[CF 5959] v3 - Import Statistics in postgres_fdw before resorting to sampling.

This branch was automatically generated by a robot using patches from an
email thread registered at:

https://commitfest.postgresql.org/patch/5959

The branch will be overwritten each time a new patch version is posted to
the thread, and also periodically to check for bitrot caused by changes
on the master branch.

Patch(es): https://www.postgresql.org/message-id/CADkLM=cVc-KUAqcm1yoDkGwMrcgCvxY3WAMpaRZVLtO9sbc+kg@mail.gmail.com
Author(s): Corey Huinker

Author: Commitfest Bot

contrib/postgres_fdw/expected/postgres_fdw.out

@@ -628,6 +628,7 @@ INSERT INTO loct_empty
   SELECT id, 'AAA' || to_char(id, 'FM000') FROM generate_series(1, 100) id;
 DELETE FROM loct_empty;
 ANALYZE ft_empty;
+INFO:  Found no remote statistics for "ft_empty"
 EXPLAIN (VERBOSE, COSTS OFF) SELECT * FROM ft_empty ORDER BY c1;
                                   QUERY PLAN                                   
 -------------------------------------------------------------------------------
@@ -4551,7 +4552,8 @@ REINDEX TABLE reind_fdw_parent; -- ok
 REINDEX TABLE CONCURRENTLY reind_fdw_parent; -- ok
 DROP TABLE reind_fdw_parent;
 -- ===================================================================
--- conversion error
+-- conversion error, will generate a WARNING for imported stats and an
+-- error on locally computed stats.
 -- ===================================================================
 ALTER FOREIGN TABLE ft1 ALTER COLUMN c8 TYPE int;
 SELECT * FROM ft1 ftx(x1,x2,x3,x4,x5,x6,x7,x8) WHERE x1 = 1;  -- ERROR
@@ -4568,6 +4570,9 @@ CONTEXT:  whole-row reference to foreign table "ftx"
 SELECT sum(c2), array_agg(c8) FROM ft1 GROUP BY c8; -- ERROR
 ERROR:  invalid input syntax for type integer: "foo"
 CONTEXT:  processing expression at position 2 in select list
+ANALYZE ft1; -- WARNING
+WARNING:  invalid input syntax for type integer: "foo"
+ALTER FOREIGN TABLE ft1 OPTIONS ( fetch_stats 'false' );
 ANALYZE ft1; -- ERROR
 ERROR:  invalid input syntax for type integer: "foo"
 CONTEXT:  column "c8" of foreign table "ft1"
@@ -7102,6 +7107,7 @@ INSERT INTO loct2 VALUES (1002, 'bar');
 CREATE FOREIGN TABLE remt2 (c1 int, c2 text) SERVER loopback OPTIONS (table_name 'loct2');
 ANALYZE loct1;
 ANALYZE remt2;
+INFO:  Found no remote statistics for "remt2"
 SET enable_mergejoin TO false;
 SET enable_hashjoin TO false;
 SET enable_material TO false;
@@ -8784,6 +8790,7 @@ alter foreign table foo2 options (use_remote_estimate 'true');
 create index i_loct1_f1 on loct1(f1);
 create index i_foo_f1 on foo(f1);
 analyze foo;
+INFO:  Found no remote statistics for "foo2"
 analyze loct1;
 -- inner join; expressions in the clauses appear in the equivalence class list
 explain (verbose, costs off)
@@ -9013,7 +9020,9 @@ insert into remt1 values (2, 'bar');
 insert into remt2 values (1, 'foo');
 insert into remt2 values (2, 'bar');
 analyze remt1;
+INFO:  Found no remote statistics for "remt1"
 analyze remt2;
+INFO:  Found no remote statistics for "remt2"
 explain (verbose, costs off)
 update parent set b = parent.b || remt2.b from remt2 where parent.a = remt2.a returning *;
                                                    QUERY PLAN                                                   
@@ -10313,6 +10322,8 @@ CREATE FOREIGN TABLE ftprt1_p1 PARTITION OF fprt1 FOR VALUES FROM (0) TO (250)
 CREATE FOREIGN TABLE ftprt1_p2 PARTITION OF fprt1 FOR VALUES FROM (250) TO (500)
 	SERVER loopback OPTIONS (TABLE_NAME 'fprt1_p2');
 ANALYZE fprt1;
+INFO:  Found no remote statistics for "ftprt1_p1"
+INFO:  Found no remote statistics for "ftprt1_p2"
 ANALYZE fprt1_p1;
 ANALYZE fprt1_p2;
 CREATE TABLE fprt2 (a int, b int, c varchar) PARTITION BY RANGE(b);
@@ -10328,6 +10339,8 @@ ALTER TABLE fprt2 ATTACH PARTITION ftprt2_p1 FOR VALUES FROM (0) TO (250);
 CREATE FOREIGN TABLE ftprt2_p2 PARTITION OF fprt2 FOR VALUES FROM (250) TO (500)
 	SERVER loopback OPTIONS (table_name 'fprt2_p2', use_remote_estimate 'true');
 ANALYZE fprt2;
+INFO:  Found no remote statistics for "ftprt2_p1"
+INFO:  Found no remote statistics for "ftprt2_p2"
 ANALYZE fprt2_p1;
 ANALYZE fprt2_p2;
 -- inner join three tables
@@ -10515,9 +10528,15 @@ CREATE FOREIGN TABLE fpagg_tab_p1 PARTITION OF pagg_tab FOR VALUES FROM (0) TO (
 CREATE FOREIGN TABLE fpagg_tab_p2 PARTITION OF pagg_tab FOR VALUES FROM (10) TO (20) SERVER loopback OPTIONS (table_name 'pagg_tab_p2');
 CREATE FOREIGN TABLE fpagg_tab_p3 PARTITION OF pagg_tab FOR VALUES FROM (20) TO (30) SERVER loopback OPTIONS (table_name 'pagg_tab_p3');
 ANALYZE pagg_tab;
+INFO:  Found no remote statistics for "fpagg_tab_p1"
+INFO:  Found no remote statistics for "fpagg_tab_p2"
+INFO:  Found no remote statistics for "fpagg_tab_p3"
 ANALYZE fpagg_tab_p1;
+INFO:  Found no remote statistics for "fpagg_tab_p1"
 ANALYZE fpagg_tab_p2;
+INFO:  Found no remote statistics for "fpagg_tab_p2"
 ANALYZE fpagg_tab_p3;
+INFO:  Found no remote statistics for "fpagg_tab_p3"
 -- When GROUP BY clause matches with PARTITION KEY.
 -- Plan with partitionwise aggregates is disabled
 SET enable_partitionwise_aggregate TO false;
@@ -11463,6 +11482,8 @@ CREATE FOREIGN TABLE async_p2 PARTITION OF async_pt FOR VALUES FROM (2000) TO (3
 INSERT INTO async_p1 SELECT 1000 + i, i, to_char(i, 'FM0000') FROM generate_series(0, 999, 5) i;
 INSERT INTO async_p2 SELECT 2000 + i, i, to_char(i, 'FM0000') FROM generate_series(0, 999, 5) i;
 ANALYZE async_pt;
+INFO:  Found no remote statistics for "async_p1"
+INFO:  Found no remote statistics for "async_p2"
 -- simple queries
 CREATE TABLE result_tbl (a int, b int, c text);
 EXPLAIN (VERBOSE, COSTS OFF)
@@ -11569,6 +11590,9 @@ CREATE FOREIGN TABLE async_p3 PARTITION OF async_pt FOR VALUES FROM (3000) TO (4
   SERVER loopback2 OPTIONS (table_name 'base_tbl3');
 INSERT INTO async_p3 SELECT 3000 + i, i, to_char(i, 'FM0000') FROM generate_series(0, 999, 5) i;
 ANALYZE async_pt;
+INFO:  Found no remote statistics for "async_p1"
+INFO:  Found no remote statistics for "async_p2"
+INFO:  Found no remote statistics for "async_p3"
 EXPLAIN (VERBOSE, COSTS OFF)
 INSERT INTO result_tbl SELECT * FROM async_pt WHERE b === 505;
                            QUERY PLAN                           
@@ -11610,6 +11634,8 @@ DROP TABLE base_tbl3;
 CREATE TABLE async_p3 PARTITION OF async_pt FOR VALUES FROM (3000) TO (4000);
 INSERT INTO async_p3 SELECT 3000 + i, i, to_char(i, 'FM0000') FROM generate_series(0, 999, 5) i;
 ANALYZE async_pt;
+INFO:  Found no remote statistics for "async_p1"
+INFO:  Found no remote statistics for "async_p2"
 EXPLAIN (VERBOSE, COSTS OFF)
 INSERT INTO result_tbl SELECT * FROM async_pt WHERE b === 505;
                            QUERY PLAN                           
@@ -12665,6 +12691,42 @@ ANALYZE analyze_ftable;
 DROP FOREIGN TABLE analyze_ftable;
 DROP TABLE analyze_table;
 -- ===================================================================
+-- test remote analyze
+-- ===================================================================
+CREATE TABLE remote_analyze_table (id int, a text, b bigint);
+INSERT INTO remote_analyze_table (SELECT x FROM generate_series(1,1000) x);
+CREATE FOREIGN TABLE remote_analyze_ftable (id int, a text, b bigint)
+       SERVER loopback
+       OPTIONS (table_name 'remote_analyze_table', remote_analyze 'true');
+-- no stats before
+SELECT s.tablename, COUNT(*) AS num_stats
+FROM pg_stats AS s
+WHERE s.schemaname = 'public'
+AND s.tablename IN ('remote_analyze_table', 'remote_analyze_ftable')
+GROUP BY s.tablename
+ORDER BY s.tablename;
+ tablename | num_stats 
+-----------+-----------
+(0 rows)
+
+ANALYZE remote_analyze_ftable;
+-- both stats after
+SELECT s.tablename, COUNT(*) AS num_stats
+FROM pg_stats AS s
+WHERE s.schemaname = 'public'
+AND s.tablename IN ('remote_analyze_table', 'remote_analyze_ftable')
+GROUP BY s.tablename
+ORDER BY s.tablename;
+       tablename       | num_stats 
+-----------------------+-----------
+ remote_analyze_ftable |         3
+ remote_analyze_table  |         3
+(2 rows)
+
+-- cleanup
+DROP FOREIGN TABLE remote_analyze_ftable;
+DROP TABLE remote_analyze_table;
+-- ===================================================================
 -- test for postgres_fdw_get_connections function with check_conn = true
 -- ===================================================================
 -- Disable debug_discard_caches in order to manage remote connections

contrib/postgres_fdw/option.c

@@ -120,6 +120,8 @@ postgres_fdw_validator(PG_FUNCTION_ARGS)
 			strcmp(def->defname, "async_capable") == 0 ||
 			strcmp(def->defname, "parallel_commit") == 0 ||
 			strcmp(def->defname, "parallel_abort") == 0 ||
+			strcmp(def->defname, "fetch_stats") == 0 ||
+			strcmp(def->defname, "remote_analyze") == 0 ||
 			strcmp(def->defname, "keep_connections") == 0)
 		{
 			/* these accept only boolean values */
@@ -278,6 +280,14 @@ InitPgFdwOptions(void)
 		{"use_scram_passthrough", ForeignServerRelationId, false},
 		{"use_scram_passthrough", UserMappingRelationId, false},
 
+		/* fetch_size is available on both server and table */
+		{"fetch_stats", ForeignServerRelationId, false},
+		{"fetch_stats", ForeignTableRelationId, false},
+
+		/* remote_analyze is available on both server and table */
+		{"remote_analyze", ForeignServerRelationId, false},
+		{"remote_analyze", ForeignTableRelationId, false},
+
 		/*
 		 * sslcert and sslkey are in fact libpq options, but we repeat them
 		 * here to allow them to appear in both foreign server context (when