Dissociate btequalimage() from interval_ops, ending its deduplication.

Under interval_ops, some equal values are distinguishable.  One such
pair is '24:00:00' and '1 day'.  With that being so, btequalimage()
breaches the documented contract for the "equalimage" btree support
function.  This can cause incorrect results from index-only scans.
Users should REINDEX any btree indexes having interval-type columns.
After updating, pg_amcheck will report an error for almost all such
indexes.  This fix makes interval_ops simply omit the support function,
like numeric_ops does.  Back-pack to v13, where btequalimage() first
appeared.  In back branches, for the benefit of old catalog content,
btequalimage() code will return false for type "interval".  Going
forward, back-branch initdb will include the catalog change.

Reviewed by Peter Geoghegan.

Discussion: https://postgr.es/m/20231011013317.22.nmisch@google.com

contrib/amcheck/verify_nbtree.c

@@ -31,6 +31,7 @@
 #include "access/xact.h"
 #include "catalog/index.h"
 #include "catalog/pg_am.h"
+#include "catalog/pg_opfamily_d.h"
 #include "commands/tablecmds.h"
 #include "common/pg_prng.h"
 #include "lib/bloomfilter.h"
@@ -338,10 +339,20 @@ bt_index_check_internal(Oid indrelid, bool parentcheck, bool heapallindexed,
 					 errmsg("index \"%s\" metapage has equalimage field set on unsupported nbtree version",
 							RelationGetRelationName(indrel))));
 		if (allequalimage && !_bt_allequalimage(indrel, false))
+		{
+			bool		has_interval_ops = false;
+
+			for (int i = 0; i < IndexRelationGetNumberOfKeyAttributes(indrel); i++)
+				if (indrel->rd_opfamily[i] == INTERVAL_BTREE_FAM_OID)
+					has_interval_ops = true;
 			ereport(ERROR,
 					(errcode(ERRCODE_INDEX_CORRUPTED),
 					 errmsg("index \"%s\" metapage incorrectly indicates that deduplication is safe",
-							RelationGetRelationName(indrel))));
+							RelationGetRelationName(indrel)),
+					 has_interval_ops
+					 ? errhint("This is known of \"interval\" indexes last built on a version predating 2023-11.")
+					 : 0));
+		}
 
 		/* Check index, possibly against table it is an index on */
 		bt_check_every_level(indrel, heaprel, heapkeyspace, parentcheck,

src/backend/utils/adt/datum.c

@@ -43,6 +43,7 @@
 #include "postgres.h"
 
 #include "access/detoast.h"
+#include "catalog/pg_type_d.h"
 #include "common/hashfn.h"
 #include "fmgr.h"
 #include "utils/builtins.h"
@@ -385,20 +386,17 @@ datum_image_hash(Datum value, bool typByVal, int typLen)
  * datum_image_eq() in all cases can use this as their "equalimage" support
  * function.
  *
- * Currently, we unconditionally assume that any B-Tree operator class that
+ * Earlier minor releases erroneously associated this function with
- * registers btequalimage as its support function 4 must be able to safely use
+ * interval_ops.  Detect that case to rescind deduplication support, without
- * optimizations like deduplication (i.e. we return true unconditionally).  If
+ * requiring initdb.
- * it ever proved necessary to rescind support for an operator class, we could
- * do that in a targeted fashion by doing something with the opcintype
- * argument.
  *-------------------------------------------------------------------------
  */
 Datum
 btequalimage(PG_FUNCTION_ARGS)
 {
-	/* Oid		opcintype = PG_GETARG_OID(0); */
+	Oid			opcintype = PG_GETARG_OID(0);
 
-	PG_RETURN_BOOL(true);
+	PG_RETURN_BOOL(opcintype != INTERVALOID);
 }
 
 /*-------------------------------------------------------------------------

src/bin/pgbench/pgbench.c

@@ -7782,14 +7782,23 @@ clear_socket_set(socket_set *sa)
 static void
 add_socket_to_set(socket_set *sa, int fd, int idx)
 {
+	/* See connect_slot() for background on this code. */
+#ifdef WIN32
+	if (sa->fds.fd_count + 1 >= FD_SETSIZE)
+	{
+		pg_log_error("too many concurrent database clients for this platform: %d",
+					 sa->fds.fd_count + 1);
+		exit(1);
+	}
+#else
 	if (fd < 0 || fd >= FD_SETSIZE)
 	{
-		/*
+		pg_log_error("socket file descriptor out of range for select(): %d",
-		 * Doing a hard exit here is a bit grotty, but it doesn't seem worth
+					 fd);
-		 * complicating the API to make it less grotty.
+		pg_log_error_hint("Try fewer concurrent database clients.");
-		 */
+		exit(1);
-		pg_fatal("too many client connections for select()");
 	}
+#endif
 	FD_SET(fd, &sa->fds);
 	if (fd > sa->maxfd)
 		sa->maxfd = fd;

src/fe_utils/parallel_slot.c

@@ -295,8 +295,41 @@ connect_slot(ParallelSlotArray *sa, int slotno, const char *dbname)
 	slot->connection = connectDatabase(sa->cparams, sa->progname, sa->echo, false, true);
 	sa->cparams->override_dbname = old_override;
 
-	if (PQsocket(slot->connection) >= FD_SETSIZE)
+	/*
-		pg_fatal("too many jobs for this platform");
+	 * POSIX defines FD_SETSIZE as the highest file descriptor acceptable to
+	 * FD_SET() and allied macros.  Windows defines it as a ceiling on the
+	 * count of file descriptors in the set, not a ceiling on the value of
+	 * each file descriptor; see
+	 * https://learn.microsoft.com/en-us/windows/win32/api/winsock2/nf-winsock2-select
+	 * and
+	 * https://learn.microsoft.com/en-us/windows/win32/api/winsock/ns-winsock-fd_set.
+	 * We can't ignore that, because Windows starts file descriptors at a
+	 * higher value, delays reuse, and skips values.  With less than ten
+	 * concurrent file descriptors, opened and closed rapidly, one can reach
+	 * file descriptor 1024.
+	 *
+	 * Doing a hard exit here is a bit grotty, but it doesn't seem worth
+	 * complicating the API to make it less grotty.
+	 */
+#ifdef WIN32
+	if (slotno >= FD_SETSIZE)
+	{
+		pg_log_error("too many jobs for this platform: %d", slotno);
+		exit(1);
+	}
+#else
+	{
+		int			fd = PQsocket(slot->connection);
+
+		if (fd >= FD_SETSIZE)
+		{
+			pg_log_error("socket file descriptor out of range for select(): %d",
+						 fd);
+			pg_log_error_hint("Try fewer jobs.");
+			exit(1);
+		}
+	}
+#endif
 
 	/* Setup the connection using the supplied command, if any. */
 	if (sa->initcmd)

src/include/catalog/pg_amproc.dat

@@ -172,8 +172,6 @@
 { amprocfamily => 'btree/interval_ops', amproclefttype => 'interval',
   amprocrighttype => 'interval', amprocnum => '3',
   amproc => 'in_range(interval,interval,interval,bool,bool)' },
-{ amprocfamily => 'btree/interval_ops', amproclefttype => 'interval',
-  amprocrighttype => 'interval', amprocnum => '4', amproc => 'btequalimage' },
 { amprocfamily => 'btree/macaddr_ops', amproclefttype => 'macaddr',
   amprocrighttype => 'macaddr', amprocnum => '1', amproc => 'macaddr_cmp' },
 { amprocfamily => 'btree/macaddr_ops', amproclefttype => 'macaddr',

src/include/catalog/pg_opfamily.dat

@@ -50,7 +50,7 @@
   opfmethod => 'btree', opfname => 'integer_ops' },
 { oid => '1977',
   opfmethod => 'hash', opfname => 'integer_ops' },
-{ oid => '1982',
+{ oid => '1982', oid_symbol => 'INTERVAL_BTREE_FAM_OID',
   opfmethod => 'btree', opfname => 'interval_ops' },
 { oid => '1983',
   opfmethod => 'hash', opfname => 'interval_ops' },

src/test/regress/expected/opr_sanity.out

@@ -2208,6 +2208,7 @@ ORDER BY 1, 2, 3;
                     | array_ops        | array_ops        | anyarray
                     | float_ops        | float4_ops       | real
                     | float_ops        | float8_ops       | double precision
+                    | interval_ops     | interval_ops     | interval
                     | jsonb_ops        | jsonb_ops        | jsonb
                     | multirange_ops   | multirange_ops   | anymultirange
                     | numeric_ops      | numeric_ops      | numeric
@@ -2216,7 +2217,7 @@ ORDER BY 1, 2, 3;
                     | record_ops       | record_ops       | record
                     | tsquery_ops      | tsquery_ops      | tsquery
                     | tsvector_ops     | tsvector_ops     | tsvector
-(15 rows)
+(16 rows)
 
 -- **************** pg_index ****************
 -- Look for illegal values in pg_index fields.