postgres_fdw: Add ORDER BY to some remote SQL queries.

If the join problem's entire ORDER BY clause can be pushed to the
remote server, consider a path that adds this ORDER BY clause.  If
use_remote_estimate is on, we cost this path using an additional
remote EXPLAIN.  If not, we just estimate that the path costs 20%
more, which is intended to be large enough that we won't request a
remote sort when it's not helpful, but small enough that we'll have
the remote side do the sort when in doubt.  In some cases, the remote
sort might actually be free, because the remote query plan might
happen to produce output that is ordered the way we need, but without
remote estimates we have no way of knowing that.

It might also be useful to request sorted output from the remote side
if it enables an efficient merge join, but this patch doesn't attempt
to handle that case.

Ashutosh Bapat with revisions by me.  Also reviewed by Fabrízio de Royes
Mello and Jeevan Chalke.

1 files changed, 43 insertions, 21 deletions

diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out
index 65ea6e8d7d5..0159bf52ad0 100644
--- a/contrib/postgres_fdw/expected/postgres_fdw.out
+++ b/contrib/postgres_fdw/expected/postgres_fdw.out
@@ -134,15 +134,13 @@ ALTER FOREIGN TABLE ft2 OPTIONS (use_remote_estimate 'true');
 -- ===================================================================
 -- simple queries
 -- ===================================================================
--- single table, with/without alias
+-- single table without alias
 EXPLAIN (COSTS false) SELECT * FROM ft1 ORDER BY c3, c1 OFFSET 100 LIMIT 10;
-           QUERY PLAN            
----------------------------------
+        QUERY PLAN         
+---------------------------
  Limit
-   ->  Sort
-         Sort Key: c3, c1
-         ->  Foreign Scan on ft1
-(4 rows)
+   ->  Foreign Scan on ft1
+(2 rows)
 
 SELECT * FROM ft1 ORDER BY c3, c1 OFFSET 100 LIMIT 10;
  c1  | c2 |  c3   |              c4              |            c5            | c6 |     c7     | c8  
@@ -159,20 +157,21 @@ SELECT * FROM ft1 ORDER BY c3, c1 OFFSET 100 LIMIT 10;
  110 |  0 | 00110 | Sun Jan 11 00:00:00 1970 PST | Sun Jan 11 00:00:00 1970 | 0  | 0          | foo
 (10 rows)
 
-EXPLAIN (VERBOSE, COSTS false) SELECT * FROM ft1 t1 ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
+-- single table with alias - also test that tableoid sort is not pushed to remote side
+EXPLAIN (VERBOSE, COSTS false) SELECT * FROM ft1 t1 ORDER BY t1.c3, t1.c1, t1.tableoid OFFSET 100 LIMIT 10;
                                      QUERY PLAN                                      
 -------------------------------------------------------------------------------------
  Limit
-   Output: c1, c2, c3, c4, c5, c6, c7, c8
+   Output: c1, c2, c3, c4, c5, c6, c7, c8, tableoid
    ->  Sort
-         Output: c1, c2, c3, c4, c5, c6, c7, c8
-         Sort Key: t1.c3, t1.c1
+         Output: c1, c2, c3, c4, c5, c6, c7, c8, tableoid
+         Sort Key: t1.c3, t1.c1, t1.tableoid
          ->  Foreign Scan on public.ft1 t1
-               Output: c1, c2, c3, c4, c5, c6, c7, c8
+               Output: c1, c2, c3, c4, c5, c6, c7, c8, tableoid
                Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1"
 (8 rows)
 
-SELECT * FROM ft1 t1 ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
+SELECT * FROM ft1 t1 ORDER BY t1.c3, t1.c1, t1.tableoid OFFSET 100 LIMIT 10;
  c1  | c2 |  c3   |              c4              |            c5            | c6 |     c7     | c8  
 -----+----+-------+------------------------------+--------------------------+----+------------+-----
  101 |  1 | 00101 | Fri Jan 02 00:00:00 1970 PST | Fri Jan 02 00:00:00 1970 | 1  | 1          | foo
@@ -189,17 +188,14 @@ SELECT * FROM ft1 t1 ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
 
 -- whole-row reference
 EXPLAIN (VERBOSE, COSTS false) SELECT t1 FROM ft1 t1 ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
-                                     QUERY PLAN                                      
--------------------------------------------------------------------------------------
+                                                QUERY PLAN                                                
+----------------------------------------------------------------------------------------------------------
  Limit
    Output: t1.*, c3, c1
-   ->  Sort
+   ->  Foreign Scan on public.ft1 t1
          Output: t1.*, c3, c1
-         Sort Key: t1.c3, t1.c1
-         ->  Foreign Scan on public.ft1 t1
-               Output: t1.*, c3, c1
-               Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1"
-(8 rows)
+         Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1" ORDER BY c3 ASC, "C 1" ASC
+(5 rows)
 
 SELECT t1 FROM ft1 t1 ORDER BY t1.c3, t1.c1 OFFSET 100 LIMIT 10;
                                              t1                                             
@@ -650,6 +646,32 @@ SELECT * FROM ft2 WHERE c1 = ANY (ARRAY(SELECT c1 FROM ft1 WHERE c1 < 5));
   4 |  4 | 00004 | Mon Jan 05 00:00:00 1970 PST | Mon Jan 05 00:00:00 1970 | 4  | 4          | foo
 (4 rows)
 
+-- we should not push order by clause with volatile expressions or unsafe
+-- collations
+EXPLAIN (VERBOSE, COSTS false)
+	SELECT * FROM ft2 ORDER BY ft2.c1, random();
+                                  QUERY PLAN                                   
+-------------------------------------------------------------------------------
+ Sort
+   Output: c1, c2, c3, c4, c5, c6, c7, c8, (random())
+   Sort Key: ft2.c1, (random())
+   ->  Foreign Scan on public.ft2
+         Output: c1, c2, c3, c4, c5, c6, c7, c8, random()
+         Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1"
+(6 rows)
+
+EXPLAIN (VERBOSE, COSTS false)
+	SELECT * FROM ft2 ORDER BY ft2.c1, ft2.c3 collate "C";
+                                  QUERY PLAN                                   
+-------------------------------------------------------------------------------
+ Sort
+   Output: c1, c2, c3, c4, c5, c6, c7, c8, ((c3)::text)
+   Sort Key: ft2.c1, ft2.c3 COLLATE "C"
+   ->  Foreign Scan on public.ft2
+         Output: c1, c2, c3, c4, c5, c6, c7, c8, c3
+         Remote SQL: SELECT "C 1", c2, c3, c4, c5, c6, c7, c8 FROM "S 1"."T 1"
+(6 rows)
+
 -- ===================================================================
 -- parameterized queries
 -- ===================================================================