Fix intarray's GiST opclasses to not fail for empty arrays with <@.

contrib/intarray considers "arraycol <@ constant-array" to be indexable,
but its GiST opclass code fails to reliably find index entries for empty
array values (which of course should trivially match such queries).
This is because the test condition to see whether we should descend
through a non-leaf node is wrong.

Unfortunately, empty array entries could be anywhere in the index,
as these index opclasses are currently designed.  So there's no way
to fix this except by lobotomizing <@ indexscans to scan the whole
index ... which is what this patch does.  That's pretty unfortunate:
the performance is now actually worse than a seqscan, in most cases.
We'd be better off to remove <@ from the GiST opclasses entirely,
and perhaps a future non-back-patchable patch will do so.

In the meantime, applications whose performance is adversely impacted
have a couple of options.  They could switch to a GIN index, which
doesn't have this bug, or they could replace "arraycol <@ constant-array"
with "arraycol <@ constant-array AND arraycol && constant-array".
That will provide about the same performance as before, and it will find
all non-empty subsets of the given constant-array, which is all that
could reliably be expected of the query before.

While at it, add some more regression test cases to improve code
coverage of contrib/intarray.

In passing, adjust resize_intArrayType so that when it's returning an
empty array, it uses construct_empty_array for that rather than
cowboy hacking on the input array.  While the hack produces an array
that looks valid for most purposes, it isn't bitwise equal to empty
arrays produced by other code paths, which could have subtle odd
effects.  I don't think this code path is performance-critical
enough to justify such shortcuts.  (Back-patch this part only as far
as v11; before commit 01783ac36 we were not careful about this in
other intarray code paths either.)

Back-patch the <@ fixes to all supported versions, since this was
broken from day one.

Patch by me; thanks to Alexander Korotkov for review.

Discussion: https://postgr.es/m/458.1565114141@sss.pgh.pa.us

diff --git a/contrib/intarray/_int_gist.c b/contrib/intarray/_int_gist.c
index c7d2c35fc3f1d36713edbf34755a7e0a9bb372d8..1d5b943e1817207c973024b9f3972dca11ff13e1 100644 (file)
--- a/contrib/intarray/_int_gist.c
+++ b/contrib/intarray/_int_gist.c
@@ -94,8 +94,13 @@ g_int_consistent(PG_FUNCTION_ARGS)
                retval = inner_int_contains(query,
                                  (ArrayType *) DatumGetPointer(entry->key));
            else
-               retval = inner_int_overlap((ArrayType *) DatumGetPointer(entry->key),
-                                          query);
+           {
+               /*
+                * Unfortunately, because empty arrays could be anywhere in
+                * the index, we must search the whole tree.
+                */
+               retval = true;
+           }
            break;
        default:
            retval = FALSE;

diff --git a/contrib/intarray/_intbig_gist.c b/contrib/intarray/_intbig_gist.c
index 235db3895727c6e3b92ffa425f21aa050d7758d5..e568ae16ed487cec47150b8dd355340da45d6582 100644 (file)
--- a/contrib/intarray/_intbig_gist.c
+++ b/contrib/intarray/_intbig_gist.c
@@ -591,7 +591,13 @@ g_intbig_consistent(PG_FUNCTION_ARGS)
                }
            }
            else
-               retval = _intbig_overlap((GISTTYPE *) DatumGetPointer(entry->key), query);
+           {
+               /*
+                * Unfortunately, because empty arrays could be anywhere in
+                * the index, we must search the whole tree.
+                */
+               retval = true;
+           }
            break;
        default:
            retval = FALSE;

diff --git a/contrib/intarray/expected/_int.out b/contrib/intarray/expected/_int.out
index 4080b9633fe98a91861684e0d82f1297c21b91af..6bf48ee8f5c34c59a6af2a926395e2bd49b2bead 100644 (file)
--- a/contrib/intarray/expected/_int.out
+++ b/contrib/intarray/expected/_int.out
@@ -398,6 +398,18 @@ SELECT count(*) from test__int WHERE a @> '{20,23}';
     12
 (1 row)
 
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+ count 
+-------
+    10
+(1 row)
+
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
+ count 
+-------
+     1
+(1 row)
+
 SELECT count(*) from test__int WHERE a @@ '50&68';
  count 
 -------
@@ -416,6 +428,19 @@ SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
     21
 (1 row)
 
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+ count 
+-------
+  6566
+(1 row)
+
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
+ count 
+-------
+  6343
+(1 row)
+
+SET enable_seqscan = off;  -- not all of these would use index by default
 CREATE INDEX text_idx on test__int using gist ( a gist__int_ops );
 SELECT count(*) from test__int WHERE a && '{23,50}';
  count 
@@ -447,6 +472,18 @@ SELECT count(*) from test__int WHERE a @> '{20,23}';
     12
 (1 row)
 
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+ count 
+-------
+    10
+(1 row)
+
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
+ count 
+-------
+     1
+(1 row)
+
 SELECT count(*) from test__int WHERE a @@ '50&68';
  count 
 -------
@@ -465,6 +502,18 @@ SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
     21
 (1 row)
 
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+ count 
+-------
+  6566
+(1 row)
+
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
+ count 
+-------
+  6343
+(1 row)
+
 DROP INDEX text_idx;
 CREATE INDEX text_idx on test__int using gist ( a gist__intbig_ops );
 SELECT count(*) from test__int WHERE a && '{23,50}';
@@ -497,6 +546,18 @@ SELECT count(*) from test__int WHERE a @> '{20,23}';
     12
 (1 row)
 
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+ count 
+-------
+    10
+(1 row)
+
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
+ count 
+-------
+     1
+(1 row)
+
 SELECT count(*) from test__int WHERE a @@ '50&68';
  count 
 -------
@@ -515,6 +576,18 @@ SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
     21
 (1 row)
 
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+ count 
+-------
+  6566
+(1 row)
+
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
+ count 
+-------
+  6343
+(1 row)
+
 DROP INDEX text_idx;
 CREATE INDEX text_idx on test__int using gin ( a gin__int_ops );
 SELECT count(*) from test__int WHERE a && '{23,50}';
@@ -547,6 +620,18 @@ SELECT count(*) from test__int WHERE a @> '{20,23}';
     12
 (1 row)
 
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+ count 
+-------
+    10
+(1 row)
+
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
+ count 
+-------
+     1
+(1 row)
+
 SELECT count(*) from test__int WHERE a @@ '50&68';
  count 
 -------
@@ -565,3 +650,16 @@ SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
     21
 (1 row)
 
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+ count 
+-------
+  6566
+(1 row)
+
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
+ count 
+-------
+  6343
+(1 row)
+
+RESET enable_seqscan;

diff --git a/contrib/intarray/sql/_int.sql b/contrib/intarray/sql/_int.sql
index 216c5c58d615a7cd1a5fe3714c9a5c91fb255138..fda6f503ddc111be9b63de0dfa917fbf606d5b79 100644 (file)
--- a/contrib/intarray/sql/_int.sql
+++ b/contrib/intarray/sql/_int.sql
@@ -76,9 +76,15 @@ SELECT count(*) from test__int WHERE a @@ '23|50';
 SELECT count(*) from test__int WHERE a @> '{23,50}';
 SELECT count(*) from test__int WHERE a @@ '23&50';
 SELECT count(*) from test__int WHERE a @> '{20,23}';
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
 SELECT count(*) from test__int WHERE a @@ '50&68';
 SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}';
 SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
+
+SET enable_seqscan = off;  -- not all of these would use index by default
 
 CREATE INDEX text_idx on test__int using gist ( a gist__int_ops );
 
@@ -87,9 +93,13 @@ SELECT count(*) from test__int WHERE a @@ '23|50';
 SELECT count(*) from test__int WHERE a @> '{23,50}';
 SELECT count(*) from test__int WHERE a @@ '23&50';
 SELECT count(*) from test__int WHERE a @> '{20,23}';
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
 SELECT count(*) from test__int WHERE a @@ '50&68';
 SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}';
 SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
 
 DROP INDEX text_idx;
 CREATE INDEX text_idx on test__int using gist ( a gist__intbig_ops );
@@ -99,9 +109,13 @@ SELECT count(*) from test__int WHERE a @@ '23|50';
 SELECT count(*) from test__int WHERE a @> '{23,50}';
 SELECT count(*) from test__int WHERE a @@ '23&50';
 SELECT count(*) from test__int WHERE a @> '{20,23}';
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
 SELECT count(*) from test__int WHERE a @@ '50&68';
 SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}';
 SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
 
 DROP INDEX text_idx;
 CREATE INDEX text_idx on test__int using gin ( a gin__int_ops );
@@ -111,6 +125,12 @@ SELECT count(*) from test__int WHERE a @@ '23|50';
 SELECT count(*) from test__int WHERE a @> '{23,50}';
 SELECT count(*) from test__int WHERE a @@ '23&50';
 SELECT count(*) from test__int WHERE a @> '{20,23}';
+SELECT count(*) from test__int WHERE a <@ '{73,23,20}';
+SELECT count(*) from test__int WHERE a = '{73,23,20}';
 SELECT count(*) from test__int WHERE a @@ '50&68';
 SELECT count(*) from test__int WHERE a @> '{20,23}' or a @> '{50,68}';
 SELECT count(*) from test__int WHERE a @@ '(20&23)|(50&68)';
+SELECT count(*) from test__int WHERE a @@ '20 | !21';
+SELECT count(*) from test__int WHERE a @@ '!20 & !21';
+
+RESET enable_seqscan;