agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH 1/2] Fix and improve pg_atomic_flag fallback implementation. 3+ messages / 2 participants [nested] [flat]
* [PATCH 1/2] Fix and improve pg_atomic_flag fallback implementation. @ 2018-04-06 23:17 Andres Freund <[email protected]> 0 siblings, 0 replies; 3+ messages in thread From: Andres Freund @ 2018-04-06 23:17 UTC (permalink / raw) The atomics fallback implementation for pg_atomic_flag was broken, returning the inverted value from pg_atomic_test_set_flag(). This was unnoticed because a) atomic flags were unused until recently b) the test code wasn't run when the fallback implementation was in use (because it didn't allow to test for some edge cases). Fix the bug, and improve the fallback so it has the same behaviour as the non-fallback implementation in the problematic edge cases. That breaks ABI compatibility in the back branches when fallbacks are in use, but given they were broken until now... Author: Andres Freund Reported-by: Daniel Gustafsson Discussion: https://postgr.es/m/[email protected] Backpatch: 9.5-, where the atomics abstraction was introduced. --- src/backend/port/atomics.c | 21 +++++++++++++++++++-- src/include/port/atomics/fallback.h | 13 ++----------- src/test/regress/regress.c | 14 -------------- 3 files changed, 21 insertions(+), 27 deletions(-) diff --git a/src/backend/port/atomics.c b/src/backend/port/atomics.c index e4e4734dd23..caa84bf2b62 100644 --- a/src/backend/port/atomics.c +++ b/src/backend/port/atomics.c @@ -68,18 +68,35 @@ pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr) #else SpinLockInit((slock_t *) &ptr->sema); #endif + + ptr->value = false; } bool pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr) { - return TAS((slock_t *) &ptr->sema); + uint32 oldval; + + SpinLockAcquire((slock_t *) &ptr->sema); + oldval = ptr->value; + ptr->value = true; + SpinLockRelease((slock_t *) &ptr->sema); + + return oldval == 0; } void pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr) { - S_UNLOCK((slock_t *) &ptr->sema); + SpinLockAcquire((slock_t *) &ptr->sema); + ptr->value = false; + SpinLockRelease((slock_t *) &ptr->sema); +} + +bool +pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr) +{ + return ptr->value == 0; } #endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */ diff --git a/src/include/port/atomics/fallback.h b/src/include/port/atomics/fallback.h index 7b9dcad8073..88a967ad5b9 100644 --- a/src/include/port/atomics/fallback.h +++ b/src/include/port/atomics/fallback.h @@ -80,6 +80,7 @@ typedef struct pg_atomic_flag #else int sema; #endif + volatile bool value; } pg_atomic_flag; #endif /* PG_HAVE_ATOMIC_FLAG_SUPPORT */ @@ -132,17 +133,7 @@ extern bool pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr); extern void pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr); #define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG -static inline bool -pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr) -{ - /* - * Can't do this efficiently in the semaphore based implementation - we'd - * have to try to acquire the semaphore - so always return true. That's - * correct, because this is only an unlocked test anyway. Do this in the - * header so compilers can optimize the test away. - */ - return true; -} +extern bool pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr); #endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */ diff --git a/src/test/regress/regress.c b/src/test/regress/regress.c index e14322c798a..8bc562ee4f0 100644 --- a/src/test/regress/regress.c +++ b/src/test/regress/regress.c @@ -633,7 +633,6 @@ wait_pid(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } -#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION static void test_atomic_flag(void) { @@ -663,7 +662,6 @@ test_atomic_flag(void) pg_atomic_clear_flag(&flag); } -#endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */ static void test_atomic_uint32(void) @@ -846,19 +844,7 @@ PG_FUNCTION_INFO_V1(test_atomic_ops); Datum test_atomic_ops(PG_FUNCTION_ARGS) { - /* --- - * Can't run the test under the semaphore emulation, it doesn't handle - * checking two edge cases well: - * - pg_atomic_unlocked_test_flag() always returns true - * - locking a already locked flag blocks - * it seems better to not test the semaphore fallback here, than weaken - * the checks for the other cases. The semaphore code will be the same - * everywhere, whereas the efficient implementations wont. - * --- - */ -#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION test_atomic_flag(); -#endif test_atomic_uint32(); -- 2.17.0.rc1.dirty --4q665uo5lqbb3ggd-- ^ permalink raw reply [nested|flat] 3+ messages in thread
* [PATCH 1/2] Fix and improve pg_atomic_flag fallback implementation. @ 2018-04-06 23:17 Andres Freund <[email protected]> 0 siblings, 0 replies; 3+ messages in thread From: Andres Freund @ 2018-04-06 23:17 UTC (permalink / raw) The atomics fallback implementation for pg_atomic_flag was broken, returning the inverted value from pg_atomic_test_set_flag(). This was unnoticed because a) atomic flags were unused until recently b) the test code wasn't run when the fallback implementation was in use (because it didn't allow to test for some edge cases). Fix the bug, and improve the fallback so it has the same behaviour as the non-fallback implementation in the problematic edge cases. That breaks ABI compatibility in the back branches when fallbacks are in use, but given they were broken until now... Author: Andres Freund Reported-by: Daniel Gustafsson Discussion: https://postgr.es/m/[email protected] Backpatch: 9.5-, where the atomics abstraction was introduced. --- src/backend/port/atomics.c | 21 +++++++++++++++++++-- src/include/port/atomics/fallback.h | 13 ++----------- src/test/regress/regress.c | 14 -------------- 3 files changed, 21 insertions(+), 27 deletions(-) diff --git a/src/backend/port/atomics.c b/src/backend/port/atomics.c index e4e4734dd23..caa84bf2b62 100644 --- a/src/backend/port/atomics.c +++ b/src/backend/port/atomics.c @@ -68,18 +68,35 @@ pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr) #else SpinLockInit((slock_t *) &ptr->sema); #endif + + ptr->value = false; } bool pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr) { - return TAS((slock_t *) &ptr->sema); + uint32 oldval; + + SpinLockAcquire((slock_t *) &ptr->sema); + oldval = ptr->value; + ptr->value = true; + SpinLockRelease((slock_t *) &ptr->sema); + + return oldval == 0; } void pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr) { - S_UNLOCK((slock_t *) &ptr->sema); + SpinLockAcquire((slock_t *) &ptr->sema); + ptr->value = false; + SpinLockRelease((slock_t *) &ptr->sema); +} + +bool +pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr) +{ + return ptr->value == 0; } #endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */ diff --git a/src/include/port/atomics/fallback.h b/src/include/port/atomics/fallback.h index 7b9dcad8073..88a967ad5b9 100644 --- a/src/include/port/atomics/fallback.h +++ b/src/include/port/atomics/fallback.h @@ -80,6 +80,7 @@ typedef struct pg_atomic_flag #else int sema; #endif + volatile bool value; } pg_atomic_flag; #endif /* PG_HAVE_ATOMIC_FLAG_SUPPORT */ @@ -132,17 +133,7 @@ extern bool pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr); extern void pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr); #define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG -static inline bool -pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr) -{ - /* - * Can't do this efficiently in the semaphore based implementation - we'd - * have to try to acquire the semaphore - so always return true. That's - * correct, because this is only an unlocked test anyway. Do this in the - * header so compilers can optimize the test away. - */ - return true; -} +extern bool pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr); #endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */ diff --git a/src/test/regress/regress.c b/src/test/regress/regress.c index e14322c798a..8bc562ee4f0 100644 --- a/src/test/regress/regress.c +++ b/src/test/regress/regress.c @@ -633,7 +633,6 @@ wait_pid(PG_FUNCTION_ARGS) PG_RETURN_VOID(); } -#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION static void test_atomic_flag(void) { @@ -663,7 +662,6 @@ test_atomic_flag(void) pg_atomic_clear_flag(&flag); } -#endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */ static void test_atomic_uint32(void) @@ -846,19 +844,7 @@ PG_FUNCTION_INFO_V1(test_atomic_ops); Datum test_atomic_ops(PG_FUNCTION_ARGS) { - /* --- - * Can't run the test under the semaphore emulation, it doesn't handle - * checking two edge cases well: - * - pg_atomic_unlocked_test_flag() always returns true - * - locking a already locked flag blocks - * it seems better to not test the semaphore fallback here, than weaken - * the checks for the other cases. The semaphore code will be the same - * everywhere, whereas the efficient implementations wont. - * --- - */ -#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION test_atomic_flag(); -#endif test_atomic_uint32(); -- 2.17.0.rc1.dirty --kv6m6y6rxnxqclpg-- ^ permalink raw reply [nested|flat] 3+ messages in thread
* [PATCH v12 2/2] handle relation statistics correctly during rewrites @ 2025-11-04 13:52 Bertrand Drouvot <[email protected]> 0 siblings, 0 replies; 3+ messages in thread From: Bertrand Drouvot @ 2025-11-04 13:52 UTC (permalink / raw) Now that PGSTAT_KIND_RELATION is keyed by refilenode, we need to handle rewrites. To do so, this patch: - Adds PgStat_PendingRewrite, a new struct to track rewrite operations within a transaction, storing the old locator, new locator, and original locator (for rewrite chains). This allows stats to be copied from the original location to the final location at commit time. - Adds a new function, pgstat_mark_rewrite(), called when a table rewrite begins. It records the rewrite operation in a local list and detects rewrite chains by checking if the old_locator matches any existing new_locator, preserving the chain's original_locator. - Modifies pgstat_copy_relation_stats(), to accept RelFileLocators instead of Relations, with a new increment parameter to accumulate stats (needed for rewrite chains with DML between rewrites). - Ensures that AtEOXact_PgStat_Relations(), AtPrepare_PgStat_Relations(), pgstat_twophase_postcommit()/postabort() pgstat_drop_relation() handle the PgStat_PendingRewrite list correctly. Note that due to the new flush call in pgstat_twophase_postcommit() we can not call GetCurrentTransactionStopTimestamp() in pgstat_relation_flush_cb(). So, adding a check to handle this special case and call GetCurrentTimestamp() instead. Note that we'd call GetCurrentTimestamp() only if there is a rewrite, so that the GetCurrentTimestamp() extra cost should be negligible. Another solution could be to trigger the flush from FinishPreparedTransaction() but that's not worth the extra complexity. The new pending_rewrites list is traversed in multiple places. The overhead should be negligible in comparison to a rewrite and the list should not contain a lot of rewrites in practice. The pending_rewrites list is traversed in multiple places. In typical usage, the list will contain only a few entries so the traversal cost is negligible ( furthermore in comparison to a rewrite). --- src/backend/catalog/index.c | 2 +- src/backend/commands/cluster.c | 5 + src/backend/commands/tablecmds.c | 6 + src/backend/utils/activity/pgstat_relation.c | 391 ++++++++++++++++++- src/backend/utils/activity/pgstat_xact.c | 25 +- src/backend/utils/cache/relcache.c | 6 + src/include/pgstat.h | 5 +- src/tools/pgindent/typedefs.list | 1 + 8 files changed, 424 insertions(+), 17 deletions(-) 92.8% src/backend/utils/activity/ 4.9% src/backend/ diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index 43de42ce39e..88ef00609db 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -1793,7 +1793,7 @@ index_concurrently_swap(Oid newIndexId, Oid oldIndexId, const char *oldName) changeDependenciesOn(RelationRelationId, oldIndexId, newIndexId); /* copy over statistics from old to new index */ - pgstat_copy_relation_stats(newClassRel, oldClassRel); + pgstat_copy_relation_stats(newClassRel->rd_locator, oldClassRel->rd_locator, false); /* Copy data of pg_statistic from the old index to the new one */ CopyStatistics(oldIndexId, newIndexId); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 60a4617a585..3a446f32921 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -1196,6 +1196,11 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, rel1 = relation_open(r1, NoLock); rel2 = relation_open(r2, NoLock); + + /* Mark that a rewrite happened */ + if (RELKIND_HAS_STORAGE(rel1->rd_rel->relkind)) + pgstat_mark_rewrite(rel1->rd_locator, rel2->rd_locator); + rel2->rd_createSubid = rel1->rd_createSubid; rel2->rd_newRelfilelocatorSubid = rel1->rd_newRelfilelocatorSubid; rel2->rd_firstRelfilelocatorSubid = rel1->rd_firstRelfilelocatorSubid; diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index 85242dcc245..8d10d9d1e0f 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -16883,6 +16883,7 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) Oid reltoastrelid; RelFileNumber newrelfilenumber; RelFileLocator newrlocator; + RelFileLocator oldrlocator; List *reltoastidxids = NIL; ListCell *lc; @@ -16921,6 +16922,7 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) newrlocator = rel->rd_locator; newrlocator.relNumber = newrelfilenumber; newrlocator.spcOid = newTableSpace; + oldrlocator = rel->rd_locator; /* hand off to AM to actually create new rel storage and copy the data */ if (rel->rd_rel->relkind == RELKIND_INDEX) @@ -16933,6 +16935,10 @@ ATExecSetTableSpace(Oid tableOid, Oid newTableSpace, LOCKMODE lockmode) table_relation_copy_data(rel, &newrlocator); } + /* mark that a rewrite happened */ + if (RELKIND_HAS_STORAGE(rel->rd_rel->relkind)) + pgstat_mark_rewrite(oldrlocator, newrlocator); + /* * Update the pg_class row. * diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c index 89bf0cbed56..4d929972fab 100644 --- a/src/backend/utils/activity/pgstat_relation.c +++ b/src/backend/utils/activity/pgstat_relation.c @@ -30,6 +30,19 @@ #include "utils/syscache.h" #include "utils/timestamp.h" +/* Pending rewrite operations for stats copying */ +typedef struct PgStat_PendingRewrite +{ + RelFileLocator old_locator; + RelFileLocator new_locator; + RelFileLocator original_locator; + int nest_level; /* Transaction nesting level where rewrite + * occurred */ + struct PgStat_PendingRewrite *next; +} PgStat_PendingRewrite; + +/* The pending rewrites list for current transaction */ +static PgStat_PendingRewrite *pending_rewrites = NULL; /* Record that's written to 2PC state file when pgstat state is persisted */ typedef struct TwoPhasePgStatRecord @@ -43,6 +56,8 @@ typedef struct TwoPhasePgStatRecord PgStat_Counter deleted_pre_truncdrop; RelFileLocator locator; /* table's rd_locator */ bool truncdropped; /* was the relation truncated/dropped? */ + RelFileLocator rewrite_old_locator; + int rewrite_nest_level; } TwoPhasePgStatRecord; @@ -54,27 +69,70 @@ static void restore_truncdrop_counters(PgStat_TableXactStatus *trans); /* - * Copy stats between relations. This is used for things like REINDEX + * Copy stats between RelFileLocator. This is used for things like REINDEX * CONCURRENTLY. */ void -pgstat_copy_relation_stats(Relation dst, Relation src) +pgstat_copy_relation_stats(RelFileLocator dst, RelFileLocator src, bool increment) { PgStat_StatTabEntry *srcstats; PgStatShared_Relation *dstshstats; PgStat_EntryRef *dst_ref; - srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src)); + srcstats = (PgStat_StatTabEntry *) pgstat_fetch_entry(PGSTAT_KIND_RELATION, + src.dbOid, + RelFileLocatorToPgStatObjid(src)); if (!srcstats) return; dst_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, - dst->rd_rel->relisshared ? InvalidOid : MyDatabaseId, - RelationGetRelid(dst), + dst.dbOid, + RelFileLocatorToPgStatObjid(dst), false); dstshstats = (PgStatShared_Relation *) dst_ref->shared_stats; - dstshstats->stats = *srcstats; + + if (!increment) + dstshstats->stats = *srcstats; + else + { + /* Increment those statistics */ +#define RELFSTAT_ACC(fld, stats_to_add) \ + (dstshstats->stats.fld += stats_to_add->fld) + RELFSTAT_ACC(numscans, srcstats); + RELFSTAT_ACC(tuples_returned, srcstats); + RELFSTAT_ACC(tuples_fetched, srcstats); + RELFSTAT_ACC(tuples_inserted, srcstats); + RELFSTAT_ACC(tuples_updated, srcstats); + RELFSTAT_ACC(tuples_deleted, srcstats); + RELFSTAT_ACC(tuples_hot_updated, srcstats); + RELFSTAT_ACC(tuples_newpage_updated, srcstats); + RELFSTAT_ACC(live_tuples, srcstats); + RELFSTAT_ACC(dead_tuples, srcstats); + RELFSTAT_ACC(mod_since_analyze, srcstats); + RELFSTAT_ACC(ins_since_vacuum, srcstats); + RELFSTAT_ACC(blocks_fetched, srcstats); + RELFSTAT_ACC(blocks_hit, srcstats); + RELFSTAT_ACC(vacuum_count, srcstats); + RELFSTAT_ACC(autovacuum_count, srcstats); + RELFSTAT_ACC(analyze_count, srcstats); + RELFSTAT_ACC(autoanalyze_count, srcstats); + RELFSTAT_ACC(total_vacuum_time, srcstats); + RELFSTAT_ACC(total_autovacuum_time, srcstats); + RELFSTAT_ACC(total_analyze_time, srcstats); + RELFSTAT_ACC(total_autoanalyze_time, srcstats); +#undef RELFSTAT_ACC + + /* Replace those statistics */ +#define RELFSTAT_REP(fld, stats_to_rep) \ + (dstshstats->stats.fld = stats_to_rep->fld) + RELFSTAT_REP(lastscan, srcstats); + RELFSTAT_REP(last_vacuum_time, srcstats); + RELFSTAT_REP(last_autovacuum_time, srcstats); + RELFSTAT_REP(last_analyze_time, srcstats); + RELFSTAT_REP(last_autoanalyze_time, srcstats); +#undef RELFSTAT_REP + } pgstat_unlock_entry(dst_ref); } @@ -136,6 +194,7 @@ void pgstat_assoc_relation(Relation rel) { RelFileLocator locator; + PgStat_TableStatus *pgstat_info; Assert(rel->pgstat_enabled); Assert(rel->pgstat_info == NULL); @@ -164,14 +223,54 @@ pgstat_assoc_relation(Relation rel) locator.relNumber = rel->rd_id; } + /* + * If this relation was rewritten during the current transaction we may be + * reopening it with its new RelFileLocator. In that case, continue using + * the stats entry associated with the old locator rather than creating a + * new one. This ensures all stats from before and after the rewrite are + * tracked in a single entry which will be properly copied to the new + * locator at transaction commit. + */ + if (pending_rewrites != NULL) + { + PgStat_PendingRewrite *rewrite; + + for (rewrite = pending_rewrites; rewrite != NULL; rewrite = rewrite->next) + { + if (locator.dbOid == rewrite->new_locator.dbOid && + locator.spcOid == rewrite->new_locator.spcOid && + locator.relNumber == rewrite->new_locator.relNumber) + { + pgstat_info = pgstat_prep_relation_pending(rewrite->old_locator); + goto found_entry; + } + } + } + /* Else find or make the PgStat_TableStatus entry, and update link */ - rel->pgstat_info = pgstat_prep_relation_pending(locator); + pgstat_info = pgstat_prep_relation_pending(locator); + +found_entry: + rel->pgstat_info = pgstat_info; + + /* + * For relations stats, we key by physical file location, not by relation + * OID. This means during operations like ALTER TYPE it's possible that + * the relation OID changes but the relfilenode stays the same (no actual + * rewrite needed). Unlink the old relation first. + */ + if (pgstat_info->relation != NULL && + pgstat_info->relation != rel) + { + pgstat_info->relation->pgstat_info = NULL; + pgstat_info->relation = NULL; + } /* don't allow link a stats to multiple relcache entries */ - Assert(rel->pgstat_info->relation == NULL); + Assert(pgstat_info->relation == NULL); /* mark this relation as the owner */ - rel->pgstat_info->relation = rel; + pgstat_info->relation = rel; } /* @@ -214,14 +313,37 @@ pgstat_drop_relation(Relation rel) { int nest_level = GetCurrentTransactionNestLevel(); PgStat_TableStatus *pgstat_info; + bool skip_transactional_drop = false; /* don't track stats for relations without storage */ if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind)) return; - pgstat_drop_transactional(PGSTAT_KIND_RELATION, - rel->rd_locator.dbOid, - RelFileLocatorToPgStatObjid(rel->rd_locator)); + /* Check if this drop is part of a pending rewrite */ + if (pending_rewrites != NULL) + { + PgStat_PendingRewrite *rewrite; + + for (rewrite = pending_rewrites; rewrite != NULL; rewrite = rewrite->next) + { + if (rel->rd_locator.dbOid == rewrite->old_locator.dbOid && + rel->rd_locator.spcOid == rewrite->old_locator.spcOid && + rel->rd_locator.relNumber == rewrite->old_locator.relNumber) + { + skip_transactional_drop = true; + break; + } + } + } + + /* + * If it is part of a rewrite, drop its stats later, for example in + * AtEOXact_PgStat_Relations(), so skip it here. + */ + if (!skip_transactional_drop) + pgstat_drop_transactional(PGSTAT_KIND_RELATION, + rel->rd_locator.dbOid, + RelFileLocatorToPgStatObjid(rel->rd_locator)); if (!pgstat_should_count_relation(rel)) return; @@ -666,6 +788,48 @@ AtEOXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool isCommit) } tabstat->trans = NULL; } + + /* preserve the stats in case of rewrite */ + if (isCommit && pending_rewrites != NULL) + { + PgStat_PendingRewrite *rewrite; + PgStat_PendingRewrite *prev = NULL; + PgStat_PendingRewrite *current = pending_rewrites; + PgStat_PendingRewrite *next; + + /* reverse the rewrites list to process in chronological order */ + while (current != NULL) + { + next = current->next; + current->next = prev; + prev = current; + current = next; + } + + /* now process rewrites in chronological order */ + for (rewrite = prev; rewrite != NULL; rewrite = rewrite->next) + { + PgStat_EntryRef *old_entry_ref; + + old_entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, + rewrite->old_locator.dbOid, + RelFileLocatorToPgStatObjid(rewrite->old_locator)); + + if (old_entry_ref && old_entry_ref->pending) + pgstat_relation_flush_cb(old_entry_ref, false); + + pgstat_copy_relation_stats(rewrite->new_locator, + rewrite->old_locator, true); + + /* drop old locator's stats */ + if (!pgstat_drop_entry(PGSTAT_KIND_RELATION, + rewrite->old_locator.dbOid, + RelFileLocatorToPgStatObjid(rewrite->old_locator))) + pgstat_request_entry_refs_gc(); + } + } + + pending_rewrites = NULL; } /* @@ -681,6 +845,30 @@ AtEOSubXact_PgStat_Relations(PgStat_SubXactStatus *xact_state, bool isCommit, in PgStat_TableXactStatus *trans; PgStat_TableXactStatus *next_trans; + /* + * If we don't commit then remove the associated rewrites if any, to keep + * the rewrite chain in sync with what will be eventually committed. + */ + if (!isCommit) + { + PgStat_PendingRewrite **rewrite_ptr = &pending_rewrites; + + while (*rewrite_ptr != NULL) + { + if ((*rewrite_ptr)->nest_level >= nestDepth) + { + PgStat_PendingRewrite *to_remove = *rewrite_ptr; + + *rewrite_ptr = (*rewrite_ptr)->next; + pfree(to_remove); + } + else + { + rewrite_ptr = &((*rewrite_ptr)->next); + } + } + } + for (trans = xact_state->first; trans != NULL; trans = next_trans) { PgStat_TableStatus *tabstat; @@ -760,11 +948,19 @@ void AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) { PgStat_TableXactStatus *trans; + PgStat_PendingRewrite *rewrite; + /* + * For each tabstat, find its matching rewrite and remove it from the + * pending rewrites list. This way, after processing all tabstats, pending + * rewrites will only contain rewrite only transactions. + */ for (trans = xact_state->first; trans != NULL; trans = trans->next) { PgStat_TableStatus *tabstat PG_USED_FOR_ASSERTS_ONLY; TwoPhasePgStatRecord record; + PgStat_PendingRewrite **rewrite_ptr; + bool found_rewrite = false; Assert(trans->nest_level == 1); Assert(trans->upper == NULL); @@ -784,10 +980,83 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) record.locator = tabstat->locator; record.truncdropped = trans->truncdropped; + record.rewrite_nest_level = 0; + + /* + * Look for a matching rewrite and remove it from pending rewrites. We + * check three possible matches: + * + * The new_locator when stats have been added after the rewrite. The + * old_locator when stats have been added before the rewrite but not + * after. The original_locator when this tabstat is part of a rewrite + * chain. + */ + rewrite_ptr = &pending_rewrites; + while (*rewrite_ptr != NULL) + { + rewrite = *rewrite_ptr; + + if ((record.locator.dbOid == rewrite->new_locator.dbOid && + record.locator.spcOid == rewrite->new_locator.spcOid && + record.locator.relNumber == rewrite->new_locator.relNumber) || + (tabstat->locator.dbOid == rewrite->old_locator.dbOid && + tabstat->locator.spcOid == rewrite->old_locator.spcOid && + tabstat->locator.relNumber == rewrite->old_locator.relNumber) || + (tabstat->locator.dbOid == rewrite->original_locator.dbOid && + tabstat->locator.spcOid == rewrite->original_locator.spcOid && + tabstat->locator.relNumber == rewrite->original_locator.relNumber)) + { + /* + * Found matching rewrite. Record the rewrite information and + * remove this rewrite from the list since it's now handled. + */ + record.rewrite_old_locator = rewrite->original_locator; + record.rewrite_nest_level = rewrite->nest_level; + record.locator = rewrite->new_locator; + found_rewrite = true; + + /* Remove from pending_rewrites list */ + *rewrite_ptr = rewrite->next; + pfree(rewrite); + break; + } + else + { + /* Move to next rewrite in the list */ + rewrite_ptr = &(rewrite->next); + } + } + + /* If no rewrite found, clear the rewrite fields */ + if (!found_rewrite) + { + memset(&record.rewrite_old_locator, 0, sizeof(RelFileLocator)); + } + + RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0, + &record, sizeof(TwoPhasePgStatRecord)); + } + + /* + * Now process any rewrites still pending. These are rewrite only + * transactions. We need to preserve their stats even though there's no + * tabstat entry for them. + */ + for (rewrite = pending_rewrites; rewrite != NULL; rewrite = rewrite->next) + { + TwoPhasePgStatRecord record; + + memset(&record, 0, sizeof(TwoPhasePgStatRecord)); + record.locator = rewrite->new_locator; + record.rewrite_old_locator = rewrite->original_locator; + record.rewrite_nest_level = rewrite->nest_level; + record.truncdropped = false; RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0, &record, sizeof(TwoPhasePgStatRecord)); } + + pending_rewrites = NULL; } /* @@ -810,6 +1079,8 @@ PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state) tabstat = trans->parent; tabstat->trans = NULL; } + + pending_rewrites = NULL; } /* @@ -845,6 +1116,29 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info, pgstat_info->counts.changed_tuples += rec->tuples_inserted + rec->tuples_updated + rec->tuples_deleted; + + if (rec->rewrite_nest_level > 0) + { + PgStat_EntryRef *old_entry_ref; + + /* Flush any pending stats for old locator first */ + old_entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, + rec->rewrite_old_locator.dbOid, + RelFileLocatorToPgStatObjid(rec->rewrite_old_locator)); + + if (old_entry_ref && old_entry_ref->pending) + pgstat_relation_flush_cb(old_entry_ref, false); + + /* Copy stats from old to new locator */ + pgstat_copy_relation_stats(rec->locator, rec->rewrite_old_locator, + true); + + /* Drop old locator's stats */ + if (!pgstat_drop_entry(PGSTAT_KIND_RELATION, + rec->rewrite_old_locator.dbOid, + RelFileLocatorToPgStatObjid(rec->rewrite_old_locator))) + pgstat_request_entry_refs_gc(); + } } /* @@ -859,9 +1153,26 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info, { TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata; PgStat_TableStatus *pgstat_info; + RelFileLocator target_locator; + + /* + * For aborted transactions with rewrites (like TRUNCATE), we need to + * restore stats to the old locator, not the new one. The new locator + * should be dropped since the rewrite is being rolled back. + */ + if (rec->rewrite_nest_level > 0) + { + /* Use the old locator */ + target_locator = rec->rewrite_old_locator; + } + else + { + /* No rewrite, use the original locator */ + target_locator = rec->locator; + } /* Find or create a tabstat entry for the target locator */ - pgstat_info = pgstat_prep_relation_pending(rec->locator); + pgstat_info = pgstat_prep_relation_pending(target_locator); /* Same math as in AtEOXact_PgStat, abort case */ if (rec->truncdropped) @@ -916,7 +1227,17 @@ pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait) tabentry->numscans += lstats->counts.numscans; if (lstats->counts.numscans) { - TimestampTz t = GetCurrentTransactionStopTimestamp(); + TimestampTz t; + + /* + * Checking the transaction state due to the flush call in + * pgstat_twophase_postcommit() that would break the assertion on the + * state in GetCurrentTransactionStopTimestamp(). + */ + if (!IsTransactionState()) + t = GetCurrentTransactionStopTimestamp(); + else + t = GetCurrentTimestamp(); if (t > tabentry->lastscan) tabentry->lastscan = t; @@ -1167,3 +1488,45 @@ pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator) ReleaseSysCache(tuple); return result; } + +/* + * Mark that a relation rewrite has occurred, preserving the original locator + * so stats can be copied at transaction commit. + */ +void +pgstat_mark_rewrite(RelFileLocator old_locator, RelFileLocator new_locator) +{ + PgStat_PendingRewrite *rewrite; + PgStat_PendingRewrite *existing; + RelFileLocator original_locator = old_locator; + + for (existing = pending_rewrites; existing != NULL; existing = existing->next) + { + if (old_locator.dbOid == existing->new_locator.dbOid && + old_locator.spcOid == existing->new_locator.spcOid && + old_locator.relNumber == existing->new_locator.relNumber) + { + original_locator = existing->original_locator; + break; + } + } + + /* Allocate in TopTransactionContext memory context */ + rewrite = MemoryContextAlloc(TopTransactionContext, + sizeof(PgStat_PendingRewrite)); + + rewrite->old_locator = old_locator; + rewrite->new_locator = new_locator; + rewrite->original_locator = original_locator; + rewrite->nest_level = GetCurrentTransactionNestLevel(); + + /* Add to the list */ + rewrite->next = pending_rewrites; + pending_rewrites = rewrite; +} + +void +pgstat_clear_rewrite(void) +{ + pending_rewrites = NULL; +} diff --git a/src/backend/utils/activity/pgstat_xact.c b/src/backend/utils/activity/pgstat_xact.c index 5e2d69e6297..8ed8f5317f3 100644 --- a/src/backend/utils/activity/pgstat_xact.c +++ b/src/backend/utils/activity/pgstat_xact.c @@ -55,6 +55,8 @@ AtEOXact_PgStat(bool isCommit, bool parallel) } pgStatXactStack = NULL; + pgstat_clear_rewrite(); + /* Make sure any stats snapshot is thrown away */ pgstat_clear_snapshot(); } @@ -360,8 +362,29 @@ create_drop_transactional_internal(PgStat_Kind kind, Oid dboid, uint64 objid, bo void pgstat_create_transactional(PgStat_Kind kind, Oid dboid, uint64 objid) { - if (pgstat_get_entry_ref(kind, dboid, objid, false, NULL)) + PgStat_EntryRef *entry_ref; + + entry_ref = pgstat_get_entry_ref(kind, dboid, objid, false, NULL); + + if (entry_ref) { + /* + * For relations stats, we key by physical file location, not by + * relation OID. This means during operations like ALTER TYPE where + * the relation OID changes but the relfilenode stays the same (no + * actual rewrite needed), we'll find an existing entry. + * + * This is expected behavior, we want to preserve stats across the + * catalog change. Simply reset and recreate the entry for the new + * relation OID without warning. + */ + if (kind == PGSTAT_KIND_RELATION) + { + pgstat_reset(kind, dboid, objid); + create_drop_transactional_internal(kind, dboid, objid, true); + return; + } + ereport(WARNING, errmsg("resetting existing statistics for kind %s, db=%u, oid=%" PRIu64, (pgstat_get_kind_info(kind))->name, dboid, diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c index a1c88c6b1b6..dc5948f446c 100644 --- a/src/backend/utils/cache/relcache.c +++ b/src/backend/utils/cache/relcache.c @@ -85,6 +85,7 @@ #include "utils/inval.h" #include "utils/lsyscache.h" #include "utils/memutils.h" +#include "utils/pgstat_internal.h" #include "utils/relmapper.h" #include "utils/resowner.h" #include "utils/snapmgr.h" @@ -3775,6 +3776,7 @@ RelationSetNewRelfilenumber(Relation relation, char persistence) MultiXactId minmulti = InvalidMultiXactId; TransactionId freezeXid = InvalidTransactionId; RelFileLocator newrlocator; + RelFileLocator oldrlocator = relation->rd_locator; if (!IsBinaryUpgrade) { @@ -3946,6 +3948,10 @@ RelationSetNewRelfilenumber(Relation relation, char persistence) table_close(pg_class, RowExclusiveLock); + /* Mark that a rewrite happened */ + if (RELKIND_HAS_STORAGE(relation->rd_rel->relkind)) + pgstat_mark_rewrite(oldrlocator, newrlocator); + /* * Make the pg_class row change or relation map change visible. This will * cause the relcache entry to get updated, too. diff --git a/src/include/pgstat.h b/src/include/pgstat.h index 689c624f373..d0d5473f8a5 100644 --- a/src/include/pgstat.h +++ b/src/include/pgstat.h @@ -673,7 +673,7 @@ extern PgStat_FunctionCounts *find_funcstat_entry(Oid func_id); extern void pgstat_create_relation(Relation rel); extern void pgstat_drop_relation(Relation rel); -extern void pgstat_copy_relation_stats(Relation dst, Relation src); +extern void pgstat_copy_relation_stats(RelFileLocator dst, RelFileLocator src, bool increment); extern void pgstat_init_relation(Relation rel); extern void pgstat_assoc_relation(Relation rel); @@ -685,6 +685,9 @@ extern void pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples, extern void pgstat_report_analyze(Relation rel, PgStat_Counter livetuples, PgStat_Counter deadtuples, bool resetcounter, TimestampTz starttime); +extern void pgstat_mark_rewrite(RelFileLocator old_locator, + RelFileLocator new_locator); +extern void pgstat_clear_rewrite(void); /* * If stats are enabled, but pending data hasn't been prepared yet, call diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 3250564d4ff..fbcbe5da26a 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -2281,6 +2281,7 @@ PgStat_KindInfo PgStat_LocalState PgStat_PendingDroppedStatsItem PgStat_PendingIO +PgStat_PendingRewrite PgStat_SLRUStats PgStat_ShmemControl PgStat_Snapshot -- 2.34.1 --sdA5zuaL94ts0rne-- ^ permalink raw reply [nested|flat] 3+ messages in thread
end of thread, other threads:[~2025-11-04 13:52 UTC | newest] Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2018-04-06 23:17 [PATCH 1/2] Fix and improve pg_atomic_flag fallback implementation. Andres Freund <[email protected]> 2018-04-06 23:17 [PATCH 1/2] Fix and improve pg_atomic_flag fallback implementation. Andres Freund <[email protected]> 2025-11-04 13:52 [PATCH v12 2/2] handle relation statistics correctly during rewrites Bertrand Drouvot <[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