tor Erik Linnerud
Backpatch-through: 11, all supported versions
Discussion: https://postgr.es/m/17975-98a90c156f25c952%40postgresql.org

diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c
index b8000da56d95400da6b512d6efdef47c6ca98916..3800f0cdfb7aa59050c670c46852d31138bb19d9 100644 (file)
--- a/src/backend/optimizer/path/indxpath.c
+++ b/src/backend/optimizer/path/indxpath.c
@@ -3557,10 +3557,13 @@ relation_has_unique_index_for(PlannerInfo *root, RelOptInfo *rel,
 
        /*
         * If the index is not unique, or not immediately enforced, or if it's
-        * a partial index that doesn't match the query, it's useless here.
+        * a partial index, it's useless here.  We're unable to make use of
+        * predOK partial unique indexes due to the fact that
+        * check_index_predicates() also makes use of join predicates to
+        * determine if the partial index is usable. Here we need proofs that
+        * hold true before any joins are evaluated.
         */
-       if (!ind->unique || !ind->immediate ||
-           (ind->indpred != NIL && !ind->predOK))
+       if (!ind->unique || !ind->immediate || ind->indpred != NIL)
            continue;
 
        /*

diff --git a/src/backend/optimizer/plan/analyzejoins.c b/src/backend/optimizer/plan/analyzejoins.c
index 7ea6e26fecde6dd244a85e1c96f879a8419f039c..34efeee93f9a8eb1a39fa5f4ce3e54c81a9fee98 100644 (file)
--- a/src/backend/optimizer/plan/analyzejoins.c
+++ b/src/backend/optimizer/plan/analyzejoins.c
@@ -600,9 +600,9 @@ rel_supports_distinctness(PlannerInfo *root, RelOptInfo *rel)
        /*
         * For a plain relation, we only know how to prove uniqueness by
         * reference to unique indexes.  Make sure there's at least one
-        * suitable unique index.  It must be immediately enforced, and if
-        * it's a partial index, it must match the query.  (Keep these
-        * conditions in sync with relation_has_unique_index_for!)
+        * suitable unique index.  It must be immediately enforced, and not a
+        * partial index. (Keep these conditions in sync with
+        * relation_has_unique_index_for!)
         */
        ListCell   *lc;
 
@@ -610,8 +610,7 @@ rel_supports_distinctness(PlannerInfo *root, RelOptInfo *rel)
        {
            IndexOptInfo *ind = (IndexOptInfo *) lfirst(lc);
 
-           if (ind->unique && ind->immediate &&
-               (ind->indpred == NIL || ind->predOK))
+           if (ind->unique && ind->immediate && ind->indpred == NIL)
                return true;
        }
    }

diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out
index f635d296c27621c2e4c0cac19e59c2305f124a5a..0eb6339f6089b78245124188075c240c4b4e73b6 100644 (file)
--- a/src/test/regress/expected/join.out
+++ b/src/test/regress/expected/join.out
@@ -6503,6 +6503,23 @@ left join j2 on j1.id1 = j2.id1 where j1.id2 = 1;
          Output: j2.id1, j2.id2
 (8 rows)
 
+create unique index j1_id2_idx on j1(id2) where id2 is not null;
+-- ensure we don't use a partial unique index as unique proofs
+explain (verbose, costs off)
+select * from j1
+inner join j2 on j1.id2 = j2.id2;
+                QUERY PLAN                
+------------------------------------------
+ Nested Loop
+   Output: j1.id1, j1.id2, j2.id1, j2.id2
+   Join Filter: (j1.id2 = j2.id2)
+   ->  Seq Scan on public.j2
+         Output: j2.id1, j2.id2
+   ->  Seq Scan on public.j1
+         Output: j1.id1, j1.id2
+(7 rows)
+
+drop index j1_id2_idx;
 -- validate logic in merge joins which skips mark and restore.
 -- it should only do this if all quals which were used to detect the unique
 -- are present as join quals, and not plain quals.

diff --git a/src/test/regress/sql/join.sql b/src/test/regress/sql/join.sql
index ea9410199e91b5af33ee90b6294f71ecddce1a66..5fdacce91dfab9437c85253fcaf0a9393f0d4adf 100644 (file)
--- a/src/test/regress/sql/join.sql
+++ b/src/test/regress/sql/join.sql
@@ -2263,6 +2263,15 @@ explain (verbose, costs off)
 select * from j1
 left join j2 on j1.id1 = j2.id1 where j1.id2 = 1;
 
+create unique index j1_id2_idx on j1(id2) where id2 is not null;
+
+-- ensure we don't use a partial unique index as unique proofs
+explain (verbose, costs off)
+select * from j1
+inner join j2 on j1.id2 = j2.id2;
+
+drop index j1_id2_idx;
+
 -- validate logic in merge joins which skips mark and restore.
 -- it should only do this if all quals which were used to detect the unique
 -- are present as join quals, and not plain quals.