From 7b2eb72b1b8ce4279e42848a3978e781ae239355 Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Thu, 3 Jul 2025 08:41:25 +0900 Subject: [PATCH 1/3] Add InjectionPointList() to retrieve list of injection points This routine has come as a useful piece to be able to know the list of injection points currently attached in a system. One area would be to use it in a set-returning function, or just let out-of-core code play with it. This hides the internals of the shared memory array lookup holding the information about the injection points (point name, library and function name), allocating the result in a palloc'd List consumable by the caller. Reviewed-by: Jeff Davis Reviewed-by: Hayato Kuroda Reviewed-by: Rahila Syed Discussion: https://postgr.es/m/Z_xYkA21KyLEHvWR@paquier.xyz Discussion: https://postgr.es/m/aBG2rPwl3GE7m1-Q@paquier.xyz --- src/backend/utils/misc/injection_point.c | 46 ++++++++++++++++++++++++ src/include/utils/injection_point.h | 16 +++++++++ src/tools/pgindent/typedefs.list | 1 + 3 files changed, 63 insertions(+) diff --git a/src/backend/utils/misc/injection_point.c b/src/backend/utils/misc/injection_point.c index f58ebc8ee522d..83b887b697807 100644 --- a/src/backend/utils/misc/injection_point.c +++ b/src/backend/utils/misc/injection_point.c @@ -584,3 +584,49 @@ IsInjectionPointAttached(const char *name) return false; /* silence compiler */ #endif } + +/* + * Retrieve a list of all the injection points currently attached. + * + * This list is palloc'd in the current memory context. + */ +List * +InjectionPointList(void) +{ +#ifdef USE_INJECTION_POINTS + List *inj_points = NIL; + uint32 max_inuse; + + LWLockAcquire(InjectionPointLock, LW_SHARED); + + max_inuse = pg_atomic_read_u32(&ActiveInjectionPoints->max_inuse); + + for (uint32 idx = 0; idx < max_inuse; idx++) + { + InjectionPointEntry *entry; + InjectionPointData *inj_point; + uint64 generation; + + entry = &ActiveInjectionPoints->entries[idx]; + generation = pg_atomic_read_u64(&entry->generation); + + /* skip free slots */ + if (generation % 2 == 0) + continue; + + inj_point = (InjectionPointData *) palloc0(sizeof(InjectionPointData)); + inj_point->name = pstrdup(entry->name); + inj_point->library = pstrdup(entry->library); + inj_point->function = pstrdup(entry->function); + inj_points = lappend(inj_points, inj_point); + } + + LWLockRelease(InjectionPointLock); + + return inj_points; + +#else + elog(ERROR, "Injection points are not supported by this build"); + return NIL; /* keep compiler quiet */ +#endif +} diff --git a/src/include/utils/injection_point.h b/src/include/utils/injection_point.h index a37958e1835fd..fd5bc061b7bdf 100644 --- a/src/include/utils/injection_point.h +++ b/src/include/utils/injection_point.h @@ -11,6 +11,19 @@ #ifndef INJECTION_POINT_H #define INJECTION_POINT_H +#include "nodes/pg_list.h" + +/* + * Injection point data, used when retrieving a list of all the attached + * injection points. + */ +typedef struct InjectionPointData +{ + const char *name; + const char *library; + const char *function; +} InjectionPointData; + /* * Injection points require --enable-injection-points. */ @@ -47,6 +60,9 @@ extern void InjectionPointCached(const char *name, void *arg); extern bool IsInjectionPointAttached(const char *name); extern bool InjectionPointDetach(const char *name); +/* Get the current set of injection points attached */ +extern List *InjectionPointList(void); + #ifdef EXEC_BACKEND extern PGDLLIMPORT struct InjectionPointsCtl *ActiveInjectionPoints; #endif diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index baf636a764397..66c5782688a23 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -1291,6 +1291,7 @@ InjectionPointCacheEntry InjectionPointCallback InjectionPointCondition InjectionPointConditionType +InjectionPointData InjectionPointEntry InjectionPointSharedState InjectionPointsCtl From 0da29e4cb161f78a5ef534b3fb4467756a422e25 Mon Sep 17 00:00:00 2001 From: Richard Guo Date: Thu, 3 Jul 2025 10:57:26 +0900 Subject: [PATCH 2/3] Enable use of Memoize for ANTI joins Currently, we do not support Memoize for SEMI and ANTI joins because nested loop SEMI/ANTI joins do not scan the inner relation to completion, which prevents Memoize from marking the cache entry as complete. One might argue that we could mark the cache entry as complete after fetching the first inner tuple, but that would not be safe: if the first inner tuple and the current outer tuple do not satisfy the join clauses, a second inner tuple matching the parameters would find the cache entry already marked as complete. However, if the inner side is provably unique, this issue doesn't arise, since there would be no second matching tuple. That said, this doesn't help in the case of SEMI joins, because a SEMI join with a provably unique inner side would already have been reduced to an inner join by reduce_unique_semijoins. Therefore, in this patch, we check whether the inner relation is provably unique for ANTI joins and enable the use of Memoize in such cases. Author: Richard Guo Reviewed-by: wenhui qiu Reviewed-by: Andrei Lepikhov Discussion: https://postgr.es/m/CAMbWs48FdLiMNrmJL-g6mDvoQVt0yNyJAqMkv4e2Pk-5GKCZLA@mail.gmail.com --- src/backend/optimizer/path/joinpath.c | 47 +++++++++++---------- src/test/regress/expected/memoize.out | 60 +++++++++++++++++++++++++++ src/test/regress/sql/memoize.sql | 27 ++++++++++++ 3 files changed, 112 insertions(+), 22 deletions(-) diff --git a/src/backend/optimizer/path/joinpath.c b/src/backend/optimizer/path/joinpath.c index 7aa8f5d799cac..ebedc5574ca9c 100644 --- a/src/backend/optimizer/path/joinpath.c +++ b/src/backend/optimizer/path/joinpath.c @@ -154,13 +154,17 @@ add_paths_to_joinrel(PlannerInfo *root, /* * See if the inner relation is provably unique for this outer rel. * - * We have some special cases: for JOIN_SEMI and JOIN_ANTI, it doesn't - * matter since the executor can make the equivalent optimization anyway; - * we need not expend planner cycles on proofs. For JOIN_UNIQUE_INNER, we - * must be considering a semijoin whose inner side is not provably unique - * (else reduce_unique_semijoins would've simplified it), so there's no - * point in calling innerrel_is_unique. However, if the LHS covers all of - * the semijoin's min_lefthand, then it's appropriate to set inner_unique + * We have some special cases: for JOIN_SEMI, it doesn't matter since the + * executor can make the equivalent optimization anyway. It also doesn't + * help enable use of Memoize, since a semijoin with a provably unique + * inner side should have been reduced to an inner join in that case. + * Therefore, we need not expend planner cycles on proofs. (For + * JOIN_ANTI, although it doesn't help the executor for the same reason, + * it can benefit Memoize paths.) For JOIN_UNIQUE_INNER, we must be + * considering a semijoin whose inner side is not provably unique (else + * reduce_unique_semijoins would've simplified it), so there's no point in + * calling innerrel_is_unique. However, if the LHS covers all of the + * semijoin's min_lefthand, then it's appropriate to set inner_unique * because the path produced by create_unique_path will be unique relative * to the LHS. (If we have an LHS that's only part of the min_lefthand, * that is *not* true.) For JOIN_UNIQUE_OUTER, pass JOIN_INNER to avoid @@ -169,12 +173,6 @@ add_paths_to_joinrel(PlannerInfo *root, switch (jointype) { case JOIN_SEMI: - case JOIN_ANTI: - - /* - * XXX it may be worth proving this to allow a Memoize to be - * considered for Nested Loop Semi/Anti Joins. - */ extra.inner_unique = false; /* well, unproven */ break; case JOIN_UNIQUE_INNER: @@ -715,16 +713,21 @@ get_memoize_path(PlannerInfo *root, RelOptInfo *innerrel, return NULL; /* - * Currently we don't do this for SEMI and ANTI joins unless they're - * marked as inner_unique. This is because nested loop SEMI/ANTI joins - * don't scan the inner node to completion, which will mean memoize cannot - * mark the cache entry as complete. - * - * XXX Currently we don't attempt to mark SEMI/ANTI joins as inner_unique - * = true. Should we? See add_paths_to_joinrel() + * Currently we don't do this for SEMI and ANTI joins, because nested loop + * SEMI/ANTI joins don't scan the inner node to completion, which means + * memoize cannot mark the cache entry as complete. Nor can we mark the + * cache entry as complete after fetching the first inner tuple, because + * if that tuple and the current outer tuple don't satisfy the join + * clauses, a second inner tuple that satisfies the parameters would find + * the cache entry already marked as complete. The only exception is when + * the inner relation is provably unique, as in that case, there won't be + * a second matching tuple and we can safely mark the cache entry as + * complete after fetching the first inner tuple. Note that in such + * cases, the SEMI join should have been reduced to an inner join by + * reduce_unique_semijoins. */ - if (!extra->inner_unique && (jointype == JOIN_SEMI || - jointype == JOIN_ANTI)) + if ((jointype == JOIN_SEMI || jointype == JOIN_ANTI) && + !extra->inner_unique) return NULL; /* diff --git a/src/test/regress/expected/memoize.out b/src/test/regress/expected/memoize.out index 38dfaf021c91d..150dc1b44cf62 100644 --- a/src/test/regress/expected/memoize.out +++ b/src/test/regress/expected/memoize.out @@ -25,6 +25,7 @@ begin ln := regexp_replace(ln, 'Heap Fetches: \d+', 'Heap Fetches: N'); ln := regexp_replace(ln, 'loops=\d+', 'loops=N'); ln := regexp_replace(ln, 'Index Searches: \d+', 'Index Searches: N'); + ln := regexp_replace(ln, 'Memory: \d+kB', 'Memory: NkB'); return next ln; end loop; end; @@ -500,3 +501,62 @@ RESET max_parallel_workers_per_gather; RESET parallel_tuple_cost; RESET parallel_setup_cost; RESET min_parallel_table_scan_size; +-- Ensure memoize works for ANTI joins +CREATE TABLE tab_anti (a int, b boolean); +INSERT INTO tab_anti SELECT i%3, false FROM generate_series(1,100)i; +ANALYZE tab_anti; +-- Ensure we get a Memoize plan for ANTI join +SELECT explain_memoize(' +SELECT COUNT(*) FROM tab_anti t1 LEFT JOIN +LATERAL (SELECT DISTINCT ON (a) a, b, t1.a AS x FROM tab_anti t2) t2 +ON t1.a+1 = t2.a +WHERE t2.a IS NULL;', false); + explain_memoize +-------------------------------------------------------------------------------------------- + Aggregate (actual rows=1.00 loops=N) + -> Nested Loop Anti Join (actual rows=33.00 loops=N) + -> Seq Scan on tab_anti t1 (actual rows=100.00 loops=N) + -> Memoize (actual rows=0.67 loops=N) + Cache Key: (t1.a + 1), t1.a + Cache Mode: binary + Hits: 97 Misses: 3 Evictions: Zero Overflows: 0 Memory Usage: NkB + -> Subquery Scan on t2 (actual rows=0.67 loops=N) + Filter: ((t1.a + 1) = t2.a) + Rows Removed by Filter: 2 + -> Unique (actual rows=2.67 loops=N) + -> Sort (actual rows=67.33 loops=N) + Sort Key: t2_1.a + Sort Method: quicksort Memory: NkB + -> Seq Scan on tab_anti t2_1 (actual rows=100.00 loops=N) +(15 rows) + +-- And check we get the expected results. +SELECT COUNT(*) FROM tab_anti t1 LEFT JOIN +LATERAL (SELECT DISTINCT ON (a) a, b, t1.a AS x FROM tab_anti t2) t2 +ON t1.a+1 = t2.a +WHERE t2.a IS NULL; + count +------- + 33 +(1 row) + +-- Ensure we do not add memoize node for SEMI join +EXPLAIN (COSTS OFF) +SELECT * FROM tab_anti t1 WHERE t1.a IN + (SELECT a FROM tab_anti t2 WHERE t2.b IN + (SELECT t1.b FROM tab_anti t3 WHERE t2.a > 1 OFFSET 0)); + QUERY PLAN +------------------------------------------------- + Nested Loop Semi Join + -> Seq Scan on tab_anti t1 + -> Nested Loop Semi Join + Join Filter: (t1.a = t2.a) + -> Seq Scan on tab_anti t2 + -> Subquery Scan on "ANY_subquery" + Filter: (t2.b = "ANY_subquery".b) + -> Result + One-Time Filter: (t2.a > 1) + -> Seq Scan on tab_anti t3 +(10 rows) + +DROP TABLE tab_anti; diff --git a/src/test/regress/sql/memoize.sql b/src/test/regress/sql/memoize.sql index c0d47fa875ad9..8d1cdd6990c87 100644 --- a/src/test/regress/sql/memoize.sql +++ b/src/test/regress/sql/memoize.sql @@ -26,6 +26,7 @@ begin ln := regexp_replace(ln, 'Heap Fetches: \d+', 'Heap Fetches: N'); ln := regexp_replace(ln, 'loops=\d+', 'loops=N'); ln := regexp_replace(ln, 'Index Searches: \d+', 'Index Searches: N'); + ln := regexp_replace(ln, 'Memory: \d+kB', 'Memory: NkB'); return next ln; end loop; end; @@ -244,3 +245,29 @@ RESET max_parallel_workers_per_gather; RESET parallel_tuple_cost; RESET parallel_setup_cost; RESET min_parallel_table_scan_size; + +-- Ensure memoize works for ANTI joins +CREATE TABLE tab_anti (a int, b boolean); +INSERT INTO tab_anti SELECT i%3, false FROM generate_series(1,100)i; +ANALYZE tab_anti; + +-- Ensure we get a Memoize plan for ANTI join +SELECT explain_memoize(' +SELECT COUNT(*) FROM tab_anti t1 LEFT JOIN +LATERAL (SELECT DISTINCT ON (a) a, b, t1.a AS x FROM tab_anti t2) t2 +ON t1.a+1 = t2.a +WHERE t2.a IS NULL;', false); + +-- And check we get the expected results. +SELECT COUNT(*) FROM tab_anti t1 LEFT JOIN +LATERAL (SELECT DISTINCT ON (a) a, b, t1.a AS x FROM tab_anti t2) t2 +ON t1.a+1 = t2.a +WHERE t2.a IS NULL; + +-- Ensure we do not add memoize node for SEMI join +EXPLAIN (COSTS OFF) +SELECT * FROM tab_anti t1 WHERE t1.a IN + (SELECT a FROM tab_anti t2 WHERE t2.b IN + (SELECT t1.b FROM tab_anti t3 WHERE t2.a > 1 OFFSET 0)); + +DROP TABLE tab_anti; From fd7d7b719137b5c427681a50c0a0ac2d745b68bd Mon Sep 17 00:00:00 2001 From: Michael Paquier Date: Thu, 3 Jul 2025 11:14:20 +0900 Subject: [PATCH 3/3] Improve checks for GUC recovery_target_timeline Currently check_recovery_target_timeline() converts any value that is not "current", "latest", or a valid integer to 0. So, for example, the following configuration added to postgresql.conf followed by a startup: recovery_target_timeline = 'bogus' recovery_target_timeline = '9999999999' ... results in the following error patterns: FATAL: 22023: recovery target timeline 0 does not exist FATAL: 22023: recovery target timeline 1410065407 does not exist This is confusing, because the server does not reflect the intention of the user, and just reports incorrect data unrelated to the GUC. The origin of the problem is that we do not perform a range check in the GUC value passed-in for recovery_target_timeline. This commit improves the situation by using strtou64() and by providing stricter range checks. Some test cases are added for the cases of an incorrect, an upper-bound and a lower-bound timeline value, checking the sanity of the reports based on the contents of the server logs. Author: David Steele Discussion: https://postgr.es/m/e5d472c7-e9be-4710-8dc4-ebe721b62cea@pgbackrest.org --- src/backend/access/transam/xlogrecovery.c | 18 ++++++-- src/test/recovery/t/003_recovery_targets.pl | 50 +++++++++++++++++++++ 2 files changed, 65 insertions(+), 3 deletions(-) diff --git a/src/backend/access/transam/xlogrecovery.c b/src/backend/access/transam/xlogrecovery.c index 6ce979f2d8bc4..93d389148549c 100644 --- a/src/backend/access/transam/xlogrecovery.c +++ b/src/backend/access/transam/xlogrecovery.c @@ -4994,13 +4994,25 @@ check_recovery_target_timeline(char **newval, void **extra, GucSource source) rttg = RECOVERY_TARGET_TIMELINE_LATEST; else { + char *endp; + uint64 timeline; + rttg = RECOVERY_TARGET_TIMELINE_NUMERIC; errno = 0; - strtoul(*newval, NULL, 0); - if (errno == EINVAL || errno == ERANGE) + timeline = strtou64(*newval, &endp, 0); + + if (*endp != '\0' || errno == EINVAL || errno == ERANGE) + { + GUC_check_errdetail("\"%s\" is not a valid number.", + "recovery_target_timeline"); + return false; + } + + if (timeline < 1 || timeline > PG_UINT32_MAX) { - GUC_check_errdetail("\"recovery_target_timeline\" is not a valid number."); + GUC_check_errdetail("\"%s\" must be between %u and %u.", + "recovery_target_timeline", 1, UINT_MAX); return false; } } diff --git a/src/test/recovery/t/003_recovery_targets.pl b/src/test/recovery/t/003_recovery_targets.pl index 0ae2e98272709..f2109efa9b12d 100644 --- a/src/test/recovery/t/003_recovery_targets.pl +++ b/src/test/recovery/t/003_recovery_targets.pl @@ -187,4 +187,54 @@ sub test_recovery_standby qr/FATAL: .* recovery ended before configured recovery target was reached/, 'recovery end before target reached is a fatal error'); +# Invalid timeline target +$node_standby = PostgreSQL::Test::Cluster->new('standby_9'); +$node_standby->init_from_backup($node_primary, 'my_backup', + has_restoring => 1); +$node_standby->append_conf('postgresql.conf', + "recovery_target_timeline = 'bogus'"); + +$res = run_log( + [ + 'pg_ctl', + '--pgdata' => $node_standby->data_dir, + '--log' => $node_standby->logfile, + 'start', + ]); +ok(!$res, 'invalid timeline target (bogus value)'); + +my $log_start = $node_standby->wait_for_log("is not a valid number"); + +# Timeline target out of min range +$node_standby->append_conf('postgresql.conf', + "recovery_target_timeline = '0'"); + +$res = run_log( + [ + 'pg_ctl', + '--pgdata' => $node_standby->data_dir, + '--log' => $node_standby->logfile, + 'start', + ]); +ok(!$res, 'invalid timeline target (lower bound check)'); + +$log_start = + $node_standby->wait_for_log("must be between 1 and 4294967295", $log_start); + +# Timeline target out of max range +$node_standby->append_conf('postgresql.conf', + "recovery_target_timeline = '4294967296'"); + +$res = run_log( + [ + 'pg_ctl', + '--pgdata' => $node_standby->data_dir, + '--log' => $node_standby->logfile, + 'start', + ]); +ok(!$res, 'invalid timeline target (upper bound check)'); + +$log_start = + $node_standby->wait_for_log("must be between 1 and 4294967295", $log_start); + done_testing();