From c675c674644b7a521712913b5cfc53f899e435ce Mon Sep 17 00:00:00 2001 From: Gregory Burd Date: Mon, 27 Jan 2025 13:28:59 -0500 Subject: [PATCH v7] Expand HOT update path to include expression and partial indexes. This patch extends the cases where HOT updates are possible in the heapam by examining expression indexes and determining if indexed values where mutated or not. Previously, any expression index on a column would disqualify it from the HOT update path. Also examines partial indexes to see if the values are within the predicate or not. This is a modified application of a patch proposed on the pgsql-hackers list: https://www.postgresql.org/message-id/flat/4d9928ee-a9e6-15f9-9c82-5981f13ffca6%40postgrespro.ru applied: https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit;h=c203d6cf8 reverted: https://git.postgresql.org/gitweb/?p=postgresql.git;a=commit;h=05f84605dbeb9cf8279a157234b24bbb706c5256 Signed-off-by: Greg Burd --- doc/src/sgml/ref/create_table.sgml | 18 + doc/src/sgml/storage.sgml | 21 + src/backend/access/common/reloptions.c | 12 +- src/backend/access/heap/README.HOT | 45 +- src/backend/access/heap/heapam.c | 43 +- src/backend/access/heap/heapam_handler.c | 6 +- src/backend/access/table/tableam.c | 2 +- src/backend/catalog/index.c | 19 + src/backend/executor/execIndexing.c | 199 ++++++ src/backend/executor/nodeModifyTable.c | 3 +- src/backend/utils/cache/relcache.c | 181 +++++- src/bin/psql/tab-complete.in.c | 2 +- src/include/access/genam.h | 2 +- src/include/access/heapam.h | 3 +- src/include/access/tableam.h | 10 +- src/include/executor/executor.h | 5 + src/include/nodes/execnodes.h | 9 + src/include/utils/rel.h | 14 + src/include/utils/relcache.h | 2 + .../regress/expected/heap_hot_updates.out | 586 ++++++++++++++++++ src/test/regress/parallel_schedule | 5 + src/test/regress/sql/heap_hot_updates.sql | 440 +++++++++++++ 22 files changed, 1566 insertions(+), 61 deletions(-) create mode 100644 src/test/regress/expected/heap_hot_updates.out create mode 100644 src/test/regress/sql/heap_hot_updates.sql diff --git a/doc/src/sgml/ref/create_table.sgml b/doc/src/sgml/ref/create_table.sgml index 0a3e520f215..8ee2ac523ee 100644 --- a/doc/src/sgml/ref/create_table.sgml +++ b/doc/src/sgml/ref/create_table.sgml @@ -1981,6 +1981,24 @@ WITH ( MODULUS numeric_literal, REM + + expression_checks (boolean) + + expression_checks storage parameter + + + + + Enables or disables evaulation of predicate expressions on partial + indexes or expressions used to define indexes during updates. + If true, then these expressions are evaluated during + updates to data within the heap relation against the old and new values + and then compared to determine if HOT updates are + allowable or not. The default value is true. + + + + diff --git a/doc/src/sgml/storage.sgml b/doc/src/sgml/storage.sgml index 61250799ec0..f40ada9c989 100644 --- a/doc/src/sgml/storage.sgml +++ b/doc/src/sgml/storage.sgml @@ -1138,6 +1138,27 @@ data. Empty in ordinary tables. + + HOT updates can occur when the expression used to define + and index shows no changes to the indexed value. To determine this requires + that the expression be evaulated for the old and new values to be stored in + the index and then compared. This allows for HOT updates + when data indexed within JSONB columns is unchanged. To disable this + behavior and avoid the overhead of evaluating the expression during updates + set the expression_checks option to false for the table. + + + + HOT updates can also occur when updated values are not + within the predicate of a partial index. However, HOT + updates are not possible when the updated value and the current value differ + with regards to the predicate. To determin this requires that the predicate + expression be evaluated for the old and new values to be stored in the index + and then compared. To disable this behavior and avoid the overhead of + evaluating the expression during updates set + the expression_checks option to false for the table. + + You can increase the likelihood of sufficient page space for HOT updates by decreasing a table's t_tableOid = slot->tts_tableOid; result = heap_update(relation, otid, tuple, cid, crosscheck, wait, - tmfd, lockmode, update_indexes); + tmfd, lockmode, update_indexes, estate); ItemPointerCopy(&tuple->t_self, &slot->tts_tid); /* diff --git a/src/backend/access/table/tableam.c b/src/backend/access/table/tableam.c index e18a8f8250f..9feca8a296f 100644 --- a/src/backend/access/table/tableam.c +++ b/src/backend/access/table/tableam.c @@ -345,7 +345,7 @@ simple_table_tuple_update(Relation rel, ItemPointer otid, GetCurrentCommandId(true), snapshot, InvalidSnapshot, true /* wait for commit */ , - &tmfd, &lockmode, update_indexes); + &tmfd, &lockmode, update_indexes, NULL); switch (result) { diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index cdabf780244..78b4310e05f 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -2455,7 +2455,26 @@ BuildIndexInfo(Relation index) /* fill in attribute numbers */ for (i = 0; i < numAtts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(RelationGetDescr(index), i); + ii->ii_IndexAttrNumbers[i] = indexStruct->indkey.values[i]; + ii->ii_IndexAttrs = + bms_add_member(ii->ii_IndexAttrs, + indexStruct->indkey.values[i] - FirstLowInvalidHeapAttributeNumber); + + ii->ii_IndexAttrLen[i] = attr->attlen; + if (attr->attbyval) + ii->ii_IndexAttrByVal = bms_add_member(ii->ii_IndexAttrByVal, i); + } + + /* collect attributes used in the expression, if one is present */ + if (ii->ii_Expressions) + pull_varattnos((Node *) ii->ii_Expressions, 1, &ii->ii_ExpressionAttrs); + + /* collect attributes used in the predicate, if one is present */ + if (ii->ii_Predicate) + pull_varattnos((Node *) ii->ii_Predicate, 1, &ii->ii_PredicateAttrs); /* fetch exclusion constraint info if any */ if (indexStruct->indisexclusion) diff --git a/src/backend/executor/execIndexing.c b/src/backend/executor/execIndexing.c index 7c87f012c30..679124d1dfa 100644 --- a/src/backend/executor/execIndexing.c +++ b/src/backend/executor/execIndexing.c @@ -117,6 +117,8 @@ #include "utils/multirangetypes.h" #include "utils/rangetypes.h" #include "utils/snapmgr.h" +#include "utils/datum.h" +#include "utils/lsyscache.h" /* waitMode argument to check_exclusion_or_unique_constraint() */ typedef enum @@ -1089,6 +1091,9 @@ index_unchanged_by_update(ResultRelInfo *resultRelInfo, EState *estate, if (hasexpression) { + if (indexInfo->ii_IndexUnchanged) + return true; + indexInfo->ii_IndexUnchanged = false; return false; } @@ -1166,3 +1171,197 @@ ExecWithoutOverlapsNotEmpty(Relation rel, NameData attname, Datum attval, char t errmsg("empty WITHOUT OVERLAPS value found in column \"%s\" in relation \"%s\"", NameStr(attname), RelationGetRelationName(rel)))); } + +/* + * Determine if any index with an expression requires updating. + * + * This function will review all indexes with expressions to determine if the + * update from old to new tuple requires that the index be updated. This is + * used to determine if a HOT update is possible or not. + * + * Returns true iff none of the expression indexes require updating due to the + * change from old to new tuple or when both the old and new tuples do not + * satisfy the predicate of the index. + */ +bool +ExecIndexesExpressionsWereNotUpdated(Relation relation, + Bitmapset *modified_attrs, + EState *estate, + HeapTuple old_tuple, + HeapTuple new_tuple) +{ + ListCell *lc; + List *indexinfolist = RelationGetExprIndexInfoList(relation); + ExprContext *econtext = NULL; + TupleDesc tupledesc; + TupleTableSlot *old_tts = NULL; + TupleTableSlot *new_tts = NULL; + bool expression_checks = RelationGetExpressionChecks(relation); + bool changed = false; + +#ifndef USE_ASSERT_CHECKING + + /* + * Assume the index is changed when we don't have an estate context to use + * or the reloption is disabled. + */ + if (!expression_checks || estate == NULL) + return changed; +#endif + + Assert(expression_checks == true); + Assert(estate != NULL); + + /* + * Examine expression and partial indexs on this relation relative to the + * changes between old and new tuples. + */ + foreach(lc, indexinfolist) + { + IndexInfo *indexInfo = (IndexInfo *) lfirst(lc); + + /* + * If this is a partial index it has a predicate, evaluate the + * expression to determine if we need to include it or not. + */ + if (bms_overlap(indexInfo->ii_PredicateAttrs, modified_attrs)) + { + ExprState *pstate; + bool old_tuple_qualifies, + new_tuple_qualifies; + + /* Create these once, only if necessary, then reuse them. */ + if (!econtext) + { + econtext = GetPerTupleExprContext(estate); + tupledesc = RelationGetDescr(relation); + old_tts = MakeSingleTupleTableSlot(tupledesc, + &TTSOpsHeapTuple); + new_tts = MakeSingleTupleTableSlot(tupledesc, + &TTSOpsHeapTuple); + + ExecStoreHeapTuple(old_tuple, old_tts, InvalidBuffer); + ExecStoreHeapTuple(new_tuple, new_tts, InvalidBuffer); + } + + pstate = ExecPrepareQual(indexInfo->ii_Predicate, estate); + + /* + * Here the term "qualifies" means "satisfies the predicate + * condition of the partial index". + */ + econtext->ecxt_scantuple = old_tts; + old_tuple_qualifies = ExecQual(pstate, econtext); + + econtext->ecxt_scantuple = new_tts; + new_tuple_qualifies = ExecQual(pstate, econtext); + + /* + * If neither the old nor the new tuples satisfy the predicate we + * can be sure that this index doesn't need updating, continue to + * the next index. + */ + if ((new_tuple_qualifies == false) && (old_tuple_qualifies == false)) + continue; + + /* + * If there is a transition between indexed and not indexed, + * that's enough to require that this index is updated. + */ + if (new_tuple_qualifies != old_tuple_qualifies) + { + changed = true; + break; + } + + /* + * Otherwise the old and new values exist in the index, but did + * they get updated? We don't yet know, so proceed with the next + * statement in the loop to find out. + */ + } + + + /* + * Indexes with expressions may or may not have changed, it is + * impossible to know without exercising their expression and + * reviewing index tuple state for changes. This is a lot of work, + * but because all indexes on JSONB columns fall into this category it + * can be worth it to avoid index updates and remain on the HOT update + * path when possible. + */ + if (bms_overlap(indexInfo->ii_ExpressionAttrs, modified_attrs)) + { + Datum old_values[INDEX_MAX_KEYS]; + bool old_isnull[INDEX_MAX_KEYS]; + Datum new_values[INDEX_MAX_KEYS]; + bool new_isnull[INDEX_MAX_KEYS]; + + /* Create these once, only if necessary, then reuse them. */ + if (!econtext) + { + econtext = GetPerTupleExprContext(estate); + tupledesc = RelationGetDescr(relation); + old_tts = MakeSingleTupleTableSlot(tupledesc, + &TTSOpsHeapTuple); + new_tts = MakeSingleTupleTableSlot(tupledesc, + &TTSOpsHeapTuple); + + ExecStoreHeapTuple(old_tuple, old_tts, InvalidBuffer); + ExecStoreHeapTuple(new_tuple, new_tts, InvalidBuffer); + } + + indexInfo->ii_ExpressionsState = NIL; + + econtext->ecxt_scantuple = old_tts; + FormIndexDatum(indexInfo, + old_tts, + estate, + old_values, + old_isnull); + + econtext->ecxt_scantuple = new_tts; + FormIndexDatum(indexInfo, + new_tts, + estate, + new_values, + new_isnull); + + for (int i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++) + { + if (old_isnull[i] != new_isnull[i]) + { + changed = true; + break; + } + else if (!old_isnull[i]) + { + int16 elmlen = indexInfo->ii_IndexAttrLen[i]; + bool elmbyval = bms_is_member(i, indexInfo->ii_IndexAttrByVal); + + if (!datum_image_eq(old_values[i], new_values[i], + elmbyval, elmlen)) + { + changed = true; + break; + } + } + } + + /* Shortcut index_unchanged_by_update(), we know the answer. */ + indexInfo->ii_CheckedUnchanged = true; + indexInfo->ii_IndexUnchanged = !changed; + + if (changed) + break; + } + } + + if (econtext) + { + ExecDropSingleTupleTableSlot(old_tts); + ExecDropSingleTupleTableSlot(new_tts); + } + + return !changed; +} diff --git a/src/backend/executor/nodeModifyTable.c b/src/backend/executor/nodeModifyTable.c index b0fe50075ad..d68f40cb998 100644 --- a/src/backend/executor/nodeModifyTable.c +++ b/src/backend/executor/nodeModifyTable.c @@ -2283,7 +2283,8 @@ lreplace: estate->es_crosscheck_snapshot, true /* wait for commit */ , &context->tmfd, &updateCxt->lockmode, - &updateCxt->updateIndexes); + &updateCxt->updateIndexes, + estate); return result; } diff --git a/src/backend/utils/cache/relcache.c b/src/backend/utils/cache/relcache.c index 398114373e9..b5e47b3521e 100644 --- a/src/backend/utils/cache/relcache.c +++ b/src/backend/utils/cache/relcache.c @@ -64,6 +64,7 @@ #include "catalog/pg_type.h" #include "catalog/schemapg.h" #include "catalog/storage.h" +#include "catalog/index.h" #include "commands/policy.h" #include "commands/publicationcmds.h" #include "commands/trigger.h" @@ -5188,6 +5189,128 @@ RelationGetIndexPredicate(Relation relation) return result; } + /* + * RelationGetExprIndexInfoList -- get a list of IndexInfo for expression + * indexes on this relation + */ +List * +RelationGetExprIndexInfoList(Relation relation) +{ + ListCell *lc; + List *indexoidlist; + List *newindexoidlist; + List *result = NULL; + List *oldlist; + Oid relpkindex; + Oid relreplindex; + MemoryContext oldcxt; + + if (relation->rd_iiexprlist) + return list_copy(relation->rd_iiexprlist); + + /* Fast path if definitely no indexes */ + if (!RelationGetForm(relation)->relhasindex) + return NIL; + +restart: + indexoidlist = RelationGetIndexList(relation); + + /* Fall out if no indexes (but relhasindex was set) */ + if (indexoidlist == NIL) + return NIL; + + /* + * Copy the rd_pkindex and rd_replidindex values computed by + * RelationGetIndexList before proceeding. This is needed because a + * relcache flush could occur inside index_open below, resetting the + * fields managed by RelationGetIndexList. We need to do the work with + * stable values of these fields. + */ + relpkindex = relation->rd_pkindex; + relreplindex = relation->rd_replidindex; + + foreach(lc, indexoidlist) + { + Oid oid = lfirst_oid(lc); + Datum datum; + bool isnull; + Node *indexExpressions; + Node *indexPredicate; + Relation indexDesc; + IndexInfo *indexInfo; + + /* + * Extract index expressions and index predicate. Note: Don't use + * RelationGetIndexExpressions()/RelationGetIndexPredicate(), because + * those might run constant expressions evaluation, which needs a + * snapshot, which we might not have here. (Also, it's probably more + * sound to collect the bitmaps before any transformations that might + * eliminate columns, but the practical impact of this is limited.) + */ + indexDesc = index_open(oid, AccessShareLock); + datum = heap_getattr(indexDesc->rd_indextuple, Anum_pg_index_indexprs, + GetPgIndexDescriptor(), &isnull); + if (!isnull) + indexExpressions = stringToNode(TextDatumGetCString(datum)); + else + indexExpressions = NULL; + + datum = heap_getattr(indexDesc->rd_indextuple, Anum_pg_index_indpred, + GetPgIndexDescriptor(), &isnull); + if (!isnull) + indexPredicate = stringToNode(TextDatumGetCString(datum)); + else + indexPredicate = NULL; + + if (indexExpressions || indexPredicate) + { + oldcxt = MemoryContextSwitchTo(CacheMemoryContext); + indexInfo = BuildIndexInfo(indexDesc); + MemoryContextSwitchTo(oldcxt); + result = lappend(result, indexInfo); + } + + index_close(indexDesc, AccessShareLock); + } + + /* + * During one of the index_opens in the above loop, we might have received + * a relcache flush event on this relcache entry, which might have been + * signaling a change in the rel's index list. If so, we'd better start + * over to ensure we deliver up-to-date IndexInfo. + */ + newindexoidlist = RelationGetIndexList(relation); + if (equal(indexoidlist, newindexoidlist) && + relpkindex == relation->rd_pkindex && + relreplindex == relation->rd_replidindex) + { + /* Still the same index set, so proceed */ + list_free(newindexoidlist); + list_free(indexoidlist); + } + else + { + /* Gotta do it over ... might as well not leak memory */ + list_free(newindexoidlist); + list_free(indexoidlist); + list_free(result); + + goto restart; + } + + /* Now save a copy of the completed list in the relcache entry. */ + oldcxt = MemoryContextSwitchTo(CacheMemoryContext); + oldlist = relation->rd_iiexprlist; + relation->rd_iiexprlist = list_copy(result); + MemoryContextSwitchTo(oldcxt); + + /* Don't leak the old list, if there is one */ + if (oldlist) + list_free(oldlist); + + return result; +} + /* * RelationGetIndexAttrBitmap -- get a bitmap of index attribute numbers * @@ -5229,7 +5352,11 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind) Bitmapset *pkindexattrs; /* columns in the primary index */ Bitmapset *idindexattrs; /* columns in the replica identity */ Bitmapset *hotblockingattrs; /* columns with HOT blocking indexes */ + Bitmapset *hotblockingexprattrs; /* as above, but only those in + * expressions */ Bitmapset *summarizedattrs; /* columns with summarizing indexes */ + Bitmapset *summarizedexprattrs; /* as above, but only those in + * expressions */ List *indexoidlist; List *newindexoidlist; Oid relpkindex; @@ -5252,6 +5379,8 @@ RelationGetIndexAttrBitmap(Relation relation, IndexAttrBitmapKind attrKind) return bms_copy(relation->rd_hotblockingattr); case INDEX_ATTR_BITMAP_SUMMARIZED: return bms_copy(relation->rd_summarizedattr); + case INDEX_ATTR_BITMAP_EXPRESSION: + return bms_copy(relation->rd_expressionattr); default: elog(ERROR, "unknown attrKind %u", attrKind); } @@ -5295,7 +5424,9 @@ restart: pkindexattrs = NULL; idindexattrs = NULL; hotblockingattrs = NULL; + hotblockingexprattrs = NULL; summarizedattrs = NULL; + summarizedexprattrs = NULL; foreach(l, indexoidlist) { Oid indexOid = lfirst_oid(l); @@ -5309,6 +5440,7 @@ restart: bool isPK; /* primary key */ bool isIDKey; /* replica identity index */ Bitmapset **attrs; + Bitmapset **exprattrs; indexDesc = index_open(indexOid, AccessShareLock); @@ -5352,14 +5484,20 @@ restart: * decide which bitmap we'll update in the following loop. */ if (indexDesc->rd_indam->amsummarizing) + { attrs = &summarizedattrs; + exprattrs = &summarizedexprattrs; + } else + { attrs = &hotblockingattrs; + exprattrs = &hotblockingexprattrs; + } /* Collect simple attribute references */ for (i = 0; i < indexDesc->rd_index->indnatts; i++) { - int attrnum = indexDesc->rd_index->indkey.values[i]; + int attridx = indexDesc->rd_index->indkey.values[i]; /* * Since we have covering indexes with non-key columns, we must @@ -5375,30 +5513,28 @@ restart: * key or identity key. Hence we do not include them into * uindexattrs, pkindexattrs and idindexattrs bitmaps. */ - if (attrnum != 0) + if (attridx != 0) { - *attrs = bms_add_member(*attrs, - attrnum - FirstLowInvalidHeapAttributeNumber); + AttrNumber attrnum = attridx - FirstLowInvalidHeapAttributeNumber; + + *attrs = bms_add_member(*attrs, attrnum); if (isKey && i < indexDesc->rd_index->indnkeyatts) - uindexattrs = bms_add_member(uindexattrs, - attrnum - FirstLowInvalidHeapAttributeNumber); + uindexattrs = bms_add_member(uindexattrs, attrnum); if (isPK && i < indexDesc->rd_index->indnkeyatts) - pkindexattrs = bms_add_member(pkindexattrs, - attrnum - FirstLowInvalidHeapAttributeNumber); + pkindexattrs = bms_add_member(pkindexattrs, attrnum); if (isIDKey && i < indexDesc->rd_index->indnkeyatts) - idindexattrs = bms_add_member(idindexattrs, - attrnum - FirstLowInvalidHeapAttributeNumber); + idindexattrs = bms_add_member(idindexattrs, attrnum); } } /* Collect all attributes used in expressions, too */ - pull_varattnos(indexExpressions, 1, attrs); + pull_varattnos(indexExpressions, 1, exprattrs); /* Collect all attributes in the index predicate, too */ - pull_varattnos(indexPredicate, 1, attrs); + pull_varattnos(indexPredicate, 1, exprattrs); index_close(indexDesc, AccessShareLock); } @@ -5427,11 +5563,27 @@ restart: bms_free(pkindexattrs); bms_free(idindexattrs); bms_free(hotblockingattrs); + bms_free(hotblockingexprattrs); bms_free(summarizedattrs); + bms_free(summarizedexprattrs); goto restart; } + /* {expression-only columns} = {expression columns} - {direct columns} */ + hotblockingexprattrs = bms_del_members(hotblockingexprattrs, + hotblockingattrs); + /* {hot-blocking columns} = {direct columns} + {expression-only columns} */ + hotblockingattrs = bms_add_members(hotblockingattrs, + hotblockingexprattrs); + + /* {summarized-only columns} = {summarized columns} - {direct columns} */ + summarizedexprattrs = bms_del_members(summarizedexprattrs, + summarizedattrs); + /* {summarized columns} = {direct columns} + {summarized-only columns} */ + summarizedattrs = bms_add_members(summarizedattrs, + summarizedexprattrs); + /* Don't leak the old values of these bitmaps, if any */ relation->rd_attrsvalid = false; bms_free(relation->rd_keyattr); @@ -5444,6 +5596,8 @@ restart: relation->rd_hotblockingattr = NULL; bms_free(relation->rd_summarizedattr); relation->rd_summarizedattr = NULL; + bms_free(relation->rd_expressionattr); + relation->rd_expressionattr = NULL; /* * Now save copies of the bitmaps in the relcache entry. We intentionally @@ -5458,6 +5612,7 @@ restart: relation->rd_idattr = bms_copy(idindexattrs); relation->rd_hotblockingattr = bms_copy(hotblockingattrs); relation->rd_summarizedattr = bms_copy(summarizedattrs); + relation->rd_expressionattr = bms_copy(hotblockingexprattrs); relation->rd_attrsvalid = true; MemoryContextSwitchTo(oldcxt); @@ -5474,6 +5629,8 @@ restart: return hotblockingattrs; case INDEX_ATTR_BITMAP_SUMMARIZED: return summarizedattrs; + case INDEX_ATTR_BITMAP_EXPRESSION: + return hotblockingexprattrs; default: elog(ERROR, "unknown attrKind %u", attrKind); return NULL; diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index eb8bc128720..f0a8286a25b 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -2992,7 +2992,7 @@ match_previous_words(int pattern_id, COMPLETE_WITH("("); /* ALTER TABLESPACE SET|RESET ( */ else if (Matches("ALTER", "TABLESPACE", MatchAny, "SET|RESET", "(")) - COMPLETE_WITH("seq_page_cost", "random_page_cost", + COMPLETE_WITH("seq_page_cost", "random_page_cost", "expression_checks", "effective_io_concurrency", "maintenance_io_concurrency"); /* ALTER TEXT SEARCH */ diff --git a/src/include/access/genam.h b/src/include/access/genam.h index 1be8739573f..91af1e8238d 100644 --- a/src/include/access/genam.h +++ b/src/include/access/genam.h @@ -194,7 +194,7 @@ extern bool index_can_return(Relation indexRelation, int attno); extern RegProcedure index_getprocid(Relation irel, AttrNumber attnum, uint16 procnum); extern FmgrInfo *index_getprocinfo(Relation irel, AttrNumber attnum, - uint16 procnum); + uint16 procnum); extern void index_store_float8_orderby_distances(IndexScanDesc scan, Oid *orderByTypes, IndexOrderByDistance *distances, diff --git a/src/include/access/heapam.h b/src/include/access/heapam.h index 1640d9c32f7..e12da1934e9 100644 --- a/src/include/access/heapam.h +++ b/src/include/access/heapam.h @@ -21,6 +21,7 @@ #include "access/skey.h" #include "access/table.h" /* for backward compatibility */ #include "access/tableam.h" +#include "executor/executor.h" #include "nodes/lockoptions.h" #include "nodes/primnodes.h" #include "storage/bufpage.h" @@ -339,7 +340,7 @@ extern TM_Result heap_update(Relation relation, ItemPointer otid, HeapTuple newtup, CommandId cid, Snapshot crosscheck, bool wait, struct TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes); + TU_UpdateIndexes *update_indexes, struct EState *estate); extern TM_Result heap_lock_tuple(Relation relation, HeapTuple tuple, CommandId cid, LockTupleMode mode, LockWaitPolicy wait_policy, bool follow_updates, diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h index 131c050c15f..62ed6592b85 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -38,6 +38,7 @@ struct IndexInfo; struct SampleScanState; struct VacuumParams; struct ValidateIndexState; +struct EState; /* * Bitmask values for the flags argument to the scan_begin callback. @@ -550,7 +551,8 @@ typedef struct TableAmRoutine bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes); + TU_UpdateIndexes *update_indexes, + struct EState *estate); /* see table_tuple_lock() for reference about parameters */ TM_Result (*tuple_lock) (Relation rel, @@ -1541,12 +1543,12 @@ static inline TM_Result table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot, CommandId cid, Snapshot snapshot, Snapshot crosscheck, bool wait, TM_FailureData *tmfd, LockTupleMode *lockmode, - TU_UpdateIndexes *update_indexes) + TU_UpdateIndexes *update_indexes, struct EState *estate) { return rel->rd_tableam->tuple_update(rel, otid, slot, cid, snapshot, crosscheck, - wait, tmfd, - lockmode, update_indexes); + wait, tmfd, lockmode, + update_indexes, estate); } /* diff --git a/src/include/executor/executor.h b/src/include/executor/executor.h index 30e2a82346f..343d04fff57 100644 --- a/src/include/executor/executor.h +++ b/src/include/executor/executor.h @@ -661,6 +661,11 @@ extern void check_exclusion_constraint(Relation heap, Relation index, ItemPointer tupleid, const Datum *values, const bool *isnull, EState *estate, bool newIndex); +extern bool ExecIndexesExpressionsWereNotUpdated(Relation relation, + Bitmapset *modified_attrs, + EState *estate, + HeapTuple old_tuple, + HeapTuple new_tuple); /* * prototypes from functions in execReplication.c diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h index 2625d7e8222..aca9371dccd 100644 --- a/src/include/nodes/execnodes.h +++ b/src/include/nodes/execnodes.h @@ -159,12 +159,15 @@ typedef struct ExprState * * NumIndexAttrs total number of columns in this index * NumIndexKeyAttrs number of key columns in index + * IndexAttrs bitmap of index attributes * IndexAttrNumbers underlying-rel attribute numbers used as keys * (zeroes indicate expressions). It also contains * info about included columns. * Expressions expr trees for expression entries, or NIL if none + * ExpressionAttrs bitmap of attributes used within the expression * ExpressionsState exec state for expressions, or NIL if none * Predicate partial-index predicate, or NIL if none + * PredicateAttrs bitmap of attributes used within the predicate * PredicateState exec state for predicate, or NIL if none * ExclusionOps Per-column exclusion operators, or NULL if none * ExclusionProcs Underlying function OIDs for ExclusionOps @@ -183,6 +186,7 @@ typedef struct ExprState * ParallelWorkers # of workers requested (excludes leader) * Am Oid of index AM * AmCache private cache area for index AM + * OpClassDataTypes operator class data types * Context memory context holding this IndexInfo * * ii_Concurrent, ii_BrokenHotChain, and ii_ParallelWorkers are used only @@ -194,10 +198,15 @@ typedef struct IndexInfo NodeTag type; int ii_NumIndexAttrs; /* total number of columns in index */ int ii_NumIndexKeyAttrs; /* number of key columns in index */ + Bitmapset *ii_IndexAttrs; AttrNumber ii_IndexAttrNumbers[INDEX_MAX_KEYS]; + uint16 ii_IndexAttrLen[INDEX_MAX_KEYS]; + Bitmapset *ii_IndexAttrByVal; List *ii_Expressions; /* list of Expr */ + Bitmapset *ii_ExpressionAttrs; List *ii_ExpressionsState; /* list of ExprState */ List *ii_Predicate; /* list of Expr */ + Bitmapset *ii_PredicateAttrs; ExprState *ii_PredicateState; Oid *ii_ExclusionOps; /* array with one entry per column */ Oid *ii_ExclusionProcs; /* array with one entry per column */ diff --git a/src/include/utils/rel.h b/src/include/utils/rel.h index db3e504c3d2..3eba254a366 100644 --- a/src/include/utils/rel.h +++ b/src/include/utils/rel.h @@ -164,6 +164,11 @@ typedef struct RelationData Bitmapset *rd_idattr; /* included in replica identity index */ Bitmapset *rd_hotblockingattr; /* cols blocking HOT update */ Bitmapset *rd_summarizedattr; /* cols indexed by summarizing indexes */ + Bitmapset *rd_expressionattr; /* indexed cols referenced by expressions */ + + /* data managed by RelationGetExprIndexInfoList: */ + List *rd_iiexprlist; /* list of IndexInfo for indexes with + * expressions */ PublicationDesc *rd_pubdesc; /* publication descriptor, or NULL */ @@ -344,6 +349,7 @@ typedef struct StdRdOptions int parallel_workers; /* max number of parallel workers */ StdRdOptIndexCleanup vacuum_index_cleanup; /* controls index vacuuming */ bool vacuum_truncate; /* enables vacuum to truncate a relation */ + bool expression_checks; /* use expression to checks for changes */ /* * Fraction of pages in a relation that vacuum can eagerly scan and fail @@ -405,6 +411,14 @@ typedef struct StdRdOptions ((relation)->rd_options ? \ ((StdRdOptions *) (relation)->rd_options)->parallel_workers : (defaultpw)) +/* + * RelationGetExpressionChecks + * Returns the relation's expression_checks reloption setting. + */ +#define RelationGetExpressionChecks(relation) \ + ((relation)->rd_options ? \ + ((StdRdOptions *) (relation)->rd_options)->expression_checks : true) + /* ViewOptions->check_option values */ typedef enum ViewOptCheckOption { diff --git a/src/include/utils/relcache.h b/src/include/utils/relcache.h index a7c55db339e..56524a73399 100644 --- a/src/include/utils/relcache.h +++ b/src/include/utils/relcache.h @@ -52,6 +52,7 @@ extern List *RelationGetIndexExpressions(Relation relation); extern List *RelationGetDummyIndexExpressions(Relation relation); extern List *RelationGetIndexPredicate(Relation relation); extern bytea **RelationGetIndexAttOptions(Relation relation, bool copy); +extern List *RelationGetExprIndexInfoList(Relation relation); /* * Which set of columns to return by RelationGetIndexAttrBitmap. @@ -63,6 +64,7 @@ typedef enum IndexAttrBitmapKind INDEX_ATTR_BITMAP_IDENTITY_KEY, INDEX_ATTR_BITMAP_HOT_BLOCKING, INDEX_ATTR_BITMAP_SUMMARIZED, + INDEX_ATTR_BITMAP_EXPRESSION, } IndexAttrBitmapKind; extern Bitmapset *RelationGetIndexAttrBitmap(Relation relation, diff --git a/src/test/regress/expected/heap_hot_updates.out b/src/test/regress/expected/heap_hot_updates.out new file mode 100644 index 00000000000..2ad6e5418e9 --- /dev/null +++ b/src/test/regress/expected/heap_hot_updates.out @@ -0,0 +1,586 @@ +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This table will have two columns and two indexes, one on the primary key +-- id and one on the expression (info->>'name'). That means that the indexed +-- attributes are 'id' and 'info'. +create table keyvalue(id integer primary key, info jsonb); +create index nameindex on keyvalue((info->>'name')); +insert into keyvalue values (1, '{"name": "john", "data": "some data"}'); +-- Disable expression checks. +ALTER TABLE keyvalue SET (expression_checks = false); +SELECT reloptions FROM pg_class WHERE relname = 'keyvalue'; + reloptions +--------------------------- + {expression_checks=false} +(1 row) + +-- While the indexed attribute "name" is unchanged we've disabled expression +-- checks so this update should not go HOT as the system can't determine if +-- the indexed attribute has changed without evaluating the expression. +update keyvalue set info='{"name": "john", "data": "something else"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 0 row + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Re-enable expression checks. +ALTER TABLE keyvalue SET (expression_checks = true); +SELECT reloptions FROM pg_class WHERE relname = 'keyvalue'; + reloptions +-------------------------- + {expression_checks=true} +(1 row) + +-- The indexed attribute "name" with value "john" is unchanged, expect a HOT update. +update keyvalue set info='{"name": "john", "data": "some other data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 1 row + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- The following update changes the indexed attribute "name", this should not be a HOT update. +update keyvalue set info='{"name": "smith", "data": "some other data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Now, this update does not change the indexed attribute "name" from "smith", this should be HOT. +update keyvalue set info='{"name": "smith", "data": "some more data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 2 rows now + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 2 +(1 row) + +drop table keyvalue; +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This table is the same as the previous one but it has a third index. The +-- index 'colindex' isn't an expression index, it indexes the entire value +-- in the info column. There are still only two indexed attributes for this +-- relation, the same two as before. The presence of an index on the entire +-- value of the info column should prevent HOT updates for any updates to any +-- portion of JSONB content in that column. +create table keyvalue(id integer primary key, info jsonb); +create index nameindex on keyvalue((info->>'name')); +create index colindex on keyvalue(info); +insert into keyvalue values (1, '{"name": "john", "data": "some data"}'); +-- This update doesn't change the value of the expression index, but it does +-- change the content of the info column and so should not be HOT because the +-- indexed value changed as a result of the update. +update keyvalue set info='{"name": "john", "data": "some other data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 0 rows + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +drop table keyvalue; +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- The table has one column docs and two indexes. They are both expression +-- indexes referencing the same column attribute (docs) but one is a partial +-- index. +CREATE TABLE ex (docs JSONB) WITH (fillfactor = 60); +INSERT INTO ex (docs) VALUES ('{"a": 0, "b": 0}'); +INSERT INTO ex (docs) SELECT jsonb_build_object('b', n) FROM generate_series(100, 10000) as n; +CREATE INDEX idx_ex_a ON ex ((docs->>'a')); +CREATE INDEX idx_ex_b ON ex ((docs->>'b')) WHERE (docs->>'b')::numeric > 9; +-- We're using BTREE indexes and for this test we want to make sure that they remain +-- in sync with changes to our relation. Force the choice of index scans below so +-- that we know we're checking the index's understanding of what values should be +-- in the index or not. +SET SESSION enable_seqscan = OFF; +SET SESSION enable_bitmapscan = OFF; +-- Leave 'a' unchanged but modify 'b' to a value outside of the index predicate. +-- This should be a HOT update because neither index is changed. +UPDATE ex SET docs = jsonb_build_object('a', 0, 'b', 1) WHERE (docs->>'a')::numeric = 0; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 row + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Let's check to make sure that the index does not contain a value for 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + QUERY PLAN +-------------------------------------------------------------- + Index Scan using idx_ex_b on ex + Filter: (((docs ->> 'b'::text))::numeric < '100'::numeric) +(2 rows) + +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + docs +------ +(0 rows) + +-- Leave 'a' unchanged but modify 'b' to a value within the index predicate. +-- This represents a change for field 'b' from unindexed to indexed and so +-- this should not take the HOT path. +UPDATE ex SET docs = jsonb_build_object('a', 0, 'b', 10) WHERE (docs->>'a')::numeric = 0; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Let's check to make sure that the index contains the new value of 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + QUERY PLAN +-------------------------------------------------------------- + Index Scan using idx_ex_b on ex + Filter: (((docs ->> 'b'::text))::numeric < '100'::numeric) +(2 rows) + +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + docs +------------------- + {"a": 0, "b": 10} +(1 row) + +-- This update modifies the value of 'a', an indexed field, so it also cannot +-- be a HOT update. +UPDATE ex SET docs = jsonb_build_object('a', 1, 'b', 10) WHERE (docs->>'b')::numeric = 10; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- This update changes both 'a' and 'b' to new values that require index updates, +-- this cannot use the HOT path. +UPDATE ex SET docs = jsonb_build_object('a', 2, 'b', 12) WHERE (docs->>'b')::numeric = 10; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Let's check to make sure that the index contains the new value of 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + QUERY PLAN +-------------------------------------------------------------- + Index Scan using idx_ex_b on ex + Filter: (((docs ->> 'b'::text))::numeric < '100'::numeric) +(2 rows) + +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + docs +------------------- + {"a": 2, "b": 12} +(1 row) + +-- This update changes 'b' to a value outside its predicate requiring that +-- we remove it from the index. That's a transition that can't be done +-- during a HOT update. +UPDATE ex SET docs = jsonb_build_object('a', 2, 'b', 1) WHERE (docs->>'b')::numeric = 12; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Let's check to make sure that the index no longer contains the value of 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + QUERY PLAN +-------------------------------------------------------------- + Index Scan using idx_ex_b on ex + Filter: (((docs ->> 'b'::text))::numeric < '100'::numeric) +(2 rows) + +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + docs +------ +(0 rows) + +-- Disable expression checks. +ALTER TABLE ex SET (expression_checks = false); +SELECT reloptions FROM pg_class WHERE relname = 'ex'; + reloptions +----------------------------------------- + {fillfactor=60,expression_checks=false} +(1 row) + +-- This update changes 'b' to a value within its predicate just like it +-- previous value, which would allow for a HOT update but with expression +-- checks disabled we can't determine that so this should not be a HOT update. +UPDATE ex SET docs = jsonb_build_object('a', 2, 'b', 2) WHERE (docs->>'b')::numeric = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Let's make sure we're recording HOT updates for our 'ex' relation properly in the system +-- table pg_stat_user_tables. Note that statistics are stored within a transaction context +-- first (xact) and then later into the global statistics for a relation, so first we need +-- to ensure pending stats are flushed. +SELECT pg_stat_force_next_flush(); + pg_stat_force_next_flush +-------------------------- + +(1 row) + +SELECT + c.relname AS table_name, + -- Transaction statistics + pg_stat_get_xact_tuples_updated(c.oid) AS xact_updates, + pg_stat_get_xact_tuples_hot_updated(c.oid) AS xact_hot_updates, + ROUND(( + pg_stat_get_xact_tuples_hot_updated(c.oid)::float / + NULLIF(pg_stat_get_xact_tuples_updated(c.oid), 0) * 100 + )::numeric, 2) AS xact_hot_update_percentage, + -- Cumulative statistics + s.n_tup_upd AS total_updates, + s.n_tup_hot_upd AS hot_updates, + ROUND(( + s.n_tup_hot_upd::float / + NULLIF(s.n_tup_upd, 0) * 100 + )::numeric, 2) AS total_hot_update_percentage +FROM pg_class c +LEFT JOIN pg_stat_user_tables s ON c.relname = s.relname +WHERE c.relname = 'ex' +AND c.relnamespace = 'public'::regnamespace; + table_name | xact_updates | xact_hot_updates | xact_hot_update_percentage | total_updates | hot_updates | total_hot_update_percentage +------------+--------------+------------------+----------------------------+---------------+-------------+----------------------------- + ex | 0 | 0 | | 6 | 1 | 16.67 +(1 row) + +-- expect: 5 xact updates with 1 xact hot update and no cumulative updates as yet +SET SESSION enable_seqscan = ON; +SET SESSION enable_bitmapscan = ON; +DROP TABLE ex; +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This table has a single column 'email' and a unique constraint on it that +-- should preclude HOT updates. +CREATE TABLE users ( + user_id serial primary key, + name VARCHAR(255) NOT NULL, + email VARCHAR(255) NOT NULL, + EXCLUDE USING btree (lower(email) WITH =) +); +-- Add some data to the table and then update it in ways that should and should +-- not be HOT updates. +INSERT INTO users (name, email) VALUES +('user1', 'user1@example.com'), +('user2', 'user2@example.com'), +('taken', 'taken@EXAMPLE.com'), +('you', 'you@domain.com'), +('taken', 'taken@domain.com'); +-- Should fail because of the unique constraint on the email column. +UPDATE users SET email = 'user1@example.com' WHERE email = 'user2@example.com'; +ERROR: conflicting key value violates exclusion constraint "users_lower_excl" +DETAIL: Key (lower(email::text))=(user1@example.com) conflicts with existing key (lower(email::text))=(user1@example.com). +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 0 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Should succeed because the email column is not being updated and should go HOT. +UPDATE users SET name = 'foo' WHERE email = 'user1@example.com'; +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 1 a single new HOT update + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Create a partial index on the email column, updates +CREATE INDEX idx_users_email_no_example ON users (lower(email)) WHERE lower(email) LIKE '%@example.com%'; +-- An update that changes the email column but not the indexed portion of it and falls outside the constraint. +-- Shouldn't be a HOT update because of the exclusion constraint. +UPDATE users SET email = 'you+2@domain.com' WHERE name = 'you'; +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- An update that changes the email column but not the indexed portion of it and falls within the constraint. +-- Again, should fail constraint and fail to be a HOT update. +UPDATE users SET email = 'taken@domain.com' WHERE name = 'you'; +ERROR: conflicting key value violates exclusion constraint "users_lower_excl" +DETAIL: Key (lower(email::text))=(taken@domain.com) conflicts with existing key (lower(email::text))=(taken@domain.com). +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 1 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +DROP TABLE users; +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- Another test of constraints spoiling HOT updates, this time with a range. +CREATE TABLE events ( + id serial primary key, + name VARCHAR(255) NOT NULL, + event_time tstzrange, + constraint no_screening_time_overlap exclude using gist ( + event_time WITH && + ) +); +-- Add two non-overlapping events. +INSERT INTO events (id, event_time, name) +VALUES + (1, '["2023-01-01 19:00:00", "2023-01-01 20:45:00"]', 'event1'), + (2, '["2023-01-01 21:00:00", "2023-01-01 21:45:00"]', 'event2'); +-- Update the first event to overlap with the second, should fail the constraint and not be HOT. +UPDATE events SET event_time = '["2023-01-01 20:00:00", "2023-01-01 21:45:00"]' WHERE id = 1; +ERROR: conflicting key value violates exclusion constraint "no_screening_time_overlap" +DETAIL: Key (event_time)=(["Sun Jan 01 20:00:00 2023 PST","Sun Jan 01 21:45:00 2023 PST"]) conflicts with existing key (event_time)=(["Sun Jan 01 21:00:00 2023 PST","Sun Jan 01 21:45:00 2023 PST"]). +SELECT pg_stat_get_xact_tuples_hot_updated('events'::regclass); -- expect: 0 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Update the first event to not overlap with the second, again not HOT due to the constraint. +UPDATE events SET event_time = '["2023-01-01 22:00:00", "2023-01-01 22:45:00"]' WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('events'::regclass); -- expect: 0 no new HOT updates + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Update the first event to not overlap with the second, this time we're HOT because we don't overlap with the constraint. +UPDATE events SET name = 'new name here' WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('events'::regclass); -- expect: 1 one new HOT update + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +DROP TABLE events; +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- A test to ensure that summarizing indexes are not updated when they don't +-- change, but are updated when they do while not prefent HOT updates. +CREATE TABLE ex (att1 JSONB, att2 text) WITH (fillfactor = 60); +CREATE INDEX expression ON ex USING btree((att1->'data')); +CREATE INDEX summarizing ON ex USING BRIN(att2); +INSERT INTO ex VALUES ('{"data": []}', 'nothing special'); +-- Update the unindexed value of att1, this should be a HOT update and not +-- update the summarizing index. +UPDATE ex SET att1 = att1 || '{"status": "checkmate"}'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 one new HOT update + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Update the indexed value of att2, a summarized value, this is a summarized +-- only update and should use the HOT path while still triggering an update to +-- the summarizing BRIN index. +UPDATE ex SET att2 = 'special indeed'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 2 one new HOT update + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 2 +(1 row) + +-- Update to att1 doesn't change the indexed value while the update to att2 does, +-- this again is a summarized only update and should use the HOT path as well as +-- trigger an update to the BRIN index. +UPDATE ex SET att1 = att1 || '{"status": "checkmate!"}', att2 = 'special, so special'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 3 one new HOT update + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 3 +(1 row) + +-- This updates both indexes, the expression index on att1 and the summarizing +-- index on att2. This should not be a HOT update because there are modified +-- indexes and only some are summarized, not all. This should force all +-- indexes to be updated. +UPDATE ex SET att1 = att1 || '{"data": [1,2,3]}', att2 = 'do you want to play a game?'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 3 both indexes updated + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 3 +(1 row) + +DROP TABLE ex; +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This test is for a table with a custom type and a custom operators on +-- the BTREE index. The question is, when comparing values for equality +-- to determine if there are changes on the index or not... shouldn't we +-- be using the custom operators? +-- Create a type +CREATE TYPE my_custom_type AS (val int); +-- Comparison functions (returns boolean) +CREATE FUNCTION my_custom_lt(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val < b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +CREATE FUNCTION my_custom_le(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val <= b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +CREATE FUNCTION my_custom_eq(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val = b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +CREATE FUNCTION my_custom_ge(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val >= b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +CREATE FUNCTION my_custom_gt(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val > b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +CREATE FUNCTION my_custom_ne(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val != b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +-- Comparison function (returns -1, 0, 1) +CREATE FUNCTION my_custom_cmp(a my_custom_type, b my_custom_type) RETURNS int AS $$ +BEGIN + IF a.val < b.val THEN + RETURN -1; + ELSIF a.val > b.val THEN + RETURN 1; + ELSE + RETURN 0; + END IF; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +-- Create the operators +CREATE OPERATOR < ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_lt, + COMMUTATOR = >, + NEGATOR = >= +); +CREATE OPERATOR <= ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_le, + COMMUTATOR = >=, + NEGATOR = > +); +CREATE OPERATOR = ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_eq, + COMMUTATOR = =, + NEGATOR = <> +); +CREATE OPERATOR >= ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_ge, + COMMUTATOR = <=, + NEGATOR = < +); +CREATE OPERATOR > ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_gt, + COMMUTATOR = <, + NEGATOR = <= +); +CREATE OPERATOR <> ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_ne, + COMMUTATOR = <>, + NEGATOR = = +); +-- Create the operator class (including the support function) +CREATE OPERATOR CLASS my_custom_ops + DEFAULT FOR TYPE my_custom_type USING btree AS + OPERATOR 1 <, + OPERATOR 2 <=, + OPERATOR 3 =, + OPERATOR 4 >=, + OPERATOR 5 >, + FUNCTION 1 my_custom_cmp(my_custom_type, my_custom_type); +-- Create the table +CREATE TABLE my_table ( + id int, + custom_val my_custom_type +); +-- Insert some data +INSERT INTO my_table (id, custom_val) VALUES +(1, ROW(3)::my_custom_type), +(2, ROW(1)::my_custom_type), +(3, ROW(4)::my_custom_type), +(4, ROW(2)::my_custom_type); +-- Create a function to use when indexing +CREATE OR REPLACE FUNCTION abs_val(val my_custom_type) RETURNS int AS $$ +BEGIN + RETURN abs(val.val); +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; +-- Create the index +CREATE INDEX idx_custom_val_abs ON my_table (abs_val(custom_val)); +-- Update 1 +UPDATE my_table SET custom_val = ROW(5)::my_custom_type WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Update 2 +UPDATE my_table SET custom_val = ROW(0)::my_custom_type WHERE custom_val < ROW(3)::my_custom_type; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Update 3 +UPDATE my_table SET custom_val = ROW(6)::my_custom_type WHERE id = 3; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 0 +(1 row) + +-- Update 4 +UPDATE my_table SET id = 5 WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + pg_stat_get_xact_tuples_hot_updated +------------------------------------- + 1 +(1 row) + +-- Query using the index +EXPLAIN (COSTS OFF) SELECT * FROM my_table WHERE abs_val(custom_val) = 6; + QUERY PLAN +------------------------------------- + Seq Scan on my_table + Filter: (abs_val(custom_val) = 6) +(2 rows) + +SELECT * FROM my_table WHERE abs_val(custom_val) = 6; + id | custom_val +----+------------ + 3 | (6) +(1 row) + +-- Clean up +DROP TABLE my_table CASCADE; +DROP OPERATOR CLASS my_custom_ops USING btree CASCADE; +DROP OPERATOR < (my_custom_type, my_custom_type); +DROP OPERATOR <= (my_custom_type, my_custom_type); +DROP OPERATOR = (my_custom_type, my_custom_type); +DROP OPERATOR >= (my_custom_type, my_custom_type); +DROP OPERATOR > (my_custom_type, my_custom_type); +DROP OPERATOR <> (my_custom_type, my_custom_type); +DROP FUNCTION my_custom_lt(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_le(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_eq(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_ge(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_gt(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_ne(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_cmp(my_custom_type, my_custom_type); +DROP FUNCTION abs_val(my_custom_type); +DROP TYPE my_custom_type CASCADE; diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule index e63ee2cf2bb..f9def3d93aa 100644 --- a/src/test/regress/parallel_schedule +++ b/src/test/regress/parallel_schedule @@ -68,6 +68,11 @@ test: select_into select_distinct select_distinct_on select_implicit select_havi # ---------- test: brin gin gist spgist privileges init_privs security_label collate matview lock replica_identity rowsecurity object_address tablesample groupingsets drop_operator password identity generated_stored join_hash +# ---------- +# Another group of parallel tests +# ---------- +test: heap_hot_updates + # ---------- # Additional BRIN tests # ---------- diff --git a/src/test/regress/sql/heap_hot_updates.sql b/src/test/regress/sql/heap_hot_updates.sql new file mode 100644 index 00000000000..7728075a7ae --- /dev/null +++ b/src/test/regress/sql/heap_hot_updates.sql @@ -0,0 +1,440 @@ +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This table will have two columns and two indexes, one on the primary key +-- id and one on the expression (info->>'name'). That means that the indexed +-- attributes are 'id' and 'info'. +create table keyvalue(id integer primary key, info jsonb); +create index nameindex on keyvalue((info->>'name')); +insert into keyvalue values (1, '{"name": "john", "data": "some data"}'); + +-- Disable expression checks. +ALTER TABLE keyvalue SET (expression_checks = false); +SELECT reloptions FROM pg_class WHERE relname = 'keyvalue'; + +-- While the indexed attribute "name" is unchanged we've disabled expression +-- checks so this update should not go HOT as the system can't determine if +-- the indexed attribute has changed without evaluating the expression. +update keyvalue set info='{"name": "john", "data": "something else"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 0 row + +-- Re-enable expression checks. +ALTER TABLE keyvalue SET (expression_checks = true); +SELECT reloptions FROM pg_class WHERE relname = 'keyvalue'; + +-- The indexed attribute "name" with value "john" is unchanged, expect a HOT update. +update keyvalue set info='{"name": "john", "data": "some other data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 1 row + +-- The following update changes the indexed attribute "name", this should not be a HOT update. +update keyvalue set info='{"name": "smith", "data": "some other data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 1 no new HOT updates + +-- Now, this update does not change the indexed attribute "name" from "smith", this should be HOT. +update keyvalue set info='{"name": "smith", "data": "some more data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 2 rows now +drop table keyvalue; + + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This table is the same as the previous one but it has a third index. The +-- index 'colindex' isn't an expression index, it indexes the entire value +-- in the info column. There are still only two indexed attributes for this +-- relation, the same two as before. The presence of an index on the entire +-- value of the info column should prevent HOT updates for any updates to any +-- portion of JSONB content in that column. +create table keyvalue(id integer primary key, info jsonb); +create index nameindex on keyvalue((info->>'name')); +create index colindex on keyvalue(info); +insert into keyvalue values (1, '{"name": "john", "data": "some data"}'); + +-- This update doesn't change the value of the expression index, but it does +-- change the content of the info column and so should not be HOT because the +-- indexed value changed as a result of the update. +update keyvalue set info='{"name": "john", "data": "some other data"}' where id=1; +select pg_stat_get_xact_tuples_hot_updated('keyvalue'::regclass); -- expect: 0 rows +drop table keyvalue; + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- The table has one column docs and two indexes. They are both expression +-- indexes referencing the same column attribute (docs) but one is a partial +-- index. +CREATE TABLE ex (docs JSONB) WITH (fillfactor = 60); +INSERT INTO ex (docs) VALUES ('{"a": 0, "b": 0}'); +INSERT INTO ex (docs) SELECT jsonb_build_object('b', n) FROM generate_series(100, 10000) as n; +CREATE INDEX idx_ex_a ON ex ((docs->>'a')); +CREATE INDEX idx_ex_b ON ex ((docs->>'b')) WHERE (docs->>'b')::numeric > 9; + +-- We're using BTREE indexes and for this test we want to make sure that they remain +-- in sync with changes to our relation. Force the choice of index scans below so +-- that we know we're checking the index's understanding of what values should be +-- in the index or not. +SET SESSION enable_seqscan = OFF; +SET SESSION enable_bitmapscan = OFF; + +-- Leave 'a' unchanged but modify 'b' to a value outside of the index predicate. +-- This should be a HOT update because neither index is changed. +UPDATE ex SET docs = jsonb_build_object('a', 0, 'b', 1) WHERE (docs->>'a')::numeric = 0; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 row +-- Let's check to make sure that the index does not contain a value for 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + +-- Leave 'a' unchanged but modify 'b' to a value within the index predicate. +-- This represents a change for field 'b' from unindexed to indexed and so +-- this should not take the HOT path. +UPDATE ex SET docs = jsonb_build_object('a', 0, 'b', 10) WHERE (docs->>'a')::numeric = 0; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates +-- Let's check to make sure that the index contains the new value of 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + +-- This update modifies the value of 'a', an indexed field, so it also cannot +-- be a HOT update. +UPDATE ex SET docs = jsonb_build_object('a', 1, 'b', 10) WHERE (docs->>'b')::numeric = 10; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + +-- This update changes both 'a' and 'b' to new values that require index updates, +-- this cannot use the HOT path. +UPDATE ex SET docs = jsonb_build_object('a', 2, 'b', 12) WHERE (docs->>'b')::numeric = 10; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates +-- Let's check to make sure that the index contains the new value of 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + +-- This update changes 'b' to a value outside its predicate requiring that +-- we remove it from the index. That's a transition that can't be done +-- during a HOT update. +UPDATE ex SET docs = jsonb_build_object('a', 2, 'b', 1) WHERE (docs->>'b')::numeric = 12; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates +-- Let's check to make sure that the index no longer contains the value of 'b' +EXPLAIN (COSTS OFF) SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; +SELECT * FROM ex WHERE (docs->>'b')::numeric > 9 AND (docs->>'b')::numeric < 100; + +-- Disable expression checks. +ALTER TABLE ex SET (expression_checks = false); +SELECT reloptions FROM pg_class WHERE relname = 'ex'; + +-- This update changes 'b' to a value within its predicate just like it +-- previous value, which would allow for a HOT update but with expression +-- checks disabled we can't determine that so this should not be a HOT update. +UPDATE ex SET docs = jsonb_build_object('a', 2, 'b', 2) WHERE (docs->>'b')::numeric = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 no new HOT updates + + +-- Let's make sure we're recording HOT updates for our 'ex' relation properly in the system +-- table pg_stat_user_tables. Note that statistics are stored within a transaction context +-- first (xact) and then later into the global statistics for a relation, so first we need +-- to ensure pending stats are flushed. +SELECT pg_stat_force_next_flush(); +SELECT + c.relname AS table_name, + -- Transaction statistics + pg_stat_get_xact_tuples_updated(c.oid) AS xact_updates, + pg_stat_get_xact_tuples_hot_updated(c.oid) AS xact_hot_updates, + ROUND(( + pg_stat_get_xact_tuples_hot_updated(c.oid)::float / + NULLIF(pg_stat_get_xact_tuples_updated(c.oid), 0) * 100 + )::numeric, 2) AS xact_hot_update_percentage, + -- Cumulative statistics + s.n_tup_upd AS total_updates, + s.n_tup_hot_upd AS hot_updates, + ROUND(( + s.n_tup_hot_upd::float / + NULLIF(s.n_tup_upd, 0) * 100 + )::numeric, 2) AS total_hot_update_percentage +FROM pg_class c +LEFT JOIN pg_stat_user_tables s ON c.relname = s.relname +WHERE c.relname = 'ex' +AND c.relnamespace = 'public'::regnamespace; +-- expect: 5 xact updates with 1 xact hot update and no cumulative updates as yet + +SET SESSION enable_seqscan = ON; +SET SESSION enable_bitmapscan = ON; + +DROP TABLE ex; + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This table has a single column 'email' and a unique constraint on it that +-- should preclude HOT updates. +CREATE TABLE users ( + user_id serial primary key, + name VARCHAR(255) NOT NULL, + email VARCHAR(255) NOT NULL, + EXCLUDE USING btree (lower(email) WITH =) +); + +-- Add some data to the table and then update it in ways that should and should +-- not be HOT updates. +INSERT INTO users (name, email) VALUES +('user1', 'user1@example.com'), +('user2', 'user2@example.com'), +('taken', 'taken@EXAMPLE.com'), +('you', 'you@domain.com'), +('taken', 'taken@domain.com'); + +-- Should fail because of the unique constraint on the email column. +UPDATE users SET email = 'user1@example.com' WHERE email = 'user2@example.com'; +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 0 no new HOT updates + +-- Should succeed because the email column is not being updated and should go HOT. +UPDATE users SET name = 'foo' WHERE email = 'user1@example.com'; +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 1 a single new HOT update + +-- Create a partial index on the email column, updates +CREATE INDEX idx_users_email_no_example ON users (lower(email)) WHERE lower(email) LIKE '%@example.com%'; + +-- An update that changes the email column but not the indexed portion of it and falls outside the constraint. +-- Shouldn't be a HOT update because of the exclusion constraint. +UPDATE users SET email = 'you+2@domain.com' WHERE name = 'you'; +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 1 no new HOT updates + +-- An update that changes the email column but not the indexed portion of it and falls within the constraint. +-- Again, should fail constraint and fail to be a HOT update. +UPDATE users SET email = 'taken@domain.com' WHERE name = 'you'; +SELECT pg_stat_get_xact_tuples_hot_updated('users'::regclass); -- expect: 1 no new HOT updates + +DROP TABLE users; + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- Another test of constraints spoiling HOT updates, this time with a range. +CREATE TABLE events ( + id serial primary key, + name VARCHAR(255) NOT NULL, + event_time tstzrange, + constraint no_screening_time_overlap exclude using gist ( + event_time WITH && + ) +); + +-- Add two non-overlapping events. +INSERT INTO events (id, event_time, name) +VALUES + (1, '["2023-01-01 19:00:00", "2023-01-01 20:45:00"]', 'event1'), + (2, '["2023-01-01 21:00:00", "2023-01-01 21:45:00"]', 'event2'); + +-- Update the first event to overlap with the second, should fail the constraint and not be HOT. +UPDATE events SET event_time = '["2023-01-01 20:00:00", "2023-01-01 21:45:00"]' WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('events'::regclass); -- expect: 0 no new HOT updates + +-- Update the first event to not overlap with the second, again not HOT due to the constraint. +UPDATE events SET event_time = '["2023-01-01 22:00:00", "2023-01-01 22:45:00"]' WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('events'::regclass); -- expect: 0 no new HOT updates + +-- Update the first event to not overlap with the second, this time we're HOT because we don't overlap with the constraint. +UPDATE events SET name = 'new name here' WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('events'::regclass); -- expect: 1 one new HOT update + +DROP TABLE events; + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- A test to ensure that summarizing indexes are not updated when they don't +-- change, but are updated when they do while not prefent HOT updates. +CREATE TABLE ex (att1 JSONB, att2 text) WITH (fillfactor = 60); +CREATE INDEX expression ON ex USING btree((att1->'data')); +CREATE INDEX summarizing ON ex USING BRIN(att2); +INSERT INTO ex VALUES ('{"data": []}', 'nothing special'); + +-- Update the unindexed value of att1, this should be a HOT update and not +-- update the summarizing index. +UPDATE ex SET att1 = att1 || '{"status": "checkmate"}'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 1 one new HOT update + +-- Update the indexed value of att2, a summarized value, this is a summarized +-- only update and should use the HOT path while still triggering an update to +-- the summarizing BRIN index. +UPDATE ex SET att2 = 'special indeed'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 2 one new HOT update + +-- Update to att1 doesn't change the indexed value while the update to att2 does, +-- this again is a summarized only update and should use the HOT path as well as +-- trigger an update to the BRIN index. +UPDATE ex SET att1 = att1 || '{"status": "checkmate!"}', att2 = 'special, so special'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 3 one new HOT update + +-- This updates both indexes, the expression index on att1 and the summarizing +-- index on att2. This should not be a HOT update because there are modified +-- indexes and only some are summarized, not all. This should force all +-- indexes to be updated. +UPDATE ex SET att1 = att1 || '{"data": [1,2,3]}', att2 = 'do you want to play a game?'; +SELECT pg_stat_get_xact_tuples_hot_updated('ex'::regclass); -- expect: 3 both indexes updated + +DROP TABLE ex; + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +-- This test is for a table with a custom type and a custom operators on +-- the BTREE index. The question is, when comparing values for equality +-- to determine if there are changes on the index or not... shouldn't we +-- be using the custom operators? + +-- Create a type +CREATE TYPE my_custom_type AS (val int); + +-- Comparison functions (returns boolean) +CREATE FUNCTION my_custom_lt(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val < b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +CREATE FUNCTION my_custom_le(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val <= b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +CREATE FUNCTION my_custom_eq(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val = b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +CREATE FUNCTION my_custom_ge(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val >= b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +CREATE FUNCTION my_custom_gt(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val > b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +CREATE FUNCTION my_custom_ne(a my_custom_type, b my_custom_type) RETURNS boolean AS $$ +BEGIN + RETURN a.val != b.val; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +-- Comparison function (returns -1, 0, 1) +CREATE FUNCTION my_custom_cmp(a my_custom_type, b my_custom_type) RETURNS int AS $$ +BEGIN + IF a.val < b.val THEN + RETURN -1; + ELSIF a.val > b.val THEN + RETURN 1; + ELSE + RETURN 0; + END IF; +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +-- Create the operators +CREATE OPERATOR < ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_lt, + COMMUTATOR = >, + NEGATOR = >= +); + +CREATE OPERATOR <= ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_le, + COMMUTATOR = >=, + NEGATOR = > +); + +CREATE OPERATOR = ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_eq, + COMMUTATOR = =, + NEGATOR = <> +); + +CREATE OPERATOR >= ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_ge, + COMMUTATOR = <=, + NEGATOR = < +); + +CREATE OPERATOR > ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_gt, + COMMUTATOR = <, + NEGATOR = <= +); + +CREATE OPERATOR <> ( + LEFTARG = my_custom_type, + RIGHTARG = my_custom_type, + PROCEDURE = my_custom_ne, + COMMUTATOR = <>, + NEGATOR = = +); + +-- Create the operator class (including the support function) +CREATE OPERATOR CLASS my_custom_ops + DEFAULT FOR TYPE my_custom_type USING btree AS + OPERATOR 1 <, + OPERATOR 2 <=, + OPERATOR 3 =, + OPERATOR 4 >=, + OPERATOR 5 >, + FUNCTION 1 my_custom_cmp(my_custom_type, my_custom_type); + +-- Create the table +CREATE TABLE my_table ( + id int, + custom_val my_custom_type +); + +-- Insert some data +INSERT INTO my_table (id, custom_val) VALUES +(1, ROW(3)::my_custom_type), +(2, ROW(1)::my_custom_type), +(3, ROW(4)::my_custom_type), +(4, ROW(2)::my_custom_type); + +-- Create a function to use when indexing +CREATE OR REPLACE FUNCTION abs_val(val my_custom_type) RETURNS int AS $$ +BEGIN + RETURN abs(val.val); +END; +$$ LANGUAGE plpgsql IMMUTABLE STRICT; + +-- Create the index +CREATE INDEX idx_custom_val_abs ON my_table (abs_val(custom_val)); + +-- Update 1 +UPDATE my_table SET custom_val = ROW(5)::my_custom_type WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + +-- Update 2 +UPDATE my_table SET custom_val = ROW(0)::my_custom_type WHERE custom_val < ROW(3)::my_custom_type; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + +-- Update 3 +UPDATE my_table SET custom_val = ROW(6)::my_custom_type WHERE id = 3; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + +-- Update 4 +UPDATE my_table SET id = 5 WHERE id = 1; +SELECT pg_stat_get_xact_tuples_hot_updated('my_table'::regclass); + +-- Query using the index +EXPLAIN (COSTS OFF) SELECT * FROM my_table WHERE abs_val(custom_val) = 6; +SELECT * FROM my_table WHERE abs_val(custom_val) = 6; + +-- Clean up +DROP TABLE my_table CASCADE; +DROP OPERATOR CLASS my_custom_ops USING btree CASCADE; +DROP OPERATOR < (my_custom_type, my_custom_type); +DROP OPERATOR <= (my_custom_type, my_custom_type); +DROP OPERATOR = (my_custom_type, my_custom_type); +DROP OPERATOR >= (my_custom_type, my_custom_type); +DROP OPERATOR > (my_custom_type, my_custom_type); +DROP OPERATOR <> (my_custom_type, my_custom_type); +DROP FUNCTION my_custom_lt(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_le(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_eq(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_ge(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_gt(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_ne(my_custom_type, my_custom_type); +DROP FUNCTION my_custom_cmp(my_custom_type, my_custom_type); +DROP FUNCTION abs_val(my_custom_type); +DROP TYPE my_custom_type CASCADE; -- 2.42.0