public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v1 3/3] async postgres_fdw 50+ messages / 3 participants [nested] [flat]
* [PATCH v4 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v2 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v3 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v1 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v7 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* [PATCH v5 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 50+ 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] 50+ messages in thread
* constants for tar header offsets @ 2023-04-18 15:20 Robert Haas <[email protected]> 2023-04-18 15:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> 0 siblings, 1 reply; 50+ messages in thread From: Robert Haas @ 2023-04-18 15:20 UTC (permalink / raw) To: pgsql-hackers Hi, We have a few different places in the code where we generate or modify tar headers or just read data out of them. The code in question uses one of my less-favorite programming things: magic numbers. The offsets of the various fields within the tar header are just hard-coded in each relevant place in our code. I think we should clean that up, as in the attached patch. I hasten to emphasize that, while I think this is an improvement, I don't think the result is particularly awesome. Even with the patch, src/port/tar.c and src/include/pgtar.h do a poor job insulating callers from the details of the tar format. However, it's also not very clear to me how to fix that. For instance, I thought about writing a function that parses a tar header into a struct and then using it in all of these places, but that seems like it would lose too much efficiency relative to the current ad-hoc coding. So for now I don't have a better idea than this. -- Robert Haas EDB: http://www.enterprisedb.com Attachments: [application/octet-stream] v1-0001-Add-and-use-symbolic-constants-for-tar-header-off.patch (9.6K, ../../CA+TgmoZNbLwhmCrNtkJAvi8FLkwFdMeVU3myV2HQQpA5bvbRZg@mail.gmail.com/2-v1-0001-Add-and-use-symbolic-constants-for-tar-header-off.patch) download | inline diff: From f2949eb188ddac924885479c2b4738065b2f2d95 Mon Sep 17 00:00:00 2001 From: Robert Haas <[email protected]> Date: Tue, 18 Apr 2023 10:53:02 -0400 Subject: [PATCH v1] Add and use symbolic constants for tar header offsets. Because symbolic constants in a header file are better than magic constants embedded in the code. --- src/bin/pg_basebackup/bbstreamer_tar.c | 16 +++++------ src/bin/pg_basebackup/walmethods.c | 7 +++-- src/bin/pg_dump/pg_backup_tar.c | 16 +++++------ src/include/pgtar.h | 34 +++++++++++++++++++++++ src/port/tar.c | 38 +++++++++++++------------- 5 files changed, 73 insertions(+), 38 deletions(-) diff --git a/src/bin/pg_basebackup/bbstreamer_tar.c b/src/bin/pg_basebackup/bbstreamer_tar.c index 03d7fd3375..a60faaf045 100644 --- a/src/bin/pg_basebackup/bbstreamer_tar.c +++ b/src/bin/pg_basebackup/bbstreamer_tar.c @@ -291,17 +291,17 @@ bbstreamer_tar_header(bbstreamer_tar_parser *mystreamer) * more principled approach. It's been like this for a long time, but we * ought to do better. */ - strlcpy(member->pathname, &buffer[0], MAXPGPATH); + strlcpy(member->pathname, &buffer[TAR_OFFSET_NAME], MAXPGPATH); if (member->pathname[0] == '\0') pg_fatal("tar member has empty name"); - member->size = read_tar_number(&buffer[124], 12); - member->mode = read_tar_number(&buffer[100], 8); - member->uid = read_tar_number(&buffer[108], 8); - member->gid = read_tar_number(&buffer[116], 8); - member->is_directory = (buffer[156] == '5'); - member->is_link = (buffer[156] == '2'); + member->size = read_tar_number(&buffer[TAR_OFFSET_SIZE], 12); + member->mode = read_tar_number(&buffer[TAR_OFFSET_MODE], 8); + member->uid = read_tar_number(&buffer[TAR_OFFSET_UID], 8); + member->gid = read_tar_number(&buffer[TAR_OFFSET_GID], 8); + member->is_directory = (buffer[TAR_OFFSET_TYPEFLAG] == '5'); + member->is_link = (buffer[TAR_OFFSET_TYPEFLAG] == '2'); if (member->is_link) - strlcpy(member->linktarget, &buffer[157], 100); + strlcpy(member->linktarget, &buffer[TAR_OFFSET_LINKNAME], 100); /* Compute number of padding bytes. */ mystreamer->pad_bytes_expected = tarPaddingBytesRequired(member->size); diff --git a/src/bin/pg_basebackup/walmethods.c b/src/bin/pg_basebackup/walmethods.c index 6d14b988cb..a974ffced4 100644 --- a/src/bin/pg_basebackup/walmethods.c +++ b/src/bin/pg_basebackup/walmethods.c @@ -1131,7 +1131,7 @@ tar_close(Walfile *f, WalCloseMethod method) * possibly also renaming the file. We overwrite the entire current header * when done, including the checksum. */ - print_tar_number(&(tf->header[124]), 12, filesize); + print_tar_number(&(tf->header[TAR_OFFSET_SIZE]), 12, filesize); if (method == CLOSE_NORMAL) @@ -1139,9 +1139,10 @@ tar_close(Walfile *f, WalCloseMethod method) * We overwrite it with what it was before if we have no tempname, * since we're going to write the buffer anyway. */ - strlcpy(&(tf->header[0]), tf->base.pathname, 100); + strlcpy(&(tf->header[TAR_OFFSET_NAME]), tf->base.pathname, 100); - print_tar_number(&(tf->header[148]), 8, tarChecksum(((TarMethodFile *) f)->header)); + print_tar_number(&(tf->header[TAR_OFFSET_CHECKSUM]), 8, + tarChecksum(((TarMethodFile *) f)->header)); if (lseek(tar_data->fd, tf->ofs_start, SEEK_SET) != ((TarMethodFile *) f)->ofs_start) { f->wwmethod->lasterrno = errno; diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index babd23b4eb..59870acd17 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -975,20 +975,20 @@ isValidTarHeader(char *header) int sum; int chk = tarChecksum(header); - sum = read_tar_number(&header[148], 8); + sum = read_tar_number(&header[TAR_OFFSET_CHECKSUM], 8); if (sum != chk) return false; /* POSIX tar format */ - if (memcmp(&header[257], "ustar\0", 6) == 0 && - memcmp(&header[263], "00", 2) == 0) + if (memcmp(&header[TAR_OFFSET_MAGIC], "ustar\0", 6) == 0 && + memcmp(&header[TAR_OFFSET_VERSION], "00", 2) == 0) return true; /* GNU tar format */ - if (memcmp(&header[257], "ustar \0", 8) == 0) + if (memcmp(&header[TAR_OFFSET_MAGIC], "ustar \0", 8) == 0) return true; /* not-quite-POSIX format written by pre-9.3 pg_dump */ - if (memcmp(&header[257], "ustar00\0", 8) == 0) + if (memcmp(&header[TAR_OFFSET_MAGIC], "ustar00\0", 8) == 0) return true; return false; @@ -1151,7 +1151,7 @@ _tarGetHeader(ArchiveHandle *AH, TAR_MEMBER *th) /* Calc checksum */ chk = tarChecksum(h); - sum = read_tar_number(&h[148], 8); + sum = read_tar_number(&h[TAR_OFFSET_CHECKSUM], 8); /* * If the checksum failed, see if it is a null block. If so, silently @@ -1175,9 +1175,9 @@ _tarGetHeader(ArchiveHandle *AH, TAR_MEMBER *th) } /* Name field is 100 bytes, might not be null-terminated */ - strlcpy(tag, &h[0], 100 + 1); + strlcpy(tag, &h[TAR_OFFSET_NAME], 100 + 1); - len = read_tar_number(&h[124], 12); + len = read_tar_number(&h[TAR_OFFSET_SIZE], 12); pg_log_debug("TOC Entry %s at %llu (length %llu, checksum %d)", tag, (unsigned long long) hPos, (unsigned long long) len, sum); diff --git a/src/include/pgtar.h b/src/include/pgtar.h index 661f9d7c59..e373ead167 100644 --- a/src/include/pgtar.h +++ b/src/include/pgtar.h @@ -23,6 +23,40 @@ enum tarError TAR_SYMLINK_TOO_LONG }; +/* + * Offsets of fields within a 512-byte tar header. + * + * "tar number" values should be generated using print_tar_number() and can be + * read using read_tar_number(). Fields that contain strings are generally + * both filled and read using strlcpy(). + * + * The value for the checksum field can be computed using tarChecksum(). + * + * The file type can be 0 for a regular file, 2 for a symbolic link, or + * 5 for a directory. + * + * Some fields are not used by PostgreSQL; see tarCreateHeader(). + */ +enum tarHeaderOffset +{ + TAR_OFFSET_NAME = 0, /* 100 byte string */ + TAR_OFFSET_MODE = 100, /* 8 byte tar number, excludes S_IFMT */ + TAR_OFFSET_UID = 108, /* 8 byte tar number */ + TAR_OFFSET_GID = 116, /* 8 byte tar number */ + TAR_OFFSET_SIZE = 124, /* 8 byte tar number */ + TAR_OFFSET_MTIME = 136, /* 12 byte tar number */ + TAR_OFFSET_CHECKSUM = 148, /* 8 byte tar number */ + TAR_OFFSET_TYPEFLAG = 156, /* 1 byte file type */ + TAR_OFFSET_LINKNAME = 157, /* 100 byte string */ + TAR_OFFSET_MAGIC = 257, /* "ustar" with terminating zero byte */ + TAR_OFFSET_VERSION = 263, /* "00" */ + TAR_OFFSET_UNAME = 265, /* 32 byte string */ + TAR_OFFSET_GNAME = 297, /* 32 byte string */ + TAR_OFFSET_DEVMAJOR = 329, /* 8 byte tar number */ + TAR_OFFSET_DEVMINOR = 337, /* 8 byte tar number */ + TAR_OFFSET_PREFIX = 345 /* 155 byte string */ +}; + extern enum tarError tarCreateHeader(char *h, const char *filename, const char *linktarget, pgoff_t size, mode_t mode, uid_t uid, gid_t gid, diff --git a/src/port/tar.c b/src/port/tar.c index 4afe9f2533..185776270a 100644 --- a/src/port/tar.c +++ b/src/port/tar.c @@ -120,10 +120,10 @@ tarCreateHeader(char *h, const char *filename, const char *linktarget, if (linktarget && strlen(linktarget) > 99) return TAR_SYMLINK_TOO_LONG; - memset(h, 0, 512); /* assume tar header size */ + memset(h, 0, TAR_BLOCK_SIZE); /* Name 100 */ - strlcpy(&h[0], filename, 100); + strlcpy(&h[TAR_OFFSET_NAME], filename, 100); if (linktarget != NULL || S_ISDIR(mode)) { /* @@ -139,68 +139,68 @@ tarCreateHeader(char *h, const char *filename, const char *linktarget, } /* Mode 8 - this doesn't include the file type bits (S_IFMT) */ - print_tar_number(&h[100], 8, (mode & 07777)); + print_tar_number(&h[TAR_OFFSET_MODE], 8, (mode & 07777)); /* User ID 8 */ - print_tar_number(&h[108], 8, uid); + print_tar_number(&h[TAR_OFFSET_UID], 8, uid); /* Group 8 */ - print_tar_number(&h[116], 8, gid); + print_tar_number(&h[TAR_OFFSET_GID], 8, gid); /* File size 12 */ if (linktarget != NULL || S_ISDIR(mode)) /* Symbolic link or directory has size zero */ - print_tar_number(&h[124], 12, 0); + print_tar_number(&h[TAR_OFFSET_SIZE], 12, 0); else - print_tar_number(&h[124], 12, size); + print_tar_number(&h[TAR_OFFSET_SIZE], 12, size); /* Mod Time 12 */ - print_tar_number(&h[136], 12, mtime); + print_tar_number(&h[TAR_OFFSET_MTIME], 12, mtime); /* Checksum 8 cannot be calculated until we've filled all other fields */ if (linktarget != NULL) { /* Type - Symbolic link */ - h[156] = '2'; + h[TAR_OFFSET_TYPEFLAG] = '2'; /* Link Name 100 */ - strlcpy(&h[157], linktarget, 100); + strlcpy(&h[TAR_OFFSET_LINKNAME], linktarget, 100); } else if (S_ISDIR(mode)) { /* Type - directory */ - h[156] = '5'; + h[TAR_OFFSET_TYPEFLAG] = '5'; } else { /* Type - regular file */ - h[156] = '0'; + h[TAR_OFFSET_TYPEFLAG] = '0'; } /* Magic 6 */ - strcpy(&h[257], "ustar"); + strcpy(&h[TAR_OFFSET_MAGIC], "ustar"); /* Version 2 */ - memcpy(&h[263], "00", 2); + memcpy(&h[TAR_OFFSET_VERSION], "00", 2); /* User 32 */ /* XXX: Do we need to care about setting correct username? */ - strlcpy(&h[265], "postgres", 32); + strlcpy(&h[TAR_OFFSET_UNAME], "postgres", 32); /* Group 32 */ /* XXX: Do we need to care about setting correct group name? */ - strlcpy(&h[297], "postgres", 32); + strlcpy(&h[TAR_OFFSET_GNAME], "postgres", 32); /* Major Dev 8 */ - print_tar_number(&h[329], 8, 0); + print_tar_number(&h[TAR_OFFSET_DEVMAJOR], 8, 0); /* Minor Dev 8 */ - print_tar_number(&h[337], 8, 0); + print_tar_number(&h[TAR_OFFSET_DEVMINOR], 8, 0); /* Prefix 155 - not used, leave as nulls */ /* Finally, compute and insert the checksum */ - print_tar_number(&h[148], 8, tarChecksum(h)); + print_tar_number(&h[TAR_OFFSET_CHECKSUM], 8, tarChecksum(h)); return TAR_OK; } -- 2.37.1 (Apple Git-137.1) ^ permalink raw reply [nested|flat] 50+ messages in thread
* Re: constants for tar header offsets 2023-04-18 15:20 constants for tar header offsets Robert Haas <[email protected]> @ 2023-04-18 15:38 ` Tom Lane <[email protected]> 2023-04-18 15:53 ` Re: constants for tar header offsets Robert Haas <[email protected]> 0 siblings, 1 reply; 50+ messages in thread From: Tom Lane @ 2023-04-18 15:38 UTC (permalink / raw) To: Robert Haas <[email protected]>; +Cc: pgsql-hackers Robert Haas <[email protected]> writes: > We have a few different places in the code where we generate or modify > tar headers or just read data out of them. The code in question uses > one of my less-favorite programming things: magic numbers. The offsets > of the various fields within the tar header are just hard-coded in > each relevant place in our code. I think we should clean that up, as > in the attached patch. Generally +1, with a couple of additional thoughts: 1. Is it worth inventing macros for the values of the file type, rather than just writing the comment you did? 2. The header size is defined as 512 bytes, but this doesn't sum to 512: + TAR_OFFSET_PREFIX = 345 /* 155 byte string */ Either that field's length is really 167 bytes, or there's some other field you didn't document. (It looks like you may have copied "155" from an incorrect existing comment?) > I hasten to emphasize that, while I think this is an improvement, I > don't think the result is particularly awesome. Even with the patch, > src/port/tar.c and src/include/pgtar.h do a poor job insulating > callers from the details of the tar format. However, it's also not > very clear to me how to fix that. Yeah, this is adding greppability (a good thing!) but little more. However, I'm not convinced it's worth doing more. It's not like this data structure will change anytime soon. regards, tom lane ^ permalink raw reply [nested|flat] 50+ messages in thread
* Re: constants for tar header offsets 2023-04-18 15:20 constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 15:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> @ 2023-04-18 15:53 ` Robert Haas <[email protected]> 2023-04-18 16:06 ` Re: constants for tar header offsets Tom Lane <[email protected]> 0 siblings, 1 reply; 50+ messages in thread From: Robert Haas @ 2023-04-18 15:53 UTC (permalink / raw) To: Tom Lane <[email protected]>; +Cc: pgsql-hackers On Tue, Apr 18, 2023 at 11:38 AM Tom Lane <[email protected]> wrote: > Robert Haas <[email protected]> writes: > > We have a few different places in the code where we generate or modify > > tar headers or just read data out of them. The code in question uses > > one of my less-favorite programming things: magic numbers. The offsets > > of the various fields within the tar header are just hard-coded in > > each relevant place in our code. I think we should clean that up, as > > in the attached patch. > > Generally +1, with a couple of additional thoughts: > > 1. Is it worth inventing macros for the values of the file type, > rather than just writing the comment you did? Might be. > 2. The header size is defined as 512 bytes, but this doesn't sum to 512: > > + TAR_OFFSET_PREFIX = 345 /* 155 byte string */ > > Either that field's length is really 167 bytes, or there's some other > field you didn't document. (It looks like you may have copied "155" > from an incorrect existing comment?) According to my research, it is neither of those, e.g. see https://www.subspacefield.org/~vax/tar_format.html https://www.ibm.com/docs/en/zos/2.4.0?topic=formats-tar-format-tar-archives https://wiki.osdev.org/USTAR I think that what happened is that whoever designed the original tar format decided on 512 byte blocks. And the header did not take up the whole block. The USTAR format is an extension of the original format which uses more of the block, but still not all of it. > Yeah, this is adding greppability (a good thing!) but little more. > However, I'm not convinced it's worth doing more. It's not like > this data structure will change anytime soon. Right. greppability is a major concern for me here, and also bug surface. Right now, to use the functions in pgtar.h, you need to know all the header offsets as well as the format and length of each header field. This centralizes constants for the header offsets, and at least provides some centralized documentation of the rest. It's not great, though, because it seems like there's some risk of someone writing new code and getting confused about whether the length of a certain field is 8 or 12, for example. A thicker abstraction layer might be able to avoid or minimize such risks better than what we have, but I don't really know how to design it, whereas this seems like an obvious improvement. -- Robert Haas EDB: http://www.enterprisedb.com ^ permalink raw reply [nested|flat] 50+ messages in thread
* Re: constants for tar header offsets 2023-04-18 15:20 constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 15:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> 2023-04-18 15:53 ` Re: constants for tar header offsets Robert Haas <[email protected]> @ 2023-04-18 16:06 ` Tom Lane <[email protected]> 2023-04-18 16:24 ` Re: constants for tar header offsets Robert Haas <[email protected]> 0 siblings, 1 reply; 50+ messages in thread From: Tom Lane @ 2023-04-18 16:06 UTC (permalink / raw) To: Robert Haas <[email protected]>; +Cc: pgsql-hackers Robert Haas <[email protected]> writes: > On Tue, Apr 18, 2023 at 11:38 AM Tom Lane <[email protected]> wrote: >> 2. The header size is defined as 512 bytes, but this doesn't sum to 512: >> + TAR_OFFSET_PREFIX = 345 /* 155 byte string */ > I think that what happened is that whoever designed the original tar > format decided on 512 byte blocks. And the header did not take up the > whole block. The USTAR format is an extension of the original format > which uses more of the block, but still not all of it. Hmm, you're right: I checked the POSIX.1-2018 spec as well, and it agrees that the prefix field is 155 bytes long. Perhaps just add another comment line indicating that 12 bytes remain unassigned? regards, tom lane ^ permalink raw reply [nested|flat] 50+ messages in thread
* Re: constants for tar header offsets 2023-04-18 15:20 constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 15:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> 2023-04-18 15:53 ` Re: constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 16:06 ` Re: constants for tar header offsets Tom Lane <[email protected]> @ 2023-04-18 16:24 ` Robert Haas <[email protected]> 2023-04-18 16:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> 0 siblings, 1 reply; 50+ messages in thread From: Robert Haas @ 2023-04-18 16:24 UTC (permalink / raw) To: Tom Lane <[email protected]>; +Cc: pgsql-hackers On Tue, Apr 18, 2023 at 12:06 PM Tom Lane <[email protected]> wrote: > Hmm, you're right: I checked the POSIX.1-2018 spec as well, and > it agrees that the prefix field is 155 bytes long. Perhaps just > add another comment line indicating that 12 bytes remain unassigned? OK. Here's v2, with that change and a few others. -- Robert Haas EDB: http://www.enterprisedb.com Attachments: [application/octet-stream] v2-0001-Add-and-use-symbolic-constants-for-tar-header-off.patch (10.0K, ../../CA+Tgmob3wRzUhZbWDQ-6kgs84S+A7CJVsBWcD7+q+mKd3taZ3Q@mail.gmail.com/2-v2-0001-Add-and-use-symbolic-constants-for-tar-header-off.patch) download | inline diff: From 5e7f7dec0b9c3ecf86f2c7fb490e21165fe5a01f Mon Sep 17 00:00:00 2001 From: Robert Haas <[email protected]> Date: Tue, 18 Apr 2023 10:53:02 -0400 Subject: [PATCH v2] Add and use symbolic constants for tar header offsets and file types. Because symbolic constants in a header file are better than magic constants embedded in the code. Patch by me, reviewed by Tom Lane. --- src/bin/pg_basebackup/bbstreamer_tar.c | 22 +++++++-------- src/bin/pg_basebackup/walmethods.c | 7 +++-- src/bin/pg_dump/pg_backup_tar.c | 16 +++++------ src/include/pgtar.h | 39 ++++++++++++++++++++++++++ src/port/tar.c | 38 ++++++++++++------------- 5 files changed, 80 insertions(+), 42 deletions(-) diff --git a/src/bin/pg_basebackup/bbstreamer_tar.c b/src/bin/pg_basebackup/bbstreamer_tar.c index 03d7fd3375..d7b438d0f5 100644 --- a/src/bin/pg_basebackup/bbstreamer_tar.c +++ b/src/bin/pg_basebackup/bbstreamer_tar.c @@ -286,22 +286,20 @@ bbstreamer_tar_header(bbstreamer_tar_parser *mystreamer) /* * Parse key fields out of the header. - * - * FIXME: It's terrible that we use hard-coded values here instead of some - * more principled approach. It's been like this for a long time, but we - * ought to do better. */ - strlcpy(member->pathname, &buffer[0], MAXPGPATH); + strlcpy(member->pathname, &buffer[TAR_OFFSET_NAME], MAXPGPATH); if (member->pathname[0] == '\0') pg_fatal("tar member has empty name"); - member->size = read_tar_number(&buffer[124], 12); - member->mode = read_tar_number(&buffer[100], 8); - member->uid = read_tar_number(&buffer[108], 8); - member->gid = read_tar_number(&buffer[116], 8); - member->is_directory = (buffer[156] == '5'); - member->is_link = (buffer[156] == '2'); + member->size = read_tar_number(&buffer[TAR_OFFSET_SIZE], 12); + member->mode = read_tar_number(&buffer[TAR_OFFSET_MODE], 8); + member->uid = read_tar_number(&buffer[TAR_OFFSET_UID], 8); + member->gid = read_tar_number(&buffer[TAR_OFFSET_GID], 8); + member->is_directory = + (buffer[TAR_OFFSET_TYPEFLAG] == TAR_FILETYPE_DIRECTORY); + member->is_link = + (buffer[TAR_OFFSET_TYPEFLAG] == TAR_FILETYPE_SYMLINK); if (member->is_link) - strlcpy(member->linktarget, &buffer[157], 100); + strlcpy(member->linktarget, &buffer[TAR_OFFSET_LINKNAME], 100); /* Compute number of padding bytes. */ mystreamer->pad_bytes_expected = tarPaddingBytesRequired(member->size); diff --git a/src/bin/pg_basebackup/walmethods.c b/src/bin/pg_basebackup/walmethods.c index 6d14b988cb..a974ffced4 100644 --- a/src/bin/pg_basebackup/walmethods.c +++ b/src/bin/pg_basebackup/walmethods.c @@ -1131,7 +1131,7 @@ tar_close(Walfile *f, WalCloseMethod method) * possibly also renaming the file. We overwrite the entire current header * when done, including the checksum. */ - print_tar_number(&(tf->header[124]), 12, filesize); + print_tar_number(&(tf->header[TAR_OFFSET_SIZE]), 12, filesize); if (method == CLOSE_NORMAL) @@ -1139,9 +1139,10 @@ tar_close(Walfile *f, WalCloseMethod method) * We overwrite it with what it was before if we have no tempname, * since we're going to write the buffer anyway. */ - strlcpy(&(tf->header[0]), tf->base.pathname, 100); + strlcpy(&(tf->header[TAR_OFFSET_NAME]), tf->base.pathname, 100); - print_tar_number(&(tf->header[148]), 8, tarChecksum(((TarMethodFile *) f)->header)); + print_tar_number(&(tf->header[TAR_OFFSET_CHECKSUM]), 8, + tarChecksum(((TarMethodFile *) f)->header)); if (lseek(tar_data->fd, tf->ofs_start, SEEK_SET) != ((TarMethodFile *) f)->ofs_start) { f->wwmethod->lasterrno = errno; diff --git a/src/bin/pg_dump/pg_backup_tar.c b/src/bin/pg_dump/pg_backup_tar.c index babd23b4eb..59870acd17 100644 --- a/src/bin/pg_dump/pg_backup_tar.c +++ b/src/bin/pg_dump/pg_backup_tar.c @@ -975,20 +975,20 @@ isValidTarHeader(char *header) int sum; int chk = tarChecksum(header); - sum = read_tar_number(&header[148], 8); + sum = read_tar_number(&header[TAR_OFFSET_CHECKSUM], 8); if (sum != chk) return false; /* POSIX tar format */ - if (memcmp(&header[257], "ustar\0", 6) == 0 && - memcmp(&header[263], "00", 2) == 0) + if (memcmp(&header[TAR_OFFSET_MAGIC], "ustar\0", 6) == 0 && + memcmp(&header[TAR_OFFSET_VERSION], "00", 2) == 0) return true; /* GNU tar format */ - if (memcmp(&header[257], "ustar \0", 8) == 0) + if (memcmp(&header[TAR_OFFSET_MAGIC], "ustar \0", 8) == 0) return true; /* not-quite-POSIX format written by pre-9.3 pg_dump */ - if (memcmp(&header[257], "ustar00\0", 8) == 0) + if (memcmp(&header[TAR_OFFSET_MAGIC], "ustar00\0", 8) == 0) return true; return false; @@ -1151,7 +1151,7 @@ _tarGetHeader(ArchiveHandle *AH, TAR_MEMBER *th) /* Calc checksum */ chk = tarChecksum(h); - sum = read_tar_number(&h[148], 8); + sum = read_tar_number(&h[TAR_OFFSET_CHECKSUM], 8); /* * If the checksum failed, see if it is a null block. If so, silently @@ -1175,9 +1175,9 @@ _tarGetHeader(ArchiveHandle *AH, TAR_MEMBER *th) } /* Name field is 100 bytes, might not be null-terminated */ - strlcpy(tag, &h[0], 100 + 1); + strlcpy(tag, &h[TAR_OFFSET_NAME], 100 + 1); - len = read_tar_number(&h[124], 12); + len = read_tar_number(&h[TAR_OFFSET_SIZE], 12); pg_log_debug("TOC Entry %s at %llu (length %llu, checksum %d)", tag, (unsigned long long) hPos, (unsigned long long) len, sum); diff --git a/src/include/pgtar.h b/src/include/pgtar.h index 661f9d7c59..8abfb9c19c 100644 --- a/src/include/pgtar.h +++ b/src/include/pgtar.h @@ -23,6 +23,45 @@ enum tarError TAR_SYMLINK_TOO_LONG }; +/* + * Offsets of fields within a 512-byte tar header. + * + * "tar number" values should be generated using print_tar_number() and can be + * read using read_tar_number(). Fields that contain strings are generally + * both filled and read using strlcpy(). + * + * The value for the checksum field can be computed using tarChecksum(). + * + * Some fields are not used by PostgreSQL; see tarCreateHeader(). + */ +enum tarHeaderOffset +{ + TAR_OFFSET_NAME = 0, /* 100 byte string */ + TAR_OFFSET_MODE = 100, /* 8 byte tar number, excludes S_IFMT */ + TAR_OFFSET_UID = 108, /* 8 byte tar number */ + TAR_OFFSET_GID = 116, /* 8 byte tar number */ + TAR_OFFSET_SIZE = 124, /* 8 byte tar number */ + TAR_OFFSET_MTIME = 136, /* 12 byte tar number */ + TAR_OFFSET_CHECKSUM = 148, /* 8 byte tar number */ + TAR_OFFSET_TYPEFLAG = 156, /* 1 byte file type, see TAR_FILETYPE_* */ + TAR_OFFSET_LINKNAME = 157, /* 100 byte string */ + TAR_OFFSET_MAGIC = 257, /* "ustar" with terminating zero byte */ + TAR_OFFSET_VERSION = 263, /* "00" */ + TAR_OFFSET_UNAME = 265, /* 32 byte string */ + TAR_OFFSET_GNAME = 297, /* 32 byte string */ + TAR_OFFSET_DEVMAJOR = 329, /* 8 byte tar number */ + TAR_OFFSET_DEVMINOR = 337, /* 8 byte tar number */ + TAR_OFFSET_PREFIX = 345 /* 155 byte string */ + /* last 12 bytes of the 512-byte block are unassigned */ +}; + +enum tarFileType +{ + TAR_FILETYPE_PLAIN = '0', + TAR_FILETYPE_SYMLINK = '2', + TAR_FILETYPE_DIRECTORY = '5' +}; + extern enum tarError tarCreateHeader(char *h, const char *filename, const char *linktarget, pgoff_t size, mode_t mode, uid_t uid, gid_t gid, diff --git a/src/port/tar.c b/src/port/tar.c index 4afe9f2533..592b4fb7b0 100644 --- a/src/port/tar.c +++ b/src/port/tar.c @@ -120,10 +120,10 @@ tarCreateHeader(char *h, const char *filename, const char *linktarget, if (linktarget && strlen(linktarget) > 99) return TAR_SYMLINK_TOO_LONG; - memset(h, 0, 512); /* assume tar header size */ + memset(h, 0, TAR_BLOCK_SIZE); /* Name 100 */ - strlcpy(&h[0], filename, 100); + strlcpy(&h[TAR_OFFSET_NAME], filename, 100); if (linktarget != NULL || S_ISDIR(mode)) { /* @@ -139,68 +139,68 @@ tarCreateHeader(char *h, const char *filename, const char *linktarget, } /* Mode 8 - this doesn't include the file type bits (S_IFMT) */ - print_tar_number(&h[100], 8, (mode & 07777)); + print_tar_number(&h[TAR_OFFSET_MODE], 8, (mode & 07777)); /* User ID 8 */ - print_tar_number(&h[108], 8, uid); + print_tar_number(&h[TAR_OFFSET_UID], 8, uid); /* Group 8 */ - print_tar_number(&h[116], 8, gid); + print_tar_number(&h[TAR_OFFSET_GID], 8, gid); /* File size 12 */ if (linktarget != NULL || S_ISDIR(mode)) /* Symbolic link or directory has size zero */ - print_tar_number(&h[124], 12, 0); + print_tar_number(&h[TAR_OFFSET_SIZE], 12, 0); else - print_tar_number(&h[124], 12, size); + print_tar_number(&h[TAR_OFFSET_SIZE], 12, size); /* Mod Time 12 */ - print_tar_number(&h[136], 12, mtime); + print_tar_number(&h[TAR_OFFSET_MTIME], 12, mtime); /* Checksum 8 cannot be calculated until we've filled all other fields */ if (linktarget != NULL) { /* Type - Symbolic link */ - h[156] = '2'; + h[TAR_OFFSET_TYPEFLAG] = TAR_FILETYPE_SYMLINK; /* Link Name 100 */ - strlcpy(&h[157], linktarget, 100); + strlcpy(&h[TAR_OFFSET_LINKNAME], linktarget, 100); } else if (S_ISDIR(mode)) { /* Type - directory */ - h[156] = '5'; + h[TAR_OFFSET_TYPEFLAG] = TAR_FILETYPE_DIRECTORY; } else { /* Type - regular file */ - h[156] = '0'; + h[TAR_OFFSET_TYPEFLAG] = TAR_FILETYPE_PLAIN; } /* Magic 6 */ - strcpy(&h[257], "ustar"); + strcpy(&h[TAR_OFFSET_MAGIC], "ustar"); /* Version 2 */ - memcpy(&h[263], "00", 2); + memcpy(&h[TAR_OFFSET_VERSION], "00", 2); /* User 32 */ /* XXX: Do we need to care about setting correct username? */ - strlcpy(&h[265], "postgres", 32); + strlcpy(&h[TAR_OFFSET_UNAME], "postgres", 32); /* Group 32 */ /* XXX: Do we need to care about setting correct group name? */ - strlcpy(&h[297], "postgres", 32); + strlcpy(&h[TAR_OFFSET_GNAME], "postgres", 32); /* Major Dev 8 */ - print_tar_number(&h[329], 8, 0); + print_tar_number(&h[TAR_OFFSET_DEVMAJOR], 8, 0); /* Minor Dev 8 */ - print_tar_number(&h[337], 8, 0); + print_tar_number(&h[TAR_OFFSET_DEVMINOR], 8, 0); /* Prefix 155 - not used, leave as nulls */ /* Finally, compute and insert the checksum */ - print_tar_number(&h[148], 8, tarChecksum(h)); + print_tar_number(&h[TAR_OFFSET_CHECKSUM], 8, tarChecksum(h)); return TAR_OK; } -- 2.37.1 (Apple Git-137.1) ^ permalink raw reply [nested|flat] 50+ messages in thread
* Re: constants for tar header offsets 2023-04-18 15:20 constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 15:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> 2023-04-18 15:53 ` Re: constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 16:06 ` Re: constants for tar header offsets Tom Lane <[email protected]> 2023-04-18 16:24 ` Re: constants for tar header offsets Robert Haas <[email protected]> @ 2023-04-18 16:38 ` Tom Lane <[email protected]> 0 siblings, 0 replies; 50+ messages in thread From: Tom Lane @ 2023-04-18 16:38 UTC (permalink / raw) To: Robert Haas <[email protected]>; +Cc: pgsql-hackers Robert Haas <[email protected]> writes: > OK. Here's v2, with that change and a few others. LGTM. regards, tom lane ^ permalink raw reply [nested|flat] 50+ messages in thread
end of thread, other threads:[~2023-04-18 16:38 UTC | newest] Thread overview: 50+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 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 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 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 v2 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 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 v3 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 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 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 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 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 v1 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 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]> 2023-04-18 15:20 constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 15:38 ` Re: constants for tar header offsets Tom Lane <[email protected]> 2023-04-18 15:53 ` Re: constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 16:06 ` Re: constants for tar header offsets Tom Lane <[email protected]> 2023-04-18 16:24 ` Re: constants for tar header offsets Robert Haas <[email protected]> 2023-04-18 16:38 ` Re: constants for tar header offsets Tom Lane <[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