agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH v5 3/3] async postgres_fdw 51+ messages / 4 participants [nested] [flat]
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v3 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 222 ++++--- contrib/postgres_fdw/postgres_fdw.c | 603 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 694 insertions(+), 181 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..29aa09db8e 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..b04b6a0e54 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,244 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + /* It's the leader */ + ForeignScanState *next_leader; + + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1791,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1799,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1829,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1849,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1857,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2646,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2733,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2784,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2983,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3028,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3610,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3677,120 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; char sql[64]; - int numrows; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3800,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3980,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4069,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4099,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4114,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4153,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4163,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4176,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4307,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4475,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4485,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5979,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.2 ----Next_Part(Thu_Jun__4_15_00_15_2020_826)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v4 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 222 ++++--- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 691 insertions(+), 182 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..29aa09db8e 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.2 ----Next_Part(Wed_Jun_10_12_05_10_2020_221)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v7 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 10e23d02ed..0634ab9f6a 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6986,7 +6986,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7014,7 +7014,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7042,7 +7042,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7070,7 +7070,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7140,35 +7140,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7178,35 +7184,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7236,11 +7248,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7254,12 +7267,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7289,16 +7303,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7316,17 +7331,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7476,27 +7492,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8571,11 +8593,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8610,20 +8633,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8652,11 +8677,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8709,21 +8735,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8758,18 +8786,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8780,13 +8809,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8808,29 +8838,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8850,20 +8873,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index a31abce7c9..14824368cc 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1433,12 +1475,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1486,40 +1538,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1534,7 +1787,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1542,6 +1795,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1570,9 +1825,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1590,7 +1845,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1598,15 +1853,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2371,7 +2642,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2456,7 +2729,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2503,8 +2780,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2702,6 +2979,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2746,6 +3024,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3316,11 +3606,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3383,50 +3673,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3436,22 +3795,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3565,7 +3975,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3652,6 +4064,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3679,14 +4094,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3694,10 +4109,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3733,7 +4148,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3743,12 +4158,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3756,9 +4171,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3887,16 +4302,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4055,9 +4470,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4065,10 +4480,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5559,6 +5974,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 78156d10b4..17d461b1a4 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1799,25 +1799,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1859,12 +1859,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1923,8 +1923,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Oct__1_13_43_31_2020_721)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 08daf26fdf..be5948f613 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -59,6 +59,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -203,6 +204,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -216,6 +218,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 90db550b92..9374fa3a6c 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Aug_20_16_36_08_2020_519)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 272 ++++---- contrib/postgres_fdw/postgres_fdw.c | 601 +++++++++++++++--- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 710 insertions(+), 213 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 52d1fe3563..d9edc5e4de 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Returns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not yet. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 82fc1290ef..bf9b4041cd 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 + Output: ROW(foo_1.f1), foo_1.f1 + Remote SQL: SELECT f1 FROM public.loct1 + -> Async Foreign Scan on public.foo2 foo_3 + Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) + Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 - Output: ROW(foo_1.f1), foo_1.f1 - Remote SQL: SELECT f1 FROM public.loct1 -> Seq Scan on public.foo foo_2 Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 - Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) - Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count @@ -8795,29 +8825,22 @@ SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; Sort Output: t1.a, (count(((t1.*)::pagg_tab))) Sort Key: t1.a - -> Append - -> HashAggregate - Output: t1.a, count(((t1.*)::pagg_tab)) - Group Key: t1.a - Filter: (avg(t1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p1 t1 - Output: t1.a, t1.*, t1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 - -> HashAggregate - Output: t1_1.a, count(((t1_1.*)::pagg_tab)) - Group Key: t1_1.a - Filter: (avg(t1_1.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p2 t1_1 + -> HashAggregate + Output: t1.a, count(((t1.*)::pagg_tab)) + Group Key: t1.a + Filter: (avg(t1.b) < '22'::numeric) + -> Append + Async subplans: 3 + -> Async Foreign Scan on public.fpagg_tab_p1 t1_1 Output: t1_1.a, t1_1.*, t1_1.b - Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 - -> HashAggregate - Output: t1_2.a, count(((t1_2.*)::pagg_tab)) - Group Key: t1_2.a - Filter: (avg(t1_2.b) < '22'::numeric) - -> Foreign Scan on public.fpagg_tab_p3 t1_2 + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p1 + -> Async Foreign Scan on public.fpagg_tab_p2 t1_2 Output: t1_2.a, t1_2.*, t1_2.b + Remote SQL: SELECT a, b, c FROM public.pagg_tab_p2 + -> Async Foreign Scan on public.fpagg_tab_p3 t1_3 + Output: t1_3.a, t1_3.*, t1_3.b Remote SQL: SELECT a, b, c FROM public.pagg_tab_p3 -(25 rows) +(18 rows) SELECT a, count(t1) FROM pagg_tab t1 GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | count @@ -8837,20 +8860,15 @@ SELECT b, avg(a), max(a), count(*) FROM pagg_tab GROUP BY b HAVING sum(a) < 700 ----------------------------------------------------------------- Sort Sort Key: pagg_tab.b - -> Finalize HashAggregate + -> HashAggregate Group Key: pagg_tab.b Filter: (sum(pagg_tab.a) < 700) -> Append - -> Partial HashAggregate - Group Key: pagg_tab.b - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Partial HashAggregate - Group Key: pagg_tab_1.b - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Partial HashAggregate - Group Key: pagg_tab_2.b - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(15 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- =================================================================== -- access rights and superuser diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 9fc53cad68..4bfc2d39ea 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrieve PgFdwScanState struct from ForeignScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,29 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state - shared among all PgFdwState instances using the + * same connection. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +161,6 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool async; /* true if run asynchronously */ + bool queued; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last element in waiter queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->async = false; + fsstate->queued = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,241 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipulation functions + */ + +/* + * add_async_waiter: + * + * Enqueue node if it isn't in the queue. Immediately send request it if the + * underlying connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* + * Do nothing if the node is already in the queue or already eof'ed. + * Note: leader node is not marked as queued. + */ + if (leader == node || fsstate->queued || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* no leader means not busy, send request immediately */ + request_more_data(node); + } + else + { + /* the connection is busy, queue the node */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->queued = true; + } +} + +/* + * move_to_next_waiter: + * + * Make the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *leader_state = GetPgFdwScanState(node); + ForeignScanState *next_leader = leader_state->waiter; + + Assert(leader_state->s.commonstate->leader = node); + + if (next_leader) + { + /* the first waiter becomes the next leader */ + PgFdwScanState *next_leader_state = GetPgFdwScanState(next_leader); + next_leader_state->last_waiter = leader_state->last_waiter; + next_leader_state->queued = false; + } + + leader_state->waiter = NULL; + leader_state->s.commonstate->leader = next_leader; + + return next_leader; +} + +/* + * Remove the node from waiter queue. + * + * Remaining results are cleared if the node is a busy leader. + * This intended to be used during node shutdown. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->queued) + return; + + leader_state = GetPgFdwScanState(leader); + + if (leader == node) + { + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + move_to_next_waiter(node); + + return; + } + + /* + * Just remove the node from the queue + * + * Nodes don't have a link to the previous node but anyway this function is + * called on the shutdown path, so we don't bother seeking for faster way + * to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + + /* relink to the previous node if the last node was removed */ + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + + fsstate->queued = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check async state to tell if all tuples received + * (AS_AVAILABLE) or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); - - /* - * Get some more tuples, if we've run out. - */ + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* + * finish the running query before sending the next command for + * this node + */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy, queue the request */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* + * The request for the next node cannot be sent before the leader + * responds. Finish the current leader if possible. + */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* fetch the leader's data and enqueue it for the next request */ + if (available) + { + fetch_received_data(leader); + add_async_waiter(leader); + } + } + } + if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + node->ss.ps.asyncstate = AS_AVAILABLE; + else + node->ss.ps.asyncstate = AS_WAITING; + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1788,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1796,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1826,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1846,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1854,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2643,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2730,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2781,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2980,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3025,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3607,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3674,119 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof'ed */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* The node is the current leader, just return. */ + if (leader == node) + return; + + /* Let the node be the leader */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* There's some remains. Move them to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; - char sql[64]; - int numrows; + PGconn *conn = fsstate->s.conn; + int addrows; + size_t newsize; int i; - snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", - fsstate->fetch_size, fsstate->cursor_number); - - res = pgfdw_exec_query(conn, sql); - /* On error, report the original query, not the FETCH. */ + res = pgfdw_get_result(conn, fsstate->query); if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3796,73 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate the underlying connection so that this node can send the next query. + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + Assert(commonstate != NULL); + + /* just return if the connection is already available */ + if (commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read all of the result for the running + * query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3976,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4065,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4095,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4110,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4149,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4159,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4172,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4303,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4471,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4481,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5975,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.4 ----Next_Part(Thu_Jul__2_11_14_48_2020_705)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v2 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 28 + .../postgres_fdw/expected/postgres_fdw.out | 222 ++++--- contrib/postgres_fdw/postgres_fdw.c | 607 ++++++++++++++++-- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 703 insertions(+), 176 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index e45647f3ea..2184f7745a 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -58,6 +58,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -202,6 +203,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -215,6 +217,32 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Rerturns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + /* Find storage using the same key with GetConnection */ + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + /* Create one if not any. */ + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 62c2697920..e11e0d40a7 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6973,7 +6973,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -7001,7 +7001,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7029,7 +7029,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -7057,7 +7057,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7127,35 +7127,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7165,35 +7171,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar bar_1 + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid + Sort Key: bar_1.f1 + -> Seq Scan on public.bar bar_1 + Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid -> Foreign Scan on public.bar2 bar_2 Output: bar_2.f1, bar_2.f2, bar_2.ctid, bar_2.*, bar_2.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7223,11 +7235,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7241,12 +7254,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo foo_1 - Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid - -> Foreign Scan on public.foo2 foo_2 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_2 Output: foo_2.ctid, foo_2.f1, foo_2.*, foo_2.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo foo_1 + Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7276,16 +7290,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append - -> Seq Scan on public.foo - Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 Output: ROW(foo_1.f1), foo_1.f1 Remote SQL: SELECT f1 FROM public.loct1 - -> Seq Scan on public.foo foo_2 - Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 + -> Async Foreign Scan on public.foo2 foo_3 Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) Remote SQL: SELECT f1 FROM public.loct1 + -> Seq Scan on public.foo + Output: ROW(foo.f1), foo.f1 + -> Seq Scan on public.foo foo_2 + Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7303,17 +7318,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append - -> Seq Scan on public.foo - Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 Output: ROW(foo_1.f1), foo_1.f1 Remote SQL: SELECT f1 FROM public.loct1 - -> Seq Scan on public.foo foo_2 - Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 + -> Async Foreign Scan on public.foo2 foo_3 Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) + -> Seq Scan on public.foo + Output: ROW(foo.f1), foo.f1 + -> Seq Scan on public.foo foo_2 + Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) +(47 rows) update bar set f2 = f2 + 100 from @@ -7463,27 +7479,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8558,11 +8580,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1)) INNER JOIN (ftprt1_p1 t3_1) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2)) INNER JOIN (ftprt1_p2 t3_2) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8597,20 +8620,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8639,11 +8664,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1_1) INNER JOIN (ftprt2_p1 t2_1) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_2) INNER JOIN (ftprt2_p2 t2_2) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8696,21 +8722,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2_1 - -> Foreign Scan on ftprt2_p2 t2_2 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2_1 + -> Async Foreign Scan on ftprt2_p2 t2_2 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1_1 - -> Foreign Scan on ftprt1_p2 t1_2 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1_1 + -> Async Foreign Scan on ftprt1_p2 t1_2 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8745,18 +8773,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p2 pagg_tab_2 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_3 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_2 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_3 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8767,13 +8796,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index 2175dff824..7b34afa119 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrive PgFdwScanState struct from ForeginScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,28 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection common state. + */ +typedef struct PgFdwConnCommonState +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnCommonState; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnCommonState *commonstate; /* connection common state */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +160,7 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ + bool result_ready; unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool run_async; /* true if run asynchronously */ + bool inqueue; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last waiting node in waiting queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); + fsstate->s.commonstate->leader = NULL; + fsstate->s.commonstate->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->run_async = false; + fsstate->inqueue = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,249 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipuration functions + */ + +/* + * add_async_waiter: + * + * Enqueue the node if it doesn't in the queue. Immediately starts the node if + * the connection is not busy. + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + + /* do nothing if the node is already in the queue or already eof'ed */ + if (leader == node || fsstate->inqueue || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* immediately send request if not busy */ + request_more_data(node); + } + else + { + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->inqueue = true; + } +} + +/* + * move_to_next_waiter: + * + * Makes the first waiter be the next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *ret = fsstate->waiter; + + Assert(fsstate->s.commonstate->leader = node); + + if (ret) + { + PgFdwScanState *retstate = GetPgFdwScanState(ret); + fsstate->waiter = NULL; + retstate->last_waiter = fsstate->last_waiter; + retstate->inqueue = false; + } + + fsstate->s.commonstate->leader = ret; + + return ret; +} + +/* + * Remove the node from waiter queue. + * + * Results are cleared before removing leader if it is busy. + */ +static inline void +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->inqueue) + return; + + leader_state = GetPgFdwScanState(leader); + + /* Remove the leader node */ + if (leader == node) + { + ForeignScanState *next_leader; + + if (leader_state->s.commonstate->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.commonstate->busy = false; + } + + /* Make the first waiter the leader */ + if (leader_state->waiter) + { + PgFdwScanState *next_leader_state; + + next_leader = leader_state->waiter; + next_leader_state = GetPgFdwScanState(next_leader); + + leader_state->s.commonstate->leader = next_leader; + next_leader_state->last_waiter = leader_state->last_waiter; + } + leader_state->waiter = NULL; + + return; + } + + /* + * Just remove the node in queue + * + * This function is called on the shutdown path. We don't bother + * considering faster way to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + else + leader_state->last_waiter = cur; + + fsstate->inqueue = false; + + return; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuple slot means EOF. + * + * For asynchronous nodes, if clear tuple slot is returned, the caller + * needs to check asyncstate to tell if all tuples received (AS_AVAILABLE) + * or waiting for the next data to come (AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* finish the running query before sending command for this node */ + if (!fsstate->s.commonstate->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* Fetch the result immediately. */ + fetch_received_data(node); + } + else if (!fsstate->s.commonstate->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* The connection is busy */ + bool available = true; + ForeignScanState *leader = fsstate->s.commonstate->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* Check if the result is immediately available */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* Fetch the leader's data if any */ + if (available) + fetch_received_data(leader); + + /* queue the requested node */ + add_async_waiter(node); + + /* queue the previous leader for the next request if needed */ + add_async_waiter(leader); + } + } - /* - * Get some more tuples, if we've run out. - */ if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + /* + * We haven't received a result for the given node this time, return + * with no tuple to give way to another node. + */ + if (fsstate->eof_reached) + { + fsstate->result_ready = true; + node->ss.ps.asyncstate = AS_AVAILABLE; + } + else + { + fsstate->result_ready = false; + node->ss.ps.asyncstate = AS_WAITING; + } + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + fsstate->result_ready = true; + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1796,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1804,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1834,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1854,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1862,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2651,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2738,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2789,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2988,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnCommonState *commonstate; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3033,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + commonstate = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnCommonState)); + if (commonstate) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.commonstate = commonstate; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3615,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3682,127 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.commonstate->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.commonstate->busy); + /* must be not-eof */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.commonstate->busy = true; + + /* Let the node be the leader if it is different from current one */ + if (leader != node) + { + /* + * If the connection leader exists, insert the node as the connection + * leader making the current leader be the first waiter. + */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.commonstate->leader = node; + } +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.commonstate->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* move the remaining tuples to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; char sql[64]; - int numrows; + int addrows; + size_t newsize; int i; snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", fsstate->fetch_size, fsstate->cursor_number); - res = pgfdw_exec_query(conn, sql); + res = pgfdw_get_result(conn, sql); /* On error, report the original query, not the FETCH. */ if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3812,75 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); + + PQclear(res); + res = NULL; } PG_FINALLY(); { + fsstate->s.commonstate->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + fsstate->s.commonstate->busy = false; + + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate a connection so that this node can send the next query + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnCommonState *commonstate = fdwstate->commonstate; + ForeignScanState *leader; + + /* the connection is alrady available */ + if (commonstate == NULL || commonstate->leader == NULL || !commonstate->busy) + return; + + /* + * let the current connection leader read the result for the running query + */ + leader = commonstate->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +3994,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.commonstate = (PgFdwConnCommonState *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnCommonState)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4083,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4113,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4128,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4167,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4177,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4190,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4321,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4489,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4499,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +5993,40 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add wait event so that the ForeignScan node is going to wait for. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* Reinit is not supported for now. */ + Assert(reinit); + + if (fsstate->s.commonstate->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index eef410db39..96af75a33e 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 83971665e3..359208a12a 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1780,25 +1780,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1840,12 +1840,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1904,8 +1904,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.18.2 ----Next_Part(Fri_Feb_28_17_06_50_2020_928)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* [PATCH v1 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Kyotaro Horiguchi @ 2017-10-19 08:24 UTC (permalink / raw) --- contrib/postgres_fdw/connection.c | 26 + .../postgres_fdw/expected/postgres_fdw.out | 222 ++++--- contrib/postgres_fdw/postgres_fdw.c | 615 ++++++++++++++++-- contrib/postgres_fdw/postgres_fdw.h | 2 + contrib/postgres_fdw/sql/postgres_fdw.sql | 20 +- 5 files changed, 711 insertions(+), 174 deletions(-) diff --git a/contrib/postgres_fdw/connection.c b/contrib/postgres_fdw/connection.c index 27b86a03f8..1afd99cad8 100644 --- a/contrib/postgres_fdw/connection.c +++ b/contrib/postgres_fdw/connection.c @@ -56,6 +56,7 @@ typedef struct ConnCacheEntry bool invalidated; /* true if reconnect is pending */ uint32 server_hashvalue; /* hash value of foreign server OID */ uint32 mapping_hashvalue; /* hash value of user mapping OID */ + void *storage; /* connection specific storage */ } ConnCacheEntry; /* @@ -200,6 +201,7 @@ GetConnection(UserMapping *user, bool will_prep_stmt) elog(DEBUG3, "new postgres_fdw connection %p for server \"%s\" (user mapping oid %u, userid %u)", entry->conn, server->servername, user->umid, user->userid); + entry->storage = NULL; } /* @@ -213,6 +215,30 @@ GetConnection(UserMapping *user, bool will_prep_stmt) return entry->conn; } +/* + * Rerturns the connection specific storage for this user. Allocate with + * initsize if not exists. + */ +void * +GetConnectionSpecificStorage(UserMapping *user, size_t initsize) +{ + bool found; + ConnCacheEntry *entry; + ConnCacheKey key; + + key = user->umid; + entry = hash_search(ConnectionHash, &key, HASH_ENTER, &found); + Assert(found); + + if (entry->storage == NULL) + { + entry->storage = MemoryContextAlloc(CacheMemoryContext, initsize); + memset(entry->storage, 0, initsize); + } + + return entry->storage; +} + /* * Connect to remote server using specified server and user mapping properties. */ diff --git a/contrib/postgres_fdw/expected/postgres_fdw.out b/contrib/postgres_fdw/expected/postgres_fdw.out index 48282ab151..bd2e835d2d 100644 --- a/contrib/postgres_fdw/expected/postgres_fdw.out +++ b/contrib/postgres_fdw/expected/postgres_fdw.out @@ -6900,7 +6900,7 @@ INSERT INTO a(aa) VALUES('aaaaa'); INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+------- a | aaa @@ -6928,7 +6928,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -6956,7 +6956,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | aaa @@ -6984,7 +6984,7 @@ SELECT tableoid::regclass, * FROM ONLY a; (3 rows) UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; tableoid | aa ----------+-------- a | newtoo @@ -7054,35 +7054,41 @@ insert into bar2 values(3,33,33); insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for update; + QUERY PLAN +----------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar.f1, bar.f2, bar.ctid, bar.*, bar.tableoid + Sort Key: bar.f1 + -> Seq Scan on public.bar + Output: bar.f1, bar.f2, bar.ctid, bar.*, bar.tableoid -> Foreign Scan on public.bar2 bar_1 Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR UPDATE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR UPDATE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo - Output: foo.ctid, foo.f1, foo.*, foo.tableoid - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_1 Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo + Output: foo.ctid, foo.f1, foo.*, foo.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; f1 | f2 ----+---- 1 | 11 @@ -7092,35 +7098,41 @@ select * from bar where f1 in (select f1 from foo) for update; (4 rows) explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; - QUERY PLAN ----------------------------------------------------------------------------------------------- +select * from bar where f1 in (select f1 from foo) order by 1 for share; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------- LockRows Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid - -> Hash Join + -> Merge Join Output: bar.f1, bar.f2, bar.ctid, foo.ctid, bar.*, bar.tableoid, foo.*, foo.tableoid Inner Unique: true - Hash Cond: (bar.f1 = foo.f1) - -> Append - -> Seq Scan on public.bar + Merge Cond: (bar.f1 = foo.f1) + -> Merge Append + Sort Key: bar.f1 + -> Sort Output: bar.f1, bar.f2, bar.ctid, bar.*, bar.tableoid + Sort Key: bar.f1 + -> Seq Scan on public.bar + Output: bar.f1, bar.f2, bar.ctid, bar.*, bar.tableoid -> Foreign Scan on public.bar2 bar_1 Output: bar_1.f1, bar_1.f2, bar_1.ctid, bar_1.*, bar_1.tableoid - Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 FOR SHARE - -> Hash + Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct2 ORDER BY f1 ASC NULLS LAST FOR SHARE + -> Sort Output: foo.ctid, foo.f1, foo.*, foo.tableoid + Sort Key: foo.f1 -> HashAggregate Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo - Output: foo.ctid, foo.f1, foo.*, foo.tableoid - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_1 Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(23 rows) + -> Seq Scan on public.foo + Output: foo.ctid, foo.f1, foo.*, foo.tableoid +(29 rows) -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; f1 | f2 ----+---- 1 | 11 @@ -7150,11 +7162,12 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo - Output: foo.ctid, foo.f1, foo.*, foo.tableoid - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_1 Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 + -> Seq Scan on public.foo + Output: foo.ctid, foo.f1, foo.*, foo.tableoid -> Hash Join Output: bar_1.f1, (bar_1.f2 + 100), bar_1.f3, bar_1.ctid, foo.ctid, foo.*, foo.tableoid Inner Unique: true @@ -7168,12 +7181,13 @@ update bar set f2 = f2 + 100 where f1 in (select f1 from foo); Output: foo.ctid, foo.f1, foo.*, foo.tableoid Group Key: foo.f1 -> Append - -> Seq Scan on public.foo - Output: foo.ctid, foo.f1, foo.*, foo.tableoid - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 1 + -> Async Foreign Scan on public.foo2 foo_1 Output: foo_1.ctid, foo_1.f1, foo_1.*, foo_1.tableoid Remote SQL: SELECT f1, f2, f3, ctid FROM public.loct1 -(39 rows) + -> Seq Scan on public.foo + Output: foo.ctid, foo.f1, foo.*, foo.tableoid +(41 rows) update bar set f2 = f2 + 100 where f1 in (select f1 from foo); select tableoid::regclass, * from bar order by 1,2; @@ -7203,16 +7217,17 @@ where bar.f1 = ss.f1; Output: bar.f1, (bar.f2 + 100), bar.ctid, (ROW(foo.f1)) Hash Cond: (foo.f1 = bar.f1) -> Append - -> Seq Scan on public.foo - Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 Output: ROW(foo_1.f1), foo_1.f1 Remote SQL: SELECT f1 FROM public.loct1 - -> Seq Scan on public.foo foo_2 - Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 + -> Async Foreign Scan on public.foo2 foo_3 Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) Remote SQL: SELECT f1 FROM public.loct1 + -> Seq Scan on public.foo + Output: ROW(foo.f1), foo.f1 + -> Seq Scan on public.foo foo_2 + Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) -> Hash Output: bar.f1, bar.f2, bar.ctid -> Seq Scan on public.bar @@ -7230,17 +7245,18 @@ where bar.f1 = ss.f1; Output: (ROW(foo.f1)), foo.f1 Sort Key: foo.f1 -> Append - -> Seq Scan on public.foo - Output: ROW(foo.f1), foo.f1 - -> Foreign Scan on public.foo2 foo_1 + Async subplans: 2 + -> Async Foreign Scan on public.foo2 foo_1 Output: ROW(foo_1.f1), foo_1.f1 Remote SQL: SELECT f1 FROM public.loct1 - -> Seq Scan on public.foo foo_2 - Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) - -> Foreign Scan on public.foo2 foo_3 + -> Async Foreign Scan on public.foo2 foo_3 Output: ROW((foo_3.f1 + 3)), (foo_3.f1 + 3) Remote SQL: SELECT f1 FROM public.loct1 -(45 rows) + -> Seq Scan on public.foo + Output: ROW(foo.f1), foo.f1 + -> Seq Scan on public.foo foo_2 + Output: ROW((foo_2.f1 + 3)), (foo_2.f1 + 3) +(47 rows) update bar set f2 = f2 + 100 from @@ -7390,27 +7406,33 @@ delete from foo where f1 < 5 returning *; (5 rows) explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; - QUERY PLAN ------------------------------------------------------------------------------- - Update on public.bar - Output: bar.f1, bar.f2 - Update on public.bar - Foreign Update on public.bar2 bar_1 - -> Seq Scan on public.bar - Output: bar.f1, (bar.f2 + 100), bar.ctid - -> Foreign Update on public.bar2 bar_1 - Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 -(8 rows) +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; + QUERY PLAN +-------------------------------------------------------------------------------------- + Sort + Output: u.f1, u.f2 + Sort Key: u.f1 + CTE u + -> Update on public.bar + Output: bar.f1, bar.f2 + Update on public.bar + Foreign Update on public.bar2 bar_1 + -> Seq Scan on public.bar + Output: bar.f1, (bar.f2 + 100), bar.ctid + -> Foreign Update on public.bar2 bar_1 + Remote SQL: UPDATE public.loct2 SET f2 = (f2 + 100) RETURNING f1, f2 + -> CTE Scan on u + Output: u.f1, u.f2 +(14 rows) -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; f1 | f2 ----+----- 1 | 311 2 | 322 - 6 | 266 3 | 333 4 | 344 + 6 | 266 7 | 277 (6 rows) @@ -8485,11 +8507,12 @@ SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER J Sort Sort Key: t1.a, t3.c -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: ((ftprt1_p1 t1) INNER JOIN (ftprt2_p1 t2)) INNER JOIN (ftprt1_p1 t3) - -> Foreign Scan + -> Async Foreign Scan Relations: ((ftprt1_p2 t1_1) INNER JOIN (ftprt2_p2 t2_1)) INNER JOIN (ftprt1_p2 t3_1) -(7 rows) +(8 rows) SELECT t1.a,t2.b,t3.c FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) INNER JOIN fprt1 t3 ON (t2.b = t3.a) WHERE t1.a % 25 =0 ORDER BY 1,2,3; a | b | c @@ -8524,20 +8547,22 @@ SELECT t1.a,t2.b,t2.c FROM fprt1 t1 LEFT JOIN (SELECT * FROM fprt2 WHERE a < 10) -- with whole-row reference; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; - QUERY PLAN --------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------- Sort Sort Key: ((t1.*)::fprt1), ((t2.*)::fprt2) -> Hash Full Join Hash Cond: (t1.a = t2.b) -> Append - -> Foreign Scan on ftprt1_p1 t1 - -> Foreign Scan on ftprt1_p2 t1_1 + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1 + -> Async Foreign Scan on ftprt1_p2 t1_1 -> Hash -> Append - -> Foreign Scan on ftprt2_p1 t2 - -> Foreign Scan on ftprt2_p2 t2_1 -(11 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2 + -> Async Foreign Scan on ftprt2_p2 t2_1 +(13 rows) SELECT t1.wr, t2.wr FROM (SELECT t1 wr, a FROM fprt1 t1 WHERE t1.a % 25 = 0) t1 FULL JOIN (SELECT t2 wr, b FROM fprt2 t2 WHERE t2.b % 25 = 0) t2 ON (t1.a = t2.b) ORDER BY 1,2; wr | wr @@ -8566,11 +8591,12 @@ SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t Sort Sort Key: t1.a, t1.b -> Append - -> Foreign Scan + Async subplans: 2 + -> Async Foreign Scan Relations: (ftprt1_p1 t1) INNER JOIN (ftprt2_p1 t2) - -> Foreign Scan + -> Async Foreign Scan Relations: (ftprt1_p2 t1_1) INNER JOIN (ftprt2_p2 t2_1) -(7 rows) +(8 rows) SELECT t1.a,t1.b FROM fprt1 t1, LATERAL (SELECT t2.a, t2.b FROM fprt2 t2 WHERE t1.a = t2.b AND t1.b = t2.a) q WHERE t1.a%25 = 0 ORDER BY 1,2; a | b @@ -8623,21 +8649,23 @@ SELECT t1.a, t1.phv, t2.b, t2.phv FROM (SELECT 't1_phv' phv, * FROM fprt1 WHERE -- test FOR UPDATE; partitionwise join does not apply EXPLAIN (COSTS OFF) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; - QUERY PLAN --------------------------------------------------------------- + QUERY PLAN +-------------------------------------------------------------------- LockRows -> Sort Sort Key: t1.a -> Hash Join Hash Cond: (t2.b = t1.a) -> Append - -> Foreign Scan on ftprt2_p1 t2 - -> Foreign Scan on ftprt2_p2 t2_1 + Async subplans: 2 + -> Async Foreign Scan on ftprt2_p1 t2 + -> Async Foreign Scan on ftprt2_p2 t2_1 -> Hash -> Append - -> Foreign Scan on ftprt1_p1 t1 - -> Foreign Scan on ftprt1_p2 t1_1 -(12 rows) + Async subplans: 2 + -> Async Foreign Scan on ftprt1_p1 t1 + -> Async Foreign Scan on ftprt1_p2 t1_1 +(14 rows) SELECT t1.a, t2.b FROM fprt1 t1 INNER JOIN fprt2 t2 ON (t1.a = t2.b) WHERE t1.a % 25 = 0 ORDER BY 1,2 FOR UPDATE OF t1; a | b @@ -8672,18 +8700,19 @@ ANALYZE fpagg_tab_p3; SET enable_partitionwise_aggregate TO false; EXPLAIN (COSTS OFF) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; - QUERY PLAN ------------------------------------------------------------ + QUERY PLAN +----------------------------------------------------------------- Sort Sort Key: pagg_tab.a -> HashAggregate Group Key: pagg_tab.a Filter: (avg(pagg_tab.b) < '22'::numeric) -> Append - -> Foreign Scan on fpagg_tab_p1 pagg_tab - -> Foreign Scan on fpagg_tab_p2 pagg_tab_1 - -> Foreign Scan on fpagg_tab_p3 pagg_tab_2 -(9 rows) + Async subplans: 3 + -> Async Foreign Scan on fpagg_tab_p1 pagg_tab + -> Async Foreign Scan on fpagg_tab_p2 pagg_tab_1 + -> Async Foreign Scan on fpagg_tab_p3 pagg_tab_2 +(10 rows) -- Plan with partitionwise aggregates is enabled SET enable_partitionwise_aggregate TO true; @@ -8694,13 +8723,14 @@ SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 O Sort Sort Key: pagg_tab.a -> Append - -> Foreign Scan + Async subplans: 3 + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p1 pagg_tab) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p2 pagg_tab_1) - -> Foreign Scan + -> Async Foreign Scan Relations: Aggregate on (fpagg_tab_p3 pagg_tab_2) -(9 rows) +(10 rows) SELECT a, sum(b), min(b), count(*) FROM pagg_tab GROUP BY a HAVING avg(b) < 22 ORDER BY 1; a | sum | min | count diff --git a/contrib/postgres_fdw/postgres_fdw.c b/contrib/postgres_fdw/postgres_fdw.c index bdc21b36d1..f3212aac90 100644 --- a/contrib/postgres_fdw/postgres_fdw.c +++ b/contrib/postgres_fdw/postgres_fdw.c @@ -21,6 +21,8 @@ #include "commands/defrem.h" #include "commands/explain.h" #include "commands/vacuum.h" +#include "executor/execAsync.h" +#include "executor/nodeForeignscan.h" #include "foreign/fdwapi.h" #include "funcapi.h" #include "miscadmin.h" @@ -35,6 +37,7 @@ #include "optimizer/restrictinfo.h" #include "optimizer/tlist.h" #include "parser/parsetree.h" +#include "pgstat.h" #include "postgres_fdw.h" #include "utils/builtins.h" #include "utils/float.h" @@ -56,6 +59,9 @@ PG_MODULE_MAGIC; /* If no remote estimates, assume a sort costs 20% extra */ #define DEFAULT_FDW_SORT_MULTIPLIER 1.2 +/* Retrive PgFdwScanState struct from ForeginScanState */ +#define GetPgFdwScanState(n) ((PgFdwScanState *)(n)->fdw_state) + /* * Indexes of FDW-private information stored in fdw_private lists. * @@ -122,11 +128,28 @@ enum FdwDirectModifyPrivateIndex FdwDirectModifyPrivateSetProcessed }; +/* + * Connection private area structure. + */ +typedef struct PgFdwConnpriv +{ + ForeignScanState *leader; /* leader node of this connection */ + bool busy; /* true if this connection is busy */ +} PgFdwConnpriv; + +/* Execution state base type */ +typedef struct PgFdwState +{ + PGconn *conn; /* connection for the scan */ + PgFdwConnpriv *connpriv; /* connection private memory */ +} PgFdwState; + /* * Execution state of a foreign scan using postgres_fdw. */ typedef struct PgFdwScanState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table. NULL * for a foreign join scan. */ TupleDesc tupdesc; /* tuple descriptor of scan */ @@ -137,7 +160,7 @@ typedef struct PgFdwScanState List *retrieved_attrs; /* list of retrieved attribute numbers */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ + bool result_ready; unsigned int cursor_number; /* quasi-unique ID for my cursor */ bool cursor_exists; /* have we created the cursor? */ int numParams; /* number of parameters passed to query */ @@ -153,6 +176,12 @@ typedef struct PgFdwScanState /* batch-level state, for optimizing rewinds and avoiding useless fetch */ int fetch_ct_2; /* Min(# of fetches done, 2) */ bool eof_reached; /* true if last fetch reached EOF */ + bool run_async; /* true if run asynchronously */ + bool inqueue; /* true if this node is in waiter queue */ + ForeignScanState *waiter; /* Next node to run a query among nodes + * sharing the same connection */ + ForeignScanState *last_waiter; /* last waiting node in waiting queue. + * valid only on the leader node */ /* working memory contexts */ MemoryContext batch_cxt; /* context holding current batch of tuples */ @@ -166,11 +195,11 @@ typedef struct PgFdwScanState */ typedef struct PgFdwModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ /* for remote query execution */ - PGconn *conn; /* connection for the scan */ char *p_name; /* name of prepared statement, if created */ /* extracted fdw_private data */ @@ -197,6 +226,7 @@ typedef struct PgFdwModifyState */ typedef struct PgFdwDirectModifyState { + PgFdwState s; /* common structure */ Relation rel; /* relcache entry for the foreign table */ AttInMetadata *attinmeta; /* attribute datatype conversion metadata */ @@ -326,6 +356,7 @@ static void postgresBeginForeignScan(ForeignScanState *node, int eflags); static TupleTableSlot *postgresIterateForeignScan(ForeignScanState *node); static void postgresReScanForeignScan(ForeignScanState *node); static void postgresEndForeignScan(ForeignScanState *node); +static void postgresShutdownForeignScan(ForeignScanState *node); static void postgresAddForeignUpdateTargets(Query *parsetree, RangeTblEntry *target_rte, Relation target_relation); @@ -391,6 +422,10 @@ static void postgresGetForeignUpperPaths(PlannerInfo *root, RelOptInfo *input_rel, RelOptInfo *output_rel, void *extra); +static bool postgresIsForeignPathAsyncCapable(ForeignPath *path); +static bool postgresForeignAsyncConfigureWait(ForeignScanState *node, + WaitEventSet *wes, + void *caller_data, bool reinit); /* * Helper functions @@ -419,7 +454,9 @@ static bool ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, EquivalenceClass *ec, EquivalenceMember *em, void *arg); static void create_cursor(ForeignScanState *node); -static void fetch_more_data(ForeignScanState *node); +static void request_more_data(ForeignScanState *node); +static void fetch_received_data(ForeignScanState *node); +static void vacate_connection(PgFdwState *fdwconn, bool clear_queue); static void close_cursor(PGconn *conn, unsigned int cursor_number); static PgFdwModifyState *create_foreign_modify(EState *estate, RangeTblEntry *rte, @@ -522,6 +559,7 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) routine->IterateForeignScan = postgresIterateForeignScan; routine->ReScanForeignScan = postgresReScanForeignScan; routine->EndForeignScan = postgresEndForeignScan; + routine->ShutdownForeignScan = postgresShutdownForeignScan; /* Functions for updating foreign tables */ routine->AddForeignUpdateTargets = postgresAddForeignUpdateTargets; @@ -558,6 +596,10 @@ postgres_fdw_handler(PG_FUNCTION_ARGS) /* Support functions for upper relation push-down */ routine->GetForeignUpperPaths = postgresGetForeignUpperPaths; + /* Support functions for async execution */ + routine->IsForeignPathAsyncCapable = postgresIsForeignPathAsyncCapable; + routine->ForeignAsyncConfigureWait = postgresForeignAsyncConfigureWait; + PG_RETURN_POINTER(routine); } @@ -1434,12 +1476,22 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - fsstate->conn = GetConnection(user, false); + fsstate->s.conn = GetConnection(user, false); + fsstate->s.connpriv = (PgFdwConnpriv *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnpriv)); + fsstate->s.connpriv->leader = NULL; + fsstate->s.connpriv->busy = false; + fsstate->waiter = NULL; + fsstate->last_waiter = node; /* Assign a unique ID for my cursor */ - fsstate->cursor_number = GetCursorNumber(fsstate->conn); + fsstate->cursor_number = GetCursorNumber(fsstate->s.conn); fsstate->cursor_exists = false; + /* Initialize async execution status */ + fsstate->run_async = false; + fsstate->inqueue = false; + /* Get private info created by planner functions. */ fsstate->query = strVal(list_nth(fsplan->fdw_private, FdwScanPrivateSelectSql)); @@ -1487,40 +1539,259 @@ postgresBeginForeignScan(ForeignScanState *node, int eflags) &fsstate->param_values); } +/* + * Async queue manipuration functions + */ + +/* + * add_async_waiter: + * + * adds the node to the end of waiter queue. Immediately starts the node if no + * node is running + */ +static inline void +add_async_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.connpriv->leader; + + /* do nothing if the node is already in the queue or already eof'ed */ + if (leader == node || fsstate->inqueue || fsstate->eof_reached) + return; + + if (leader == NULL) + { + /* immediately send request if not busy */ + request_more_data(node); + } + else + { + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PgFdwScanState *last_waiter_state + = GetPgFdwScanState(leader_state->last_waiter); + + last_waiter_state->waiter = node; + leader_state->last_waiter = node; + fsstate->inqueue = true; + } +} + +/* + * move_to_next_waiter: + * + * Makes the first waiter be next leader + * Returns the new leader or NULL if there's no waiter. + */ +static inline ForeignScanState * +move_to_next_waiter(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *ret = fsstate->waiter; + + Assert(fsstate->s.connpriv->leader = node); + + if (ret) + { + PgFdwScanState *retstate = GetPgFdwScanState(ret); + fsstate->waiter = NULL; + retstate->last_waiter = fsstate->last_waiter; + retstate->inqueue = false; + } + + fsstate->s.connpriv->leader = ret; + + return ret; +} + +/* + * remove the node from waiter queue + * + * This is a bit different from the two above in the sense that this can + * operate on connection leader. The result is absorbed when this is called on + * active leader. + * + * Returns true if the node was found. + */ +static inline bool +remove_async_node(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.connpriv->leader; + PgFdwScanState *leader_state; + ForeignScanState *prev; + PgFdwScanState *prev_state; + ForeignScanState *cur; + + /* no need to remove me */ + if (!leader || !fsstate->inqueue) + return false; + + leader_state = GetPgFdwScanState(leader); + + /* Remove the leader node */ + if (leader == node) + { + ForeignScanState *next_leader; + + if (leader_state->s.connpriv->busy) + { + /* + * this node is waiting for result, absorb the result first so + * that the following commands can be sent on the connection. + */ + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + PGconn *conn = leader_state->s.conn; + + while(PQisBusy(conn)) + PQclear(PQgetResult(conn)); + + leader_state->s.connpriv->busy = false; + } + + /* Make the first waiter the leader */ + if (leader_state->waiter) + { + PgFdwScanState *next_leader_state; + + next_leader = leader_state->waiter; + next_leader_state = GetPgFdwScanState(next_leader); + + leader_state->s.connpriv->leader = next_leader; + next_leader_state->last_waiter = leader_state->last_waiter; + } + leader_state->waiter = NULL; + + return true; + } + + /* + * Just remove the node in queue + * + * This function is called on the shutdown path. We don't bother + * considering faster way to do this. + */ + prev = leader; + prev_state = leader_state; + cur = GetPgFdwScanState(prev)->waiter; + while (cur) + { + PgFdwScanState *curstate = GetPgFdwScanState(cur); + + if (cur == node) + { + prev_state->waiter = curstate->waiter; + if (leader_state->last_waiter == cur) + leader_state->last_waiter = prev; + else + leader_state->last_waiter = cur; + + fsstate->inqueue = false; + + return true; + } + prev = cur; + prev_state = curstate; + cur = curstate->waiter; + } + + return false; +} + /* * postgresIterateForeignScan - * Retrieve next row from the result set, or clear tuple slot to indicate - * EOF. + * Retrieve next row from the result set. + * + * For synchronous nodes, returns clear tuples slot to indicte EOF. + * + * If the node is asynchronous one, clear tuple slot has two meanings. + * If the caller receives clear tuple slot, asyncstate indicates wheter + * the node is EOF (AS_AVAILABLE) or waiting for data to + * come(AS_WAITING). */ static TupleTableSlot * postgresIterateForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); TupleTableSlot *slot = node->ss.ss_ScanTupleSlot; - /* - * If this is the first call after Begin or ReScan, we need to create the - * cursor on the remote side. - */ - if (!fsstate->cursor_exists) - create_cursor(node); + if (fsstate->next_tuple >= fsstate->num_tuples && !fsstate->eof_reached) + { + /* we've run out, get some more tuples */ + if (!node->fs_async) + { + /* finish running query to send my command */ + if (!fsstate->s.connpriv->busy) + vacate_connection((PgFdwState *)fsstate, false); + + request_more_data(node); + + /* + * Fetch the result immediately. This executes the next waiter if + * any. + */ + fetch_received_data(node); + } + else if (!fsstate->s.connpriv->busy) + { + /* If the connection is not busy, just send the request. */ + request_more_data(node); + } + else + { + /* This connection is busy */ + bool available = true; + ForeignScanState *leader = fsstate->s.connpriv->leader; + PgFdwScanState *leader_state = GetPgFdwScanState(leader); + + /* Check if the result is immediately available */ + if (PQisBusy(leader_state->s.conn)) + { + int rc = WaitLatchOrSocket(NULL, + WL_SOCKET_READABLE | WL_TIMEOUT | + WL_EXIT_ON_PM_DEATH, + PQsocket(leader_state->s.conn), 0, + WAIT_EVENT_ASYNC_WAIT); + if (!(rc & WL_SOCKET_READABLE)) + available = false; + } + + /* The next waiter is executed automatcically */ + if (available) + fetch_received_data(leader); + + /* add the requested node */ + add_async_waiter(node); + + /* add the previous leader */ + add_async_waiter(leader); + } + } /* - * Get some more tuples, if we've run out. + * If we haven't received a result for the given node this time, + * return with no tuple to give way to another node. */ if (fsstate->next_tuple >= fsstate->num_tuples) { - /* No point in another fetch if we already detected EOF, though. */ - if (!fsstate->eof_reached) - fetch_more_data(node); - /* If we didn't get any tuples, must be end of data. */ - if (fsstate->next_tuple >= fsstate->num_tuples) - return ExecClearTuple(slot); + if (fsstate->eof_reached) + { + fsstate->result_ready = true; + node->ss.ps.asyncstate = AS_AVAILABLE; + } + else + { + fsstate->result_ready = false; + node->ss.ps.asyncstate = AS_WAITING; + } + + return ExecClearTuple(slot); } /* * Return the next tuple. */ + fsstate->result_ready = true; + node->ss.ps.asyncstate = AS_AVAILABLE; ExecStoreHeapTuple(fsstate->tuples[fsstate->next_tuple++], slot, false); @@ -1535,7 +1806,7 @@ postgresIterateForeignScan(ForeignScanState *node) static void postgresReScanForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); char sql[64]; PGresult *res; @@ -1543,6 +1814,8 @@ postgresReScanForeignScan(ForeignScanState *node) if (!fsstate->cursor_exists) return; + vacate_connection((PgFdwState *)fsstate, true); + /* * If any internal parameters affecting this node have changed, we'd * better destroy and recreate the cursor. Otherwise, rewinding it should @@ -1571,9 +1844,9 @@ postgresReScanForeignScan(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fsstate->conn, sql); + res = pgfdw_exec_query(fsstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fsstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fsstate->s.conn, true, sql); PQclear(res); /* Now force a fresh FETCH. */ @@ -1591,7 +1864,7 @@ postgresReScanForeignScan(ForeignScanState *node) static void postgresEndForeignScan(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); /* if fsstate is NULL, we are in EXPLAIN; nothing to do */ if (fsstate == NULL) @@ -1599,15 +1872,31 @@ postgresEndForeignScan(ForeignScanState *node) /* Close the cursor if open, to prevent accumulation of cursors */ if (fsstate->cursor_exists) - close_cursor(fsstate->conn, fsstate->cursor_number); + close_cursor(fsstate->s.conn, fsstate->cursor_number); /* Release remote connection */ - ReleaseConnection(fsstate->conn); - fsstate->conn = NULL; + ReleaseConnection(fsstate->s.conn); + fsstate->s.conn = NULL; /* MemoryContexts will be deleted automatically. */ } +/* + * postgresShutdownForeignScan + * Remove asynchrony stuff and cleanup garbage on the connection. + */ +static void +postgresShutdownForeignScan(ForeignScanState *node) +{ + ForeignScan *plan = (ForeignScan *) node->ss.ps.plan; + + if (plan->operation != CMD_SELECT) + return; + + /* remove the node from waiting queue */ + remove_async_node(node); +} + /* * postgresAddForeignUpdateTargets * Add resjunk column(s) needed for update/delete on a foreign table @@ -2372,7 +2661,9 @@ postgresBeginDirectModify(ForeignScanState *node, int eflags) * Get connection to the foreign server. Connection manager will * establish new connection if necessary. */ - dmstate->conn = GetConnection(user, false); + dmstate->s.conn = GetConnection(user, false); + dmstate->s.connpriv = (PgFdwConnpriv *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnpriv)); /* Update the foreign-join-related fields. */ if (fsplan->scan.scanrelid == 0) @@ -2457,7 +2748,11 @@ postgresIterateDirectModify(ForeignScanState *node) * If this is the first call after Begin, execute the statement. */ if (dmstate->num_tuples == -1) + { + /* finish running query to send my command */ + vacate_connection((PgFdwState *)dmstate, true); execute_dml_stmt(node); + } /* * If the local query doesn't specify RETURNING, just clear tuple slot. @@ -2504,8 +2799,8 @@ postgresEndDirectModify(ForeignScanState *node) PQclear(dmstate->result); /* Release remote connection */ - ReleaseConnection(dmstate->conn); - dmstate->conn = NULL; + ReleaseConnection(dmstate->s.conn); + dmstate->s.conn = NULL; /* MemoryContext will be deleted automatically. */ } @@ -2703,6 +2998,7 @@ estimate_path_cost_size(PlannerInfo *root, List *local_param_join_conds; StringInfoData sql; PGconn *conn; + PgFdwConnpriv *connpriv; Selectivity local_sel; QualCost local_cost; List *fdw_scan_tlist = NIL; @@ -2747,6 +3043,18 @@ estimate_path_cost_size(PlannerInfo *root, /* Get the remote estimate */ conn = GetConnection(fpinfo->user, false); + connpriv = GetConnectionSpecificStorage(fpinfo->user, + sizeof(PgFdwConnpriv)); + if (connpriv) + { + PgFdwState tmpstate; + tmpstate.conn = conn; + tmpstate.connpriv = connpriv; + + /* finish running query to send my command */ + vacate_connection(&tmpstate, true); + } + get_remote_estimate(sql.data, conn, &rows, &width, &startup_cost, &total_cost); ReleaseConnection(conn); @@ -3317,11 +3625,11 @@ ec_member_matches_foreign(PlannerInfo *root, RelOptInfo *rel, static void create_cursor(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); ExprContext *econtext = node->ss.ps.ps_ExprContext; int numParams = fsstate->numParams; const char **values = fsstate->param_values; - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; StringInfoData buf; PGresult *res; @@ -3384,50 +3692,127 @@ create_cursor(ForeignScanState *node) } /* - * Fetch some more rows from the node's cursor. + * Sends the next request of the node. If the given node is different from the + * current connection leader, pushes it back to waiter queue and let the given + * node be the leader. */ static void -fetch_more_data(ForeignScanState *node) +request_more_data(ForeignScanState *node) { - PgFdwScanState *fsstate = (PgFdwScanState *) node->fdw_state; + PgFdwScanState *fsstate = GetPgFdwScanState(node); + ForeignScanState *leader = fsstate->s.connpriv->leader; + PGconn *conn = fsstate->s.conn; + char sql[64]; + + /* must be non-busy */ + Assert(!fsstate->s.connpriv->busy); + /* must be not-eof */ + Assert(!fsstate->eof_reached); + + /* + * If this is the first call after Begin or ReScan, we need to create the + * cursor on the remote side. + */ + if (!fsstate->cursor_exists) + create_cursor(node); + + snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", + fsstate->fetch_size, fsstate->cursor_number); + + if (!PQsendQuery(conn, sql)) + pgfdw_report_error(ERROR, NULL, conn, false, sql); + + fsstate->s.connpriv->busy = true; + + /* Let the node be the leader if it is different from current one */ + if (leader != node) + { + /* + * If the connection leader exists, insert the node as the connection + * leader making the current leader be the first waiter. + */ + if (leader != NULL) + { + remove_async_node(node); + fsstate->last_waiter = GetPgFdwScanState(leader)->last_waiter; + fsstate->waiter = leader; + } + else + { + fsstate->last_waiter = node; + fsstate->waiter = NULL; + } + + fsstate->s.connpriv->leader = node; + } +} + +/* + * Fetches received data and automatically send requests of the next waiter. + */ +static void +fetch_received_data(ForeignScanState *node) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); PGresult *volatile res = NULL; MemoryContext oldcontext; + ForeignScanState *waiter; + + /* I should be the current connection leader */ + Assert(fsstate->s.connpriv->leader == node); /* * We'll store the tuples in the batch_cxt. First, flush the previous - * batch. + * batch if no tuple is remaining */ - fsstate->tuples = NULL; - MemoryContextReset(fsstate->batch_cxt); + if (fsstate->next_tuple >= fsstate->num_tuples) + { + fsstate->tuples = NULL; + fsstate->num_tuples = 0; + MemoryContextReset(fsstate->batch_cxt); + } + else if (fsstate->next_tuple > 0) + { + /* move the remaining tuples to the beginning of the store */ + int n = 0; + + while(fsstate->next_tuple < fsstate->num_tuples) + fsstate->tuples[n++] = fsstate->tuples[fsstate->next_tuple++]; + fsstate->num_tuples = n; + } + oldcontext = MemoryContextSwitchTo(fsstate->batch_cxt); /* PGresult must be released before leaving this function. */ PG_TRY(); { - PGconn *conn = fsstate->conn; + PGconn *conn = fsstate->s.conn; char sql[64]; - int numrows; + int addrows; + size_t newsize; int i; snprintf(sql, sizeof(sql), "FETCH %d FROM c%u", fsstate->fetch_size, fsstate->cursor_number); - res = pgfdw_exec_query(conn, sql); + res = pgfdw_get_result(conn, sql); /* On error, report the original query, not the FETCH. */ if (PQresultStatus(res) != PGRES_TUPLES_OK) pgfdw_report_error(ERROR, res, conn, false, fsstate->query); /* Convert the data into HeapTuples */ - numrows = PQntuples(res); - fsstate->tuples = (HeapTuple *) palloc0(numrows * sizeof(HeapTuple)); - fsstate->num_tuples = numrows; - fsstate->next_tuple = 0; + addrows = PQntuples(res); + newsize = (fsstate->num_tuples + addrows) * sizeof(HeapTuple); + if (fsstate->tuples) + fsstate->tuples = (HeapTuple *) repalloc(fsstate->tuples, newsize); + else + fsstate->tuples = (HeapTuple *) palloc(newsize); - for (i = 0; i < numrows; i++) + for (i = 0; i < addrows; i++) { Assert(IsA(node->ss.ps.plan, ForeignScan)); - fsstate->tuples[i] = + fsstate->tuples[fsstate->num_tuples + i] = make_tuple_from_result_row(res, i, fsstate->rel, fsstate->attinmeta, @@ -3437,22 +3822,75 @@ fetch_more_data(ForeignScanState *node) } /* Update fetch_ct_2 */ - if (fsstate->fetch_ct_2 < 2) + if (fsstate->fetch_ct_2 < 2 && fsstate->next_tuple == 0) fsstate->fetch_ct_2++; + fsstate->next_tuple = 0; + fsstate->num_tuples += addrows; + /* Must be EOF if we didn't get as many tuples as we asked for. */ - fsstate->eof_reached = (numrows < fsstate->fetch_size); + fsstate->eof_reached = (addrows < fsstate->fetch_size); + + PQclear(res); + res = NULL; } PG_FINALLY(); { + fsstate->s.connpriv->busy = false; + if (res) PQclear(res); } PG_END_TRY(); + fsstate->s.connpriv->busy = false; + + /* let the first waiter be the next leader of this connection */ + waiter = move_to_next_waiter(node); + + /* send the next request if any */ + if (waiter) + request_more_data(waiter); + MemoryContextSwitchTo(oldcontext); } +/* + * Vacate a connection so that this node can send the next query + */ +static void +vacate_connection(PgFdwState *fdwstate, bool clear_queue) +{ + PgFdwConnpriv *connpriv = fdwstate->connpriv; + ForeignScanState *leader; + + /* the connection is alrady available */ + if (connpriv == NULL || connpriv->leader == NULL || !connpriv->busy) + return; + + /* + * let the current connection leader read the result for the running query + */ + leader = connpriv->leader; + fetch_received_data(leader); + + /* let the first waiter be the next leader of this connection */ + move_to_next_waiter(leader); + + if (!clear_queue) + return; + + /* Clear the waiting list */ + while (leader) + { + PgFdwScanState *fsstate = GetPgFdwScanState(leader); + + fsstate->last_waiter = NULL; + leader = fsstate->waiter; + fsstate->waiter = NULL; + } +} + /* * Force assorted GUC parameters to settings that ensure that we'll output * data values in a form that is unambiguous to the remote server. @@ -3566,7 +4004,9 @@ create_foreign_modify(EState *estate, user = GetUserMapping(userid, table->serverid); /* Open connection; report that we'll create a prepared statement. */ - fmstate->conn = GetConnection(user, true); + fmstate->s.conn = GetConnection(user, true); + fmstate->s.connpriv = (PgFdwConnpriv *) + GetConnectionSpecificStorage(user, sizeof(PgFdwConnpriv)); fmstate->p_name = NULL; /* prepared statement not made yet */ /* Set up remote query information. */ @@ -3653,6 +4093,9 @@ execute_foreign_modify(EState *estate, operation == CMD_UPDATE || operation == CMD_DELETE); + /* finish running query to send my command */ + vacate_connection((PgFdwState *)fmstate, true); + /* Set up the prepared statement on the remote server, if we didn't yet */ if (!fmstate->p_name) prepare_foreign_modify(fmstate); @@ -3680,14 +4123,14 @@ execute_foreign_modify(EState *estate, /* * Execute the prepared statement. */ - if (!PQsendQueryPrepared(fmstate->conn, + if (!PQsendQueryPrepared(fmstate->s.conn, fmstate->p_name, fmstate->p_nums, p_values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3695,10 +4138,10 @@ execute_foreign_modify(EState *estate, * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != (fmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); /* Check number of rows affected, and fetch RETURNING tuple if any */ if (fmstate->has_returning) @@ -3734,7 +4177,7 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) /* Construct name we'll use for the prepared statement. */ snprintf(prep_name, sizeof(prep_name), "pgsql_fdw_prep_%u", - GetPrepStmtNumber(fmstate->conn)); + GetPrepStmtNumber(fmstate->s.conn)); p_name = pstrdup(prep_name); /* @@ -3744,12 +4187,12 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * the prepared statements we use in this module are simple enough that * the remote server will make the right choices. */ - if (!PQsendPrepare(fmstate->conn, + if (!PQsendPrepare(fmstate->s.conn, p_name, fmstate->query, 0, NULL)) - pgfdw_report_error(ERROR, NULL, fmstate->conn, false, fmstate->query); + pgfdw_report_error(ERROR, NULL, fmstate->s.conn, false, fmstate->query); /* * Get the result, and check for success. @@ -3757,9 +4200,9 @@ prepare_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_get_result(fmstate->conn, fmstate->query); + res = pgfdw_get_result(fmstate->s.conn, fmstate->query); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, fmstate->query); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, fmstate->query); PQclear(res); /* This action shows that the prepare has been done. */ @@ -3888,16 +4331,16 @@ finish_foreign_modify(PgFdwModifyState *fmstate) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - res = pgfdw_exec_query(fmstate->conn, sql); + res = pgfdw_exec_query(fmstate->s.conn, sql); if (PQresultStatus(res) != PGRES_COMMAND_OK) - pgfdw_report_error(ERROR, res, fmstate->conn, true, sql); + pgfdw_report_error(ERROR, res, fmstate->s.conn, true, sql); PQclear(res); fmstate->p_name = NULL; } /* Release remote connection */ - ReleaseConnection(fmstate->conn); - fmstate->conn = NULL; + ReleaseConnection(fmstate->s.conn); + fmstate->s.conn = NULL; } /* @@ -4056,9 +4499,9 @@ execute_dml_stmt(ForeignScanState *node) * the desired result. This allows us to avoid assuming that the remote * server has the same OIDs we do for the parameters' types. */ - if (!PQsendQueryParams(dmstate->conn, dmstate->query, numParams, + if (!PQsendQueryParams(dmstate->s.conn, dmstate->query, numParams, NULL, values, NULL, NULL, 0)) - pgfdw_report_error(ERROR, NULL, dmstate->conn, false, dmstate->query); + pgfdw_report_error(ERROR, NULL, dmstate->s.conn, false, dmstate->query); /* * Get the result, and check for success. @@ -4066,10 +4509,10 @@ execute_dml_stmt(ForeignScanState *node) * We don't use a PG_TRY block here, so be careful not to throw error * without releasing the PGresult. */ - dmstate->result = pgfdw_get_result(dmstate->conn, dmstate->query); + dmstate->result = pgfdw_get_result(dmstate->s.conn, dmstate->query); if (PQresultStatus(dmstate->result) != (dmstate->has_returning ? PGRES_TUPLES_OK : PGRES_COMMAND_OK)) - pgfdw_report_error(ERROR, dmstate->result, dmstate->conn, true, + pgfdw_report_error(ERROR, dmstate->result, dmstate->s.conn, true, dmstate->query); /* Get the number of rows affected. */ @@ -5560,6 +6003,42 @@ postgresGetForeignJoinPaths(PlannerInfo *root, /* XXX Consider parameterized paths for the join relation */ } +static bool +postgresIsForeignPathAsyncCapable(ForeignPath *path) +{ + return true; +} + + +/* + * Configure waiting event. + * + * Add an wait event only when the node is the connection leader. Elsewise + * another node on this connection is the leader. + */ +static bool +postgresForeignAsyncConfigureWait(ForeignScanState *node, WaitEventSet *wes, + void *caller_data, bool reinit) +{ + PgFdwScanState *fsstate = GetPgFdwScanState(node); + + + /* If the caller didn't reinit, this event is already in event set */ + if (!reinit) + return true; + + if (fsstate->s.connpriv->leader == node) + { + AddWaitEventToSet(wes, + WL_SOCKET_READABLE, PQsocket(fsstate->s.conn), + NULL, caller_data); + return true; + } + + return false; +} + + /* * Assess whether the aggregation, grouping and having operations can be pushed * down to the foreign server. As a side effect, save information we obtain in diff --git a/contrib/postgres_fdw/postgres_fdw.h b/contrib/postgres_fdw/postgres_fdw.h index ea052872c3..696af73408 100644 --- a/contrib/postgres_fdw/postgres_fdw.h +++ b/contrib/postgres_fdw/postgres_fdw.h @@ -85,6 +85,7 @@ typedef struct PgFdwRelationInfo UserMapping *user; /* only set in use_remote_estimate mode */ int fetch_size; /* fetch size for this remote table */ + bool allow_prefetch; /* true to allow overlapped fetching */ /* * Name of the relation, for use while EXPLAINing ForeignScan. It is used @@ -130,6 +131,7 @@ extern void reset_transmission_modes(int nestlevel); /* in connection.c */ extern PGconn *GetConnection(UserMapping *user, bool will_prep_stmt); +void *GetConnectionSpecificStorage(UserMapping *user, size_t initsize); extern void ReleaseConnection(PGconn *conn); extern unsigned int GetCursorNumber(PGconn *conn); extern unsigned int GetPrepStmtNumber(PGconn *conn); diff --git a/contrib/postgres_fdw/sql/postgres_fdw.sql b/contrib/postgres_fdw/sql/postgres_fdw.sql index 1c5c37b783..69c06ac6e4 100644 --- a/contrib/postgres_fdw/sql/postgres_fdw.sql +++ b/contrib/postgres_fdw/sql/postgres_fdw.sql @@ -1730,25 +1730,25 @@ INSERT INTO b(aa) VALUES('bbb'); INSERT INTO b(aa) VALUES('bbbb'); INSERT INTO b(aa) VALUES('bbbbb'); -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'zzzzzz' WHERE aa LIKE 'aaaa%'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE b SET aa = 'new'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; UPDATE a SET aa = 'newtoo'; -SELECT tableoid::regclass, * FROM a; +SELECT tableoid::regclass, * FROM a ORDER BY 1, 2; SELECT tableoid::regclass, * FROM b; SELECT tableoid::regclass, * FROM ONLY a; @@ -1790,12 +1790,12 @@ insert into bar2 values(4,44,44); insert into bar2 values(7,77,77); explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for update; -select * from bar where f1 in (select f1 from foo) for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; +select * from bar where f1 in (select f1 from foo) order by 1 for update; explain (verbose, costs off) -select * from bar where f1 in (select f1 from foo) for share; -select * from bar where f1 in (select f1 from foo) for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; +select * from bar where f1 in (select f1 from foo) order by 1 for share; -- Check UPDATE with inherited target and an inherited source table explain (verbose, costs off) @@ -1854,8 +1854,8 @@ explain (verbose, costs off) delete from foo where f1 < 5 returning *; delete from foo where f1 < 5 returning *; explain (verbose, costs off) -update bar set f2 = f2 + 100 returning *; -update bar set f2 = f2 + 100 returning *; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; +with u as (update bar set f2 = f2 + 100 returning *) select * from u order by 1; -- Test that UPDATE/DELETE with inherited target works with row-level triggers CREATE TRIGGER trig_row_before -- 2.23.0 ----Next_Part(Fri_Dec__6_17_12_11_2019_974)---- ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-25 16:18 Vitaly Davydov <[email protected]> 0 siblings, 1 reply; 51+ messages in thread From: Vitaly Davydov @ 2024-12-25 16:18 UTC (permalink / raw) To: Michael Paquier <[email protected]>; +Cc: pgsql-hackers Hi Michael, Thank you for the explanation and the patch! I'm happy, that I seem to be on the right way. On Wednesday, December 25, 2024 08:04 MSK, Michael Paquier <[email protected]> wrote: > Vitaly, have you seen that in the wild as an effect of future 2PC files? I haven't heard about this problem in production, but I've encountered it when I did some development in two-phase functionality. I fixed it by swapping the if blocks and it solved my problem. It is pretty easy to reproduce it on the master branch: 1. Start an instance with enabled prepared transactions 2. Create a simple prepared transaction 3. Do checkpoint to write the transaction two-phase state into a file in pg_twophase subdirectory 4. Copy the created file, change its name to reflect a future xid (in my case: cp 00000000000002E8 00000000000FF2E8) 5. Commit the prepared transaction 6. Stop the instance with -m immediate 7. Start the instance After starting, you can get an error like "could not start server". In the log file you can find a message like: LOG: database system was not properly shut down; automatic recovery in progress FATAL: could not access status of transaction 1045224 DETAIL: Could not read from file "pg_xact/0000" at offset 253952: read too few bytes. 2024-12-25 18:38:30.606 MSK [795557] LOG: startup process (PID 795560) exited with exit code 1 I tried your patch and it seems the server is started successfully. But I've found another problem in my synthetic test - it can not remove the file with the following message: LOG: database system was not properly shut down; automatic recovery in progress WARNING: removing future two-phase state file for transaction 1045224 WARNING: could not remove file "pg_twophase/FFFFFFFF000FF2E8": No such file or directory LOG: redo starts at 0/1762978 The fill will never be removed automatically. I guess, it is because we incorrectly calculate the two-phase file name using TwoPhaseFilePath in RemoveTwoPhaseFile in this scenario. It can be fixed if to pass file path directly from RecoverPreparedTransactions or StandbyRecoverPreparedTransaction into ProcessTwoPhaseBuffer -> RemoveTwoPhaseFile. I did it in the proposed patch https://www.postgresql.org/message-id/cedbe-65e0c000-1-6db17700%40133269862 (it is incomplete now). With best regards, Vitaly ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-25 22:42 Michael Paquier <[email protected]> parent: Vitaly Davydov <[email protected]> 0 siblings, 1 reply; 51+ messages in thread From: Michael Paquier @ 2024-12-25 22:42 UTC (permalink / raw) To: Vitaly Davydov <[email protected]>; +Cc: pgsql-hackers On Wed, Dec 25, 2024 at 07:18:18PM +0300, Vitaly Davydov wrote: > I tried your patch and it seems the server is started > successfully. But I've found another problem in my synthetic test - > it can not remove the file with the following message: > > LOG: database system was not properly shut down; automatic recovery in progress > WARNING: removing future two-phase state file for transaction 1045224 > WARNING: could not remove file "pg_twophase/FFFFFFFF000FF2E8": No such file or directory > LOG: redo starts at 0/1762978 That works properly up to v16~. I have slept over this problem and I think that we'd better backpatch the fix for the first problem. Now, I also want to add a test to provide coverage. As you say, that's simple: - Create an empty file with a future XID name - Restart the server. - Scan the logs for the WARNING where the future file is removed. > The fill will never be removed automatically. > I guess, it is because we incorrectly calculate the two-phase file > name using TwoPhaseFilePath in RemoveTwoPhaseFile in this > scenario. It can be fixed if to pass file path directly from > RecoverPreparedTransactions or StandbyRecoverPreparedTransaction > into ProcessTwoPhaseBuffer -> RemoveTwoPhaseFile. Yeah, I've noticed that as well. We are dealing with a second bug that affects 17~ caused by the switch to FullTransactionIds for 2PC file names, which had been introduced in 5a1dfde8334b (pretty sure that it is the culprit, did not bisect). Attempting to remove a future file triggers an assertion failure: #3 0x00007fed046324f0 in __GI_abort () at ./stdlib/abort.c:79 #4 0x0000563e68a9bd07 in ExceptionalCondition (conditionName=0x563e68c66fc3 "epoch > 0", fileName=0x563e68c66b0b "twophase.c", lineNumber=953) at assert.c:66 #5 0x0000563e67683060 in AdjustToFullTransactionId (xid=4095) at twophase.c:953 #6 0x0000563e67683092 in TwoPhaseFilePath (path=0x7ffcb515b4a0 "h\307!\227>V", xid=4095) at twophase.c:963 #7 0x0000563e67686603 in RemoveTwoPhaseFile (xid=4095, giveWarning=true) at twophase.c:1728 #8 0x0000563e67688989 in ProcessTwoPhaseBuffer (xid=4095, prepare_start_lsn=0, fromdisk=true, setParent=false, setNextXid=false) at twophase.c:2219 #9 0x0000563e676872a6 in restoreTwoPhaseData () at twophase.c:1924 #10 0x0000563e676b5c8b in StartupXLOG () at xlog.c:5642 So this means that we are dealing with two different bugs, and that we need to fix the assertion failure of the second problem first down to 17, then fix the first problem on all stable branches with a test to cover both the first and second problems. > I did it in the proposed patch > https://www.postgresql.org/message-id/cedbe-65e0c000-1-6db17700%40133269862 > (it is incomplete now). I suspect that this can be still dangerous as-is while complicating the code with more possible paths for the removal of the 2PC files, because we may still build a file name from an XID, and that's what's causing this issue.. -- Michael Attachments: [application/pgp-signature] signature.asc (833B, ../../[email protected]/2-signature.asc) download ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-26 05:34 Michael Paquier <[email protected]> parent: Michael Paquier <[email protected]> 0 siblings, 1 reply; 51+ messages in thread From: Michael Paquier @ 2024-12-26 05:34 UTC (permalink / raw) To: Vitaly Davydov <[email protected]>; +Cc: pgsql-hackers On Thu, Dec 26, 2024 at 07:42:34AM +0900, Michael Paquier wrote: > I suspect that this can be still dangerous as-is while complicating > the code with more possible paths for the removal of the 2PC files, > because we may still build a file name from an XID, and that's what's > causing this issue.. Here are two patches to address both issues: - 0001 for the epoch calculation, down to 17, which would take care of the underflow problem when having a 2PC file that has an XID in the future at epoch 0. It is true that it could be smarter when dealing with files from other epochs, and that this is a problem in v17~. I think that this should integrate better with FullTransactionIds moving forward rather than pass the file names. That would be something quite invasive, only for HEAD. At least that's my impression. - 0002, to take care of the future file issue, down to 13. This includes a TAP test to demonstrate the problem. The test needs a tweak for the 2PC file name in v17~. -- Michael Attachments: [text/x-diff] v1-0001-Fix-failure-with-incorrect-epoch-for-future-2PC-f.patch (1.4K, ../../[email protected]/2-v1-0001-Fix-failure-with-incorrect-epoch-for-future-2PC-f.patch) download | inline diff: From d45d0c95a0ddee51563b5e94ea046ce4c5cf1baf Mon Sep 17 00:00:00 2001 From: Michael Paquier <[email protected]> Date: Thu, 26 Dec 2024 14:06:01 +0900 Subject: [PATCH v1 1/2] Fix failure with incorrect epoch for future 2PC files at recovery A two-phase file in the future would be able to trigger an assertion failure in AdjustToFullTransactionId() as the epoch counter would underflow if the checkpoint record uses an epoch of 0. In non-assert builds, this would create a WARNING message referring to a 2PC file with an epoch of "FFFFFFFF" (or UINT32_MAX), as an effect of the underflow calculation. Issue introduced by 5a1dfde8334b. Reported-by: Vitaly Davydov Discussion: https://postgr.es/m/13b5b6-676c3080-4d-531db900@47931709 Backpatch-through: 17 --- src/backend/access/transam/twophase.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index 49be1df91c..d2649264f9 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -947,10 +947,9 @@ AdjustToFullTransactionId(TransactionId xid) nextXid = XidFromFullTransactionId(nextFullXid); epoch = EpochFromFullTransactionId(nextFullXid); - if (unlikely(xid > nextXid)) + if (unlikely(xid > nextXid) && epoch > 0) { /* Wraparound occurred, must be from a prev epoch. */ - Assert(epoch > 0); epoch--; } -- 2.45.2 [text/x-diff] v1-0002-Fix-handling-of-orphaned-2PC-files-in-the-future-.patch (5.4K, ../../[email protected]/3-v1-0002-Fix-handling-of-orphaned-2PC-files-in-the-future-.patch) download | inline diff: From 31ebbadbca629abf8b7cf982d573ad2c838bf27f Mon Sep 17 00:00:00 2001 From: Michael Paquier <[email protected]> Date: Thu, 26 Dec 2024 14:15:51 +0900 Subject: [PATCH v1 2/2] Fix handling of orphaned 2PC files in the future at recovery Issue introduced by 728bd991c3c4, that has added support for 2PC files in shared memory at recovery. Before this feature was introduced, files in the future of the transaction ID horizon were checked first, followed by a check if a transaction ID is aborted or committed which could involve a pg_xact lookup. After this commit, these checks were done in a reversed order, but files in the future do not have a state that can be checked in pg_xact, hence this caused recovery to fail abruptly should an orphaned 2PC file in the future of the transaction horizon exist in pg_twophase at the beginning of recovery. A test is added to check this scenario, using an empty 2PC with a transaction ID large enough to be in the future when running the test. Author: Vitaly Davydov, Michael Paquier Discussion: https://postgr.es/m/11e597-676ab680-8d-374f23c0@145466129 Backpatch-through: 13 --- src/backend/access/transam/twophase.c | 40 ++++++++++----------- src/test/recovery/t/009_twophase.pl | 51 ++++++++++----------------- 2 files changed, 38 insertions(+), 53 deletions(-) diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index d2649264f9..4b5a3146f1 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -2205,26 +2205,6 @@ ProcessTwoPhaseBuffer(TransactionId xid, if (!fromdisk) Assert(prepare_start_lsn != InvalidXLogRecPtr); - /* Already processed? */ - if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) - { - if (fromdisk) - { - ereport(WARNING, - (errmsg("removing stale two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); - } - else - { - ereport(WARNING, - (errmsg("removing stale two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); - } - return NULL; - } - /* Reject XID if too new */ if (TransactionIdFollowsOrEquals(xid, origNextXid)) { @@ -2245,6 +2225,26 @@ ProcessTwoPhaseBuffer(TransactionId xid, return NULL; } + /* Already processed? */ + if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) + { + if (fromdisk) + { + ereport(WARNING, + (errmsg("removing stale two-phase state file for transaction %u", + xid))); + RemoveTwoPhaseFile(xid, true); + } + else + { + ereport(WARNING, + (errmsg("removing stale two-phase state from memory for transaction %u", + xid))); + PrepareRedoRemove(xid, true); + } + return NULL; + } + if (fromdisk) { /* Read and validate file */ diff --git a/src/test/recovery/t/009_twophase.pl b/src/test/recovery/t/009_twophase.pl index 4b3e0f77dc..854910ea68 100644 --- a/src/test/recovery/t/009_twophase.pl +++ b/src/test/recovery/t/009_twophase.pl @@ -534,42 +534,27 @@ is( $psql_out, qq{27|issued to paris}, "Check expected t_009_tbl2 data on standby"); +############################################################################### +# Check handling of orphaned 2PC files at recovery. +############################################################################### -# Exercise the 2PC recovery code in StartupSUBTRANS, which is concerned with -# ensuring that enough pg_subtrans pages exist on disk to cover the range of -# prepared transactions at server start time. There's not much we can verify -# directly, but let's at least get the code to run. -$cur_standby->stop(); -configure_and_reload($cur_primary, "synchronous_standby_names = ''"); +$cur_primary->teardown_node; -$cur_primary->safe_psql('postgres', "CHECKPOINT"); +# Grab location in logs of primary +my $log_offset = -s $cur_primary->logfile; + +# Create a fake file with a transaction ID large enough to be in the future, +# then check that the primary is able to start and remove this file at +# recovery. + +my $future_2pc_file = $cur_primary->data_dir . '/pg_twophase/0000000000FFFFFF'; +append_to_file $future_2pc_file, ""; -my $start_lsn = - $cur_primary->safe_psql('postgres', 'select pg_current_wal_insert_lsn()'); -$cur_primary->safe_psql('postgres', - "CREATE TABLE test(); BEGIN; CREATE TABLE test1(); PREPARE TRANSACTION 'foo';" -); -my $osubtrans = $cur_primary->safe_psql('postgres', - "select 'pg_subtrans/'||f, s.size from pg_ls_dir('pg_subtrans') f, pg_stat_file('pg_subtrans/'||f) s" -); -$cur_primary->pgbench( - '--no-vacuum --client=5 --transactions=1000', - 0, - [], - [], - 'pgbench run to cause pg_subtrans traffic', - { - '009_twophase.pgb' => 'insert into test default values' - }); -# StartupSUBTRANS is exercised with a wide range of visible XIDs in this -# stop/start sequence, because we left a prepared transaction open above. -# Also, setting subtransaction_buffers to 32 above causes to switch SLRU -# bank, for additional code coverage. -$cur_primary->stop; $cur_primary->start; -my $nsubtrans = $cur_primary->safe_psql('postgres', - "select 'pg_subtrans/'||f, s.size from pg_ls_dir('pg_subtrans') f, pg_stat_file('pg_subtrans/'||f) s" -); -isnt($osubtrans, $nsubtrans, "contents of pg_subtrans/ have changed"); +$cur_primary->log_check( + "future two-phase file removed at recovery", + $log_offset, + log_like => + [qr/removing future two-phase state file for transaction 16777215/]); done_testing(); -- 2.45.2 [text/x-diff] v1-0002-Fix-handling-of-orphaned-2PC-files-in-the-fut-v16.patch (3.9K, ../../[email protected]/4-v1-0002-Fix-handling-of-orphaned-2PC-files-in-the-fut-v16.patch) download | inline diff: From 854c87ae2ec2a44457143f24bc457158d2dac3ac Mon Sep 17 00:00:00 2001 From: Michael Paquier <[email protected]> Date: Thu, 26 Dec 2024 13:26:46 +0900 Subject: [PATCH v1] Fix handling of orphaned 2PC files in the future at recovery Issue introduced by 728bd991c3c4, that has added support for 2PC files in shared memory at recovery. Before this feature was introduced, files in the future of the transaction ID horizon were checked first, followed by a check if a transaction ID is aborted or committed which could involve a pg_xact lookup. After this commit, these checks were done in a reversed order, but files in the future do not have a state that can be checked in pg_xact, hence this caused recovery to fail abruptly should an orphaned 2PC file in the future of the transaction horizon exist in pg_twophase at the beginning of recovery. A test is added to check this scenario, using an empty 2PC with a transaction ID large enough to be in the future when running the test. Author: Vitaly Davydov, Michael Paquier Discussion: https://postgr.es/m/11e597-676ab680-8d-374f23c0@145466129 Backpatch-through: 13 --- src/backend/access/transam/twophase.c | 40 +++++++++++++-------------- src/test/recovery/t/009_twophase.pl | 23 +++++++++++++++ 2 files changed, 43 insertions(+), 20 deletions(-) diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index bca653e485..5adb98163a 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -2183,26 +2183,6 @@ ProcessTwoPhaseBuffer(TransactionId xid, if (!fromdisk) Assert(prepare_start_lsn != InvalidXLogRecPtr); - /* Already processed? */ - if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) - { - if (fromdisk) - { - ereport(WARNING, - (errmsg("removing stale two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); - } - else - { - ereport(WARNING, - (errmsg("removing stale two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); - } - return NULL; - } - /* Reject XID if too new */ if (TransactionIdFollowsOrEquals(xid, origNextXid)) { @@ -2223,6 +2203,26 @@ ProcessTwoPhaseBuffer(TransactionId xid, return NULL; } + /* Already processed? */ + if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) + { + if (fromdisk) + { + ereport(WARNING, + (errmsg("removing stale two-phase state file for transaction %u", + xid))); + RemoveTwoPhaseFile(xid, true); + } + else + { + ereport(WARNING, + (errmsg("removing stale two-phase state from memory for transaction %u", + xid))); + PrepareRedoRemove(xid, true); + } + return NULL; + } + if (fromdisk) { /* Read and validate file */ diff --git a/src/test/recovery/t/009_twophase.pl b/src/test/recovery/t/009_twophase.pl index fe7e8e7980..7642e4f0b3 100644 --- a/src/test/recovery/t/009_twophase.pl +++ b/src/test/recovery/t/009_twophase.pl @@ -528,4 +528,27 @@ is( $psql_out, qq{27|issued to paris}, "Check expected t_009_tbl2 data on standby"); +############################################################################### +# Check handling of orphaned 2PC files at recovery. +############################################################################### + +$cur_primary->teardown_node; + +# Grab location in logs of primary +my $log_offset = -s $cur_primary->logfile; + +# Create a fake file with a transaction ID large enough to be in the future, +# then check that the primary is able to start and remove this file at +# recovery. + +my $future_2pc_file = $cur_primary->data_dir . '/pg_twophase/00FFFFFF'; +append_to_file $future_2pc_file, ""; + +$cur_primary->start; +$cur_primary->log_check( + "future two-phase file removed at recovery", + $log_offset, + log_like => + [qr/removing future two-phase state file for transaction 16777215/]); + done_testing(); -- 2.45.2 [application/pgp-signature] signature.asc (833B, ../../[email protected]/5-signature.asc) download ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-26 15:11 Давыдов Виталий <[email protected]> parent: Michael Paquier <[email protected]> 0 siblings, 1 reply; 51+ messages in thread From: Давыдов Виталий @ 2024-12-26 15:11 UTC (permalink / raw) To: Michael Paquier <[email protected]>; +Cc: pgsql-hackers Hi Michael, > Here are two patches to address both issues: Thank you for the preparing the patches and test simplification. My bad, I overcompilcated it. I concerned about twophase file name generation. The function TwoPhaseFilePath() is pretty straitforward and unambiguous in 16 and earlier versions. The logic of this function in 17+ seems to be more complex. I do not understand it clearly. But, I guess, it will work incorrectly after turning to a newer epoch, because the epoch is calculated from TransamVariables->nextXid, but not from problem xid. The same problem may happen if we are in epoch 1 or greater. It will produce a wrong file name, because the epoch will be obtained from the last xid, not from file name xid. In another words, the function AdjustToFullTransactionId assumes that if xid > TransamVariables->nextXid, then the xid from the previous epoch. I may be not the case in our scenario. > I suspect that this can be still dangerous as-is while complicating the code with more possible paths for the removal of the 2PC files Agree, but we may pass file name into TwoPhaseFilePath if any, instead of creation of two functions as in the patch. The cost - two new if conditions. Using file names is pretty safe. Once we read the file and extract xid from its name, just pass this file name to TwoPhaseFilePath(). If not, try to generate it. Anyway, I do not insist on it, just try to discuss. With best regards, Vitaly ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-27 07:37 Michael Paquier <[email protected]> parent: Давыдов Виталий <[email protected]> 0 siblings, 1 reply; 51+ messages in thread From: Michael Paquier @ 2024-12-27 07:37 UTC (permalink / raw) To: Давыдов Виталий <[email protected]>; +Cc: pgsql-hackers On Thu, Dec 26, 2024 at 06:11:25PM +0300, Давыдов Виталий wrote: > I concerned about twophase file name generation. The function > TwoPhaseFilePath() is pretty straitforward and unambiguous in 16 and > earlier versions. The logic of this function in 17+ seems to be more > complex. I do not understand it clearly. But, I guess, it will work > incorrectly after turning to a newer epoch, because the epoch is > calculated from TransamVariables->nextXid, but not from problem > xid. The same problem may happen if we are in epoch 1 or greater. It > will produce a wrong file name, because the epoch will be obtained > from the last xid, not from file name xid. In another words, the > function AdjustToFullTransactionId assumes that if xid > > TransamVariables->nextXid, then the xid from the previous epoch. I > may be not the case in our scenario. Yeah. At this stage, we can pretty much say that the whole idea of relying AdjustToFullTransactionId() is broken, because we would build 2PC file names based on wrong assumptions, while orphaned files could be in the far past or far future depending on the epoch. TBH, we'll live better if we remove AdjustToFullTransactionId() and sprinkle a bit more the knowledge of FullTransactionIds to build correctly the 2PC file path in v17~. I've been playing with this code for a couple of hours and finished with the attached patch. I have wondered if ReadTwoPhaseFile() should gain the same knowledge as TwoPhaseFilePath(), but decided to limit the invasiness because we always call ReadTwoPhaseFile() once we don't have any orphaned files, for all the phases of recovery. So while this requires a bit more logic that depends on FullTransactionIdFromEpochAndXid() and ReadNextFullTransactionId() to build a FullTransactionId and get the current epoch, that's still acceptable as we only store an XID in the 2PC file. So please see the attached. You will note that RemoveTwoPhaseFile(), ProcessTwoPhaseBuffer() and TwoPhaseFilePath() now require a FullTransactionId, hence callers need to think about the epoch to use. That should limit future errors compared to passing the file name as optional argument. What do you think? -- Michael Attachments: [text/x-diff] v2-0001-Fix-failure-with-incorrect-epoch-handling-for-2PC.patch (16.8K, ../../[email protected]/2-v2-0001-Fix-failure-with-incorrect-epoch-handling-for-2PC.patch) download | inline diff: From bb250c0cd303f0d8db0fee2d26353bf0e0cb1275 Mon Sep 17 00:00:00 2001 From: Michael Paquier <[email protected]> Date: Fri, 27 Dec 2024 16:34:44 +0900 Subject: [PATCH v2] Fix failure with incorrect epoch handling for 2PC files at recovery At the beginning of recovery, an orphaned two-phase file in an epoch different than the one defined in the checkpoint record could not be removed based on the assumption that AdjustToFullTransactionId() relies on, assuming that all files would be either from the current epoch for the epoch before that. If the checkpoint epoch was 0 while the 2PC file was orphaned and in the future, AdjustToFullTransactionId() would underflow the epoch used to build the 2PC file path. In non-assert builds, this would create a WARNING message referring to a 2PC file with an epoch of "FFFFFFFF" (or UINT32_MAX), as an effect of the underflow calculation. Some tests are added with dummy 2PC files in the past and the future, checking that these are properly removed. Issue introduced by 5a1dfde8334b. Reported-by: Vitaly Davydov Discussion: https://postgr.es/m/13b5b6-676c3080-4d-531db900@47931709 Backpatch-through: 17 --- src/backend/access/transam/twophase.c | 231 +++++++++++++++++--------- src/test/recovery/t/009_twophase.pl | 31 ++++ 2 files changed, 184 insertions(+), 78 deletions(-) diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index 49be1df91c..01f5d728be 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -221,13 +221,13 @@ static void ProcessRecords(char *bufptr, TransactionId xid, static void RemoveGXact(GlobalTransaction gxact); static void XlogReadTwoPhaseData(XLogRecPtr lsn, char **buf, int *len); -static char *ProcessTwoPhaseBuffer(TransactionId xid, +static char *ProcessTwoPhaseBuffer(FullTransactionId xid, XLogRecPtr prepare_start_lsn, bool fromdisk, bool setParent, bool setNextXid); static void MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid, TimestampTz prepared_at, Oid owner, Oid databaseid); -static void RemoveTwoPhaseFile(TransactionId xid, bool giveWarning); +static void RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning); static void RecreateTwoPhaseFile(TransactionId xid, void *content, int len); /* @@ -926,42 +926,9 @@ TwoPhaseGetDummyProc(TransactionId xid, bool lock_held) /* State file support */ /************************************************************************/ -/* - * Compute the FullTransactionId for the given TransactionId. - * - * The wrap logic is safe here because the span of active xids cannot exceed one - * epoch at any given time. - */ -static inline FullTransactionId -AdjustToFullTransactionId(TransactionId xid) -{ - FullTransactionId nextFullXid; - TransactionId nextXid; - uint32 epoch; - - Assert(TransactionIdIsValid(xid)); - - LWLockAcquire(XidGenLock, LW_SHARED); - nextFullXid = TransamVariables->nextXid; - LWLockRelease(XidGenLock); - - nextXid = XidFromFullTransactionId(nextFullXid); - epoch = EpochFromFullTransactionId(nextFullXid); - if (unlikely(xid > nextXid)) - { - /* Wraparound occurred, must be from a prev epoch. */ - Assert(epoch > 0); - epoch--; - } - - return FullTransactionIdFromEpochAndXid(epoch, xid); -} - static inline int -TwoPhaseFilePath(char *path, TransactionId xid) +TwoPhaseFilePath(char *path, FullTransactionId fxid) { - FullTransactionId fxid = AdjustToFullTransactionId(xid); - return snprintf(path, MAXPGPATH, TWOPHASE_DIR "/%08X%08X", EpochFromFullTransactionId(fxid), XidFromFullTransactionId(fxid)); @@ -1297,7 +1264,8 @@ RegisterTwoPhaseRecord(TwoPhaseRmgrId rmid, uint16 info, * If it looks OK (has a valid magic number and CRC), return the palloc'd * contents of the file, issuing an error when finding corrupted data. If * missing_ok is true, which indicates that missing files can be safely - * ignored, then return NULL. This state can be reached when doing recovery. + * ignored, then return NULL. This state can be reached when doing recovery + * after discarding twophase files from other epochs. */ static char * ReadTwoPhaseFile(TransactionId xid, bool missing_ok) @@ -1311,8 +1279,16 @@ ReadTwoPhaseFile(TransactionId xid, bool missing_ok) pg_crc32c calc_crc, file_crc; int r; + FullTransactionId fxid; + FullTransactionId nextFullXid; + uint32 epoch; - TwoPhaseFilePath(path, xid); + /* get current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + TwoPhaseFilePath(path, fxid); fd = OpenTransientFile(path, O_RDONLY | PG_BINARY); if (fd < 0) @@ -1537,7 +1513,6 @@ FinishPreparedTransaction(const char *gid, bool isCommit) else XlogReadTwoPhaseData(gxact->prepare_start_lsn, &buf, NULL); - /* * Disassemble the header area */ @@ -1677,10 +1652,22 @@ FinishPreparedTransaction(const char *gid, bool isCommit) AtEOXact_PgStat(isCommit, false); /* - * And now we can clean up any files we may have left. + * And now we can clean up any files we may have left. These should + * be from the current epoch. */ if (ondisk) - RemoveTwoPhaseFile(xid, true); + { + uint32 epoch; + FullTransactionId nextFullXid; + FullTransactionId fxid; + + /* get current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + RemoveTwoPhaseFile(fxid, true); + } MyLockedGxact = NULL; @@ -1718,13 +1705,17 @@ ProcessRecords(char *bufptr, TransactionId xid, * * If giveWarning is false, do not complain about file-not-present; * this is an expected case during WAL replay. + * + * This routine is used at early stages at recovery where future and + * past orphaned files are checked, hence the FullTransactionId to build + * a complete file name fit for the removal. */ static void -RemoveTwoPhaseFile(TransactionId xid, bool giveWarning) +RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning) { char path[MAXPGPATH]; - TwoPhaseFilePath(path, xid); + TwoPhaseFilePath(path, fxid); if (unlink(path)) if (errno != ENOENT || giveWarning) ereport(WARNING, @@ -1744,13 +1735,21 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len) char path[MAXPGPATH]; pg_crc32c statefile_crc; int fd; + FullTransactionId fxid; + FullTransactionId nextFullXid; + uint32 epoch; /* Recompute CRC */ INIT_CRC32C(statefile_crc); COMP_CRC32C(statefile_crc, content, len); FIN_CRC32C(statefile_crc); - TwoPhaseFilePath(path, xid); + /* Use current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + TwoPhaseFilePath(path, fxid); fd = OpenTransientFile(path, O_CREAT | O_TRUNC | O_WRONLY | PG_BINARY); @@ -1898,7 +1897,9 @@ CheckPointTwoPhase(XLogRecPtr redo_horizon) * Scan pg_twophase and fill TwoPhaseState depending on the on-disk data. * This is called once at the beginning of recovery, saving any extra * lookups in the future. Two-phase files that are newer than the - * minimum XID horizon are discarded on the way. + * minimum XID horizon are discarded on the way. Two phase files with + * an epoch older or newer than the current checkpoint's record epoch + * are also discarded. */ void restoreTwoPhaseData(void) @@ -1913,14 +1914,11 @@ restoreTwoPhaseData(void) if (strlen(clde->d_name) == 16 && strspn(clde->d_name, "0123456789ABCDEF") == 16) { - TransactionId xid; FullTransactionId fxid; char *buf; fxid = FullTransactionIdFromU64(strtou64(clde->d_name, NULL, 16)); - xid = XidFromFullTransactionId(fxid); - - buf = ProcessTwoPhaseBuffer(xid, InvalidXLogRecPtr, + buf = ProcessTwoPhaseBuffer(fxid, InvalidXLogRecPtr, true, false, false); if (buf == NULL) continue; @@ -1971,6 +1969,7 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) TransactionId origNextXid = XidFromFullTransactionId(nextXid); TransactionId result = origNextXid; TransactionId *xids = NULL; + uint32 epoch = EpochFromFullTransactionId(nextXid); int nxids = 0; int allocsize = 0; int i; @@ -1979,6 +1978,7 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { TransactionId xid; + FullTransactionId fxid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; @@ -1986,7 +1986,12 @@ PrescanPreparedTransactions(TransactionId **xids_p, int *nxids_p) xid = gxact->xid; - buf = ProcessTwoPhaseBuffer(xid, + /* + * All two-phase files with past and future epoch in pg_twophase are + * gone at this point, so we're OK to rely on only the current epoch. + */ + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + buf = ProcessTwoPhaseBuffer(fxid, gxact->prepare_start_lsn, gxact->ondisk, false, true); @@ -2048,11 +2053,18 @@ void StandbyRecoverPreparedTransactions(void) { int i; + uint32 epoch; + FullTransactionId nextFullXid; + + /* get current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { TransactionId xid; + FullTransactionId fxid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; @@ -2060,7 +2072,12 @@ StandbyRecoverPreparedTransactions(void) xid = gxact->xid; - buf = ProcessTwoPhaseBuffer(xid, + /* + * At this stage, we're OK to work with the current epoch + * as all past and future files have been already discarded. + */ + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + buf = ProcessTwoPhaseBuffer(fxid, gxact->prepare_start_lsn, gxact->ondisk, true, false); if (buf != NULL) @@ -2089,11 +2106,18 @@ void RecoverPreparedTransactions(void) { int i; + uint32 epoch; + FullTransactionId nextFullXid; + + /* get current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); LWLockAcquire(TwoPhaseStateLock, LW_EXCLUSIVE); for (i = 0; i < TwoPhaseState->numPrepXacts; i++) { TransactionId xid; + FullTransactionId fxid; char *buf; GlobalTransaction gxact = TwoPhaseState->prepXacts[i]; char *bufptr; @@ -2101,6 +2125,10 @@ RecoverPreparedTransactions(void) TransactionId *subxids; const char *gid; + /* + * At this stage, we're OK to work with the current epoch + * as all past and future files have been already discarded. + */ xid = gxact->xid; /* @@ -2112,7 +2140,8 @@ RecoverPreparedTransactions(void) * SubTransSetParent has been set before, if the prepared transaction * generated xid assignment records. */ - buf = ProcessTwoPhaseBuffer(xid, + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + buf = ProcessTwoPhaseBuffer(fxid, gxact->prepare_start_lsn, gxact->ondisk, true, false); if (buf == NULL) @@ -2180,7 +2209,7 @@ RecoverPreparedTransactions(void) /* * ProcessTwoPhaseBuffer * - * Given a transaction id, read it either from disk or read it directly + * Given a FullTransactionId, read it either from disk or read it directly * via shmem xlog record pointer using the provided "prepare_start_lsn". * * If setParent is true, set up subtransaction parent linkages. @@ -2189,23 +2218,66 @@ RecoverPreparedTransactions(void) * value scanned. */ static char * -ProcessTwoPhaseBuffer(TransactionId xid, +ProcessTwoPhaseBuffer(FullTransactionId fxid, XLogRecPtr prepare_start_lsn, bool fromdisk, bool setParent, bool setNextXid) { FullTransactionId nextXid = TransamVariables->nextXid; - TransactionId origNextXid = XidFromFullTransactionId(nextXid); TransactionId *subxids; char *buf; TwoPhaseFileHeader *hdr; int i; + TransactionId xid = XidFromFullTransactionId(fxid); Assert(LWLockHeldByMeInMode(TwoPhaseStateLock, LW_EXCLUSIVE)); if (!fromdisk) Assert(prepare_start_lsn != InvalidXLogRecPtr); + /* + * Reject full XID if too new. Note that this discards files from future + * epochs. + */ + if (FullTransactionIdFollowsOrEquals(fxid, nextXid)) + { + if (fromdisk) + { + ereport(WARNING, + (errmsg("removing future two-phase state file of epoch %u for transaction %u", + EpochFromFullTransactionId(fxid), xid))); + RemoveTwoPhaseFile(fxid, true); + } + else + { + ereport(WARNING, + (errmsg("removing future two-phase state from memory for transaction %u", + xid))); + PrepareRedoRemove(xid, true); + } + return NULL; + } + + /* Discard files from past epochs */ + if (EpochFromFullTransactionId(fxid) < EpochFromFullTransactionId(nextXid)) + { + if (fromdisk) + { + ereport(WARNING, + (errmsg("removing past two-phase state file of epoch %u for transaction %u", + EpochFromFullTransactionId(fxid), xid))); + RemoveTwoPhaseFile(fxid, true); + } + else + { + ereport(WARNING, + (errmsg("removing past two-phase state from memory for transaction %u", + xid))); + PrepareRedoRemove(xid, true); + } + return NULL; + } + /* Already processed? */ if (TransactionIdDidCommit(xid) || TransactionIdDidAbort(xid)) { @@ -2214,7 +2286,8 @@ ProcessTwoPhaseBuffer(TransactionId xid, ereport(WARNING, (errmsg("removing stale two-phase state file for transaction %u", xid))); - RemoveTwoPhaseFile(xid, true); + + RemoveTwoPhaseFile(fxid, true); } else { @@ -2226,26 +2299,6 @@ ProcessTwoPhaseBuffer(TransactionId xid, return NULL; } - /* Reject XID if too new */ - if (TransactionIdFollowsOrEquals(xid, origNextXid)) - { - if (fromdisk) - { - ereport(WARNING, - (errmsg("removing future two-phase state file for transaction %u", - xid))); - RemoveTwoPhaseFile(xid, true); - } - else - { - ereport(WARNING, - (errmsg("removing future two-phase state from memory for transaction %u", - xid))); - PrepareRedoRemove(xid, true); - } - return NULL; - } - if (fromdisk) { /* Read and validate file */ @@ -2520,8 +2573,16 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, if (!XLogRecPtrIsInvalid(start_lsn)) { char path[MAXPGPATH]; + uint32 epoch; + FullTransactionId fxid; + FullTransactionId nextFullXid; - TwoPhaseFilePath(path, hdr->xid); + /* Use current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + + fxid = FullTransactionIdFromEpochAndXid(epoch, hdr->xid); + TwoPhaseFilePath(path, fxid); if (access(path, F_OK) == 0) { @@ -2616,7 +2677,21 @@ PrepareRedoRemove(TransactionId xid, bool giveWarning) */ elog(DEBUG2, "removing 2PC data for transaction %u", xid); if (gxact->ondisk) - RemoveTwoPhaseFile(xid, giveWarning); + { + uint32 epoch; + FullTransactionId nextFullXid; + FullTransactionId fxid; + + /* + * We should deal with a file at the current epoch here, so + * grab it. + */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + + RemoveTwoPhaseFile(fxid, giveWarning); + } RemoveGXact(gxact); } diff --git a/src/test/recovery/t/009_twophase.pl b/src/test/recovery/t/009_twophase.pl index 4b3e0f77dc..2463b7ea30 100644 --- a/src/test/recovery/t/009_twophase.pl +++ b/src/test/recovery/t/009_twophase.pl @@ -572,4 +572,35 @@ my $nsubtrans = $cur_primary->safe_psql('postgres', ); isnt($osubtrans, $nsubtrans, "contents of pg_subtrans/ have changed"); +############################################################################### +# Check handling of orphaned 2PC files at recovery. +############################################################################### + +$cur_standby->teardown_node; +$cur_primary->teardown_node; + +# Grab location in logs of primary +my $log_offset = -s $cur_primary->logfile; + +# Create fake files with a transaction ID large or low enough to be in the +# future or the past, in different epochs, then check that the primary is able +# to start and remove these files at recovery. + +# First bump the epoch with pg_resetwal. +$cur_primary->command_ok([ 'pg_resetwal', '-e', 256, '-f', $cur_primary->data_dir ], + 'bump epoch of primary'); + +my $future_2pc_file = $cur_primary->data_dir . '/pg_twophase/000001FF00000FFF'; +append_to_file $future_2pc_file, ""; +my $past_2pc_file = $cur_primary->data_dir . '/pg_twophase/000000EE00000FFF'; +append_to_file $past_2pc_file, ""; + +$cur_primary->start; +$cur_primary->log_check( + "two-phase files removed at recovery", + $log_offset, + log_like => + [qr/removing past two-phase state file of epoch 238 for transaction 4095/, + qr/removing future two-phase state file of epoch 511 for transaction 4095/]); + done_testing(); -- 2.45.2 [application/pgp-signature] signature.asc (833B, ../../[email protected]/3-signature.asc) download ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-27 15:16 Vitaly Davydov <[email protected]> parent: Michael Paquier <[email protected]> 0 siblings, 1 reply; 51+ messages in thread From: Vitaly Davydov @ 2024-12-27 15:16 UTC (permalink / raw) To: Michael Paquier <[email protected]>; +Cc: pgsql-hackers On Friday, December 27, 2024 10:37 MSK, Michael Paquier <[email protected]> wrote: > So please see the attached. You will note that RemoveTwoPhaseFile(), > ProcessTwoPhaseBuffer() and TwoPhaseFilePath() now require a > FullTransactionId, hence callers need to think about the epoch to use. > That should limit future errors compared to passing the file name as > optional argument. In general, I like your solution to use FullTransactionId. I haven't found any evident problems. I just would like to propose to create a couple of new functions like RemoveTwoPhaseFileInCurrentEpoch, TwoPhaseFilePathInCurrentEpoch which accept TransactionId instead FullTransactionId. It may make the code clearer and result into less boilerplate code. I tried to do some hand testing. It seems, the problem is gone with the patch. Thank you! As an idea, I would like to propose to store FullTransactionId in global transaction state instead of TransactionId. I'm not sure, it will consume significant additional memory, but it make the code more clear and probably result into less number of locks. With best regards, Vitaly Attachments: [text/x-patch] 0001-Some-cosmetic-fixes.patch (5.1K, ../../16aa85-676ec500-3d-23db9b40@59039559/2-0001-Some-cosmetic-fixes.patch) download | inline diff: From 1e74e01a2485e2b3a59f880a5eaf86af1af81cc5 Mon Sep 17 00:00:00 2001 From: Vitaly Davydov <[email protected]> Date: Fri, 27 Dec 2024 18:03:28 +0300 Subject: [PATCH] Some cosmetic fixes --- src/backend/access/transam/twophase.c | 92 +++++++++++---------------- 1 file changed, 37 insertions(+), 55 deletions(-) diff --git a/src/backend/access/transam/twophase.c b/src/backend/access/transam/twophase.c index 01f5d728be..9418fd74ee 100644 --- a/src/backend/access/transam/twophase.c +++ b/src/backend/access/transam/twophase.c @@ -228,6 +228,7 @@ static void MarkAsPreparingGuts(GlobalTransaction gxact, TransactionId xid, const char *gid, TimestampTz prepared_at, Oid owner, Oid databaseid); static void RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning); +static void RemoveTwoPhaseFileInCurrentEpoch(TransactionId xid, bool giveWarning); static void RecreateTwoPhaseFile(TransactionId xid, void *content, int len); /* @@ -934,6 +935,22 @@ TwoPhaseFilePath(char *path, FullTransactionId fxid) XidFromFullTransactionId(fxid)); } +static inline int +TwoPhaseFilePathInCurrentEpoch(char *path, TransactionId xid) +{ + uint32 epoch; + FullTransactionId fxid; + FullTransactionId nextFullXid; + + /* Use current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + + return TwoPhaseFilePath(path, fxid); +} + /* * 2PC state file format: * @@ -1279,16 +1296,8 @@ ReadTwoPhaseFile(TransactionId xid, bool missing_ok) pg_crc32c calc_crc, file_crc; int r; - FullTransactionId fxid; - FullTransactionId nextFullXid; - uint32 epoch; - - /* get current epoch */ - nextFullXid = ReadNextFullTransactionId(); - epoch = EpochFromFullTransactionId(nextFullXid); - fxid = FullTransactionIdFromEpochAndXid(epoch, xid); - TwoPhaseFilePath(path, fxid); + TwoPhaseFilePathInCurrentEpoch(path, xid); fd = OpenTransientFile(path, O_RDONLY | PG_BINARY); if (fd < 0) @@ -1656,18 +1665,7 @@ FinishPreparedTransaction(const char *gid, bool isCommit) * be from the current epoch. */ if (ondisk) - { - uint32 epoch; - FullTransactionId nextFullXid; - FullTransactionId fxid; - - /* get current epoch */ - nextFullXid = ReadNextFullTransactionId(); - epoch = EpochFromFullTransactionId(nextFullXid); - - fxid = FullTransactionIdFromEpochAndXid(epoch, xid); - RemoveTwoPhaseFile(fxid, true); - } + RemoveTwoPhaseFileInCurrentEpoch(xid, true); MyLockedGxact = NULL; @@ -1723,6 +1721,21 @@ RemoveTwoPhaseFile(FullTransactionId fxid, bool giveWarning) errmsg("could not remove file \"%s\": %m", path))); } +static void +RemoveTwoPhaseFileInCurrentEpoch(TransactionId xid, bool giveWarning) +{ + uint32 epoch; + FullTransactionId nextFullXid; + FullTransactionId fxid; + + /* get current epoch */ + nextFullXid = ReadNextFullTransactionId(); + epoch = EpochFromFullTransactionId(nextFullXid); + + fxid = FullTransactionIdFromEpochAndXid(epoch, xid); + RemoveTwoPhaseFile(fxid, true); +} + /* * Recreates a state file. This is used in WAL replay and during * checkpoint creation. @@ -1735,21 +1748,13 @@ RecreateTwoPhaseFile(TransactionId xid, void *content, int len) char path[MAXPGPATH]; pg_crc32c statefile_crc; int fd; - FullTransactionId fxid; - FullTransactionId nextFullXid; - uint32 epoch; /* Recompute CRC */ INIT_CRC32C(statefile_crc); COMP_CRC32C(statefile_crc, content, len); FIN_CRC32C(statefile_crc); - /* Use current epoch */ - nextFullXid = ReadNextFullTransactionId(); - epoch = EpochFromFullTransactionId(nextFullXid); - - fxid = FullTransactionIdFromEpochAndXid(epoch, xid); - TwoPhaseFilePath(path, fxid); + TwoPhaseFilePathInCurrentEpoch(path, xid); fd = OpenTransientFile(path, O_CREAT | O_TRUNC | O_WRONLY | PG_BINARY); @@ -2286,7 +2291,6 @@ ProcessTwoPhaseBuffer(FullTransactionId fxid, ereport(WARNING, (errmsg("removing stale two-phase state file for transaction %u", xid))); - RemoveTwoPhaseFile(fxid, true); } else @@ -2573,16 +2577,8 @@ PrepareRedoAdd(char *buf, XLogRecPtr start_lsn, if (!XLogRecPtrIsInvalid(start_lsn)) { char path[MAXPGPATH]; - uint32 epoch; - FullTransactionId fxid; - FullTransactionId nextFullXid; - /* Use current epoch */ - nextFullXid = ReadNextFullTransactionId(); - epoch = EpochFromFullTransactionId(nextFullXid); - - fxid = FullTransactionIdFromEpochAndXid(epoch, hdr->xid); - TwoPhaseFilePath(path, fxid); + TwoPhaseFilePathInCurrentEpoch(path, hdr->xid); if (access(path, F_OK) == 0) { @@ -2677,21 +2673,7 @@ PrepareRedoRemove(TransactionId xid, bool giveWarning) */ elog(DEBUG2, "removing 2PC data for transaction %u", xid); if (gxact->ondisk) - { - uint32 epoch; - FullTransactionId nextFullXid; - FullTransactionId fxid; - - /* - * We should deal with a file at the current epoch here, so - * grab it. - */ - nextFullXid = ReadNextFullTransactionId(); - epoch = EpochFromFullTransactionId(nextFullXid); - fxid = FullTransactionIdFromEpochAndXid(epoch, xid); - - RemoveTwoPhaseFile(fxid, giveWarning); - } + RemoveTwoPhaseFileInCurrentEpoch(xid, giveWarning); RemoveGXact(gxact); } -- 2.34.1 ^ permalink raw reply [nested|flat] 51+ messages in thread
* Re: An improvement of ProcessTwoPhaseBuffer logic @ 2024-12-30 01:08 Michael Paquier <[email protected]> parent: Vitaly Davydov <[email protected]> 0 siblings, 0 replies; 51+ messages in thread From: Michael Paquier @ 2024-12-30 01:08 UTC (permalink / raw) To: Vitaly Davydov <[email protected]>; +Cc: pgsql-hackers On Fri, Dec 27, 2024 at 06:16:24PM +0300, Vitaly Davydov wrote: > In general, I like your solution to use FullTransactionId. I haven't > found any evident problems. I just would like to propose to create a > couple of new functions like RemoveTwoPhaseFileInCurrentEpoch, > TwoPhaseFilePathInCurrentEpoch which accept TransactionId instead > FullTransactionId. It may make the code clearer and result into less > boilerplate code. I tried to do some hand testing. It seems, the > problem is gone with the patch. Thanks for the review. Agreed that it would be a good thing to limit the number of paths calling ReadNextFullTransactionId(), but I did not like much the suggestion TwoPhaseFilePathInCurrentEpoch(), feeling that it was more important to keep a single code path in charge of building the file names. Instead, I have gone with a new FullTransactionIdFromCurrentEpoch() that replaces AdjustToFullTransactionId(). It cleans up most of the calls to ReadNextFullTransactionId() compared to the previous patch. It is true that these couple with calls to ProcessTwoPhaseBuffer(), but the result felt OK this way in the scope of this fix. > As an idea, I would like to propose to store FullTransactionId in > global transaction state instead of TransactionId. I'm not sure, it > will consume significant additional memory, but it make the code > more clear and probably result into less number of locks. FWIW, I was wondering about doing the same thing. However, I have concluded that this some refactoring work out of the scope of fixing the primary issue we have here, as we are hit by the way the file names are built when we attempt to remove them. Note that the memory footprint of storing a FullTransactionId in twophase.c's GlobalTransactionData does not worry me much. It is more important to not increase the size of the two-phase state data, impacting files on disk and their WAL records. This size argument has been mentioned on the thread that has added epochs to the 2PC file names, as far as I recall. At the end, I have applied two patches, the first one down to 13 that took care of the "future" issue, with tests added in the v14~v16 range. v13 was lacking a perl routine, and it's not a big deal to not have coverage for this code path anyway. The second patch has been applied down to v17, to fix the epoch issue, with the more advanced tests. If you have a suggestion of patch to plug in a FullTransactionId into GlobalTransactionData rather than a TransactionId, feel free to propose something! Help is always welcome, and this would be HEAD-only work, making it less urgent to deal with. -- Michael Attachments: [application/pgp-signature] signature.asc (833B, ../../[email protected]/2-signature.asc) download ^ permalink raw reply [nested|flat] 51+ messages in thread
end of thread, other threads:[~2024-12-30 01:08 UTC | newest] Thread overview: 51+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v4 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v7 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v2 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v3 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v5 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2017-10-19 08:24 [PATCH v1 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2024-12-25 16:18 Re: An improvement of ProcessTwoPhaseBuffer logic Vitaly Davydov <[email protected]> 2024-12-25 22:42 ` Re: An improvement of ProcessTwoPhaseBuffer logic Michael Paquier <[email protected]> 2024-12-26 05:34 ` Re: An improvement of ProcessTwoPhaseBuffer logic Michael Paquier <[email protected]> 2024-12-26 15:11 ` Re: An improvement of ProcessTwoPhaseBuffer logic Давыдов Виталий <[email protected]> 2024-12-27 07:37 ` Re: An improvement of ProcessTwoPhaseBuffer logic Michael Paquier <[email protected]> 2024-12-27 15:16 ` Re: An improvement of ProcessTwoPhaseBuffer logic Vitaly Davydov <[email protected]> 2024-12-30 01:08 ` Re: An improvement of ProcessTwoPhaseBuffer logic Michael Paquier <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox