Be sure to rewind the tuplestore read pointer in non-leader CTEScan nodes.

ExecInitCteScan supposed that it didn't have to do anything to the extra
tuplestore read pointer it gets from tuplestore_alloc_read_pointer.
However, it needs this read pointer to be positioned at the start of the
tuplestore, while tuplestore_alloc_read_pointer is actually defined as
cloning the current position of read pointer 0.  In normal situations
that accidentally works because we initialize the whole plan tree at once,
before anything gets read.  But it fails in an EvalPlanQual recheck, as
illustrated in bug #14328 from Dima Pavlov.  To fix, just forcibly rewind
the pointer after tuplestore_alloc_read_pointer.  The cost of doing so is
negligible unless the tuplestore is already in TSS_READFILE state, which
wouldn't happen in normal cases.  We could consider altering tuplestore's
API to make that case cheaper, but that would make for a more invasive
back-patch and it doesn't seem worth it.

This has been broken probably for as long as we've had CTEs, so back-patch
to all supported branches.

Discussion: <32468.1474548308@sss.pgh.pa.us>

diff --git a/src/backend/executor/nodeCtescan.c b/src/backend/executor/nodeCtescan.c
index 7e10b8a530deb2850938c254e80eae9fe09d4cd9..f39bbf405f764b9a74074a7e6e72de375fcc5f2c 100644 (file)
--- a/src/backend/executor/nodeCtescan.c
+++ b/src/backend/executor/nodeCtescan.c
@@ -224,9 +224,13 @@ ExecInitCteScan(CteScan *node, EState *estate, int eflags)
        {
                /* Not the leader */
                Assert(IsA(scanstate->leader, CteScanState));
+               /* Create my own read pointer, and ensure it is at start */
                scanstate->readptr =
                        tuplestore_alloc_read_pointer(scanstate->leader->cte_table,
                                                                                  scanstate->eflags);
+               tuplestore_select_read_pointer(scanstate->leader->cte_table,
+                                                                          scanstate->readptr);
+               tuplestore_rescan(scanstate->leader->cte_table);
        }
 
        /*

diff --git a/src/test/isolation/expected/eval-plan-qual.out b/src/test/isolation/expected/eval-plan-qual.out
index 433533e6117f9561356484bce352356c1cacc12a..99c4137e14a5b7d1179308002b412a21dae05b38 100644 (file)
--- a/src/test/isolation/expected/eval-plan-qual.out
+++ b/src/test/isolation/expected/eval-plan-qual.out
@@ -104,3 +104,24 @@ a              b              c
 2              2              2              
 2              3              0              
 step c2: COMMIT;
+
+starting permutation: wrtwcte readwcte c1 c2
+step wrtwcte: UPDATE table_a SET value = 'tableAValue2' WHERE id = 1;
+step readwcte: 
+       WITH
+           cte1 AS (
+             SELECT id FROM table_b WHERE value = 'tableBValue'
+           ),
+           cte2 AS (
+             SELECT * FROM table_a
+             WHERE id = (SELECT id FROM cte1)
+             FOR UPDATE
+           )
+       SELECT * FROM cte2;
+ <waiting ...>
+step c1: COMMIT;
+step c2: COMMIT;
+step readwcte: <... completed>
+id             value          
+
+1              tableAValue2   

diff --git a/src/test/isolation/specs/eval-plan-qual.spec b/src/test/isolation/specs/eval-plan-qual.spec
index 6fb24322863dc2ff7a81e8c027b6b5aafbe55c94..f15dee385fce681dbe4eed8231088e1782895832 100644 (file)
--- a/src/test/isolation/specs/eval-plan-qual.spec
+++ b/src/test/isolation/specs/eval-plan-qual.spec
@@ -16,12 +16,18 @@ setup
  INSERT INTO c1 SELECT 0, a / 3, a % 3 FROM generate_series(0, 9) a;
  INSERT INTO c2 SELECT 1, a / 3, a % 3 FROM generate_series(0, 9) a;
  INSERT INTO c3 SELECT 2, a / 3, a % 3 FROM generate_series(0, 9) a;
+
+ CREATE TABLE table_a (id integer, value text);
+ CREATE TABLE table_b (id integer, value text);
+ INSERT INTO table_a VALUES (1, 'tableAValue');
+ INSERT INTO table_b VALUES (1, 'tableBValue');
 }
 
 teardown
 {
  DROP TABLE accounts;
  DROP TABLE p CASCADE;
+ DROP TABLE table_a, table_b;
 }
 
 session "s1"
@@ -67,11 +73,27 @@ step "returningp1" {
        WITH u AS ( UPDATE p SET b = b WHERE a > 0 RETURNING * )
          SELECT * FROM u;
 }
+step "wrtwcte" { UPDATE table_a SET value = 'tableAValue2' WHERE id = 1; }
 step "c2"      { COMMIT; }
 
 session "s3"
 setup          { BEGIN ISOLATION LEVEL READ COMMITTED; }
 step "read"    { SELECT * FROM accounts ORDER BY accountid; }
+
+# this test exercises EvalPlanQual with a CTE, cf bug #14328
+step "readwcte"        {
+       WITH
+           cte1 AS (
+             SELECT id FROM table_b WHERE value = 'tableBValue'
+           ),
+           cte2 AS (
+             SELECT * FROM table_a
+             WHERE id = (SELECT id FROM cte1)
+             FOR UPDATE
+           )
+       SELECT * FROM cte2;
+}
+
 teardown       { COMMIT; }
 
 permutation "wx1" "wx2" "c1" "c2" "read"
@@ -79,3 +101,4 @@ permutation "wy1" "wy2" "c1" "c2" "read"
 permutation "upsert1" "upsert2" "c1" "c2" "read"
 permutation "readp1" "writep1" "readp2" "c1" "c2"
 permutation "writep2" "returningp1" "c1" "c2"
+permutation "wrtwcte" "readwcte" "c1" "c2"