public inbox for [email protected]help / color / mirror / Atom feed
[PATCH v6 3/3] async postgres_fdw 2+ messages / 2 participants [nested] [flat]
* [PATCH v6 3/3] async postgres_fdw @ 2017-10-19 08:24 Kyotaro Horiguchi <[email protected]> 0 siblings, 0 replies; 2+ 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] 2+ messages in thread
* [PATCH] Teach REPACK to upgrade its lock safely. @ 2026-04-14 09:59 Antonin Houska <[email protected]> 0 siblings, 0 replies; 2+ messages in thread From: Antonin Houska @ 2026-04-14 09:59 UTC (permalink / raw) REPACK (CONCURRENTLY) needs to upgrade its ShareUpdateExclusiveLock (SUEL) to AccessExclusiveLock at the end of table processing. If another session, which already has a non-conflicting lock on the table, tried to get SUEL too, it would end up in a deadlock with REPACK. Such situation does not hurt as long as the deadlock detector choses to terminate the other session, but it's possible that it terminates REPACK. A lot of REPACK's work would be wasted this way. This patch checks for such situation, and if the other session tries to get the SUEL, it receives a deadlock report before it actually starts waiting. Please note that the other session can safely run VACUUM w/o receiving the deadlock report. The point is that VACUUM cannot run in a transaction block, so the session cannot have any other lock when trying to get SUEL on the table. In that case, REPACK gets its AccessExclusiveLock first, even if VACUUM requested SUEL earlier. VACUUM then just needs wait for REPACK to finish, and then it can start. --- src/backend/commands/repack.c | 25 +++++++- src/backend/storage/lmgr/deadlock.c | 10 ++-- src/backend/storage/lmgr/lock.c | 30 ++++++++++ src/backend/storage/lmgr/proc.c | 55 ++++++++++++++++- src/include/storage/lock.h | 5 +- src/include/storage/proc.h | 6 +- .../injection_points/expected/repack.out | 59 ++++++++++++++++++- .../injection_points/specs/repack.spec | 29 +++++++++ 8 files changed, 209 insertions(+), 10 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 58e3867246f..e9193067666 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -285,6 +285,18 @@ ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) * to understand and we don't lose any functionality. */ PreventInTransactionBlock(isTopLevel, "REPACK (CONCURRENTLY)"); + + /* + * Also set the PROC_IN_CONCURRENT_REPACK flag. This makes the lock + * manager cause anyone that would conflict with us to error out. + * It's important to set this flag ahead of actually locking the + * relation; it won't of course affect anyone until we do have a lock + * that others can conflict with. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags |= PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); } /* @@ -3086,7 +3098,18 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, LockRelationOid(OldHeap->rd_rel->reltoastrelid, AccessExclusiveLock); /* - * Tuples and pages of the old heap will be gone, but the heap will stay. + * Now that we have all access-exclusive locks on all relations, we no + * longer want other processes to error out when trying to acquire a + * conflicting lock. Therefore, unset our flag. + */ + LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE); + MyProc->statusFlags &= ~PROC_IN_CONCURRENT_REPACK; + ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags; + LWLockRelease(ProcArrayLock); + + /* + * Tuples and pages of the old heap will be gone, but the heap itself will + * stay. */ TransferPredicateLocksToHeapRelation(OldHeap); foreach_ptr(RelationData, index, indexrels) diff --git a/src/backend/storage/lmgr/deadlock.c b/src/backend/storage/lmgr/deadlock.c index b8962d875b6..3772a7aa3df 100644 --- a/src/backend/storage/lmgr/deadlock.c +++ b/src/backend/storage/lmgr/deadlock.c @@ -1146,8 +1146,10 @@ DeadLockReport(void) void RememberSimpleDeadLock(PGPROC *proc1, LOCKMODE lockmode, - LOCK *lock, - PGPROC *proc2) + LOCK *lock, /* XXX Only lockmode? */ + PGPROC *proc2, + LOCKMODE lockmode2, + LOCKTAG *locktag2) { DEADLOCK_INFO *info = &deadlockDetails[0]; @@ -1155,8 +1157,8 @@ RememberSimpleDeadLock(PGPROC *proc1, info->lockmode = lockmode; info->pid = proc1->pid; info++; - info->locktag = proc2->waitLock->tag; - info->lockmode = proc2->waitLockMode; + info->locktag = *locktag2; + info->lockmode = lockmode2; info->pid = proc2->pid; nDeadlockDetails = 2; } diff --git a/src/backend/storage/lmgr/lock.c b/src/backend/storage/lmgr/lock.c index c221fe96889..44aa2ca26a7 100644 --- a/src/backend/storage/lmgr/lock.c +++ b/src/backend/storage/lmgr/lock.c @@ -674,6 +674,36 @@ LockHeldByMe(const LOCKTAG *locktag, return false; } +/* + * HaveRelLock -- test whether the current backend has a fast path lock on + * the relation in any mode. + */ +bool +HaveFastPathLock(Oid relid) +{ + uint32 group = FAST_PATH_REL_GROUP(relid); + bool result = false; + + LWLockAcquire(&MyProc->fpInfoLock, LW_SHARED); + for (int i = 0; i < FP_LOCK_SLOTS_PER_GROUP; i++) + { + uint32 f = FAST_PATH_SLOT(group, i); + uint32 lockmask; + + if (relid != MyProc->fpRelId[f]) + continue; + lockmask = FAST_PATH_GET_BITS(MyProc, f); + if (lockmask) + { + result = true; + break; + } + } + LWLockRelease(&MyProc->fpInfoLock); + + return result; +} + #ifdef USE_ASSERT_CHECKING /* * GetLockMethodLocalHash -- return the hash of local locks, for modules that diff --git a/src/backend/storage/lmgr/proc.c b/src/backend/storage/lmgr/proc.c index 1ac25068d62..3d47b1284a3 100644 --- a/src/backend/storage/lmgr/proc.c +++ b/src/backend/storage/lmgr/proc.c @@ -1156,6 +1156,7 @@ JoinWaitQueue(LOCALLOCK *locallock, LockMethod lockMethodTable, bool dontWait) LOCKMASK myHeldLocks; bool early_deadlock = false; PGPROC *leader = MyProc->lockGroupLeader; + bool check_repack = false; Assert(LWLockHeldByMeInMode(partitionLock, LW_EXCLUSIVE)); @@ -1193,6 +1194,56 @@ JoinWaitQueue(LOCALLOCK *locallock, LockMethod lockMethodTable, bool dontWait) } } + /* + * If I am already holding this lock (in any mode) and trying to get + * ShareUpdateExclusiveLock (or higher), check if REPACK (CONCURRENTLY) is + * already holding ShareUpdateExclusiveLock. The problem is if that by + * trying to upgrade the lock to AccessExclusiveLock it would get into a + * deadlock with us. + */ + if (lock->tag.locktag_type == LOCKTAG_RELATION && + lock->tag.locktag_field1 == MyDatabaseId && + lockmode >= ShareUpdateExclusiveLock) + { + if (myHeldLocks > 0 || + HaveFastPathLock(lock->tag.locktag_field2)) + check_repack = true; + } + if (check_repack) + { + dlist_iter iter; + + dlist_foreach(iter, &lock->procLocks) + { + PROCLOCK *otherproclock; + PGPROC *otherproc; + + otherproclock = dlist_container(PROCLOCK, lockLink, iter.cur); + otherproc = otherproclock->tag.myProc; + if (otherproc != MyProc && + otherproc->statusFlags & PROC_IN_CONCURRENT_REPACK) + { + LOCKMASK repackmask = otherproclock->holdMask; + + /* + * Is REPACK already holding ShareUpdateExclusiveLock? + */ + if ((repackmask & LOCKBIT_ON(ShareUpdateExclusiveLock)) != 0) + { + /* + * There should be no more than one REPACK working on + * particular table, so let's error out. + */ + RememberSimpleDeadLock(MyProc, lockmode, lock, + otherproc, + ShareUpdateExclusiveLock, + &otherproclock->tag.myLock->tag); + return PROC_WAIT_STATUS_ERROR; + } + } + } + } + /* * Determine where to add myself in the wait queue. * @@ -1240,7 +1291,9 @@ JoinWaitQueue(LOCALLOCK *locallock, LockMethod lockMethodTable, bool dontWait) * a flag to check below, and break out of loop. Also, * record deadlock info for later message. */ - RememberSimpleDeadLock(MyProc, lockmode, lock, proc); + RememberSimpleDeadLock(MyProc, lockmode, lock, proc, + proc->waitLockMode, + &proc->waitLock->tag); early_deadlock = true; break; } diff --git a/src/include/storage/lock.h b/src/include/storage/lock.h index ee3cb1dc203..85804d61ce9 100644 --- a/src/include/storage/lock.h +++ b/src/include/storage/lock.h @@ -401,6 +401,7 @@ extern void LockReleaseCurrentOwner(LOCALLOCK **locallocks, int nlocks); extern void LockReassignCurrentOwner(LOCALLOCK **locallocks, int nlocks); extern bool LockHeldByMe(const LOCKTAG *locktag, LOCKMODE lockmode, bool orstronger); +extern bool HaveFastPathLock(Oid relid); #ifdef USE_ASSERT_CHECKING extern HTAB *GetLockMethodLocalHash(void); #endif @@ -440,7 +441,9 @@ pg_noreturn extern void DeadLockReport(void); extern void RememberSimpleDeadLock(PGPROC *proc1, LOCKMODE lockmode, LOCK *lock, - PGPROC *proc2); + PGPROC *proc2, + LOCKMODE lockmode2, + LOCKTAG *locktag2); extern void InitDeadLockChecking(void); extern int LockWaiterCount(const LOCKTAG *locktag); diff --git a/src/include/storage/proc.h b/src/include/storage/proc.h index 3e1d1fad5f9..76c6bb44251 100644 --- a/src/include/storage/proc.h +++ b/src/include/storage/proc.h @@ -70,10 +70,12 @@ struct XidCache #define PROC_AFFECTS_ALL_HORIZONS 0x20 /* this proc's xmin must be * included in vacuum horizons * in all databases */ +#define PROC_IN_CONCURRENT_REPACK 0x40 /* REPACK (CONCURRENTLY) */ -/* flags reset at EOXact */ +/* flags reset at EOXact. A bit of a misnomer ... */ #define PROC_VACUUM_STATE_MASK \ - (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND) + (PROC_IN_VACUUM | PROC_IN_SAFE_IC | PROC_VACUUM_FOR_WRAPAROUND | \ + PROC_IN_CONCURRENT_REPACK) /* * Xmin-related flags. Make sure any flags that affect how the process' Xmin diff --git a/src/test/modules/injection_points/expected/repack.out b/src/test/modules/injection_points/expected/repack.out index b575e9052ee..960044776f4 100644 --- a/src/test/modules/injection_points/expected/repack.out +++ b/src/test/modules/injection_points/expected/repack.out @@ -1,4 +1,4 @@ -Parsed test spec with 2 sessions +Parsed test spec with 3 sessions starting permutation: wait_before_lock change_existing change_new change_subxact1 change_subxact2 check2 wakeup_before_lock check1 injection_points_attach @@ -111,3 +111,60 @@ injection_points_detach (1 row) + +starting permutation: check1_relnode_only wait_before_lock lock3 wakeup_before_lock check1_relnode_only +injection_points_attach +----------------------- + +(1 row) + +step check1_relnode_only: + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_test'; + + SELECT count(DISTINCT node) FROM relfilenodes; + +count +----- + 1 +(1 row) + +step wait_before_lock: + REPACK (CONCURRENTLY) repack_test USING INDEX repack_test_pkey; + <waiting ...> +step lock3: + BEGIN; + SELECT * FROM repack_test ORDER BY i LIMIT 1; + LOCK TABLE repack_test IN SHARE UPDATE EXCLUSIVE MODE; + +i|j +-+- +1|1 +(1 row) + +ERROR: deadlock detected +step wakeup_before_lock: + SELECT injection_points_wakeup('repack-concurrently-before-lock'); + +injection_points_wakeup +----------------------- + +(1 row) + +step wait_before_lock: <... completed> +step check1_relnode_only: + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_test'; + + SELECT count(DISTINCT node) FROM relfilenodes; + +count +----- + 2 +(1 row) + +injection_points_detach +----------------------- + +(1 row) + diff --git a/src/test/modules/injection_points/specs/repack.spec b/src/test/modules/injection_points/specs/repack.spec index d727a9b056b..5ffcb558718 100644 --- a/src/test/modules/injection_points/specs/repack.spec +++ b/src/test/modules/injection_points/specs/repack.spec @@ -55,6 +55,13 @@ step check1 FROM data_s1 d1 FULL JOIN data_s2 d2 USING (i, j) WHERE d1.i ISNULL OR d2.i ISNULL; } +step check1_relnode_only +{ + INSERT INTO relfilenodes(node) + SELECT relfilenode FROM pg_class WHERE relname='repack_test'; + + SELECT count(DISTINCT node) FROM relfilenodes; +} teardown { SELECT injection_points_detach('repack-concurrently-before-lock'); @@ -129,6 +136,20 @@ step wakeup_before_lock SELECT injection_points_wakeup('repack-concurrently-before-lock'); } +session s3 +# Try to acquire SharedUpdateExclusiveLock on a table while REPACK is already +# holding it and before it tries to upgrade it to AccessExclusiveLock. Since +# this session is already holding another lock no the table, REPACK cannot +# resolve the problem by getting ahead in the wait queue. The solution is that +# the LOCK TABLE triggers a deadlock report. The deadlock does not actually +# take place, but it would if this session started to wait. +step lock3 +{ + BEGIN; + SELECT * FROM repack_test ORDER BY i LIMIT 1; + LOCK TABLE repack_test IN SHARE UPDATE EXCLUSIVE MODE; +} + # Test if data changes introduced while one session is performing REPACK # CONCURRENTLY find their way into the table. permutation @@ -140,3 +161,11 @@ permutation check2 wakeup_before_lock check1 + +# See 'lock3' above. We check relnodes to make sure that REPACK finished. +permutation + check1_relnode_only + wait_before_lock + lock3 + wakeup_before_lock + check1_relnode_only -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 2+ messages in thread
end of thread, other threads:[~2026-04-14 09:59 UTC | newest] Thread overview: 2+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2017-10-19 08:24 [PATCH v6 3/3] async postgres_fdw Kyotaro Horiguchi <[email protected]> 2026-04-14 09:59 [PATCH] Teach REPACK to upgrade its lock safely. Antonin Houska <[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