agora inbox for pgsql-hackers@postgresql.orghelp / color / mirror / Atom feed
[PATCH v19 1/3] Move pg_stat_statements query jumbling to core. 4+ messages / 3 participants [nested] [flat]
* [PATCH v19 1/3] Move pg_stat_statements query jumbling to core. @ 2020-10-13 18:11 Julien Rouhaud <julien.rouhaud@free.fr> 0 siblings, 0 replies; 4+ messages in thread From: Julien Rouhaud @ 2020-10-13 18:11 UTC (permalink / raw) A new compute_query_id GUC is also added, to control whether a query identifier should be computed by the core. It's thefore now possible to disable core queryid computation and use pg_stat_statements with a different algorithm to compute the query identifier by using third-party module. To ensure that a single source of query identifier can be used and is well defined, modules that calculate a query identifier should throw an error if compute_query_id is enabled or if a query idenfitier was already calculated. Author: Julien Rouhaud Reviewed-by: Bruce Momjian Discussion: https://postgr.es/m/CA+8PKvQnMfOE-c3YLRwxOsCYXQDyP8VXs6CDtMZp1V4=D4LuFA@mail.gmail.com --- .../pg_stat_statements/pg_stat_statements.c | 805 +---------------- .../pg_stat_statements.conf | 1 + doc/src/sgml/config.sgml | 26 + doc/src/sgml/pgstatstatements.sgml | 20 +- src/backend/parser/analyze.c | 14 +- src/backend/tcop/postgres.c | 6 +- src/backend/utils/misc/Makefile | 1 + src/backend/utils/misc/guc.c | 10 + src/backend/utils/misc/postgresql.conf.sample | 1 + src/backend/utils/misc/queryjumble.c | 834 ++++++++++++++++++ src/include/parser/analyze.h | 4 +- src/include/utils/guc.h | 1 + src/include/utils/queryjumble.h | 58 ++ 13 files changed, 996 insertions(+), 785 deletions(-) create mode 100644 src/backend/utils/misc/queryjumble.c create mode 100644 src/include/utils/queryjumble.h diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c index 62cccbfa44..498f2aa376 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.c +++ b/contrib/pg_stat_statements/pg_stat_statements.c @@ -8,24 +8,9 @@ * a shared hashtable. (We track only as many distinct queries as will fit * in the designated amount of shared memory.) * - * As of Postgres 9.2, this module normalizes query entries. Normalization - * is a process whereby similar queries, typically differing only in their - * constants (though the exact rules are somewhat more subtle than that) are - * recognized as equivalent, and are tracked as a single entry. This is - * particularly useful for non-prepared queries. - * - * Normalization is implemented by fingerprinting queries, selectively - * serializing those fields of each query tree's nodes that are judged to be - * essential to the query. This is referred to as a query jumble. This is - * distinct from a regular serialization in that various extraneous - * information is ignored as irrelevant or not essential to the query, such - * as the collations of Vars and, most notably, the values of constants. - * - * This jumble is acquired at the end of parse analysis of each query, and - * a 64-bit hash of it is stored into the query's Query.queryId field. - * The server then copies this value around, making it available in plan - * tree(s) generated from the query. The executor can then use this value - * to blame query costs on the proper queryId. + * As of Postgres 9.2, this module normalizes query entries. As of Postgres + * 14, the normalization is done by the core if compute_query_id is enabled, + * or optionally by third-party modules. * * To facilitate presenting entries to users, we create "representative" query * strings in which constants are replaced with parameter symbols ($n), to @@ -114,8 +99,6 @@ static const uint32 PGSS_PG_MAJOR_VERSION = PG_VERSION_NUM / 100; #define USAGE_DEALLOC_PERCENT 5 /* free this % of entries at once */ #define IS_STICKY(c) ((c.calls[PGSS_PLAN] + c.calls[PGSS_EXEC]) == 0) -#define JUMBLE_SIZE 1024 /* query serialization buffer size */ - /* * Extension version number, for supporting older extension versions' objects */ @@ -235,40 +218,6 @@ typedef struct pgssSharedState pgssGlobalStats stats; /* global statistics for pgss */ } pgssSharedState; -/* - * Struct for tracking locations/lengths of constants during normalization - */ -typedef struct pgssLocationLen -{ - int location; /* start offset in query text */ - int length; /* length in bytes, or -1 to ignore */ -} pgssLocationLen; - -/* - * Working state for computing a query jumble and producing a normalized - * query string - */ -typedef struct pgssJumbleState -{ - /* Jumble of current query tree */ - unsigned char *jumble; - - /* Number of bytes used in jumble[] */ - Size jumble_len; - - /* Array of locations of constants that should be removed */ - pgssLocationLen *clocations; - - /* Allocated length of clocations array */ - int clocations_buf_size; - - /* Current number of valid entries in clocations array */ - int clocations_count; - - /* highest Param id we've seen, in order to start normalization correctly */ - int highest_extern_param_id; -} pgssJumbleState; - /*---- Local variables ----*/ /* Current nesting depth of ExecutorRun+ProcessUtility calls */ @@ -342,7 +291,8 @@ PG_FUNCTION_INFO_V1(pg_stat_statements_info); static void pgss_shmem_startup(void); static void pgss_shmem_shutdown(int code, Datum arg); -static void pgss_post_parse_analyze(ParseState *pstate, Query *query); +static void pgss_post_parse_analyze(ParseState *pstate, Query *query, + JumbleState *jstate); static PlannedStmt *pgss_planner(Query *parse, const char *query_string, int cursorOptions, @@ -364,7 +314,7 @@ static void pgss_store(const char *query, uint64 queryId, double total_time, uint64 rows, const BufferUsage *bufusage, const WalUsage *walusage, - pgssJumbleState *jstate); + JumbleState *jstate); static void pg_stat_statements_internal(FunctionCallInfo fcinfo, pgssVersion api_version, bool showtext); @@ -380,16 +330,9 @@ static char *qtext_fetch(Size query_offset, int query_len, static bool need_gc_qtexts(void); static void gc_qtexts(void); static void entry_reset(Oid userid, Oid dbid, uint64 queryid); -static void AppendJumble(pgssJumbleState *jstate, - const unsigned char *item, Size size); -static void JumbleQuery(pgssJumbleState *jstate, Query *query); -static void JumbleRangeTable(pgssJumbleState *jstate, List *rtable); -static void JumbleRowMarks(pgssJumbleState *jstate, List *rowMarks); -static void JumbleExpr(pgssJumbleState *jstate, Node *node); -static void RecordConstLocation(pgssJumbleState *jstate, int location); -static char *generate_normalized_query(pgssJumbleState *jstate, const char *query, +static char *generate_normalized_query(JumbleState *jstate, const char *query, int query_loc, int *query_len_p); -static void fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, +static void fill_in_constant_lengths(JumbleState *jstate, const char *query, int query_loc); static int comp_location(const void *a, const void *b); @@ -851,15 +794,10 @@ error: * Post-parse-analysis hook: mark query with a queryId */ static void -pgss_post_parse_analyze(ParseState *pstate, Query *query) +pgss_post_parse_analyze(ParseState *pstate, Query *query, JumbleState *jstate) { - pgssJumbleState jstate; - if (prev_post_parse_analyze_hook) - prev_post_parse_analyze_hook(pstate, query); - - /* Assert we didn't do this already */ - Assert(query->queryId == UINT64CONST(0)); + prev_post_parse_analyze_hook(pstate, query, jstate); /* Safety check... */ if (!pgss || !pgss_hash || !pgss_enabled(exec_nested_level)) @@ -879,35 +817,14 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query) return; } - /* Set up workspace for query jumbling */ - jstate.jumble = (unsigned char *) palloc(JUMBLE_SIZE); - jstate.jumble_len = 0; - jstate.clocations_buf_size = 32; - jstate.clocations = (pgssLocationLen *) - palloc(jstate.clocations_buf_size * sizeof(pgssLocationLen)); - jstate.clocations_count = 0; - jstate.highest_extern_param_id = 0; - - /* Compute query ID and mark the Query node with it */ - JumbleQuery(&jstate, query); - query->queryId = - DatumGetUInt64(hash_any_extended(jstate.jumble, jstate.jumble_len, 0)); - /* - * If we are unlucky enough to get a hash of zero, use 1 instead, to - * prevent confusion with the utility-statement case. + * If query jumbling were able to identify any ignorable constants, we + * immediately create a hash table entry for the query, so that we can + * record the normalized form of the query string. If there were no such + * constants, the normalized string would be the same as the query text + * anyway, so there's no need for an early entry. */ - if (query->queryId == UINT64CONST(0)) - query->queryId = UINT64CONST(1); - - /* - * If we were able to identify any ignorable constants, we immediately - * create a hash table entry for the query, so that we can record the - * normalized form of the query string. If there were no such constants, - * the normalized string would be the same as the query text anyway, so - * there's no need for an early entry. - */ - if (jstate.clocations_count > 0) + if (jstate && jstate->clocations_count > 0) pgss_store(pstate->p_sourcetext, query->queryId, query->stmt_location, @@ -917,7 +834,7 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query) 0, NULL, NULL, - &jstate); + jstate); } /* @@ -1267,7 +1184,7 @@ pgss_store(const char *query, uint64 queryId, double total_time, uint64 rows, const BufferUsage *bufusage, const WalUsage *walusage, - pgssJumbleState *jstate) + JumbleState *jstate) { pgssHashKey key; pgssEntry *entry; @@ -2627,678 +2544,6 @@ release_lock: LWLockRelease(pgss->lock); } -/* - * AppendJumble: Append a value that is substantive in a given query to - * the current jumble. - */ -static void -AppendJumble(pgssJumbleState *jstate, const unsigned char *item, Size size) -{ - unsigned char *jumble = jstate->jumble; - Size jumble_len = jstate->jumble_len; - - /* - * Whenever the jumble buffer is full, we hash the current contents and - * reset the buffer to contain just that hash value, thus relying on the - * hash to summarize everything so far. - */ - while (size > 0) - { - Size part_size; - - if (jumble_len >= JUMBLE_SIZE) - { - uint64 start_hash; - - start_hash = DatumGetUInt64(hash_any_extended(jumble, - JUMBLE_SIZE, 0)); - memcpy(jumble, &start_hash, sizeof(start_hash)); - jumble_len = sizeof(start_hash); - } - part_size = Min(size, JUMBLE_SIZE - jumble_len); - memcpy(jumble + jumble_len, item, part_size); - jumble_len += part_size; - item += part_size; - size -= part_size; - } - jstate->jumble_len = jumble_len; -} - -/* - * Wrappers around AppendJumble to encapsulate details of serialization - * of individual local variable elements. - */ -#define APP_JUMB(item) \ - AppendJumble(jstate, (const unsigned char *) &(item), sizeof(item)) -#define APP_JUMB_STRING(str) \ - AppendJumble(jstate, (const unsigned char *) (str), strlen(str) + 1) - -/* - * JumbleQuery: Selectively serialize the query tree, appending significant - * data to the "query jumble" while ignoring nonsignificant data. - * - * Rule of thumb for what to include is that we should ignore anything not - * semantically significant (such as alias names) as well as anything that can - * be deduced from child nodes (else we'd just be double-hashing that piece - * of information). - */ -static void -JumbleQuery(pgssJumbleState *jstate, Query *query) -{ - Assert(IsA(query, Query)); - Assert(query->utilityStmt == NULL); - - APP_JUMB(query->commandType); - /* resultRelation is usually predictable from commandType */ - JumbleExpr(jstate, (Node *) query->cteList); - JumbleRangeTable(jstate, query->rtable); - JumbleExpr(jstate, (Node *) query->jointree); - JumbleExpr(jstate, (Node *) query->targetList); - JumbleExpr(jstate, (Node *) query->onConflict); - JumbleExpr(jstate, (Node *) query->returningList); - JumbleExpr(jstate, (Node *) query->groupClause); - JumbleExpr(jstate, (Node *) query->groupingSets); - JumbleExpr(jstate, query->havingQual); - JumbleExpr(jstate, (Node *) query->windowClause); - JumbleExpr(jstate, (Node *) query->distinctClause); - JumbleExpr(jstate, (Node *) query->sortClause); - JumbleExpr(jstate, query->limitOffset); - JumbleExpr(jstate, query->limitCount); - JumbleRowMarks(jstate, query->rowMarks); - JumbleExpr(jstate, query->setOperations); -} - -/* - * Jumble a range table - */ -static void -JumbleRangeTable(pgssJumbleState *jstate, List *rtable) -{ - ListCell *lc; - - foreach(lc, rtable) - { - RangeTblEntry *rte = lfirst_node(RangeTblEntry, lc); - - APP_JUMB(rte->rtekind); - switch (rte->rtekind) - { - case RTE_RELATION: - APP_JUMB(rte->relid); - JumbleExpr(jstate, (Node *) rte->tablesample); - break; - case RTE_SUBQUERY: - JumbleQuery(jstate, rte->subquery); - break; - case RTE_JOIN: - APP_JUMB(rte->jointype); - break; - case RTE_FUNCTION: - JumbleExpr(jstate, (Node *) rte->functions); - break; - case RTE_TABLEFUNC: - JumbleExpr(jstate, (Node *) rte->tablefunc); - break; - case RTE_VALUES: - JumbleExpr(jstate, (Node *) rte->values_lists); - break; - case RTE_CTE: - - /* - * Depending on the CTE name here isn't ideal, but it's the - * only info we have to identify the referenced WITH item. - */ - APP_JUMB_STRING(rte->ctename); - APP_JUMB(rte->ctelevelsup); - break; - case RTE_NAMEDTUPLESTORE: - APP_JUMB_STRING(rte->enrname); - break; - case RTE_RESULT: - break; - default: - elog(ERROR, "unrecognized RTE kind: %d", (int) rte->rtekind); - break; - } - } -} - -/* - * Jumble a rowMarks list - */ -static void -JumbleRowMarks(pgssJumbleState *jstate, List *rowMarks) -{ - ListCell *lc; - - foreach(lc, rowMarks) - { - RowMarkClause *rowmark = lfirst_node(RowMarkClause, lc); - - if (!rowmark->pushedDown) - { - APP_JUMB(rowmark->rti); - APP_JUMB(rowmark->strength); - APP_JUMB(rowmark->waitPolicy); - } - } -} - -/* - * Jumble an expression tree - * - * In general this function should handle all the same node types that - * expression_tree_walker() does, and therefore it's coded to be as parallel - * to that function as possible. However, since we are only invoked on - * queries immediately post-parse-analysis, we need not handle node types - * that only appear in planning. - * - * Note: the reason we don't simply use expression_tree_walker() is that the - * point of that function is to support tree walkers that don't care about - * most tree node types, but here we care about all types. We should complain - * about any unrecognized node type. - */ -static void -JumbleExpr(pgssJumbleState *jstate, Node *node) -{ - ListCell *temp; - - if (node == NULL) - return; - - /* Guard against stack overflow due to overly complex expressions */ - check_stack_depth(); - - /* - * We always emit the node's NodeTag, then any additional fields that are - * considered significant, and then we recurse to any child nodes. - */ - APP_JUMB(node->type); - - switch (nodeTag(node)) - { - case T_Var: - { - Var *var = (Var *) node; - - APP_JUMB(var->varno); - APP_JUMB(var->varattno); - APP_JUMB(var->varlevelsup); - } - break; - case T_Const: - { - Const *c = (Const *) node; - - /* We jumble only the constant's type, not its value */ - APP_JUMB(c->consttype); - /* Also, record its parse location for query normalization */ - RecordConstLocation(jstate, c->location); - } - break; - case T_Param: - { - Param *p = (Param *) node; - - APP_JUMB(p->paramkind); - APP_JUMB(p->paramid); - APP_JUMB(p->paramtype); - /* Also, track the highest external Param id */ - if (p->paramkind == PARAM_EXTERN && - p->paramid > jstate->highest_extern_param_id) - jstate->highest_extern_param_id = p->paramid; - } - break; - case T_Aggref: - { - Aggref *expr = (Aggref *) node; - - APP_JUMB(expr->aggfnoid); - JumbleExpr(jstate, (Node *) expr->aggdirectargs); - JumbleExpr(jstate, (Node *) expr->args); - JumbleExpr(jstate, (Node *) expr->aggorder); - JumbleExpr(jstate, (Node *) expr->aggdistinct); - JumbleExpr(jstate, (Node *) expr->aggfilter); - } - break; - case T_GroupingFunc: - { - GroupingFunc *grpnode = (GroupingFunc *) node; - - JumbleExpr(jstate, (Node *) grpnode->refs); - } - break; - case T_WindowFunc: - { - WindowFunc *expr = (WindowFunc *) node; - - APP_JUMB(expr->winfnoid); - APP_JUMB(expr->winref); - JumbleExpr(jstate, (Node *) expr->args); - JumbleExpr(jstate, (Node *) expr->aggfilter); - } - break; - case T_SubscriptingRef: - { - SubscriptingRef *sbsref = (SubscriptingRef *) node; - - JumbleExpr(jstate, (Node *) sbsref->refupperindexpr); - JumbleExpr(jstate, (Node *) sbsref->reflowerindexpr); - JumbleExpr(jstate, (Node *) sbsref->refexpr); - JumbleExpr(jstate, (Node *) sbsref->refassgnexpr); - } - break; - case T_FuncExpr: - { - FuncExpr *expr = (FuncExpr *) node; - - APP_JUMB(expr->funcid); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_NamedArgExpr: - { - NamedArgExpr *nae = (NamedArgExpr *) node; - - APP_JUMB(nae->argnumber); - JumbleExpr(jstate, (Node *) nae->arg); - } - break; - case T_OpExpr: - case T_DistinctExpr: /* struct-equivalent to OpExpr */ - case T_NullIfExpr: /* struct-equivalent to OpExpr */ - { - OpExpr *expr = (OpExpr *) node; - - APP_JUMB(expr->opno); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_ScalarArrayOpExpr: - { - ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node; - - APP_JUMB(expr->opno); - APP_JUMB(expr->useOr); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_BoolExpr: - { - BoolExpr *expr = (BoolExpr *) node; - - APP_JUMB(expr->boolop); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_SubLink: - { - SubLink *sublink = (SubLink *) node; - - APP_JUMB(sublink->subLinkType); - APP_JUMB(sublink->subLinkId); - JumbleExpr(jstate, (Node *) sublink->testexpr); - JumbleQuery(jstate, castNode(Query, sublink->subselect)); - } - break; - case T_FieldSelect: - { - FieldSelect *fs = (FieldSelect *) node; - - APP_JUMB(fs->fieldnum); - JumbleExpr(jstate, (Node *) fs->arg); - } - break; - case T_FieldStore: - { - FieldStore *fstore = (FieldStore *) node; - - JumbleExpr(jstate, (Node *) fstore->arg); - JumbleExpr(jstate, (Node *) fstore->newvals); - } - break; - case T_RelabelType: - { - RelabelType *rt = (RelabelType *) node; - - APP_JUMB(rt->resulttype); - JumbleExpr(jstate, (Node *) rt->arg); - } - break; - case T_CoerceViaIO: - { - CoerceViaIO *cio = (CoerceViaIO *) node; - - APP_JUMB(cio->resulttype); - JumbleExpr(jstate, (Node *) cio->arg); - } - break; - case T_ArrayCoerceExpr: - { - ArrayCoerceExpr *acexpr = (ArrayCoerceExpr *) node; - - APP_JUMB(acexpr->resulttype); - JumbleExpr(jstate, (Node *) acexpr->arg); - JumbleExpr(jstate, (Node *) acexpr->elemexpr); - } - break; - case T_ConvertRowtypeExpr: - { - ConvertRowtypeExpr *crexpr = (ConvertRowtypeExpr *) node; - - APP_JUMB(crexpr->resulttype); - JumbleExpr(jstate, (Node *) crexpr->arg); - } - break; - case T_CollateExpr: - { - CollateExpr *ce = (CollateExpr *) node; - - APP_JUMB(ce->collOid); - JumbleExpr(jstate, (Node *) ce->arg); - } - break; - case T_CaseExpr: - { - CaseExpr *caseexpr = (CaseExpr *) node; - - JumbleExpr(jstate, (Node *) caseexpr->arg); - foreach(temp, caseexpr->args) - { - CaseWhen *when = lfirst_node(CaseWhen, temp); - - JumbleExpr(jstate, (Node *) when->expr); - JumbleExpr(jstate, (Node *) when->result); - } - JumbleExpr(jstate, (Node *) caseexpr->defresult); - } - break; - case T_CaseTestExpr: - { - CaseTestExpr *ct = (CaseTestExpr *) node; - - APP_JUMB(ct->typeId); - } - break; - case T_ArrayExpr: - JumbleExpr(jstate, (Node *) ((ArrayExpr *) node)->elements); - break; - case T_RowExpr: - JumbleExpr(jstate, (Node *) ((RowExpr *) node)->args); - break; - case T_RowCompareExpr: - { - RowCompareExpr *rcexpr = (RowCompareExpr *) node; - - APP_JUMB(rcexpr->rctype); - JumbleExpr(jstate, (Node *) rcexpr->largs); - JumbleExpr(jstate, (Node *) rcexpr->rargs); - } - break; - case T_CoalesceExpr: - JumbleExpr(jstate, (Node *) ((CoalesceExpr *) node)->args); - break; - case T_MinMaxExpr: - { - MinMaxExpr *mmexpr = (MinMaxExpr *) node; - - APP_JUMB(mmexpr->op); - JumbleExpr(jstate, (Node *) mmexpr->args); - } - break; - case T_SQLValueFunction: - { - SQLValueFunction *svf = (SQLValueFunction *) node; - - APP_JUMB(svf->op); - /* type is fully determined by op */ - APP_JUMB(svf->typmod); - } - break; - case T_XmlExpr: - { - XmlExpr *xexpr = (XmlExpr *) node; - - APP_JUMB(xexpr->op); - JumbleExpr(jstate, (Node *) xexpr->named_args); - JumbleExpr(jstate, (Node *) xexpr->args); - } - break; - case T_NullTest: - { - NullTest *nt = (NullTest *) node; - - APP_JUMB(nt->nulltesttype); - JumbleExpr(jstate, (Node *) nt->arg); - } - break; - case T_BooleanTest: - { - BooleanTest *bt = (BooleanTest *) node; - - APP_JUMB(bt->booltesttype); - JumbleExpr(jstate, (Node *) bt->arg); - } - break; - case T_CoerceToDomain: - { - CoerceToDomain *cd = (CoerceToDomain *) node; - - APP_JUMB(cd->resulttype); - JumbleExpr(jstate, (Node *) cd->arg); - } - break; - case T_CoerceToDomainValue: - { - CoerceToDomainValue *cdv = (CoerceToDomainValue *) node; - - APP_JUMB(cdv->typeId); - } - break; - case T_SetToDefault: - { - SetToDefault *sd = (SetToDefault *) node; - - APP_JUMB(sd->typeId); - } - break; - case T_CurrentOfExpr: - { - CurrentOfExpr *ce = (CurrentOfExpr *) node; - - APP_JUMB(ce->cvarno); - if (ce->cursor_name) - APP_JUMB_STRING(ce->cursor_name); - APP_JUMB(ce->cursor_param); - } - break; - case T_NextValueExpr: - { - NextValueExpr *nve = (NextValueExpr *) node; - - APP_JUMB(nve->seqid); - APP_JUMB(nve->typeId); - } - break; - case T_InferenceElem: - { - InferenceElem *ie = (InferenceElem *) node; - - APP_JUMB(ie->infercollid); - APP_JUMB(ie->inferopclass); - JumbleExpr(jstate, ie->expr); - } - break; - case T_TargetEntry: - { - TargetEntry *tle = (TargetEntry *) node; - - APP_JUMB(tle->resno); - APP_JUMB(tle->ressortgroupref); - JumbleExpr(jstate, (Node *) tle->expr); - } - break; - case T_RangeTblRef: - { - RangeTblRef *rtr = (RangeTblRef *) node; - - APP_JUMB(rtr->rtindex); - } - break; - case T_JoinExpr: - { - JoinExpr *join = (JoinExpr *) node; - - APP_JUMB(join->jointype); - APP_JUMB(join->isNatural); - APP_JUMB(join->rtindex); - JumbleExpr(jstate, join->larg); - JumbleExpr(jstate, join->rarg); - JumbleExpr(jstate, join->quals); - } - break; - case T_FromExpr: - { - FromExpr *from = (FromExpr *) node; - - JumbleExpr(jstate, (Node *) from->fromlist); - JumbleExpr(jstate, from->quals); - } - break; - case T_OnConflictExpr: - { - OnConflictExpr *conf = (OnConflictExpr *) node; - - APP_JUMB(conf->action); - JumbleExpr(jstate, (Node *) conf->arbiterElems); - JumbleExpr(jstate, conf->arbiterWhere); - JumbleExpr(jstate, (Node *) conf->onConflictSet); - JumbleExpr(jstate, conf->onConflictWhere); - APP_JUMB(conf->constraint); - APP_JUMB(conf->exclRelIndex); - JumbleExpr(jstate, (Node *) conf->exclRelTlist); - } - break; - case T_List: - foreach(temp, (List *) node) - { - JumbleExpr(jstate, (Node *) lfirst(temp)); - } - break; - case T_IntList: - foreach(temp, (List *) node) - { - APP_JUMB(lfirst_int(temp)); - } - break; - case T_SortGroupClause: - { - SortGroupClause *sgc = (SortGroupClause *) node; - - APP_JUMB(sgc->tleSortGroupRef); - APP_JUMB(sgc->eqop); - APP_JUMB(sgc->sortop); - APP_JUMB(sgc->nulls_first); - } - break; - case T_GroupingSet: - { - GroupingSet *gsnode = (GroupingSet *) node; - - JumbleExpr(jstate, (Node *) gsnode->content); - } - break; - case T_WindowClause: - { - WindowClause *wc = (WindowClause *) node; - - APP_JUMB(wc->winref); - APP_JUMB(wc->frameOptions); - JumbleExpr(jstate, (Node *) wc->partitionClause); - JumbleExpr(jstate, (Node *) wc->orderClause); - JumbleExpr(jstate, wc->startOffset); - JumbleExpr(jstate, wc->endOffset); - } - break; - case T_CommonTableExpr: - { - CommonTableExpr *cte = (CommonTableExpr *) node; - - /* we store the string name because RTE_CTE RTEs need it */ - APP_JUMB_STRING(cte->ctename); - APP_JUMB(cte->ctematerialized); - JumbleQuery(jstate, castNode(Query, cte->ctequery)); - } - break; - case T_SetOperationStmt: - { - SetOperationStmt *setop = (SetOperationStmt *) node; - - APP_JUMB(setop->op); - APP_JUMB(setop->all); - JumbleExpr(jstate, setop->larg); - JumbleExpr(jstate, setop->rarg); - } - break; - case T_RangeTblFunction: - { - RangeTblFunction *rtfunc = (RangeTblFunction *) node; - - JumbleExpr(jstate, rtfunc->funcexpr); - } - break; - case T_TableFunc: - { - TableFunc *tablefunc = (TableFunc *) node; - - JumbleExpr(jstate, tablefunc->docexpr); - JumbleExpr(jstate, tablefunc->rowexpr); - JumbleExpr(jstate, (Node *) tablefunc->colexprs); - } - break; - case T_TableSampleClause: - { - TableSampleClause *tsc = (TableSampleClause *) node; - - APP_JUMB(tsc->tsmhandler); - JumbleExpr(jstate, (Node *) tsc->args); - JumbleExpr(jstate, (Node *) tsc->repeatable); - } - break; - default: - /* Only a warning, since we can stumble along anyway */ - elog(WARNING, "unrecognized node type: %d", - (int) nodeTag(node)); - break; - } -} - -/* - * Record location of constant within query string of query tree - * that is currently being walked. - */ -static void -RecordConstLocation(pgssJumbleState *jstate, int location) -{ - /* -1 indicates unknown or undefined location */ - if (location >= 0) - { - /* enlarge array if needed */ - if (jstate->clocations_count >= jstate->clocations_buf_size) - { - jstate->clocations_buf_size *= 2; - jstate->clocations = (pgssLocationLen *) - repalloc(jstate->clocations, - jstate->clocations_buf_size * - sizeof(pgssLocationLen)); - } - jstate->clocations[jstate->clocations_count].location = location; - /* initialize lengths to -1 to simplify fill_in_constant_lengths */ - jstate->clocations[jstate->clocations_count].length = -1; - jstate->clocations_count++; - } -} - /* * Generate a normalized version of the query string that will be used to * represent all similar queries. @@ -3319,7 +2564,7 @@ RecordConstLocation(pgssJumbleState *jstate, int location) * Returns a palloc'd string. */ static char * -generate_normalized_query(pgssJumbleState *jstate, const char *query, +generate_normalized_query(JumbleState *jstate, const char *query, int query_loc, int *query_len_p) { char *norm_query; @@ -3426,10 +2671,10 @@ generate_normalized_query(pgssJumbleState *jstate, const char *query, * reason for a constant to start with a '-'. */ static void -fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, +fill_in_constant_lengths(JumbleState *jstate, const char *query, int query_loc) { - pgssLocationLen *locs; + LocationLen *locs; core_yyscan_t yyscanner; core_yy_extra_type yyextra; core_YYSTYPE yylval; @@ -3443,7 +2688,7 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, */ if (jstate->clocations_count > 1) qsort(jstate->clocations, jstate->clocations_count, - sizeof(pgssLocationLen), comp_location); + sizeof(LocationLen), comp_location); locs = jstate->clocations; /* initialize the flex scanner --- should match raw_parser() */ @@ -3523,13 +2768,13 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, } /* - * comp_location: comparator for qsorting pgssLocationLen structs by location + * comp_location: comparator for qsorting LocationLen structs by location */ static int comp_location(const void *a, const void *b) { - int l = ((const pgssLocationLen *) a)->location; - int r = ((const pgssLocationLen *) b)->location; + int l = ((const LocationLen *) a)->location; + int r = ((const LocationLen *) b)->location; if (l < r) return -1; diff --git a/contrib/pg_stat_statements/pg_stat_statements.conf b/contrib/pg_stat_statements/pg_stat_statements.conf index 13346e2807..e47b26040f 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.conf +++ b/contrib/pg_stat_statements/pg_stat_statements.conf @@ -1 +1,2 @@ shared_preload_libraries = 'pg_stat_statements' +compute_query_id = on diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index ee4925d6d9..176d448798 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -7561,6 +7561,32 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv; <title>Statistics Monitoring</title> <variablelist> + <varlistentry id="guc-compute-query-id" xreflabel="compute_query_id"> + <term><varname>compute_query_id</varname> (<type>boolean</type>) + <indexterm> + <primary><varname>compute_query_id</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Enables or disables in core query identifier computation. The + <xref linkend="pgstatstatements"/> extension requires a query + identifier to be computed. Note that an external module can + alternatively be used if the in core query identifier computation + specification doesn't suit your need. In this case, in core + computation must be disabled. The default is <literal>off</literal>. + </para> + <note> + <para> + To ensure that a single source of query identifier can be used and is + well defined, extensions that calculate a query identifier should + throw an error if this parameter is <literal>on</literal> or if a + query idenfitier was already calculated. + </para> + </note> + </listitem> + </varlistentry> + <varlistentry> <term><varname>log_statement_stats</varname> (<type>boolean</type>) <indexterm> diff --git a/doc/src/sgml/pgstatstatements.sgml b/doc/src/sgml/pgstatstatements.sgml index 464bf0e5ae..b242568041 100644 --- a/doc/src/sgml/pgstatstatements.sgml +++ b/doc/src/sgml/pgstatstatements.sgml @@ -20,6 +20,14 @@ This means that a server restart is needed to add or remove the module. </para> + <para> + The module won't track any statistics unless query identifiers are + calculated. This can be done by enabling <xref + linkend="guc-compute-query-id"/> or using a third-party module. Note that + all statistics tracked by this module must be reset if the query identifier + is changed. + </para> + <para> When <filename>pg_stat_statements</filename> is loaded, it tracks statistics across all databases of the server. To access and manipulate @@ -84,7 +92,7 @@ <structfield>queryid</structfield> <type>bigint</type> </para> <para> - Internal hash code, computed from the statement's parse tree + Hash code to identify identical normalized queries. </para></entry> </row> @@ -386,6 +394,16 @@ are compared strictly on the basis of their textual query strings, however. </para> + <note> + <para> + All the following details about constant replacement and + <structfield>queryid</structfield> only applies when <xref + linkend="guc-compute-query-id"/> is enabled. If you use an external module + instead, you should refer to its documentation for the implication of their + <structfield>queryid</structfield> heuristics. + </para> + </note> + <para> When a constant's value has been ignored for purposes of matching the query to other queries, the constant is replaced by a parameter symbol, such diff --git a/src/backend/parser/analyze.c b/src/backend/parser/analyze.c index 7149724953..c565c80365 100644 --- a/src/backend/parser/analyze.c +++ b/src/backend/parser/analyze.c @@ -46,6 +46,8 @@ #include "parser/parsetree.h" #include "rewrite/rewriteManip.h" #include "utils/builtins.h" +#include "utils/guc.h" +#include "utils/queryjumble.h" #include "utils/rel.h" @@ -107,6 +109,7 @@ parse_analyze(RawStmt *parseTree, const char *sourceText, { ParseState *pstate = make_parsestate(NULL); Query *query; + JumbleState *jstate = NULL; Assert(sourceText != NULL); /* required as of 8.4 */ @@ -119,8 +122,11 @@ parse_analyze(RawStmt *parseTree, const char *sourceText, query = transformTopLevelStmt(pstate, parseTree); + if (compute_query_id) + jstate = JumbleQuery(query, sourceText); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); @@ -140,6 +146,7 @@ parse_analyze_varparams(RawStmt *parseTree, const char *sourceText, { ParseState *pstate = make_parsestate(NULL); Query *query; + JumbleState *jstate = NULL; Assert(sourceText != NULL); /* required as of 8.4 */ @@ -152,8 +159,11 @@ parse_analyze_varparams(RawStmt *parseTree, const char *sourceText, /* make sure all is well with parameter types */ check_variable_parameters(pstate, query); + if (compute_query_id) + jstate = JumbleQuery(query, sourceText); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index 2b1b68109f..7e034b72b1 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -665,6 +665,7 @@ pg_analyze_and_rewrite_params(RawStmt *parsetree, ParseState *pstate; Query *query; List *querytree_list; + JumbleState *jstate = NULL; Assert(query_string != NULL); /* required as of 8.4 */ @@ -683,8 +684,11 @@ pg_analyze_and_rewrite_params(RawStmt *parsetree, query = transformTopLevelStmt(pstate, parsetree); + if (compute_query_id) + jstate = JumbleQuery(query, query_string); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); diff --git a/src/backend/utils/misc/Makefile b/src/backend/utils/misc/Makefile index 2397fc2453..1d5327cf64 100644 --- a/src/backend/utils/misc/Makefile +++ b/src/backend/utils/misc/Makefile @@ -22,6 +22,7 @@ OBJS = \ pg_rusage.o \ ps_status.o \ queryenvironment.o \ + queryjumble.o \ rls.o \ sampling.o \ superuser.o \ diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index 2964efda96..72a8f6d9ff 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -521,6 +521,7 @@ extern const struct config_enum_entry dynamic_shared_memory_options[]; /* * GUC option variables that are exported from this module */ +bool compute_query_id = false; bool log_duration = false; bool Debug_print_plan = false; bool Debug_print_parse = false; @@ -1435,6 +1436,15 @@ static struct config_bool ConfigureNamesBool[] = true, NULL, NULL, NULL }, + { + {"compute_query_id", PGC_SUSET, STATS_MONITORING, + gettext_noop("Compute query identifiers."), + NULL + }, + &compute_query_id, + false, + NULL, NULL, NULL + }, { {"log_parser_stats", PGC_SUSET, STATS_MONITORING, gettext_noop("Writes parser performance statistics to the server log."), diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 86425965d0..01493ed3d4 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -595,6 +595,7 @@ # - Monitoring - +#compute_query_id = off #log_parser_stats = off #log_planner_stats = off #log_executor_stats = off diff --git a/src/backend/utils/misc/queryjumble.c b/src/backend/utils/misc/queryjumble.c new file mode 100644 index 0000000000..ae84fcac6e --- /dev/null +++ b/src/backend/utils/misc/queryjumble.c @@ -0,0 +1,834 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.c + * Query normalization and fingerprinting. + * + * Normalization is a process whereby similar queries, typically differing only + * in their constants (though the exact rules are somewhat more subtle than + * that) are recognized as equivalent, and are tracked as a single entry. This + * is particularly useful for non-prepared queries. + * + * Normalization is implemented by fingerprinting queries, selectively + * serializing those fields of each query tree's nodes that are judged to be + * essential to the query. This is referred to as a query jumble. This is + * distinct from a regular serialization in that various extraneous + * information is ignored as irrelevant or not essential to the query, such + * as the collations of Vars and, most notably, the values of constants. + * + * This jumble is acquired at the end of parse analysis of each query, and + * a 64-bit hash of it is stored into the query's Query.queryId field. + * The server then copies this value around, making it available in plan + * tree(s) generated from the query. The executor can then use this value + * to blame query costs on the proper queryId. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/misc/queryjumble.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "common/hashfn.h" +#include "miscadmin.h" +#include "parser/scansup.h" +#include "utils/queryjumble.h" + +#define JUMBLE_SIZE 1024 /* query serialization buffer size */ + +static uint64 compute_utility_queryid(const char *str, int query_len); +static void AppendJumble(JumbleState *jstate, + const unsigned char *item, Size size); +static void JumbleQueryInternal(JumbleState *jstate, Query *query); +static void JumbleRangeTable(JumbleState *jstate, List *rtable); +static void JumbleRowMarks(JumbleState *jstate, List *rowMarks); +static void JumbleExpr(JumbleState *jstate, Node *node); +static void RecordConstLocation(JumbleState *jstate, int location); + +/* + * Given a possibly multi-statement source string, confine our attention to the + * relevant part of the string. + */ +const char * +clean_querytext(const char *query, int *location, int *len) +{ + int query_location = *location; + int query_len = *len; + + /* First apply starting offset, unless it's -1 (unknown). */ + if (query_location >= 0) + { + Assert(query_location <= strlen(query)); + query += query_location; + /* Length of 0 (or -1) means "rest of string" */ + if (query_len <= 0) + query_len = strlen(query); + else + Assert(query_len <= strlen(query)); + } + else + { + /* If query location is unknown, distrust query_len as well */ + query_location = 0; + query_len = strlen(query); + } + + /* + * Discard leading and trailing whitespace, too. Use scanner_isspace() + * not libc's isspace(), because we want to match the lexer's behavior. + */ + while (query_len > 0 && scanner_isspace(query[0])) + query++, query_location++, query_len--; + while (query_len > 0 && scanner_isspace(query[query_len - 1])) + query_len--; + + *location = query_location; + *len = query_len; + + return query; +} + +JumbleState * +JumbleQuery(Query *query, const char *querytext) +{ + JumbleState *jstate = NULL; + if (query->utilityStmt) + { + const char *sql; + int query_location = query->stmt_location; + int query_len = query->stmt_len; + + /* + * Confine our attention to the relevant part of the string, if the + * query is a portion of a multi-statement source string. + */ + sql = clean_querytext(querytext, &query_location, &query_len); + + query->queryId = compute_utility_queryid(sql, query_len); + } + else + { + jstate = (JumbleState *) palloc(sizeof(JumbleState)); + + /* Set up workspace for query jumbling */ + jstate->jumble = (unsigned char *) palloc(JUMBLE_SIZE); + jstate->jumble_len = 0; + jstate->clocations_buf_size = 32; + jstate->clocations = (LocationLen *) + palloc(jstate->clocations_buf_size * sizeof(LocationLen)); + jstate->clocations_count = 0; + jstate->highest_extern_param_id = 0; + + /* Compute query ID and mark the Query node with it */ + JumbleQueryInternal(jstate, query); + query->queryId = DatumGetUInt64(hash_any_extended(jstate->jumble, + jstate->jumble_len, + 0)); + + /* + * If we are unlucky enough to get a hash of zero, use 1 instead, to + * prevent confusion with the utility-statement case. + */ + if (query->queryId == UINT64CONST(0)) + query->queryId = UINT64CONST(1); + } + + return jstate; +} + +/* + * Compute a query identifier for the given utility query string. + */ +static uint64 +compute_utility_queryid(const char *str, int query_len) +{ + uint64 queryId; + + queryId = DatumGetUInt64(hash_any_extended((const unsigned char *) str, + query_len, 0)); + + /* + * If we are unlucky enough to get a hash of zero(invalid), use + * queryID as 2 instead, queryID 1 is already in use for normal + * statements. + */ + if (queryId == UINT64CONST(0)) + queryId = UINT64CONST(2); + + return queryId; +} + +/* + * AppendJumble: Append a value that is substantive in a given query to + * the current jumble. + */ +static void +AppendJumble(JumbleState *jstate, const unsigned char *item, Size size) +{ + unsigned char *jumble = jstate->jumble; + Size jumble_len = jstate->jumble_len; + + /* + * Whenever the jumble buffer is full, we hash the current contents and + * reset the buffer to contain just that hash value, thus relying on the + * hash to summarize everything so far. + */ + while (size > 0) + { + Size part_size; + + if (jumble_len >= JUMBLE_SIZE) + { + uint64 start_hash; + + start_hash = DatumGetUInt64(hash_any_extended(jumble, + JUMBLE_SIZE, 0)); + memcpy(jumble, &start_hash, sizeof(start_hash)); + jumble_len = sizeof(start_hash); + } + part_size = Min(size, JUMBLE_SIZE - jumble_len); + memcpy(jumble + jumble_len, item, part_size); + jumble_len += part_size; + item += part_size; + size -= part_size; + } + jstate->jumble_len = jumble_len; +} + +/* + * Wrappers around AppendJumble to encapsulate details of serialization + * of individual local variable elements. + */ +#define APP_JUMB(item) \ + AppendJumble(jstate, (const unsigned char *) &(item), sizeof(item)) +#define APP_JUMB_STRING(str) \ + AppendJumble(jstate, (const unsigned char *) (str), strlen(str) + 1) + +/* + * JumbleQueryInternal: Selectively serialize the query tree, appending + * significant data to the "query jumble" while ignoring nonsignificant data. + * + * Rule of thumb for what to include is that we should ignore anything not + * semantically significant (such as alias names) as well as anything that can + * be deduced from child nodes (else we'd just be double-hashing that piece + * of information). + */ +static void +JumbleQueryInternal(JumbleState *jstate, Query *query) +{ + Assert(IsA(query, Query)); + Assert(query->utilityStmt == NULL); + + APP_JUMB(query->commandType); + /* resultRelation is usually predictable from commandType */ + JumbleExpr(jstate, (Node *) query->cteList); + JumbleRangeTable(jstate, query->rtable); + JumbleExpr(jstate, (Node *) query->jointree); + JumbleExpr(jstate, (Node *) query->targetList); + JumbleExpr(jstate, (Node *) query->onConflict); + JumbleExpr(jstate, (Node *) query->returningList); + JumbleExpr(jstate, (Node *) query->groupClause); + JumbleExpr(jstate, (Node *) query->groupingSets); + JumbleExpr(jstate, query->havingQual); + JumbleExpr(jstate, (Node *) query->windowClause); + JumbleExpr(jstate, (Node *) query->distinctClause); + JumbleExpr(jstate, (Node *) query->sortClause); + JumbleExpr(jstate, query->limitOffset); + JumbleExpr(jstate, query->limitCount); + JumbleRowMarks(jstate, query->rowMarks); + JumbleExpr(jstate, query->setOperations); +} + +/* + * Jumble a range table + */ +static void +JumbleRangeTable(JumbleState *jstate, List *rtable) +{ + ListCell *lc; + + foreach(lc, rtable) + { + RangeTblEntry *rte = lfirst_node(RangeTblEntry, lc); + + APP_JUMB(rte->rtekind); + switch (rte->rtekind) + { + case RTE_RELATION: + APP_JUMB(rte->relid); + JumbleExpr(jstate, (Node *) rte->tablesample); + break; + case RTE_SUBQUERY: + JumbleQueryInternal(jstate, rte->subquery); + break; + case RTE_JOIN: + APP_JUMB(rte->jointype); + break; + case RTE_FUNCTION: + JumbleExpr(jstate, (Node *) rte->functions); + break; + case RTE_TABLEFUNC: + JumbleExpr(jstate, (Node *) rte->tablefunc); + break; + case RTE_VALUES: + JumbleExpr(jstate, (Node *) rte->values_lists); + break; + case RTE_CTE: + + /* + * Depending on the CTE name here isn't ideal, but it's the + * only info we have to identify the referenced WITH item. + */ + APP_JUMB_STRING(rte->ctename); + APP_JUMB(rte->ctelevelsup); + break; + case RTE_NAMEDTUPLESTORE: + APP_JUMB_STRING(rte->enrname); + break; + case RTE_RESULT: + break; + default: + elog(ERROR, "unrecognized RTE kind: %d", (int) rte->rtekind); + break; + } + } +} + +/* + * Jumble a rowMarks list + */ +static void +JumbleRowMarks(JumbleState *jstate, List *rowMarks) +{ + ListCell *lc; + + foreach(lc, rowMarks) + { + RowMarkClause *rowmark = lfirst_node(RowMarkClause, lc); + + if (!rowmark->pushedDown) + { + APP_JUMB(rowmark->rti); + APP_JUMB(rowmark->strength); + APP_JUMB(rowmark->waitPolicy); + } + } +} + +/* + * Jumble an expression tree + * + * In general this function should handle all the same node types that + * expression_tree_walker() does, and therefore it's coded to be as parallel + * to that function as possible. However, since we are only invoked on + * queries immediately post-parse-analysis, we need not handle node types + * that only appear in planning. + * + * Note: the reason we don't simply use expression_tree_walker() is that the + * point of that function is to support tree walkers that don't care about + * most tree node types, but here we care about all types. We should complain + * about any unrecognized node type. + */ +static void +JumbleExpr(JumbleState *jstate, Node *node) +{ + ListCell *temp; + + if (node == NULL) + return; + + /* Guard against stack overflow due to overly complex expressions */ + check_stack_depth(); + + /* + * We always emit the node's NodeTag, then any additional fields that are + * considered significant, and then we recurse to any child nodes. + */ + APP_JUMB(node->type); + + switch (nodeTag(node)) + { + case T_Var: + { + Var *var = (Var *) node; + + APP_JUMB(var->varno); + APP_JUMB(var->varattno); + APP_JUMB(var->varlevelsup); + } + break; + case T_Const: + { + Const *c = (Const *) node; + + /* We jumble only the constant's type, not its value */ + APP_JUMB(c->consttype); + /* Also, record its parse location for query normalization */ + RecordConstLocation(jstate, c->location); + } + break; + case T_Param: + { + Param *p = (Param *) node; + + APP_JUMB(p->paramkind); + APP_JUMB(p->paramid); + APP_JUMB(p->paramtype); + /* Also, track the highest external Param id */ + if (p->paramkind == PARAM_EXTERN && + p->paramid > jstate->highest_extern_param_id) + jstate->highest_extern_param_id = p->paramid; + } + break; + case T_Aggref: + { + Aggref *expr = (Aggref *) node; + + APP_JUMB(expr->aggfnoid); + JumbleExpr(jstate, (Node *) expr->aggdirectargs); + JumbleExpr(jstate, (Node *) expr->args); + JumbleExpr(jstate, (Node *) expr->aggorder); + JumbleExpr(jstate, (Node *) expr->aggdistinct); + JumbleExpr(jstate, (Node *) expr->aggfilter); + } + break; + case T_GroupingFunc: + { + GroupingFunc *grpnode = (GroupingFunc *) node; + + JumbleExpr(jstate, (Node *) grpnode->refs); + } + break; + case T_WindowFunc: + { + WindowFunc *expr = (WindowFunc *) node; + + APP_JUMB(expr->winfnoid); + APP_JUMB(expr->winref); + JumbleExpr(jstate, (Node *) expr->args); + JumbleExpr(jstate, (Node *) expr->aggfilter); + } + break; + case T_SubscriptingRef: + { + SubscriptingRef *sbsref = (SubscriptingRef *) node; + + JumbleExpr(jstate, (Node *) sbsref->refupperindexpr); + JumbleExpr(jstate, (Node *) sbsref->reflowerindexpr); + JumbleExpr(jstate, (Node *) sbsref->refexpr); + JumbleExpr(jstate, (Node *) sbsref->refassgnexpr); + } + break; + case T_FuncExpr: + { + FuncExpr *expr = (FuncExpr *) node; + + APP_JUMB(expr->funcid); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_NamedArgExpr: + { + NamedArgExpr *nae = (NamedArgExpr *) node; + + APP_JUMB(nae->argnumber); + JumbleExpr(jstate, (Node *) nae->arg); + } + break; + case T_OpExpr: + case T_DistinctExpr: /* struct-equivalent to OpExpr */ + case T_NullIfExpr: /* struct-equivalent to OpExpr */ + { + OpExpr *expr = (OpExpr *) node; + + APP_JUMB(expr->opno); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_ScalarArrayOpExpr: + { + ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node; + + APP_JUMB(expr->opno); + APP_JUMB(expr->useOr); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_BoolExpr: + { + BoolExpr *expr = (BoolExpr *) node; + + APP_JUMB(expr->boolop); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_SubLink: + { + SubLink *sublink = (SubLink *) node; + + APP_JUMB(sublink->subLinkType); + APP_JUMB(sublink->subLinkId); + JumbleExpr(jstate, (Node *) sublink->testexpr); + JumbleQueryInternal(jstate, castNode(Query, sublink->subselect)); + } + break; + case T_FieldSelect: + { + FieldSelect *fs = (FieldSelect *) node; + + APP_JUMB(fs->fieldnum); + JumbleExpr(jstate, (Node *) fs->arg); + } + break; + case T_FieldStore: + { + FieldStore *fstore = (FieldStore *) node; + + JumbleExpr(jstate, (Node *) fstore->arg); + JumbleExpr(jstate, (Node *) fstore->newvals); + } + break; + case T_RelabelType: + { + RelabelType *rt = (RelabelType *) node; + + APP_JUMB(rt->resulttype); + JumbleExpr(jstate, (Node *) rt->arg); + } + break; + case T_CoerceViaIO: + { + CoerceViaIO *cio = (CoerceViaIO *) node; + + APP_JUMB(cio->resulttype); + JumbleExpr(jstate, (Node *) cio->arg); + } + break; + case T_ArrayCoerceExpr: + { + ArrayCoerceExpr *acexpr = (ArrayCoerceExpr *) node; + + APP_JUMB(acexpr->resulttype); + JumbleExpr(jstate, (Node *) acexpr->arg); + JumbleExpr(jstate, (Node *) acexpr->elemexpr); + } + break; + case T_ConvertRowtypeExpr: + { + ConvertRowtypeExpr *crexpr = (ConvertRowtypeExpr *) node; + + APP_JUMB(crexpr->resulttype); + JumbleExpr(jstate, (Node *) crexpr->arg); + } + break; + case T_CollateExpr: + { + CollateExpr *ce = (CollateExpr *) node; + + APP_JUMB(ce->collOid); + JumbleExpr(jstate, (Node *) ce->arg); + } + break; + case T_CaseExpr: + { + CaseExpr *caseexpr = (CaseExpr *) node; + + JumbleExpr(jstate, (Node *) caseexpr->arg); + foreach(temp, caseexpr->args) + { + CaseWhen *when = lfirst_node(CaseWhen, temp); + + JumbleExpr(jstate, (Node *) when->expr); + JumbleExpr(jstate, (Node *) when->result); + } + JumbleExpr(jstate, (Node *) caseexpr->defresult); + } + break; + case T_CaseTestExpr: + { + CaseTestExpr *ct = (CaseTestExpr *) node; + + APP_JUMB(ct->typeId); + } + break; + case T_ArrayExpr: + JumbleExpr(jstate, (Node *) ((ArrayExpr *) node)->elements); + break; + case T_RowExpr: + JumbleExpr(jstate, (Node *) ((RowExpr *) node)->args); + break; + case T_RowCompareExpr: + { + RowCompareExpr *rcexpr = (RowCompareExpr *) node; + + APP_JUMB(rcexpr->rctype); + JumbleExpr(jstate, (Node *) rcexpr->largs); + JumbleExpr(jstate, (Node *) rcexpr->rargs); + } + break; + case T_CoalesceExpr: + JumbleExpr(jstate, (Node *) ((CoalesceExpr *) node)->args); + break; + case T_MinMaxExpr: + { + MinMaxExpr *mmexpr = (MinMaxExpr *) node; + + APP_JUMB(mmexpr->op); + JumbleExpr(jstate, (Node *) mmexpr->args); + } + break; + case T_SQLValueFunction: + { + SQLValueFunction *svf = (SQLValueFunction *) node; + + APP_JUMB(svf->op); + /* type is fully determined by op */ + APP_JUMB(svf->typmod); + } + break; + case T_XmlExpr: + { + XmlExpr *xexpr = (XmlExpr *) node; + + APP_JUMB(xexpr->op); + JumbleExpr(jstate, (Node *) xexpr->named_args); + JumbleExpr(jstate, (Node *) xexpr->args); + } + break; + case T_NullTest: + { + NullTest *nt = (NullTest *) node; + + APP_JUMB(nt->nulltesttype); + JumbleExpr(jstate, (Node *) nt->arg); + } + break; + case T_BooleanTest: + { + BooleanTest *bt = (BooleanTest *) node; + + APP_JUMB(bt->booltesttype); + JumbleExpr(jstate, (Node *) bt->arg); + } + break; + case T_CoerceToDomain: + { + CoerceToDomain *cd = (CoerceToDomain *) node; + + APP_JUMB(cd->resulttype); + JumbleExpr(jstate, (Node *) cd->arg); + } + break; + case T_CoerceToDomainValue: + { + CoerceToDomainValue *cdv = (CoerceToDomainValue *) node; + + APP_JUMB(cdv->typeId); + } + break; + case T_SetToDefault: + { + SetToDefault *sd = (SetToDefault *) node; + + APP_JUMB(sd->typeId); + } + break; + case T_CurrentOfExpr: + { + CurrentOfExpr *ce = (CurrentOfExpr *) node; + + APP_JUMB(ce->cvarno); + if (ce->cursor_name) + APP_JUMB_STRING(ce->cursor_name); + APP_JUMB(ce->cursor_param); + } + break; + case T_NextValueExpr: + { + NextValueExpr *nve = (NextValueExpr *) node; + + APP_JUMB(nve->seqid); + APP_JUMB(nve->typeId); + } + break; + case T_InferenceElem: + { + InferenceElem *ie = (InferenceElem *) node; + + APP_JUMB(ie->infercollid); + APP_JUMB(ie->inferopclass); + JumbleExpr(jstate, ie->expr); + } + break; + case T_TargetEntry: + { + TargetEntry *tle = (TargetEntry *) node; + + APP_JUMB(tle->resno); + APP_JUMB(tle->ressortgroupref); + JumbleExpr(jstate, (Node *) tle->expr); + } + break; + case T_RangeTblRef: + { + RangeTblRef *rtr = (RangeTblRef *) node; + + APP_JUMB(rtr->rtindex); + } + break; + case T_JoinExpr: + { + JoinExpr *join = (JoinExpr *) node; + + APP_JUMB(join->jointype); + APP_JUMB(join->isNatural); + APP_JUMB(join->rtindex); + JumbleExpr(jstate, join->larg); + JumbleExpr(jstate, join->rarg); + JumbleExpr(jstate, join->quals); + } + break; + case T_FromExpr: + { + FromExpr *from = (FromExpr *) node; + + JumbleExpr(jstate, (Node *) from->fromlist); + JumbleExpr(jstate, from->quals); + } + break; + case T_OnConflictExpr: + { + OnConflictExpr *conf = (OnConflictExpr *) node; + + APP_JUMB(conf->action); + JumbleExpr(jstate, (Node *) conf->arbiterElems); + JumbleExpr(jstate, conf->arbiterWhere); + JumbleExpr(jstate, (Node *) conf->onConflictSet); + JumbleExpr(jstate, conf->onConflictWhere); + APP_JUMB(conf->constraint); + APP_JUMB(conf->exclRelIndex); + JumbleExpr(jstate, (Node *) conf->exclRelTlist); + } + break; + case T_List: + foreach(temp, (List *) node) + { + JumbleExpr(jstate, (Node *) lfirst(temp)); + } + break; + case T_IntList: + foreach(temp, (List *) node) + { + APP_JUMB(lfirst_int(temp)); + } + break; + case T_SortGroupClause: + { + SortGroupClause *sgc = (SortGroupClause *) node; + + APP_JUMB(sgc->tleSortGroupRef); + APP_JUMB(sgc->eqop); + APP_JUMB(sgc->sortop); + APP_JUMB(sgc->nulls_first); + } + break; + case T_GroupingSet: + { + GroupingSet *gsnode = (GroupingSet *) node; + + JumbleExpr(jstate, (Node *) gsnode->content); + } + break; + case T_WindowClause: + { + WindowClause *wc = (WindowClause *) node; + + APP_JUMB(wc->winref); + APP_JUMB(wc->frameOptions); + JumbleExpr(jstate, (Node *) wc->partitionClause); + JumbleExpr(jstate, (Node *) wc->orderClause); + JumbleExpr(jstate, wc->startOffset); + JumbleExpr(jstate, wc->endOffset); + } + break; + case T_CommonTableExpr: + { + CommonTableExpr *cte = (CommonTableExpr *) node; + + /* we store the string name because RTE_CTE RTEs need it */ + APP_JUMB_STRING(cte->ctename); + APP_JUMB(cte->ctematerialized); + JumbleQueryInternal(jstate, castNode(Query, cte->ctequery)); + } + break; + case T_SetOperationStmt: + { + SetOperationStmt *setop = (SetOperationStmt *) node; + + APP_JUMB(setop->op); + APP_JUMB(setop->all); + JumbleExpr(jstate, setop->larg); + JumbleExpr(jstate, setop->rarg); + } + break; + case T_RangeTblFunction: + { + RangeTblFunction *rtfunc = (RangeTblFunction *) node; + + JumbleExpr(jstate, rtfunc->funcexpr); + } + break; + case T_TableFunc: + { + TableFunc *tablefunc = (TableFunc *) node; + + JumbleExpr(jstate, tablefunc->docexpr); + JumbleExpr(jstate, tablefunc->rowexpr); + JumbleExpr(jstate, (Node *) tablefunc->colexprs); + } + break; + case T_TableSampleClause: + { + TableSampleClause *tsc = (TableSampleClause *) node; + + APP_JUMB(tsc->tsmhandler); + JumbleExpr(jstate, (Node *) tsc->args); + JumbleExpr(jstate, (Node *) tsc->repeatable); + } + break; + default: + /* Only a warning, since we can stumble along anyway */ + elog(WARNING, "unrecognized node type: %d", + (int) nodeTag(node)); + break; + } +} + +/* + * Record location of constant within query string of query tree + * that is currently being walked. + */ +static void +RecordConstLocation(JumbleState *jstate, int location) +{ + /* -1 indicates unknown or undefined location */ + if (location >= 0) + { + /* enlarge array if needed */ + if (jstate->clocations_count >= jstate->clocations_buf_size) + { + jstate->clocations_buf_size *= 2; + jstate->clocations = (LocationLen *) + repalloc(jstate->clocations, + jstate->clocations_buf_size * + sizeof(LocationLen)); + } + jstate->clocations[jstate->clocations_count].location = location; + /* initialize lengths to -1 to simplify third-party module usage */ + jstate->clocations[jstate->clocations_count].length = -1; + jstate->clocations_count++; + } +} diff --git a/src/include/parser/analyze.h b/src/include/parser/analyze.h index 4a3c9686f9..6716db6c13 100644 --- a/src/include/parser/analyze.h +++ b/src/include/parser/analyze.h @@ -15,10 +15,12 @@ #define ANALYZE_H #include "parser/parse_node.h" +#include "utils/queryjumble.h" /* Hook for plugins to get control at end of parse analysis */ typedef void (*post_parse_analyze_hook_type) (ParseState *pstate, - Query *query); + Query *query, + JumbleState *jstate); extern PGDLLIMPORT post_parse_analyze_hook_type post_parse_analyze_hook; diff --git a/src/include/utils/guc.h b/src/include/utils/guc.h index 5004ee4177..9b6552b25b 100644 --- a/src/include/utils/guc.h +++ b/src/include/utils/guc.h @@ -248,6 +248,7 @@ extern bool log_btree_build_stats; extern PGDLLIMPORT bool check_function_bodies; extern bool session_auth_is_superuser; +extern bool compute_query_id; extern bool log_duration; extern int log_parameter_max_length; extern int log_parameter_max_length_on_error; diff --git a/src/include/utils/queryjumble.h b/src/include/utils/queryjumble.h new file mode 100644 index 0000000000..14087eea43 --- /dev/null +++ b/src/include/utils/queryjumble.h @@ -0,0 +1,58 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.h + * Query normalization and fingerprinting. + * + * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/include/utils/queryjumble.h + * + *------------------------------------------------------------------------- + */ +#ifndef QUERYJUBLE_H +#define QUERYJUBLE_H + +#include "nodes/parsenodes.h" + +#define JUMBLE_SIZE 1024 /* query serialization buffer size */ + +/* + * Struct for tracking locations/lengths of constants during normalization + */ +typedef struct LocationLen +{ + int location; /* start offset in query text */ + int length; /* length in bytes, or -1 to ignore */ +} LocationLen; + +/* + * Working state for computing a query jumble and producing a normalized + * query string + */ +typedef struct JumbleState +{ + /* Jumble of current query tree */ + unsigned char *jumble; + + /* Number of bytes used in jumble[] */ + Size jumble_len; + + /* Array of locations of constants that should be removed */ + LocationLen *clocations; + + /* Allocated length of clocations array */ + int clocations_buf_size; + + /* Current number of valid entries in clocations array */ + int clocations_count; + + /* highest Param id we've seen, in order to start normalization correctly */ + int highest_extern_param_id; +} JumbleState; + +const char *clean_querytext(const char *query, int *location, int *len); +JumbleState *JumbleQuery(Query *query, const char *querytext); + +#endif /* QUERYJUMBLE_H */ -- 2.30.1 --73wevpdk5oenpgx2 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v19-0002-Expose-queryid-in-pg_stat_activity-and-log_line_.patch" ^ permalink raw reply [nested|flat] 4+ messages in thread
* [PATCH v23 1/3] Move pg_stat_statements query jumbling to core. @ 2021-03-22 21:43 Bruce Momjian <bruce@momjian.us> 0 siblings, 0 replies; 4+ messages in thread From: Bruce Momjian @ 2021-03-22 21:43 UTC (permalink / raw) A new compute_query_id GUC is also added, to control whether a query identifier should be computed by the core. It's thefore now possible to disable core queryid computation and use pg_stat_statements with a different algorithm to compute the query identifier by using third-party module. To ensure that a single source of query identifier can be used and is well defined, modules that calculate a query identifier should throw an error if compute_query_id is enabled or if a query idenfitier was already calculated. --- .../pg_stat_statements/pg_stat_statements.c | 805 +---------------- .../pg_stat_statements.conf | 1 + doc/src/sgml/config.sgml | 25 + doc/src/sgml/pgstatstatements.sgml | 20 +- src/backend/parser/analyze.c | 14 +- src/backend/tcop/postgres.c | 6 +- src/backend/utils/misc/Makefile | 1 + src/backend/utils/misc/guc.c | 10 + src/backend/utils/misc/postgresql.conf.sample | 1 + src/backend/utils/misc/queryjumble.c | 834 ++++++++++++++++++ src/include/parser/analyze.h | 4 +- src/include/utils/guc.h | 1 + src/include/utils/queryjumble.h | 58 ++ 13 files changed, 995 insertions(+), 785 deletions(-) create mode 100644 src/backend/utils/misc/queryjumble.c create mode 100644 src/include/utils/queryjumble.h diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c index 1141d2b067..0f8bac0cca 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.c +++ b/contrib/pg_stat_statements/pg_stat_statements.c @@ -8,24 +8,9 @@ * a shared hashtable. (We track only as many distinct queries as will fit * in the designated amount of shared memory.) * - * As of Postgres 9.2, this module normalizes query entries. Normalization - * is a process whereby similar queries, typically differing only in their - * constants (though the exact rules are somewhat more subtle than that) are - * recognized as equivalent, and are tracked as a single entry. This is - * particularly useful for non-prepared queries. - * - * Normalization is implemented by fingerprinting queries, selectively - * serializing those fields of each query tree's nodes that are judged to be - * essential to the query. This is referred to as a query jumble. This is - * distinct from a regular serialization in that various extraneous - * information is ignored as irrelevant or not essential to the query, such - * as the collations of Vars and, most notably, the values of constants. - * - * This jumble is acquired at the end of parse analysis of each query, and - * a 64-bit hash of it is stored into the query's Query.queryId field. - * The server then copies this value around, making it available in plan - * tree(s) generated from the query. The executor can then use this value - * to blame query costs on the proper queryId. + * Starting in Postgres 9.2, this module normalized query entries. As of + * Postgres 14, the normalization is done by the core if compute_query_id is + * enabled, or optionally by third-party modules. * * To facilitate presenting entries to users, we create "representative" query * strings in which constants are replaced with parameter symbols ($n), to @@ -116,8 +101,6 @@ static const uint32 PGSS_PG_MAJOR_VERSION = PG_VERSION_NUM / 100; #define USAGE_DEALLOC_PERCENT 5 /* free this % of entries at once */ #define IS_STICKY(c) ((c.calls[PGSS_PLAN] + c.calls[PGSS_EXEC]) == 0) -#define JUMBLE_SIZE 1024 /* query serialization buffer size */ - /* * Extension version number, for supporting older extension versions' objects */ @@ -237,40 +220,6 @@ typedef struct pgssSharedState pgssGlobalStats stats; /* global statistics for pgss */ } pgssSharedState; -/* - * Struct for tracking locations/lengths of constants during normalization - */ -typedef struct pgssLocationLen -{ - int location; /* start offset in query text */ - int length; /* length in bytes, or -1 to ignore */ -} pgssLocationLen; - -/* - * Working state for computing a query jumble and producing a normalized - * query string - */ -typedef struct pgssJumbleState -{ - /* Jumble of current query tree */ - unsigned char *jumble; - - /* Number of bytes used in jumble[] */ - Size jumble_len; - - /* Array of locations of constants that should be removed */ - pgssLocationLen *clocations; - - /* Allocated length of clocations array */ - int clocations_buf_size; - - /* Current number of valid entries in clocations array */ - int clocations_count; - - /* highest Param id we've seen, in order to start normalization correctly */ - int highest_extern_param_id; -} pgssJumbleState; - /*---- Local variables ----*/ /* Current nesting depth of ExecutorRun+ProcessUtility calls */ @@ -344,7 +293,8 @@ PG_FUNCTION_INFO_V1(pg_stat_statements_info); static void pgss_shmem_startup(void); static void pgss_shmem_shutdown(int code, Datum arg); -static void pgss_post_parse_analyze(ParseState *pstate, Query *query); +static void pgss_post_parse_analyze(ParseState *pstate, Query *query, + JumbleState *jstate); static PlannedStmt *pgss_planner(Query *parse, const char *query_string, int cursorOptions, @@ -366,7 +316,7 @@ static void pgss_store(const char *query, uint64 queryId, double total_time, uint64 rows, const BufferUsage *bufusage, const WalUsage *walusage, - pgssJumbleState *jstate); + JumbleState *jstate); static void pg_stat_statements_internal(FunctionCallInfo fcinfo, pgssVersion api_version, bool showtext); @@ -382,16 +332,9 @@ static char *qtext_fetch(Size query_offset, int query_len, static bool need_gc_qtexts(void); static void gc_qtexts(void); static void entry_reset(Oid userid, Oid dbid, uint64 queryid); -static void AppendJumble(pgssJumbleState *jstate, - const unsigned char *item, Size size); -static void JumbleQuery(pgssJumbleState *jstate, Query *query); -static void JumbleRangeTable(pgssJumbleState *jstate, List *rtable); -static void JumbleRowMarks(pgssJumbleState *jstate, List *rowMarks); -static void JumbleExpr(pgssJumbleState *jstate, Node *node); -static void RecordConstLocation(pgssJumbleState *jstate, int location); -static char *generate_normalized_query(pgssJumbleState *jstate, const char *query, +static char *generate_normalized_query(JumbleState *jstate, const char *query, int query_loc, int *query_len_p); -static void fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, +static void fill_in_constant_lengths(JumbleState *jstate, const char *query, int query_loc); static int comp_location(const void *a, const void *b); @@ -853,15 +796,10 @@ error: * Post-parse-analysis hook: mark query with a queryId */ static void -pgss_post_parse_analyze(ParseState *pstate, Query *query) +pgss_post_parse_analyze(ParseState *pstate, Query *query, JumbleState *jstate) { - pgssJumbleState jstate; - if (prev_post_parse_analyze_hook) - prev_post_parse_analyze_hook(pstate, query); - - /* Assert we didn't do this already */ - Assert(query->queryId == UINT64CONST(0)); + prev_post_parse_analyze_hook(pstate, query, jstate); /* Safety check... */ if (!pgss || !pgss_hash || !pgss_enabled(exec_nested_level)) @@ -881,35 +819,14 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query) return; } - /* Set up workspace for query jumbling */ - jstate.jumble = (unsigned char *) palloc(JUMBLE_SIZE); - jstate.jumble_len = 0; - jstate.clocations_buf_size = 32; - jstate.clocations = (pgssLocationLen *) - palloc(jstate.clocations_buf_size * sizeof(pgssLocationLen)); - jstate.clocations_count = 0; - jstate.highest_extern_param_id = 0; - - /* Compute query ID and mark the Query node with it */ - JumbleQuery(&jstate, query); - query->queryId = - DatumGetUInt64(hash_any_extended(jstate.jumble, jstate.jumble_len, 0)); - /* - * If we are unlucky enough to get a hash of zero, use 1 instead, to - * prevent confusion with the utility-statement case. + * If query jumbling were able to identify any ignorable constants, we + * immediately create a hash table entry for the query, so that we can + * record the normalized form of the query string. If there were no such + * constants, the normalized string would be the same as the query text + * anyway, so there's no need for an early entry. */ - if (query->queryId == UINT64CONST(0)) - query->queryId = UINT64CONST(1); - - /* - * If we were able to identify any ignorable constants, we immediately - * create a hash table entry for the query, so that we can record the - * normalized form of the query string. If there were no such constants, - * the normalized string would be the same as the query text anyway, so - * there's no need for an early entry. - */ - if (jstate.clocations_count > 0) + if (jstate && jstate->clocations_count > 0) pgss_store(pstate->p_sourcetext, query->queryId, query->stmt_location, @@ -919,7 +836,7 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query) 0, NULL, NULL, - &jstate); + jstate); } /* @@ -1269,7 +1186,7 @@ pgss_store(const char *query, uint64 queryId, double total_time, uint64 rows, const BufferUsage *bufusage, const WalUsage *walusage, - pgssJumbleState *jstate) + JumbleState *jstate) { pgssHashKey key; pgssEntry *entry; @@ -2629,678 +2546,6 @@ release_lock: LWLockRelease(pgss->lock); } -/* - * AppendJumble: Append a value that is substantive in a given query to - * the current jumble. - */ -static void -AppendJumble(pgssJumbleState *jstate, const unsigned char *item, Size size) -{ - unsigned char *jumble = jstate->jumble; - Size jumble_len = jstate->jumble_len; - - /* - * Whenever the jumble buffer is full, we hash the current contents and - * reset the buffer to contain just that hash value, thus relying on the - * hash to summarize everything so far. - */ - while (size > 0) - { - Size part_size; - - if (jumble_len >= JUMBLE_SIZE) - { - uint64 start_hash; - - start_hash = DatumGetUInt64(hash_any_extended(jumble, - JUMBLE_SIZE, 0)); - memcpy(jumble, &start_hash, sizeof(start_hash)); - jumble_len = sizeof(start_hash); - } - part_size = Min(size, JUMBLE_SIZE - jumble_len); - memcpy(jumble + jumble_len, item, part_size); - jumble_len += part_size; - item += part_size; - size -= part_size; - } - jstate->jumble_len = jumble_len; -} - -/* - * Wrappers around AppendJumble to encapsulate details of serialization - * of individual local variable elements. - */ -#define APP_JUMB(item) \ - AppendJumble(jstate, (const unsigned char *) &(item), sizeof(item)) -#define APP_JUMB_STRING(str) \ - AppendJumble(jstate, (const unsigned char *) (str), strlen(str) + 1) - -/* - * JumbleQuery: Selectively serialize the query tree, appending significant - * data to the "query jumble" while ignoring nonsignificant data. - * - * Rule of thumb for what to include is that we should ignore anything not - * semantically significant (such as alias names) as well as anything that can - * be deduced from child nodes (else we'd just be double-hashing that piece - * of information). - */ -static void -JumbleQuery(pgssJumbleState *jstate, Query *query) -{ - Assert(IsA(query, Query)); - Assert(query->utilityStmt == NULL); - - APP_JUMB(query->commandType); - /* resultRelation is usually predictable from commandType */ - JumbleExpr(jstate, (Node *) query->cteList); - JumbleRangeTable(jstate, query->rtable); - JumbleExpr(jstate, (Node *) query->jointree); - JumbleExpr(jstate, (Node *) query->targetList); - JumbleExpr(jstate, (Node *) query->onConflict); - JumbleExpr(jstate, (Node *) query->returningList); - JumbleExpr(jstate, (Node *) query->groupClause); - JumbleExpr(jstate, (Node *) query->groupingSets); - JumbleExpr(jstate, query->havingQual); - JumbleExpr(jstate, (Node *) query->windowClause); - JumbleExpr(jstate, (Node *) query->distinctClause); - JumbleExpr(jstate, (Node *) query->sortClause); - JumbleExpr(jstate, query->limitOffset); - JumbleExpr(jstate, query->limitCount); - JumbleRowMarks(jstate, query->rowMarks); - JumbleExpr(jstate, query->setOperations); -} - -/* - * Jumble a range table - */ -static void -JumbleRangeTable(pgssJumbleState *jstate, List *rtable) -{ - ListCell *lc; - - foreach(lc, rtable) - { - RangeTblEntry *rte = lfirst_node(RangeTblEntry, lc); - - APP_JUMB(rte->rtekind); - switch (rte->rtekind) - { - case RTE_RELATION: - APP_JUMB(rte->relid); - JumbleExpr(jstate, (Node *) rte->tablesample); - break; - case RTE_SUBQUERY: - JumbleQuery(jstate, rte->subquery); - break; - case RTE_JOIN: - APP_JUMB(rte->jointype); - break; - case RTE_FUNCTION: - JumbleExpr(jstate, (Node *) rte->functions); - break; - case RTE_TABLEFUNC: - JumbleExpr(jstate, (Node *) rte->tablefunc); - break; - case RTE_VALUES: - JumbleExpr(jstate, (Node *) rte->values_lists); - break; - case RTE_CTE: - - /* - * Depending on the CTE name here isn't ideal, but it's the - * only info we have to identify the referenced WITH item. - */ - APP_JUMB_STRING(rte->ctename); - APP_JUMB(rte->ctelevelsup); - break; - case RTE_NAMEDTUPLESTORE: - APP_JUMB_STRING(rte->enrname); - break; - case RTE_RESULT: - break; - default: - elog(ERROR, "unrecognized RTE kind: %d", (int) rte->rtekind); - break; - } - } -} - -/* - * Jumble a rowMarks list - */ -static void -JumbleRowMarks(pgssJumbleState *jstate, List *rowMarks) -{ - ListCell *lc; - - foreach(lc, rowMarks) - { - RowMarkClause *rowmark = lfirst_node(RowMarkClause, lc); - - if (!rowmark->pushedDown) - { - APP_JUMB(rowmark->rti); - APP_JUMB(rowmark->strength); - APP_JUMB(rowmark->waitPolicy); - } - } -} - -/* - * Jumble an expression tree - * - * In general this function should handle all the same node types that - * expression_tree_walker() does, and therefore it's coded to be as parallel - * to that function as possible. However, since we are only invoked on - * queries immediately post-parse-analysis, we need not handle node types - * that only appear in planning. - * - * Note: the reason we don't simply use expression_tree_walker() is that the - * point of that function is to support tree walkers that don't care about - * most tree node types, but here we care about all types. We should complain - * about any unrecognized node type. - */ -static void -JumbleExpr(pgssJumbleState *jstate, Node *node) -{ - ListCell *temp; - - if (node == NULL) - return; - - /* Guard against stack overflow due to overly complex expressions */ - check_stack_depth(); - - /* - * We always emit the node's NodeTag, then any additional fields that are - * considered significant, and then we recurse to any child nodes. - */ - APP_JUMB(node->type); - - switch (nodeTag(node)) - { - case T_Var: - { - Var *var = (Var *) node; - - APP_JUMB(var->varno); - APP_JUMB(var->varattno); - APP_JUMB(var->varlevelsup); - } - break; - case T_Const: - { - Const *c = (Const *) node; - - /* We jumble only the constant's type, not its value */ - APP_JUMB(c->consttype); - /* Also, record its parse location for query normalization */ - RecordConstLocation(jstate, c->location); - } - break; - case T_Param: - { - Param *p = (Param *) node; - - APP_JUMB(p->paramkind); - APP_JUMB(p->paramid); - APP_JUMB(p->paramtype); - /* Also, track the highest external Param id */ - if (p->paramkind == PARAM_EXTERN && - p->paramid > jstate->highest_extern_param_id) - jstate->highest_extern_param_id = p->paramid; - } - break; - case T_Aggref: - { - Aggref *expr = (Aggref *) node; - - APP_JUMB(expr->aggfnoid); - JumbleExpr(jstate, (Node *) expr->aggdirectargs); - JumbleExpr(jstate, (Node *) expr->args); - JumbleExpr(jstate, (Node *) expr->aggorder); - JumbleExpr(jstate, (Node *) expr->aggdistinct); - JumbleExpr(jstate, (Node *) expr->aggfilter); - } - break; - case T_GroupingFunc: - { - GroupingFunc *grpnode = (GroupingFunc *) node; - - JumbleExpr(jstate, (Node *) grpnode->refs); - } - break; - case T_WindowFunc: - { - WindowFunc *expr = (WindowFunc *) node; - - APP_JUMB(expr->winfnoid); - APP_JUMB(expr->winref); - JumbleExpr(jstate, (Node *) expr->args); - JumbleExpr(jstate, (Node *) expr->aggfilter); - } - break; - case T_SubscriptingRef: - { - SubscriptingRef *sbsref = (SubscriptingRef *) node; - - JumbleExpr(jstate, (Node *) sbsref->refupperindexpr); - JumbleExpr(jstate, (Node *) sbsref->reflowerindexpr); - JumbleExpr(jstate, (Node *) sbsref->refexpr); - JumbleExpr(jstate, (Node *) sbsref->refassgnexpr); - } - break; - case T_FuncExpr: - { - FuncExpr *expr = (FuncExpr *) node; - - APP_JUMB(expr->funcid); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_NamedArgExpr: - { - NamedArgExpr *nae = (NamedArgExpr *) node; - - APP_JUMB(nae->argnumber); - JumbleExpr(jstate, (Node *) nae->arg); - } - break; - case T_OpExpr: - case T_DistinctExpr: /* struct-equivalent to OpExpr */ - case T_NullIfExpr: /* struct-equivalent to OpExpr */ - { - OpExpr *expr = (OpExpr *) node; - - APP_JUMB(expr->opno); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_ScalarArrayOpExpr: - { - ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node; - - APP_JUMB(expr->opno); - APP_JUMB(expr->useOr); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_BoolExpr: - { - BoolExpr *expr = (BoolExpr *) node; - - APP_JUMB(expr->boolop); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_SubLink: - { - SubLink *sublink = (SubLink *) node; - - APP_JUMB(sublink->subLinkType); - APP_JUMB(sublink->subLinkId); - JumbleExpr(jstate, (Node *) sublink->testexpr); - JumbleQuery(jstate, castNode(Query, sublink->subselect)); - } - break; - case T_FieldSelect: - { - FieldSelect *fs = (FieldSelect *) node; - - APP_JUMB(fs->fieldnum); - JumbleExpr(jstate, (Node *) fs->arg); - } - break; - case T_FieldStore: - { - FieldStore *fstore = (FieldStore *) node; - - JumbleExpr(jstate, (Node *) fstore->arg); - JumbleExpr(jstate, (Node *) fstore->newvals); - } - break; - case T_RelabelType: - { - RelabelType *rt = (RelabelType *) node; - - APP_JUMB(rt->resulttype); - JumbleExpr(jstate, (Node *) rt->arg); - } - break; - case T_CoerceViaIO: - { - CoerceViaIO *cio = (CoerceViaIO *) node; - - APP_JUMB(cio->resulttype); - JumbleExpr(jstate, (Node *) cio->arg); - } - break; - case T_ArrayCoerceExpr: - { - ArrayCoerceExpr *acexpr = (ArrayCoerceExpr *) node; - - APP_JUMB(acexpr->resulttype); - JumbleExpr(jstate, (Node *) acexpr->arg); - JumbleExpr(jstate, (Node *) acexpr->elemexpr); - } - break; - case T_ConvertRowtypeExpr: - { - ConvertRowtypeExpr *crexpr = (ConvertRowtypeExpr *) node; - - APP_JUMB(crexpr->resulttype); - JumbleExpr(jstate, (Node *) crexpr->arg); - } - break; - case T_CollateExpr: - { - CollateExpr *ce = (CollateExpr *) node; - - APP_JUMB(ce->collOid); - JumbleExpr(jstate, (Node *) ce->arg); - } - break; - case T_CaseExpr: - { - CaseExpr *caseexpr = (CaseExpr *) node; - - JumbleExpr(jstate, (Node *) caseexpr->arg); - foreach(temp, caseexpr->args) - { - CaseWhen *when = lfirst_node(CaseWhen, temp); - - JumbleExpr(jstate, (Node *) when->expr); - JumbleExpr(jstate, (Node *) when->result); - } - JumbleExpr(jstate, (Node *) caseexpr->defresult); - } - break; - case T_CaseTestExpr: - { - CaseTestExpr *ct = (CaseTestExpr *) node; - - APP_JUMB(ct->typeId); - } - break; - case T_ArrayExpr: - JumbleExpr(jstate, (Node *) ((ArrayExpr *) node)->elements); - break; - case T_RowExpr: - JumbleExpr(jstate, (Node *) ((RowExpr *) node)->args); - break; - case T_RowCompareExpr: - { - RowCompareExpr *rcexpr = (RowCompareExpr *) node; - - APP_JUMB(rcexpr->rctype); - JumbleExpr(jstate, (Node *) rcexpr->largs); - JumbleExpr(jstate, (Node *) rcexpr->rargs); - } - break; - case T_CoalesceExpr: - JumbleExpr(jstate, (Node *) ((CoalesceExpr *) node)->args); - break; - case T_MinMaxExpr: - { - MinMaxExpr *mmexpr = (MinMaxExpr *) node; - - APP_JUMB(mmexpr->op); - JumbleExpr(jstate, (Node *) mmexpr->args); - } - break; - case T_SQLValueFunction: - { - SQLValueFunction *svf = (SQLValueFunction *) node; - - APP_JUMB(svf->op); - /* type is fully determined by op */ - APP_JUMB(svf->typmod); - } - break; - case T_XmlExpr: - { - XmlExpr *xexpr = (XmlExpr *) node; - - APP_JUMB(xexpr->op); - JumbleExpr(jstate, (Node *) xexpr->named_args); - JumbleExpr(jstate, (Node *) xexpr->args); - } - break; - case T_NullTest: - { - NullTest *nt = (NullTest *) node; - - APP_JUMB(nt->nulltesttype); - JumbleExpr(jstate, (Node *) nt->arg); - } - break; - case T_BooleanTest: - { - BooleanTest *bt = (BooleanTest *) node; - - APP_JUMB(bt->booltesttype); - JumbleExpr(jstate, (Node *) bt->arg); - } - break; - case T_CoerceToDomain: - { - CoerceToDomain *cd = (CoerceToDomain *) node; - - APP_JUMB(cd->resulttype); - JumbleExpr(jstate, (Node *) cd->arg); - } - break; - case T_CoerceToDomainValue: - { - CoerceToDomainValue *cdv = (CoerceToDomainValue *) node; - - APP_JUMB(cdv->typeId); - } - break; - case T_SetToDefault: - { - SetToDefault *sd = (SetToDefault *) node; - - APP_JUMB(sd->typeId); - } - break; - case T_CurrentOfExpr: - { - CurrentOfExpr *ce = (CurrentOfExpr *) node; - - APP_JUMB(ce->cvarno); - if (ce->cursor_name) - APP_JUMB_STRING(ce->cursor_name); - APP_JUMB(ce->cursor_param); - } - break; - case T_NextValueExpr: - { - NextValueExpr *nve = (NextValueExpr *) node; - - APP_JUMB(nve->seqid); - APP_JUMB(nve->typeId); - } - break; - case T_InferenceElem: - { - InferenceElem *ie = (InferenceElem *) node; - - APP_JUMB(ie->infercollid); - APP_JUMB(ie->inferopclass); - JumbleExpr(jstate, ie->expr); - } - break; - case T_TargetEntry: - { - TargetEntry *tle = (TargetEntry *) node; - - APP_JUMB(tle->resno); - APP_JUMB(tle->ressortgroupref); - JumbleExpr(jstate, (Node *) tle->expr); - } - break; - case T_RangeTblRef: - { - RangeTblRef *rtr = (RangeTblRef *) node; - - APP_JUMB(rtr->rtindex); - } - break; - case T_JoinExpr: - { - JoinExpr *join = (JoinExpr *) node; - - APP_JUMB(join->jointype); - APP_JUMB(join->isNatural); - APP_JUMB(join->rtindex); - JumbleExpr(jstate, join->larg); - JumbleExpr(jstate, join->rarg); - JumbleExpr(jstate, join->quals); - } - break; - case T_FromExpr: - { - FromExpr *from = (FromExpr *) node; - - JumbleExpr(jstate, (Node *) from->fromlist); - JumbleExpr(jstate, from->quals); - } - break; - case T_OnConflictExpr: - { - OnConflictExpr *conf = (OnConflictExpr *) node; - - APP_JUMB(conf->action); - JumbleExpr(jstate, (Node *) conf->arbiterElems); - JumbleExpr(jstate, conf->arbiterWhere); - JumbleExpr(jstate, (Node *) conf->onConflictSet); - JumbleExpr(jstate, conf->onConflictWhere); - APP_JUMB(conf->constraint); - APP_JUMB(conf->exclRelIndex); - JumbleExpr(jstate, (Node *) conf->exclRelTlist); - } - break; - case T_List: - foreach(temp, (List *) node) - { - JumbleExpr(jstate, (Node *) lfirst(temp)); - } - break; - case T_IntList: - foreach(temp, (List *) node) - { - APP_JUMB(lfirst_int(temp)); - } - break; - case T_SortGroupClause: - { - SortGroupClause *sgc = (SortGroupClause *) node; - - APP_JUMB(sgc->tleSortGroupRef); - APP_JUMB(sgc->eqop); - APP_JUMB(sgc->sortop); - APP_JUMB(sgc->nulls_first); - } - break; - case T_GroupingSet: - { - GroupingSet *gsnode = (GroupingSet *) node; - - JumbleExpr(jstate, (Node *) gsnode->content); - } - break; - case T_WindowClause: - { - WindowClause *wc = (WindowClause *) node; - - APP_JUMB(wc->winref); - APP_JUMB(wc->frameOptions); - JumbleExpr(jstate, (Node *) wc->partitionClause); - JumbleExpr(jstate, (Node *) wc->orderClause); - JumbleExpr(jstate, wc->startOffset); - JumbleExpr(jstate, wc->endOffset); - } - break; - case T_CommonTableExpr: - { - CommonTableExpr *cte = (CommonTableExpr *) node; - - /* we store the string name because RTE_CTE RTEs need it */ - APP_JUMB_STRING(cte->ctename); - APP_JUMB(cte->ctematerialized); - JumbleQuery(jstate, castNode(Query, cte->ctequery)); - } - break; - case T_SetOperationStmt: - { - SetOperationStmt *setop = (SetOperationStmt *) node; - - APP_JUMB(setop->op); - APP_JUMB(setop->all); - JumbleExpr(jstate, setop->larg); - JumbleExpr(jstate, setop->rarg); - } - break; - case T_RangeTblFunction: - { - RangeTblFunction *rtfunc = (RangeTblFunction *) node; - - JumbleExpr(jstate, rtfunc->funcexpr); - } - break; - case T_TableFunc: - { - TableFunc *tablefunc = (TableFunc *) node; - - JumbleExpr(jstate, tablefunc->docexpr); - JumbleExpr(jstate, tablefunc->rowexpr); - JumbleExpr(jstate, (Node *) tablefunc->colexprs); - } - break; - case T_TableSampleClause: - { - TableSampleClause *tsc = (TableSampleClause *) node; - - APP_JUMB(tsc->tsmhandler); - JumbleExpr(jstate, (Node *) tsc->args); - JumbleExpr(jstate, (Node *) tsc->repeatable); - } - break; - default: - /* Only a warning, since we can stumble along anyway */ - elog(WARNING, "unrecognized node type: %d", - (int) nodeTag(node)); - break; - } -} - -/* - * Record location of constant within query string of query tree - * that is currently being walked. - */ -static void -RecordConstLocation(pgssJumbleState *jstate, int location) -{ - /* -1 indicates unknown or undefined location */ - if (location >= 0) - { - /* enlarge array if needed */ - if (jstate->clocations_count >= jstate->clocations_buf_size) - { - jstate->clocations_buf_size *= 2; - jstate->clocations = (pgssLocationLen *) - repalloc(jstate->clocations, - jstate->clocations_buf_size * - sizeof(pgssLocationLen)); - } - jstate->clocations[jstate->clocations_count].location = location; - /* initialize lengths to -1 to simplify fill_in_constant_lengths */ - jstate->clocations[jstate->clocations_count].length = -1; - jstate->clocations_count++; - } -} - /* * Generate a normalized version of the query string that will be used to * represent all similar queries. @@ -3321,7 +2566,7 @@ RecordConstLocation(pgssJumbleState *jstate, int location) * Returns a palloc'd string. */ static char * -generate_normalized_query(pgssJumbleState *jstate, const char *query, +generate_normalized_query(JumbleState *jstate, const char *query, int query_loc, int *query_len_p) { char *norm_query; @@ -3428,10 +2673,10 @@ generate_normalized_query(pgssJumbleState *jstate, const char *query, * reason for a constant to start with a '-'. */ static void -fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, +fill_in_constant_lengths(JumbleState *jstate, const char *query, int query_loc) { - pgssLocationLen *locs; + LocationLen *locs; core_yyscan_t yyscanner; core_yy_extra_type yyextra; core_YYSTYPE yylval; @@ -3445,7 +2690,7 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, */ if (jstate->clocations_count > 1) qsort(jstate->clocations, jstate->clocations_count, - sizeof(pgssLocationLen), comp_location); + sizeof(LocationLen), comp_location); locs = jstate->clocations; /* initialize the flex scanner --- should match raw_parser() */ @@ -3525,13 +2770,13 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, } /* - * comp_location: comparator for qsorting pgssLocationLen structs by location + * comp_location: comparator for qsorting LocationLen structs by location */ static int comp_location(const void *a, const void *b) { - int l = ((const pgssLocationLen *) a)->location; - int r = ((const pgssLocationLen *) b)->location; + int l = ((const LocationLen *) a)->location; + int r = ((const LocationLen *) b)->location; if (l < r) return -1; diff --git a/contrib/pg_stat_statements/pg_stat_statements.conf b/contrib/pg_stat_statements/pg_stat_statements.conf index 13346e2807..e47b26040f 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.conf +++ b/contrib/pg_stat_statements/pg_stat_statements.conf @@ -1 +1,2 @@ shared_preload_libraries = 'pg_stat_statements' +compute_query_id = on diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 0c9128a55d..b28f7000c1 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -7617,6 +7617,31 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv; <title>Statistics Monitoring</title> <variablelist> + <varlistentry id="guc-compute-query-id" xreflabel="compute_query_id"> + <term><varname>compute_query_id</varname> (<type>boolean</type>) + <indexterm> + <primary><varname>compute_query_id</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Enables in-core computation of a query identifier. The <xref + linkend="pgstatstatements"/> extension requires a query identifier + to be computed. Note that an external module can alternatively + be used if the in-core query identifier computation method + isn't acceptable. In this case, in-core computation should + remain disabled. The default is <literal>off</literal>. + </para> + <note> + <para> + To ensure that a only one query identifier is calculated and + displayed, extensions that calculate query identifiers should + throw an error if a query identifier has already been computed. + </para> + </note> + </listitem> + </varlistentry> + <varlistentry> <term><varname>log_statement_stats</varname> (<type>boolean</type>) <indexterm> diff --git a/doc/src/sgml/pgstatstatements.sgml b/doc/src/sgml/pgstatstatements.sgml index 464bf0e5ae..3ca292d71f 100644 --- a/doc/src/sgml/pgstatstatements.sgml +++ b/doc/src/sgml/pgstatstatements.sgml @@ -20,6 +20,14 @@ This means that a server restart is needed to add or remove the module. </para> + <para> + The module will not track statistics unless query + identifiers are calculated. This can be done by enabling <xref + linkend="guc-compute-query-id"/> or using a third-party module that + computes its own query identifiers. Note that all statistics tracked + by this module must be reset if the query identifier method is changed. + </para> + <para> When <filename>pg_stat_statements</filename> is loaded, it tracks statistics across all databases of the server. To access and manipulate @@ -84,7 +92,7 @@ <structfield>queryid</structfield> <type>bigint</type> </para> <para> - Internal hash code, computed from the statement's parse tree + Hash code to identify identical normalized queries. </para></entry> </row> @@ -386,6 +394,16 @@ are compared strictly on the basis of their textual query strings, however. </para> + <note> + <para> + The following details about constant replacement and + <structfield>queryid</structfield> only applies when <xref + linkend="guc-compute-query-id"/> is enabled. If you use an external + module instead to compute <structfield>queryid</structfield>, you + should refer to its documentation for details. + </para> + </note> + <para> When a constant's value has been ignored for purposes of matching the query to other queries, the constant is replaced by a parameter symbol, such diff --git a/src/backend/parser/analyze.c b/src/backend/parser/analyze.c index 5de1307570..35cb9ebfd7 100644 --- a/src/backend/parser/analyze.c +++ b/src/backend/parser/analyze.c @@ -46,6 +46,8 @@ #include "parser/parsetree.h" #include "rewrite/rewriteManip.h" #include "utils/builtins.h" +#include "utils/guc.h" +#include "utils/queryjumble.h" #include "utils/rel.h" @@ -107,6 +109,7 @@ parse_analyze(RawStmt *parseTree, const char *sourceText, { ParseState *pstate = make_parsestate(NULL); Query *query; + JumbleState *jstate = NULL; Assert(sourceText != NULL); /* required as of 8.4 */ @@ -119,8 +122,11 @@ parse_analyze(RawStmt *parseTree, const char *sourceText, query = transformTopLevelStmt(pstate, parseTree); + if (compute_query_id) + jstate = JumbleQuery(query, sourceText); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); @@ -140,6 +146,7 @@ parse_analyze_varparams(RawStmt *parseTree, const char *sourceText, { ParseState *pstate = make_parsestate(NULL); Query *query; + JumbleState *jstate = NULL; Assert(sourceText != NULL); /* required as of 8.4 */ @@ -152,8 +159,11 @@ parse_analyze_varparams(RawStmt *parseTree, const char *sourceText, /* make sure all is well with parameter types */ check_variable_parameters(pstate, query); + if (compute_query_id) + jstate = JumbleQuery(query, sourceText); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index ad351e2fd1..3a62e45bef 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -668,6 +668,7 @@ pg_analyze_and_rewrite_params(RawStmt *parsetree, ParseState *pstate; Query *query; List *querytree_list; + JumbleState *jstate = NULL; Assert(query_string != NULL); /* required as of 8.4 */ @@ -686,8 +687,11 @@ pg_analyze_and_rewrite_params(RawStmt *parsetree, query = transformTopLevelStmt(pstate, parsetree); + if (compute_query_id) + jstate = JumbleQuery(query, query_string); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); diff --git a/src/backend/utils/misc/Makefile b/src/backend/utils/misc/Makefile index 2397fc2453..1d5327cf64 100644 --- a/src/backend/utils/misc/Makefile +++ b/src/backend/utils/misc/Makefile @@ -22,6 +22,7 @@ OBJS = \ pg_rusage.o \ ps_status.o \ queryenvironment.o \ + queryjumble.o \ rls.o \ sampling.o \ superuser.o \ diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index c9c9da85f3..20b677543a 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -534,6 +534,7 @@ extern const struct config_enum_entry dynamic_shared_memory_options[]; /* * GUC option variables that are exported from this module */ +bool compute_query_id = false; bool log_duration = false; bool Debug_print_plan = false; bool Debug_print_parse = false; @@ -1458,6 +1459,15 @@ static struct config_bool ConfigureNamesBool[] = true, NULL, NULL, NULL }, + { + {"compute_query_id", PGC_SUSET, STATS_MONITORING, + gettext_noop("Compute query identifiers."), + NULL + }, + &compute_query_id, + false, + NULL, NULL, NULL + }, { {"log_parser_stats", PGC_SUSET, STATS_MONITORING, gettext_noop("Writes parser performance statistics to the server log."), diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 39da7cc942..192577a02e 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -596,6 +596,7 @@ # - Monitoring - +#compute_query_id = off #log_parser_stats = off #log_planner_stats = off #log_executor_stats = off diff --git a/src/backend/utils/misc/queryjumble.c b/src/backend/utils/misc/queryjumble.c new file mode 100644 index 0000000000..2a47688fd6 --- /dev/null +++ b/src/backend/utils/misc/queryjumble.c @@ -0,0 +1,834 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.c + * Query normalization and fingerprinting. + * + * Normalization is a process whereby similar queries, typically differing only + * in their constants (though the exact rules are somewhat more subtle than + * that) are recognized as equivalent, and are tracked as a single entry. This + * is particularly useful for non-prepared queries. + * + * Normalization is implemented by fingerprinting queries, selectively + * serializing those fields of each query tree's nodes that are judged to be + * essential to the query. This is referred to as a query jumble. This is + * distinct from a regular serialization in that various extraneous + * information is ignored as irrelevant or not essential to the query, such + * as the collations of Vars and, most notably, the values of constants. + * + * This jumble is acquired at the end of parse analysis of each query, and + * a 64-bit hash of it is stored into the query's Query.queryId field. + * The server then copies this value around, making it available in plan + * tree(s) generated from the query. The executor can then use this value + * to blame query costs on the proper queryId. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/misc/queryjumble.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "common/hashfn.h" +#include "miscadmin.h" +#include "parser/scansup.h" +#include "utils/queryjumble.h" + +#define JUMBLE_SIZE 1024 /* query serialization buffer size */ + +static uint64 compute_utility_queryid(const char *str, int query_len); +static void AppendJumble(JumbleState *jstate, + const unsigned char *item, Size size); +static void JumbleQueryInternal(JumbleState *jstate, Query *query); +static void JumbleRangeTable(JumbleState *jstate, List *rtable); +static void JumbleRowMarks(JumbleState *jstate, List *rowMarks); +static void JumbleExpr(JumbleState *jstate, Node *node); +static void RecordConstLocation(JumbleState *jstate, int location); + +/* + * Given a possibly multi-statement source string, confine our attention to the + * relevant part of the string. + */ +const char * +CleanQuerytext(const char *query, int *location, int *len) +{ + int query_location = *location; + int query_len = *len; + + /* First apply starting offset, unless it's -1 (unknown). */ + if (query_location >= 0) + { + Assert(query_location <= strlen(query)); + query += query_location; + /* Length of 0 (or -1) means "rest of string" */ + if (query_len <= 0) + query_len = strlen(query); + else + Assert(query_len <= strlen(query)); + } + else + { + /* If query location is unknown, distrust query_len as well */ + query_location = 0; + query_len = strlen(query); + } + + /* + * Discard leading and trailing whitespace, too. Use scanner_isspace() + * not libc's isspace(), because we want to match the lexer's behavior. + */ + while (query_len > 0 && scanner_isspace(query[0])) + query++, query_location++, query_len--; + while (query_len > 0 && scanner_isspace(query[query_len - 1])) + query_len--; + + *location = query_location; + *len = query_len; + + return query; +} + +JumbleState * +JumbleQuery(Query *query, const char *querytext) +{ + JumbleState *jstate = NULL; + if (query->utilityStmt) + { + const char *sql; + int query_location = query->stmt_location; + int query_len = query->stmt_len; + + /* + * Confine our attention to the relevant part of the string, if the + * query is a portion of a multi-statement source string. + */ + sql = CleanQuerytext(querytext, &query_location, &query_len); + + query->queryId = compute_utility_queryid(sql, query_len); + } + else + { + jstate = (JumbleState *) palloc(sizeof(JumbleState)); + + /* Set up workspace for query jumbling */ + jstate->jumble = (unsigned char *) palloc(JUMBLE_SIZE); + jstate->jumble_len = 0; + jstate->clocations_buf_size = 32; + jstate->clocations = (LocationLen *) + palloc(jstate->clocations_buf_size * sizeof(LocationLen)); + jstate->clocations_count = 0; + jstate->highest_extern_param_id = 0; + + /* Compute query ID and mark the Query node with it */ + JumbleQueryInternal(jstate, query); + query->queryId = DatumGetUInt64(hash_any_extended(jstate->jumble, + jstate->jumble_len, + 0)); + + /* + * If we are unlucky enough to get a hash of zero, use 1 instead, to + * prevent confusion with the utility-statement case. + */ + if (query->queryId == UINT64CONST(0)) + query->queryId = UINT64CONST(1); + } + + return jstate; +} + +/* + * Compute a query identifier for the given utility query string. + */ +static uint64 +compute_utility_queryid(const char *str, int query_len) +{ + uint64 queryId; + + queryId = DatumGetUInt64(hash_any_extended((const unsigned char *) str, + query_len, 0)); + + /* + * If we are unlucky enough to get a hash of zero(invalid), use + * queryID as 2 instead, queryID 1 is already in use for normal + * statements. + */ + if (queryId == UINT64CONST(0)) + queryId = UINT64CONST(2); + + return queryId; +} + +/* + * AppendJumble: Append a value that is substantive in a given query to + * the current jumble. + */ +static void +AppendJumble(JumbleState *jstate, const unsigned char *item, Size size) +{ + unsigned char *jumble = jstate->jumble; + Size jumble_len = jstate->jumble_len; + + /* + * Whenever the jumble buffer is full, we hash the current contents and + * reset the buffer to contain just that hash value, thus relying on the + * hash to summarize everything so far. + */ + while (size > 0) + { + Size part_size; + + if (jumble_len >= JUMBLE_SIZE) + { + uint64 start_hash; + + start_hash = DatumGetUInt64(hash_any_extended(jumble, + JUMBLE_SIZE, 0)); + memcpy(jumble, &start_hash, sizeof(start_hash)); + jumble_len = sizeof(start_hash); + } + part_size = Min(size, JUMBLE_SIZE - jumble_len); + memcpy(jumble + jumble_len, item, part_size); + jumble_len += part_size; + item += part_size; + size -= part_size; + } + jstate->jumble_len = jumble_len; +} + +/* + * Wrappers around AppendJumble to encapsulate details of serialization + * of individual local variable elements. + */ +#define APP_JUMB(item) \ + AppendJumble(jstate, (const unsigned char *) &(item), sizeof(item)) +#define APP_JUMB_STRING(str) \ + AppendJumble(jstate, (const unsigned char *) (str), strlen(str) + 1) + +/* + * JumbleQueryInternal: Selectively serialize the query tree, appending + * significant data to the "query jumble" while ignoring nonsignificant data. + * + * Rule of thumb for what to include is that we should ignore anything not + * semantically significant (such as alias names) as well as anything that can + * be deduced from child nodes (else we'd just be double-hashing that piece + * of information). + */ +static void +JumbleQueryInternal(JumbleState *jstate, Query *query) +{ + Assert(IsA(query, Query)); + Assert(query->utilityStmt == NULL); + + APP_JUMB(query->commandType); + /* resultRelation is usually predictable from commandType */ + JumbleExpr(jstate, (Node *) query->cteList); + JumbleRangeTable(jstate, query->rtable); + JumbleExpr(jstate, (Node *) query->jointree); + JumbleExpr(jstate, (Node *) query->targetList); + JumbleExpr(jstate, (Node *) query->onConflict); + JumbleExpr(jstate, (Node *) query->returningList); + JumbleExpr(jstate, (Node *) query->groupClause); + JumbleExpr(jstate, (Node *) query->groupingSets); + JumbleExpr(jstate, query->havingQual); + JumbleExpr(jstate, (Node *) query->windowClause); + JumbleExpr(jstate, (Node *) query->distinctClause); + JumbleExpr(jstate, (Node *) query->sortClause); + JumbleExpr(jstate, query->limitOffset); + JumbleExpr(jstate, query->limitCount); + JumbleRowMarks(jstate, query->rowMarks); + JumbleExpr(jstate, query->setOperations); +} + +/* + * Jumble a range table + */ +static void +JumbleRangeTable(JumbleState *jstate, List *rtable) +{ + ListCell *lc; + + foreach(lc, rtable) + { + RangeTblEntry *rte = lfirst_node(RangeTblEntry, lc); + + APP_JUMB(rte->rtekind); + switch (rte->rtekind) + { + case RTE_RELATION: + APP_JUMB(rte->relid); + JumbleExpr(jstate, (Node *) rte->tablesample); + break; + case RTE_SUBQUERY: + JumbleQueryInternal(jstate, rte->subquery); + break; + case RTE_JOIN: + APP_JUMB(rte->jointype); + break; + case RTE_FUNCTION: + JumbleExpr(jstate, (Node *) rte->functions); + break; + case RTE_TABLEFUNC: + JumbleExpr(jstate, (Node *) rte->tablefunc); + break; + case RTE_VALUES: + JumbleExpr(jstate, (Node *) rte->values_lists); + break; + case RTE_CTE: + + /* + * Depending on the CTE name here isn't ideal, but it's the + * only info we have to identify the referenced WITH item. + */ + APP_JUMB_STRING(rte->ctename); + APP_JUMB(rte->ctelevelsup); + break; + case RTE_NAMEDTUPLESTORE: + APP_JUMB_STRING(rte->enrname); + break; + case RTE_RESULT: + break; + default: + elog(ERROR, "unrecognized RTE kind: %d", (int) rte->rtekind); + break; + } + } +} + +/* + * Jumble a rowMarks list + */ +static void +JumbleRowMarks(JumbleState *jstate, List *rowMarks) +{ + ListCell *lc; + + foreach(lc, rowMarks) + { + RowMarkClause *rowmark = lfirst_node(RowMarkClause, lc); + + if (!rowmark->pushedDown) + { + APP_JUMB(rowmark->rti); + APP_JUMB(rowmark->strength); + APP_JUMB(rowmark->waitPolicy); + } + } +} + +/* + * Jumble an expression tree + * + * In general this function should handle all the same node types that + * expression_tree_walker() does, and therefore it's coded to be as parallel + * to that function as possible. However, since we are only invoked on + * queries immediately post-parse-analysis, we need not handle node types + * that only appear in planning. + * + * Note: the reason we don't simply use expression_tree_walker() is that the + * point of that function is to support tree walkers that don't care about + * most tree node types, but here we care about all types. We should complain + * about any unrecognized node type. + */ +static void +JumbleExpr(JumbleState *jstate, Node *node) +{ + ListCell *temp; + + if (node == NULL) + return; + + /* Guard against stack overflow due to overly complex expressions */ + check_stack_depth(); + + /* + * We always emit the node's NodeTag, then any additional fields that are + * considered significant, and then we recurse to any child nodes. + */ + APP_JUMB(node->type); + + switch (nodeTag(node)) + { + case T_Var: + { + Var *var = (Var *) node; + + APP_JUMB(var->varno); + APP_JUMB(var->varattno); + APP_JUMB(var->varlevelsup); + } + break; + case T_Const: + { + Const *c = (Const *) node; + + /* We jumble only the constant's type, not its value */ + APP_JUMB(c->consttype); + /* Also, record its parse location for query normalization */ + RecordConstLocation(jstate, c->location); + } + break; + case T_Param: + { + Param *p = (Param *) node; + + APP_JUMB(p->paramkind); + APP_JUMB(p->paramid); + APP_JUMB(p->paramtype); + /* Also, track the highest external Param id */ + if (p->paramkind == PARAM_EXTERN && + p->paramid > jstate->highest_extern_param_id) + jstate->highest_extern_param_id = p->paramid; + } + break; + case T_Aggref: + { + Aggref *expr = (Aggref *) node; + + APP_JUMB(expr->aggfnoid); + JumbleExpr(jstate, (Node *) expr->aggdirectargs); + JumbleExpr(jstate, (Node *) expr->args); + JumbleExpr(jstate, (Node *) expr->aggorder); + JumbleExpr(jstate, (Node *) expr->aggdistinct); + JumbleExpr(jstate, (Node *) expr->aggfilter); + } + break; + case T_GroupingFunc: + { + GroupingFunc *grpnode = (GroupingFunc *) node; + + JumbleExpr(jstate, (Node *) grpnode->refs); + } + break; + case T_WindowFunc: + { + WindowFunc *expr = (WindowFunc *) node; + + APP_JUMB(expr->winfnoid); + APP_JUMB(expr->winref); + JumbleExpr(jstate, (Node *) expr->args); + JumbleExpr(jstate, (Node *) expr->aggfilter); + } + break; + case T_SubscriptingRef: + { + SubscriptingRef *sbsref = (SubscriptingRef *) node; + + JumbleExpr(jstate, (Node *) sbsref->refupperindexpr); + JumbleExpr(jstate, (Node *) sbsref->reflowerindexpr); + JumbleExpr(jstate, (Node *) sbsref->refexpr); + JumbleExpr(jstate, (Node *) sbsref->refassgnexpr); + } + break; + case T_FuncExpr: + { + FuncExpr *expr = (FuncExpr *) node; + + APP_JUMB(expr->funcid); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_NamedArgExpr: + { + NamedArgExpr *nae = (NamedArgExpr *) node; + + APP_JUMB(nae->argnumber); + JumbleExpr(jstate, (Node *) nae->arg); + } + break; + case T_OpExpr: + case T_DistinctExpr: /* struct-equivalent to OpExpr */ + case T_NullIfExpr: /* struct-equivalent to OpExpr */ + { + OpExpr *expr = (OpExpr *) node; + + APP_JUMB(expr->opno); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_ScalarArrayOpExpr: + { + ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node; + + APP_JUMB(expr->opno); + APP_JUMB(expr->useOr); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_BoolExpr: + { + BoolExpr *expr = (BoolExpr *) node; + + APP_JUMB(expr->boolop); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_SubLink: + { + SubLink *sublink = (SubLink *) node; + + APP_JUMB(sublink->subLinkType); + APP_JUMB(sublink->subLinkId); + JumbleExpr(jstate, (Node *) sublink->testexpr); + JumbleQueryInternal(jstate, castNode(Query, sublink->subselect)); + } + break; + case T_FieldSelect: + { + FieldSelect *fs = (FieldSelect *) node; + + APP_JUMB(fs->fieldnum); + JumbleExpr(jstate, (Node *) fs->arg); + } + break; + case T_FieldStore: + { + FieldStore *fstore = (FieldStore *) node; + + JumbleExpr(jstate, (Node *) fstore->arg); + JumbleExpr(jstate, (Node *) fstore->newvals); + } + break; + case T_RelabelType: + { + RelabelType *rt = (RelabelType *) node; + + APP_JUMB(rt->resulttype); + JumbleExpr(jstate, (Node *) rt->arg); + } + break; + case T_CoerceViaIO: + { + CoerceViaIO *cio = (CoerceViaIO *) node; + + APP_JUMB(cio->resulttype); + JumbleExpr(jstate, (Node *) cio->arg); + } + break; + case T_ArrayCoerceExpr: + { + ArrayCoerceExpr *acexpr = (ArrayCoerceExpr *) node; + + APP_JUMB(acexpr->resulttype); + JumbleExpr(jstate, (Node *) acexpr->arg); + JumbleExpr(jstate, (Node *) acexpr->elemexpr); + } + break; + case T_ConvertRowtypeExpr: + { + ConvertRowtypeExpr *crexpr = (ConvertRowtypeExpr *) node; + + APP_JUMB(crexpr->resulttype); + JumbleExpr(jstate, (Node *) crexpr->arg); + } + break; + case T_CollateExpr: + { + CollateExpr *ce = (CollateExpr *) node; + + APP_JUMB(ce->collOid); + JumbleExpr(jstate, (Node *) ce->arg); + } + break; + case T_CaseExpr: + { + CaseExpr *caseexpr = (CaseExpr *) node; + + JumbleExpr(jstate, (Node *) caseexpr->arg); + foreach(temp, caseexpr->args) + { + CaseWhen *when = lfirst_node(CaseWhen, temp); + + JumbleExpr(jstate, (Node *) when->expr); + JumbleExpr(jstate, (Node *) when->result); + } + JumbleExpr(jstate, (Node *) caseexpr->defresult); + } + break; + case T_CaseTestExpr: + { + CaseTestExpr *ct = (CaseTestExpr *) node; + + APP_JUMB(ct->typeId); + } + break; + case T_ArrayExpr: + JumbleExpr(jstate, (Node *) ((ArrayExpr *) node)->elements); + break; + case T_RowExpr: + JumbleExpr(jstate, (Node *) ((RowExpr *) node)->args); + break; + case T_RowCompareExpr: + { + RowCompareExpr *rcexpr = (RowCompareExpr *) node; + + APP_JUMB(rcexpr->rctype); + JumbleExpr(jstate, (Node *) rcexpr->largs); + JumbleExpr(jstate, (Node *) rcexpr->rargs); + } + break; + case T_CoalesceExpr: + JumbleExpr(jstate, (Node *) ((CoalesceExpr *) node)->args); + break; + case T_MinMaxExpr: + { + MinMaxExpr *mmexpr = (MinMaxExpr *) node; + + APP_JUMB(mmexpr->op); + JumbleExpr(jstate, (Node *) mmexpr->args); + } + break; + case T_SQLValueFunction: + { + SQLValueFunction *svf = (SQLValueFunction *) node; + + APP_JUMB(svf->op); + /* type is fully determined by op */ + APP_JUMB(svf->typmod); + } + break; + case T_XmlExpr: + { + XmlExpr *xexpr = (XmlExpr *) node; + + APP_JUMB(xexpr->op); + JumbleExpr(jstate, (Node *) xexpr->named_args); + JumbleExpr(jstate, (Node *) xexpr->args); + } + break; + case T_NullTest: + { + NullTest *nt = (NullTest *) node; + + APP_JUMB(nt->nulltesttype); + JumbleExpr(jstate, (Node *) nt->arg); + } + break; + case T_BooleanTest: + { + BooleanTest *bt = (BooleanTest *) node; + + APP_JUMB(bt->booltesttype); + JumbleExpr(jstate, (Node *) bt->arg); + } + break; + case T_CoerceToDomain: + { + CoerceToDomain *cd = (CoerceToDomain *) node; + + APP_JUMB(cd->resulttype); + JumbleExpr(jstate, (Node *) cd->arg); + } + break; + case T_CoerceToDomainValue: + { + CoerceToDomainValue *cdv = (CoerceToDomainValue *) node; + + APP_JUMB(cdv->typeId); + } + break; + case T_SetToDefault: + { + SetToDefault *sd = (SetToDefault *) node; + + APP_JUMB(sd->typeId); + } + break; + case T_CurrentOfExpr: + { + CurrentOfExpr *ce = (CurrentOfExpr *) node; + + APP_JUMB(ce->cvarno); + if (ce->cursor_name) + APP_JUMB_STRING(ce->cursor_name); + APP_JUMB(ce->cursor_param); + } + break; + case T_NextValueExpr: + { + NextValueExpr *nve = (NextValueExpr *) node; + + APP_JUMB(nve->seqid); + APP_JUMB(nve->typeId); + } + break; + case T_InferenceElem: + { + InferenceElem *ie = (InferenceElem *) node; + + APP_JUMB(ie->infercollid); + APP_JUMB(ie->inferopclass); + JumbleExpr(jstate, ie->expr); + } + break; + case T_TargetEntry: + { + TargetEntry *tle = (TargetEntry *) node; + + APP_JUMB(tle->resno); + APP_JUMB(tle->ressortgroupref); + JumbleExpr(jstate, (Node *) tle->expr); + } + break; + case T_RangeTblRef: + { + RangeTblRef *rtr = (RangeTblRef *) node; + + APP_JUMB(rtr->rtindex); + } + break; + case T_JoinExpr: + { + JoinExpr *join = (JoinExpr *) node; + + APP_JUMB(join->jointype); + APP_JUMB(join->isNatural); + APP_JUMB(join->rtindex); + JumbleExpr(jstate, join->larg); + JumbleExpr(jstate, join->rarg); + JumbleExpr(jstate, join->quals); + } + break; + case T_FromExpr: + { + FromExpr *from = (FromExpr *) node; + + JumbleExpr(jstate, (Node *) from->fromlist); + JumbleExpr(jstate, from->quals); + } + break; + case T_OnConflictExpr: + { + OnConflictExpr *conf = (OnConflictExpr *) node; + + APP_JUMB(conf->action); + JumbleExpr(jstate, (Node *) conf->arbiterElems); + JumbleExpr(jstate, conf->arbiterWhere); + JumbleExpr(jstate, (Node *) conf->onConflictSet); + JumbleExpr(jstate, conf->onConflictWhere); + APP_JUMB(conf->constraint); + APP_JUMB(conf->exclRelIndex); + JumbleExpr(jstate, (Node *) conf->exclRelTlist); + } + break; + case T_List: + foreach(temp, (List *) node) + { + JumbleExpr(jstate, (Node *) lfirst(temp)); + } + break; + case T_IntList: + foreach(temp, (List *) node) + { + APP_JUMB(lfirst_int(temp)); + } + break; + case T_SortGroupClause: + { + SortGroupClause *sgc = (SortGroupClause *) node; + + APP_JUMB(sgc->tleSortGroupRef); + APP_JUMB(sgc->eqop); + APP_JUMB(sgc->sortop); + APP_JUMB(sgc->nulls_first); + } + break; + case T_GroupingSet: + { + GroupingSet *gsnode = (GroupingSet *) node; + + JumbleExpr(jstate, (Node *) gsnode->content); + } + break; + case T_WindowClause: + { + WindowClause *wc = (WindowClause *) node; + + APP_JUMB(wc->winref); + APP_JUMB(wc->frameOptions); + JumbleExpr(jstate, (Node *) wc->partitionClause); + JumbleExpr(jstate, (Node *) wc->orderClause); + JumbleExpr(jstate, wc->startOffset); + JumbleExpr(jstate, wc->endOffset); + } + break; + case T_CommonTableExpr: + { + CommonTableExpr *cte = (CommonTableExpr *) node; + + /* we store the string name because RTE_CTE RTEs need it */ + APP_JUMB_STRING(cte->ctename); + APP_JUMB(cte->ctematerialized); + JumbleQueryInternal(jstate, castNode(Query, cte->ctequery)); + } + break; + case T_SetOperationStmt: + { + SetOperationStmt *setop = (SetOperationStmt *) node; + + APP_JUMB(setop->op); + APP_JUMB(setop->all); + JumbleExpr(jstate, setop->larg); + JumbleExpr(jstate, setop->rarg); + } + break; + case T_RangeTblFunction: + { + RangeTblFunction *rtfunc = (RangeTblFunction *) node; + + JumbleExpr(jstate, rtfunc->funcexpr); + } + break; + case T_TableFunc: + { + TableFunc *tablefunc = (TableFunc *) node; + + JumbleExpr(jstate, tablefunc->docexpr); + JumbleExpr(jstate, tablefunc->rowexpr); + JumbleExpr(jstate, (Node *) tablefunc->colexprs); + } + break; + case T_TableSampleClause: + { + TableSampleClause *tsc = (TableSampleClause *) node; + + APP_JUMB(tsc->tsmhandler); + JumbleExpr(jstate, (Node *) tsc->args); + JumbleExpr(jstate, (Node *) tsc->repeatable); + } + break; + default: + /* Only a warning, since we can stumble along anyway */ + elog(WARNING, "unrecognized node type: %d", + (int) nodeTag(node)); + break; + } +} + +/* + * Record location of constant within query string of query tree + * that is currently being walked. + */ +static void +RecordConstLocation(JumbleState *jstate, int location) +{ + /* -1 indicates unknown or undefined location */ + if (location >= 0) + { + /* enlarge array if needed */ + if (jstate->clocations_count >= jstate->clocations_buf_size) + { + jstate->clocations_buf_size *= 2; + jstate->clocations = (LocationLen *) + repalloc(jstate->clocations, + jstate->clocations_buf_size * + sizeof(LocationLen)); + } + jstate->clocations[jstate->clocations_count].location = location; + /* initialize lengths to -1 to simplify third-party module usage */ + jstate->clocations[jstate->clocations_count].length = -1; + jstate->clocations_count++; + } +} diff --git a/src/include/parser/analyze.h b/src/include/parser/analyze.h index 4a3c9686f9..6716db6c13 100644 --- a/src/include/parser/analyze.h +++ b/src/include/parser/analyze.h @@ -15,10 +15,12 @@ #define ANALYZE_H #include "parser/parse_node.h" +#include "utils/queryjumble.h" /* Hook for plugins to get control at end of parse analysis */ typedef void (*post_parse_analyze_hook_type) (ParseState *pstate, - Query *query); + Query *query, + JumbleState *jstate); extern PGDLLIMPORT post_parse_analyze_hook_type post_parse_analyze_hook; diff --git a/src/include/utils/guc.h b/src/include/utils/guc.h index 5004ee4177..9b6552b25b 100644 --- a/src/include/utils/guc.h +++ b/src/include/utils/guc.h @@ -248,6 +248,7 @@ extern bool log_btree_build_stats; extern PGDLLIMPORT bool check_function_bodies; extern bool session_auth_is_superuser; +extern bool compute_query_id; extern bool log_duration; extern int log_parameter_max_length; extern int log_parameter_max_length_on_error; diff --git a/src/include/utils/queryjumble.h b/src/include/utils/queryjumble.h new file mode 100644 index 0000000000..83ba7339fa --- /dev/null +++ b/src/include/utils/queryjumble.h @@ -0,0 +1,58 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.h + * Query normalization and fingerprinting. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/include/utils/queryjumble.h + * + *------------------------------------------------------------------------- + */ +#ifndef QUERYJUBLE_H +#define QUERYJUBLE_H + +#include "nodes/parsenodes.h" + +#define JUMBLE_SIZE 1024 /* query serialization buffer size */ + +/* + * Struct for tracking locations/lengths of constants during normalization + */ +typedef struct LocationLen +{ + int location; /* start offset in query text */ + int length; /* length in bytes, or -1 to ignore */ +} LocationLen; + +/* + * Working state for computing a query jumble and producing a normalized + * query string + */ +typedef struct JumbleState +{ + /* Jumble of current query tree */ + unsigned char *jumble; + + /* Number of bytes used in jumble[] */ + Size jumble_len; + + /* Array of locations of constants that should be removed */ + LocationLen *clocations; + + /* Allocated length of clocations array */ + int clocations_buf_size; + + /* Current number of valid entries in clocations array */ + int clocations_count; + + /* highest Param id we've seen, in order to start normalization correctly */ + int highest_extern_param_id; +} JumbleState; + +const char *CleanQuerytext(const char *query, int *location, int *len); +JumbleState *JumbleQuery(Query *query, const char *querytext); + +#endif /* QUERYJUMBLE_H */ -- 2.30.1 --xbzj3q7ypaxd3o4o Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v23-0002-Expose-queryid-in-pg_stat_activity-and-log_line_.patch" ^ permalink raw reply [nested|flat] 4+ messages in thread
* [PATCH v20 1/3] Move pg_stat_statements query jumbling to core. @ 2021-03-22 21:43 Bruce Momjian <bruce@momjian.us> 0 siblings, 0 replies; 4+ messages in thread From: Bruce Momjian @ 2021-03-22 21:43 UTC (permalink / raw) A new compute_query_id GUC is also added, to control whether a query identifier should be computed by the core. It's thefore now possible to disable core queryid computation and use pg_stat_statements with a different algorithm to compute the query identifier by using third-party module. To ensure that a single source of query identifier can be used and is well defined, modules that calculate a query identifier should throw an error if compute_query_id is enabled or if a query idenfitier was already calculated. --- .../pg_stat_statements/pg_stat_statements.c | 805 +---------------- .../pg_stat_statements.conf | 1 + doc/src/sgml/config.sgml | 25 + doc/src/sgml/pgstatstatements.sgml | 20 +- src/backend/parser/analyze.c | 14 +- src/backend/tcop/postgres.c | 6 +- src/backend/utils/misc/Makefile | 1 + src/backend/utils/misc/guc.c | 10 + src/backend/utils/misc/postgresql.conf.sample | 1 + src/backend/utils/misc/queryjumble.c | 834 ++++++++++++++++++ src/include/parser/analyze.h | 4 +- src/include/utils/guc.h | 1 + src/include/utils/queryjumble.h | 58 ++ 13 files changed, 995 insertions(+), 785 deletions(-) create mode 100644 src/backend/utils/misc/queryjumble.c create mode 100644 src/include/utils/queryjumble.h diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c index 62cccbfa44..bd8c96728c 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.c +++ b/contrib/pg_stat_statements/pg_stat_statements.c @@ -8,24 +8,9 @@ * a shared hashtable. (We track only as many distinct queries as will fit * in the designated amount of shared memory.) * - * As of Postgres 9.2, this module normalizes query entries. Normalization - * is a process whereby similar queries, typically differing only in their - * constants (though the exact rules are somewhat more subtle than that) are - * recognized as equivalent, and are tracked as a single entry. This is - * particularly useful for non-prepared queries. - * - * Normalization is implemented by fingerprinting queries, selectively - * serializing those fields of each query tree's nodes that are judged to be - * essential to the query. This is referred to as a query jumble. This is - * distinct from a regular serialization in that various extraneous - * information is ignored as irrelevant or not essential to the query, such - * as the collations of Vars and, most notably, the values of constants. - * - * This jumble is acquired at the end of parse analysis of each query, and - * a 64-bit hash of it is stored into the query's Query.queryId field. - * The server then copies this value around, making it available in plan - * tree(s) generated from the query. The executor can then use this value - * to blame query costs on the proper queryId. + * Starting in Postgres 9.2, this module normalized query entries. As of + * Postgres 14, the normalization is done by the core if compute_query_id is + * enabled, or optionally by third-party modules. * * To facilitate presenting entries to users, we create "representative" query * strings in which constants are replaced with parameter symbols ($n), to @@ -114,8 +99,6 @@ static const uint32 PGSS_PG_MAJOR_VERSION = PG_VERSION_NUM / 100; #define USAGE_DEALLOC_PERCENT 5 /* free this % of entries at once */ #define IS_STICKY(c) ((c.calls[PGSS_PLAN] + c.calls[PGSS_EXEC]) == 0) -#define JUMBLE_SIZE 1024 /* query serialization buffer size */ - /* * Extension version number, for supporting older extension versions' objects */ @@ -235,40 +218,6 @@ typedef struct pgssSharedState pgssGlobalStats stats; /* global statistics for pgss */ } pgssSharedState; -/* - * Struct for tracking locations/lengths of constants during normalization - */ -typedef struct pgssLocationLen -{ - int location; /* start offset in query text */ - int length; /* length in bytes, or -1 to ignore */ -} pgssLocationLen; - -/* - * Working state for computing a query jumble and producing a normalized - * query string - */ -typedef struct pgssJumbleState -{ - /* Jumble of current query tree */ - unsigned char *jumble; - - /* Number of bytes used in jumble[] */ - Size jumble_len; - - /* Array of locations of constants that should be removed */ - pgssLocationLen *clocations; - - /* Allocated length of clocations array */ - int clocations_buf_size; - - /* Current number of valid entries in clocations array */ - int clocations_count; - - /* highest Param id we've seen, in order to start normalization correctly */ - int highest_extern_param_id; -} pgssJumbleState; - /*---- Local variables ----*/ /* Current nesting depth of ExecutorRun+ProcessUtility calls */ @@ -342,7 +291,8 @@ PG_FUNCTION_INFO_V1(pg_stat_statements_info); static void pgss_shmem_startup(void); static void pgss_shmem_shutdown(int code, Datum arg); -static void pgss_post_parse_analyze(ParseState *pstate, Query *query); +static void pgss_post_parse_analyze(ParseState *pstate, Query *query, + JumbleState *jstate); static PlannedStmt *pgss_planner(Query *parse, const char *query_string, int cursorOptions, @@ -364,7 +314,7 @@ static void pgss_store(const char *query, uint64 queryId, double total_time, uint64 rows, const BufferUsage *bufusage, const WalUsage *walusage, - pgssJumbleState *jstate); + JumbleState *jstate); static void pg_stat_statements_internal(FunctionCallInfo fcinfo, pgssVersion api_version, bool showtext); @@ -380,16 +330,9 @@ static char *qtext_fetch(Size query_offset, int query_len, static bool need_gc_qtexts(void); static void gc_qtexts(void); static void entry_reset(Oid userid, Oid dbid, uint64 queryid); -static void AppendJumble(pgssJumbleState *jstate, - const unsigned char *item, Size size); -static void JumbleQuery(pgssJumbleState *jstate, Query *query); -static void JumbleRangeTable(pgssJumbleState *jstate, List *rtable); -static void JumbleRowMarks(pgssJumbleState *jstate, List *rowMarks); -static void JumbleExpr(pgssJumbleState *jstate, Node *node); -static void RecordConstLocation(pgssJumbleState *jstate, int location); -static char *generate_normalized_query(pgssJumbleState *jstate, const char *query, +static char *generate_normalized_query(JumbleState *jstate, const char *query, int query_loc, int *query_len_p); -static void fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, +static void fill_in_constant_lengths(JumbleState *jstate, const char *query, int query_loc); static int comp_location(const void *a, const void *b); @@ -851,15 +794,10 @@ error: * Post-parse-analysis hook: mark query with a queryId */ static void -pgss_post_parse_analyze(ParseState *pstate, Query *query) +pgss_post_parse_analyze(ParseState *pstate, Query *query, JumbleState *jstate) { - pgssJumbleState jstate; - if (prev_post_parse_analyze_hook) - prev_post_parse_analyze_hook(pstate, query); - - /* Assert we didn't do this already */ - Assert(query->queryId == UINT64CONST(0)); + prev_post_parse_analyze_hook(pstate, query, jstate); /* Safety check... */ if (!pgss || !pgss_hash || !pgss_enabled(exec_nested_level)) @@ -879,35 +817,14 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query) return; } - /* Set up workspace for query jumbling */ - jstate.jumble = (unsigned char *) palloc(JUMBLE_SIZE); - jstate.jumble_len = 0; - jstate.clocations_buf_size = 32; - jstate.clocations = (pgssLocationLen *) - palloc(jstate.clocations_buf_size * sizeof(pgssLocationLen)); - jstate.clocations_count = 0; - jstate.highest_extern_param_id = 0; - - /* Compute query ID and mark the Query node with it */ - JumbleQuery(&jstate, query); - query->queryId = - DatumGetUInt64(hash_any_extended(jstate.jumble, jstate.jumble_len, 0)); - /* - * If we are unlucky enough to get a hash of zero, use 1 instead, to - * prevent confusion with the utility-statement case. + * If query jumbling were able to identify any ignorable constants, we + * immediately create a hash table entry for the query, so that we can + * record the normalized form of the query string. If there were no such + * constants, the normalized string would be the same as the query text + * anyway, so there's no need for an early entry. */ - if (query->queryId == UINT64CONST(0)) - query->queryId = UINT64CONST(1); - - /* - * If we were able to identify any ignorable constants, we immediately - * create a hash table entry for the query, so that we can record the - * normalized form of the query string. If there were no such constants, - * the normalized string would be the same as the query text anyway, so - * there's no need for an early entry. - */ - if (jstate.clocations_count > 0) + if (jstate && jstate->clocations_count > 0) pgss_store(pstate->p_sourcetext, query->queryId, query->stmt_location, @@ -917,7 +834,7 @@ pgss_post_parse_analyze(ParseState *pstate, Query *query) 0, NULL, NULL, - &jstate); + jstate); } /* @@ -1267,7 +1184,7 @@ pgss_store(const char *query, uint64 queryId, double total_time, uint64 rows, const BufferUsage *bufusage, const WalUsage *walusage, - pgssJumbleState *jstate) + JumbleState *jstate) { pgssHashKey key; pgssEntry *entry; @@ -2627,678 +2544,6 @@ release_lock: LWLockRelease(pgss->lock); } -/* - * AppendJumble: Append a value that is substantive in a given query to - * the current jumble. - */ -static void -AppendJumble(pgssJumbleState *jstate, const unsigned char *item, Size size) -{ - unsigned char *jumble = jstate->jumble; - Size jumble_len = jstate->jumble_len; - - /* - * Whenever the jumble buffer is full, we hash the current contents and - * reset the buffer to contain just that hash value, thus relying on the - * hash to summarize everything so far. - */ - while (size > 0) - { - Size part_size; - - if (jumble_len >= JUMBLE_SIZE) - { - uint64 start_hash; - - start_hash = DatumGetUInt64(hash_any_extended(jumble, - JUMBLE_SIZE, 0)); - memcpy(jumble, &start_hash, sizeof(start_hash)); - jumble_len = sizeof(start_hash); - } - part_size = Min(size, JUMBLE_SIZE - jumble_len); - memcpy(jumble + jumble_len, item, part_size); - jumble_len += part_size; - item += part_size; - size -= part_size; - } - jstate->jumble_len = jumble_len; -} - -/* - * Wrappers around AppendJumble to encapsulate details of serialization - * of individual local variable elements. - */ -#define APP_JUMB(item) \ - AppendJumble(jstate, (const unsigned char *) &(item), sizeof(item)) -#define APP_JUMB_STRING(str) \ - AppendJumble(jstate, (const unsigned char *) (str), strlen(str) + 1) - -/* - * JumbleQuery: Selectively serialize the query tree, appending significant - * data to the "query jumble" while ignoring nonsignificant data. - * - * Rule of thumb for what to include is that we should ignore anything not - * semantically significant (such as alias names) as well as anything that can - * be deduced from child nodes (else we'd just be double-hashing that piece - * of information). - */ -static void -JumbleQuery(pgssJumbleState *jstate, Query *query) -{ - Assert(IsA(query, Query)); - Assert(query->utilityStmt == NULL); - - APP_JUMB(query->commandType); - /* resultRelation is usually predictable from commandType */ - JumbleExpr(jstate, (Node *) query->cteList); - JumbleRangeTable(jstate, query->rtable); - JumbleExpr(jstate, (Node *) query->jointree); - JumbleExpr(jstate, (Node *) query->targetList); - JumbleExpr(jstate, (Node *) query->onConflict); - JumbleExpr(jstate, (Node *) query->returningList); - JumbleExpr(jstate, (Node *) query->groupClause); - JumbleExpr(jstate, (Node *) query->groupingSets); - JumbleExpr(jstate, query->havingQual); - JumbleExpr(jstate, (Node *) query->windowClause); - JumbleExpr(jstate, (Node *) query->distinctClause); - JumbleExpr(jstate, (Node *) query->sortClause); - JumbleExpr(jstate, query->limitOffset); - JumbleExpr(jstate, query->limitCount); - JumbleRowMarks(jstate, query->rowMarks); - JumbleExpr(jstate, query->setOperations); -} - -/* - * Jumble a range table - */ -static void -JumbleRangeTable(pgssJumbleState *jstate, List *rtable) -{ - ListCell *lc; - - foreach(lc, rtable) - { - RangeTblEntry *rte = lfirst_node(RangeTblEntry, lc); - - APP_JUMB(rte->rtekind); - switch (rte->rtekind) - { - case RTE_RELATION: - APP_JUMB(rte->relid); - JumbleExpr(jstate, (Node *) rte->tablesample); - break; - case RTE_SUBQUERY: - JumbleQuery(jstate, rte->subquery); - break; - case RTE_JOIN: - APP_JUMB(rte->jointype); - break; - case RTE_FUNCTION: - JumbleExpr(jstate, (Node *) rte->functions); - break; - case RTE_TABLEFUNC: - JumbleExpr(jstate, (Node *) rte->tablefunc); - break; - case RTE_VALUES: - JumbleExpr(jstate, (Node *) rte->values_lists); - break; - case RTE_CTE: - - /* - * Depending on the CTE name here isn't ideal, but it's the - * only info we have to identify the referenced WITH item. - */ - APP_JUMB_STRING(rte->ctename); - APP_JUMB(rte->ctelevelsup); - break; - case RTE_NAMEDTUPLESTORE: - APP_JUMB_STRING(rte->enrname); - break; - case RTE_RESULT: - break; - default: - elog(ERROR, "unrecognized RTE kind: %d", (int) rte->rtekind); - break; - } - } -} - -/* - * Jumble a rowMarks list - */ -static void -JumbleRowMarks(pgssJumbleState *jstate, List *rowMarks) -{ - ListCell *lc; - - foreach(lc, rowMarks) - { - RowMarkClause *rowmark = lfirst_node(RowMarkClause, lc); - - if (!rowmark->pushedDown) - { - APP_JUMB(rowmark->rti); - APP_JUMB(rowmark->strength); - APP_JUMB(rowmark->waitPolicy); - } - } -} - -/* - * Jumble an expression tree - * - * In general this function should handle all the same node types that - * expression_tree_walker() does, and therefore it's coded to be as parallel - * to that function as possible. However, since we are only invoked on - * queries immediately post-parse-analysis, we need not handle node types - * that only appear in planning. - * - * Note: the reason we don't simply use expression_tree_walker() is that the - * point of that function is to support tree walkers that don't care about - * most tree node types, but here we care about all types. We should complain - * about any unrecognized node type. - */ -static void -JumbleExpr(pgssJumbleState *jstate, Node *node) -{ - ListCell *temp; - - if (node == NULL) - return; - - /* Guard against stack overflow due to overly complex expressions */ - check_stack_depth(); - - /* - * We always emit the node's NodeTag, then any additional fields that are - * considered significant, and then we recurse to any child nodes. - */ - APP_JUMB(node->type); - - switch (nodeTag(node)) - { - case T_Var: - { - Var *var = (Var *) node; - - APP_JUMB(var->varno); - APP_JUMB(var->varattno); - APP_JUMB(var->varlevelsup); - } - break; - case T_Const: - { - Const *c = (Const *) node; - - /* We jumble only the constant's type, not its value */ - APP_JUMB(c->consttype); - /* Also, record its parse location for query normalization */ - RecordConstLocation(jstate, c->location); - } - break; - case T_Param: - { - Param *p = (Param *) node; - - APP_JUMB(p->paramkind); - APP_JUMB(p->paramid); - APP_JUMB(p->paramtype); - /* Also, track the highest external Param id */ - if (p->paramkind == PARAM_EXTERN && - p->paramid > jstate->highest_extern_param_id) - jstate->highest_extern_param_id = p->paramid; - } - break; - case T_Aggref: - { - Aggref *expr = (Aggref *) node; - - APP_JUMB(expr->aggfnoid); - JumbleExpr(jstate, (Node *) expr->aggdirectargs); - JumbleExpr(jstate, (Node *) expr->args); - JumbleExpr(jstate, (Node *) expr->aggorder); - JumbleExpr(jstate, (Node *) expr->aggdistinct); - JumbleExpr(jstate, (Node *) expr->aggfilter); - } - break; - case T_GroupingFunc: - { - GroupingFunc *grpnode = (GroupingFunc *) node; - - JumbleExpr(jstate, (Node *) grpnode->refs); - } - break; - case T_WindowFunc: - { - WindowFunc *expr = (WindowFunc *) node; - - APP_JUMB(expr->winfnoid); - APP_JUMB(expr->winref); - JumbleExpr(jstate, (Node *) expr->args); - JumbleExpr(jstate, (Node *) expr->aggfilter); - } - break; - case T_SubscriptingRef: - { - SubscriptingRef *sbsref = (SubscriptingRef *) node; - - JumbleExpr(jstate, (Node *) sbsref->refupperindexpr); - JumbleExpr(jstate, (Node *) sbsref->reflowerindexpr); - JumbleExpr(jstate, (Node *) sbsref->refexpr); - JumbleExpr(jstate, (Node *) sbsref->refassgnexpr); - } - break; - case T_FuncExpr: - { - FuncExpr *expr = (FuncExpr *) node; - - APP_JUMB(expr->funcid); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_NamedArgExpr: - { - NamedArgExpr *nae = (NamedArgExpr *) node; - - APP_JUMB(nae->argnumber); - JumbleExpr(jstate, (Node *) nae->arg); - } - break; - case T_OpExpr: - case T_DistinctExpr: /* struct-equivalent to OpExpr */ - case T_NullIfExpr: /* struct-equivalent to OpExpr */ - { - OpExpr *expr = (OpExpr *) node; - - APP_JUMB(expr->opno); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_ScalarArrayOpExpr: - { - ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node; - - APP_JUMB(expr->opno); - APP_JUMB(expr->useOr); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_BoolExpr: - { - BoolExpr *expr = (BoolExpr *) node; - - APP_JUMB(expr->boolop); - JumbleExpr(jstate, (Node *) expr->args); - } - break; - case T_SubLink: - { - SubLink *sublink = (SubLink *) node; - - APP_JUMB(sublink->subLinkType); - APP_JUMB(sublink->subLinkId); - JumbleExpr(jstate, (Node *) sublink->testexpr); - JumbleQuery(jstate, castNode(Query, sublink->subselect)); - } - break; - case T_FieldSelect: - { - FieldSelect *fs = (FieldSelect *) node; - - APP_JUMB(fs->fieldnum); - JumbleExpr(jstate, (Node *) fs->arg); - } - break; - case T_FieldStore: - { - FieldStore *fstore = (FieldStore *) node; - - JumbleExpr(jstate, (Node *) fstore->arg); - JumbleExpr(jstate, (Node *) fstore->newvals); - } - break; - case T_RelabelType: - { - RelabelType *rt = (RelabelType *) node; - - APP_JUMB(rt->resulttype); - JumbleExpr(jstate, (Node *) rt->arg); - } - break; - case T_CoerceViaIO: - { - CoerceViaIO *cio = (CoerceViaIO *) node; - - APP_JUMB(cio->resulttype); - JumbleExpr(jstate, (Node *) cio->arg); - } - break; - case T_ArrayCoerceExpr: - { - ArrayCoerceExpr *acexpr = (ArrayCoerceExpr *) node; - - APP_JUMB(acexpr->resulttype); - JumbleExpr(jstate, (Node *) acexpr->arg); - JumbleExpr(jstate, (Node *) acexpr->elemexpr); - } - break; - case T_ConvertRowtypeExpr: - { - ConvertRowtypeExpr *crexpr = (ConvertRowtypeExpr *) node; - - APP_JUMB(crexpr->resulttype); - JumbleExpr(jstate, (Node *) crexpr->arg); - } - break; - case T_CollateExpr: - { - CollateExpr *ce = (CollateExpr *) node; - - APP_JUMB(ce->collOid); - JumbleExpr(jstate, (Node *) ce->arg); - } - break; - case T_CaseExpr: - { - CaseExpr *caseexpr = (CaseExpr *) node; - - JumbleExpr(jstate, (Node *) caseexpr->arg); - foreach(temp, caseexpr->args) - { - CaseWhen *when = lfirst_node(CaseWhen, temp); - - JumbleExpr(jstate, (Node *) when->expr); - JumbleExpr(jstate, (Node *) when->result); - } - JumbleExpr(jstate, (Node *) caseexpr->defresult); - } - break; - case T_CaseTestExpr: - { - CaseTestExpr *ct = (CaseTestExpr *) node; - - APP_JUMB(ct->typeId); - } - break; - case T_ArrayExpr: - JumbleExpr(jstate, (Node *) ((ArrayExpr *) node)->elements); - break; - case T_RowExpr: - JumbleExpr(jstate, (Node *) ((RowExpr *) node)->args); - break; - case T_RowCompareExpr: - { - RowCompareExpr *rcexpr = (RowCompareExpr *) node; - - APP_JUMB(rcexpr->rctype); - JumbleExpr(jstate, (Node *) rcexpr->largs); - JumbleExpr(jstate, (Node *) rcexpr->rargs); - } - break; - case T_CoalesceExpr: - JumbleExpr(jstate, (Node *) ((CoalesceExpr *) node)->args); - break; - case T_MinMaxExpr: - { - MinMaxExpr *mmexpr = (MinMaxExpr *) node; - - APP_JUMB(mmexpr->op); - JumbleExpr(jstate, (Node *) mmexpr->args); - } - break; - case T_SQLValueFunction: - { - SQLValueFunction *svf = (SQLValueFunction *) node; - - APP_JUMB(svf->op); - /* type is fully determined by op */ - APP_JUMB(svf->typmod); - } - break; - case T_XmlExpr: - { - XmlExpr *xexpr = (XmlExpr *) node; - - APP_JUMB(xexpr->op); - JumbleExpr(jstate, (Node *) xexpr->named_args); - JumbleExpr(jstate, (Node *) xexpr->args); - } - break; - case T_NullTest: - { - NullTest *nt = (NullTest *) node; - - APP_JUMB(nt->nulltesttype); - JumbleExpr(jstate, (Node *) nt->arg); - } - break; - case T_BooleanTest: - { - BooleanTest *bt = (BooleanTest *) node; - - APP_JUMB(bt->booltesttype); - JumbleExpr(jstate, (Node *) bt->arg); - } - break; - case T_CoerceToDomain: - { - CoerceToDomain *cd = (CoerceToDomain *) node; - - APP_JUMB(cd->resulttype); - JumbleExpr(jstate, (Node *) cd->arg); - } - break; - case T_CoerceToDomainValue: - { - CoerceToDomainValue *cdv = (CoerceToDomainValue *) node; - - APP_JUMB(cdv->typeId); - } - break; - case T_SetToDefault: - { - SetToDefault *sd = (SetToDefault *) node; - - APP_JUMB(sd->typeId); - } - break; - case T_CurrentOfExpr: - { - CurrentOfExpr *ce = (CurrentOfExpr *) node; - - APP_JUMB(ce->cvarno); - if (ce->cursor_name) - APP_JUMB_STRING(ce->cursor_name); - APP_JUMB(ce->cursor_param); - } - break; - case T_NextValueExpr: - { - NextValueExpr *nve = (NextValueExpr *) node; - - APP_JUMB(nve->seqid); - APP_JUMB(nve->typeId); - } - break; - case T_InferenceElem: - { - InferenceElem *ie = (InferenceElem *) node; - - APP_JUMB(ie->infercollid); - APP_JUMB(ie->inferopclass); - JumbleExpr(jstate, ie->expr); - } - break; - case T_TargetEntry: - { - TargetEntry *tle = (TargetEntry *) node; - - APP_JUMB(tle->resno); - APP_JUMB(tle->ressortgroupref); - JumbleExpr(jstate, (Node *) tle->expr); - } - break; - case T_RangeTblRef: - { - RangeTblRef *rtr = (RangeTblRef *) node; - - APP_JUMB(rtr->rtindex); - } - break; - case T_JoinExpr: - { - JoinExpr *join = (JoinExpr *) node; - - APP_JUMB(join->jointype); - APP_JUMB(join->isNatural); - APP_JUMB(join->rtindex); - JumbleExpr(jstate, join->larg); - JumbleExpr(jstate, join->rarg); - JumbleExpr(jstate, join->quals); - } - break; - case T_FromExpr: - { - FromExpr *from = (FromExpr *) node; - - JumbleExpr(jstate, (Node *) from->fromlist); - JumbleExpr(jstate, from->quals); - } - break; - case T_OnConflictExpr: - { - OnConflictExpr *conf = (OnConflictExpr *) node; - - APP_JUMB(conf->action); - JumbleExpr(jstate, (Node *) conf->arbiterElems); - JumbleExpr(jstate, conf->arbiterWhere); - JumbleExpr(jstate, (Node *) conf->onConflictSet); - JumbleExpr(jstate, conf->onConflictWhere); - APP_JUMB(conf->constraint); - APP_JUMB(conf->exclRelIndex); - JumbleExpr(jstate, (Node *) conf->exclRelTlist); - } - break; - case T_List: - foreach(temp, (List *) node) - { - JumbleExpr(jstate, (Node *) lfirst(temp)); - } - break; - case T_IntList: - foreach(temp, (List *) node) - { - APP_JUMB(lfirst_int(temp)); - } - break; - case T_SortGroupClause: - { - SortGroupClause *sgc = (SortGroupClause *) node; - - APP_JUMB(sgc->tleSortGroupRef); - APP_JUMB(sgc->eqop); - APP_JUMB(sgc->sortop); - APP_JUMB(sgc->nulls_first); - } - break; - case T_GroupingSet: - { - GroupingSet *gsnode = (GroupingSet *) node; - - JumbleExpr(jstate, (Node *) gsnode->content); - } - break; - case T_WindowClause: - { - WindowClause *wc = (WindowClause *) node; - - APP_JUMB(wc->winref); - APP_JUMB(wc->frameOptions); - JumbleExpr(jstate, (Node *) wc->partitionClause); - JumbleExpr(jstate, (Node *) wc->orderClause); - JumbleExpr(jstate, wc->startOffset); - JumbleExpr(jstate, wc->endOffset); - } - break; - case T_CommonTableExpr: - { - CommonTableExpr *cte = (CommonTableExpr *) node; - - /* we store the string name because RTE_CTE RTEs need it */ - APP_JUMB_STRING(cte->ctename); - APP_JUMB(cte->ctematerialized); - JumbleQuery(jstate, castNode(Query, cte->ctequery)); - } - break; - case T_SetOperationStmt: - { - SetOperationStmt *setop = (SetOperationStmt *) node; - - APP_JUMB(setop->op); - APP_JUMB(setop->all); - JumbleExpr(jstate, setop->larg); - JumbleExpr(jstate, setop->rarg); - } - break; - case T_RangeTblFunction: - { - RangeTblFunction *rtfunc = (RangeTblFunction *) node; - - JumbleExpr(jstate, rtfunc->funcexpr); - } - break; - case T_TableFunc: - { - TableFunc *tablefunc = (TableFunc *) node; - - JumbleExpr(jstate, tablefunc->docexpr); - JumbleExpr(jstate, tablefunc->rowexpr); - JumbleExpr(jstate, (Node *) tablefunc->colexprs); - } - break; - case T_TableSampleClause: - { - TableSampleClause *tsc = (TableSampleClause *) node; - - APP_JUMB(tsc->tsmhandler); - JumbleExpr(jstate, (Node *) tsc->args); - JumbleExpr(jstate, (Node *) tsc->repeatable); - } - break; - default: - /* Only a warning, since we can stumble along anyway */ - elog(WARNING, "unrecognized node type: %d", - (int) nodeTag(node)); - break; - } -} - -/* - * Record location of constant within query string of query tree - * that is currently being walked. - */ -static void -RecordConstLocation(pgssJumbleState *jstate, int location) -{ - /* -1 indicates unknown or undefined location */ - if (location >= 0) - { - /* enlarge array if needed */ - if (jstate->clocations_count >= jstate->clocations_buf_size) - { - jstate->clocations_buf_size *= 2; - jstate->clocations = (pgssLocationLen *) - repalloc(jstate->clocations, - jstate->clocations_buf_size * - sizeof(pgssLocationLen)); - } - jstate->clocations[jstate->clocations_count].location = location; - /* initialize lengths to -1 to simplify fill_in_constant_lengths */ - jstate->clocations[jstate->clocations_count].length = -1; - jstate->clocations_count++; - } -} - /* * Generate a normalized version of the query string that will be used to * represent all similar queries. @@ -3319,7 +2564,7 @@ RecordConstLocation(pgssJumbleState *jstate, int location) * Returns a palloc'd string. */ static char * -generate_normalized_query(pgssJumbleState *jstate, const char *query, +generate_normalized_query(JumbleState *jstate, const char *query, int query_loc, int *query_len_p) { char *norm_query; @@ -3426,10 +2671,10 @@ generate_normalized_query(pgssJumbleState *jstate, const char *query, * reason for a constant to start with a '-'. */ static void -fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, +fill_in_constant_lengths(JumbleState *jstate, const char *query, int query_loc) { - pgssLocationLen *locs; + LocationLen *locs; core_yyscan_t yyscanner; core_yy_extra_type yyextra; core_YYSTYPE yylval; @@ -3443,7 +2688,7 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, */ if (jstate->clocations_count > 1) qsort(jstate->clocations, jstate->clocations_count, - sizeof(pgssLocationLen), comp_location); + sizeof(LocationLen), comp_location); locs = jstate->clocations; /* initialize the flex scanner --- should match raw_parser() */ @@ -3523,13 +2768,13 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query, } /* - * comp_location: comparator for qsorting pgssLocationLen structs by location + * comp_location: comparator for qsorting LocationLen structs by location */ static int comp_location(const void *a, const void *b) { - int l = ((const pgssLocationLen *) a)->location; - int r = ((const pgssLocationLen *) b)->location; + int l = ((const LocationLen *) a)->location; + int r = ((const LocationLen *) b)->location; if (l < r) return -1; diff --git a/contrib/pg_stat_statements/pg_stat_statements.conf b/contrib/pg_stat_statements/pg_stat_statements.conf index 13346e2807..e47b26040f 100644 --- a/contrib/pg_stat_statements/pg_stat_statements.conf +++ b/contrib/pg_stat_statements/pg_stat_statements.conf @@ -1 +1,2 @@ shared_preload_libraries = 'pg_stat_statements' +compute_query_id = on diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 1f0e0fc1fb..d1aa746224 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -7538,6 +7538,31 @@ COPY postgres_log FROM '/full/path/to/logfile.csv' WITH csv; <title>Statistics Monitoring</title> <variablelist> + <varlistentry id="guc-compute-query-id" xreflabel="compute_query_id"> + <term><varname>compute_query_id</varname> (<type>boolean</type>) + <indexterm> + <primary><varname>compute_query_id</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Enables in-core computation of a query identifier. The <xref + linkend="pgstatstatements"/> extension requires a query identifier + to be computed. Note that an external module can alternatively + be used if the in-core query identifier computation method + isn't acceptable. In this case, in-core computation should + remain disabled. The default is <literal>off</literal>. + </para> + <note> + <para> + To ensure that a only one query identifier is calculated and + displayed, extensions that calculate query identifiers should + throw an error if a query identifier has already been computed. + </para> + </note> + </listitem> + </varlistentry> + <varlistentry> <term><varname>log_statement_stats</varname> (<type>boolean</type>) <indexterm> diff --git a/doc/src/sgml/pgstatstatements.sgml b/doc/src/sgml/pgstatstatements.sgml index 464bf0e5ae..3ca292d71f 100644 --- a/doc/src/sgml/pgstatstatements.sgml +++ b/doc/src/sgml/pgstatstatements.sgml @@ -20,6 +20,14 @@ This means that a server restart is needed to add or remove the module. </para> + <para> + The module will not track statistics unless query + identifiers are calculated. This can be done by enabling <xref + linkend="guc-compute-query-id"/> or using a third-party module that + computes its own query identifiers. Note that all statistics tracked + by this module must be reset if the query identifier method is changed. + </para> + <para> When <filename>pg_stat_statements</filename> is loaded, it tracks statistics across all databases of the server. To access and manipulate @@ -84,7 +92,7 @@ <structfield>queryid</structfield> <type>bigint</type> </para> <para> - Internal hash code, computed from the statement's parse tree + Hash code to identify identical normalized queries. </para></entry> </row> @@ -386,6 +394,16 @@ are compared strictly on the basis of their textual query strings, however. </para> + <note> + <para> + The following details about constant replacement and + <structfield>queryid</structfield> only applies when <xref + linkend="guc-compute-query-id"/> is enabled. If you use an external + module instead to compute <structfield>queryid</structfield>, you + should refer to its documentation for details. + </para> + </note> + <para> When a constant's value has been ignored for purposes of matching the query to other queries, the constant is replaced by a parameter symbol, such diff --git a/src/backend/parser/analyze.c b/src/backend/parser/analyze.c index 7149724953..c565c80365 100644 --- a/src/backend/parser/analyze.c +++ b/src/backend/parser/analyze.c @@ -46,6 +46,8 @@ #include "parser/parsetree.h" #include "rewrite/rewriteManip.h" #include "utils/builtins.h" +#include "utils/guc.h" +#include "utils/queryjumble.h" #include "utils/rel.h" @@ -107,6 +109,7 @@ parse_analyze(RawStmt *parseTree, const char *sourceText, { ParseState *pstate = make_parsestate(NULL); Query *query; + JumbleState *jstate = NULL; Assert(sourceText != NULL); /* required as of 8.4 */ @@ -119,8 +122,11 @@ parse_analyze(RawStmt *parseTree, const char *sourceText, query = transformTopLevelStmt(pstate, parseTree); + if (compute_query_id) + jstate = JumbleQuery(query, sourceText); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); @@ -140,6 +146,7 @@ parse_analyze_varparams(RawStmt *parseTree, const char *sourceText, { ParseState *pstate = make_parsestate(NULL); Query *query; + JumbleState *jstate = NULL; Assert(sourceText != NULL); /* required as of 8.4 */ @@ -152,8 +159,11 @@ parse_analyze_varparams(RawStmt *parseTree, const char *sourceText, /* make sure all is well with parameter types */ check_variable_parameters(pstate, query); + if (compute_query_id) + jstate = JumbleQuery(query, sourceText); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index 2b1b68109f..7e034b72b1 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -665,6 +665,7 @@ pg_analyze_and_rewrite_params(RawStmt *parsetree, ParseState *pstate; Query *query; List *querytree_list; + JumbleState *jstate = NULL; Assert(query_string != NULL); /* required as of 8.4 */ @@ -683,8 +684,11 @@ pg_analyze_and_rewrite_params(RawStmt *parsetree, query = transformTopLevelStmt(pstate, parsetree); + if (compute_query_id) + jstate = JumbleQuery(query, query_string); + if (post_parse_analyze_hook) - (*post_parse_analyze_hook) (pstate, query); + (*post_parse_analyze_hook) (pstate, query, jstate); free_parsestate(pstate); diff --git a/src/backend/utils/misc/Makefile b/src/backend/utils/misc/Makefile index 2397fc2453..1d5327cf64 100644 --- a/src/backend/utils/misc/Makefile +++ b/src/backend/utils/misc/Makefile @@ -22,6 +22,7 @@ OBJS = \ pg_rusage.o \ ps_status.o \ queryenvironment.o \ + queryjumble.o \ rls.o \ sampling.o \ superuser.o \ diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index 8bfaa53541..87287ac13e 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -521,6 +521,7 @@ extern const struct config_enum_entry dynamic_shared_memory_options[]; /* * GUC option variables that are exported from this module */ +bool compute_query_id = false; bool log_duration = false; bool Debug_print_plan = false; bool Debug_print_parse = false; @@ -1425,6 +1426,15 @@ static struct config_bool ConfigureNamesBool[] = true, NULL, NULL, NULL }, + { + {"compute_query_id", PGC_SUSET, STATS_MONITORING, + gettext_noop("Compute query identifiers."), + NULL + }, + &compute_query_id, + false, + NULL, NULL, NULL + }, { {"log_parser_stats", PGC_SUSET, STATS_MONITORING, gettext_noop("Writes parser performance statistics to the server log."), diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 74b416b74a..aa34c99f0c 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -594,6 +594,7 @@ # - Monitoring - +#compute_query_id = off #log_parser_stats = off #log_planner_stats = off #log_executor_stats = off diff --git a/src/backend/utils/misc/queryjumble.c b/src/backend/utils/misc/queryjumble.c new file mode 100644 index 0000000000..2a47688fd6 --- /dev/null +++ b/src/backend/utils/misc/queryjumble.c @@ -0,0 +1,834 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.c + * Query normalization and fingerprinting. + * + * Normalization is a process whereby similar queries, typically differing only + * in their constants (though the exact rules are somewhat more subtle than + * that) are recognized as equivalent, and are tracked as a single entry. This + * is particularly useful for non-prepared queries. + * + * Normalization is implemented by fingerprinting queries, selectively + * serializing those fields of each query tree's nodes that are judged to be + * essential to the query. This is referred to as a query jumble. This is + * distinct from a regular serialization in that various extraneous + * information is ignored as irrelevant or not essential to the query, such + * as the collations of Vars and, most notably, the values of constants. + * + * This jumble is acquired at the end of parse analysis of each query, and + * a 64-bit hash of it is stored into the query's Query.queryId field. + * The server then copies this value around, making it available in plan + * tree(s) generated from the query. The executor can then use this value + * to blame query costs on the proper queryId. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * + * IDENTIFICATION + * src/backend/utils/misc/queryjumble.c + * + *------------------------------------------------------------------------- + */ +#include "postgres.h" + +#include "common/hashfn.h" +#include "miscadmin.h" +#include "parser/scansup.h" +#include "utils/queryjumble.h" + +#define JUMBLE_SIZE 1024 /* query serialization buffer size */ + +static uint64 compute_utility_queryid(const char *str, int query_len); +static void AppendJumble(JumbleState *jstate, + const unsigned char *item, Size size); +static void JumbleQueryInternal(JumbleState *jstate, Query *query); +static void JumbleRangeTable(JumbleState *jstate, List *rtable); +static void JumbleRowMarks(JumbleState *jstate, List *rowMarks); +static void JumbleExpr(JumbleState *jstate, Node *node); +static void RecordConstLocation(JumbleState *jstate, int location); + +/* + * Given a possibly multi-statement source string, confine our attention to the + * relevant part of the string. + */ +const char * +CleanQuerytext(const char *query, int *location, int *len) +{ + int query_location = *location; + int query_len = *len; + + /* First apply starting offset, unless it's -1 (unknown). */ + if (query_location >= 0) + { + Assert(query_location <= strlen(query)); + query += query_location; + /* Length of 0 (or -1) means "rest of string" */ + if (query_len <= 0) + query_len = strlen(query); + else + Assert(query_len <= strlen(query)); + } + else + { + /* If query location is unknown, distrust query_len as well */ + query_location = 0; + query_len = strlen(query); + } + + /* + * Discard leading and trailing whitespace, too. Use scanner_isspace() + * not libc's isspace(), because we want to match the lexer's behavior. + */ + while (query_len > 0 && scanner_isspace(query[0])) + query++, query_location++, query_len--; + while (query_len > 0 && scanner_isspace(query[query_len - 1])) + query_len--; + + *location = query_location; + *len = query_len; + + return query; +} + +JumbleState * +JumbleQuery(Query *query, const char *querytext) +{ + JumbleState *jstate = NULL; + if (query->utilityStmt) + { + const char *sql; + int query_location = query->stmt_location; + int query_len = query->stmt_len; + + /* + * Confine our attention to the relevant part of the string, if the + * query is a portion of a multi-statement source string. + */ + sql = CleanQuerytext(querytext, &query_location, &query_len); + + query->queryId = compute_utility_queryid(sql, query_len); + } + else + { + jstate = (JumbleState *) palloc(sizeof(JumbleState)); + + /* Set up workspace for query jumbling */ + jstate->jumble = (unsigned char *) palloc(JUMBLE_SIZE); + jstate->jumble_len = 0; + jstate->clocations_buf_size = 32; + jstate->clocations = (LocationLen *) + palloc(jstate->clocations_buf_size * sizeof(LocationLen)); + jstate->clocations_count = 0; + jstate->highest_extern_param_id = 0; + + /* Compute query ID and mark the Query node with it */ + JumbleQueryInternal(jstate, query); + query->queryId = DatumGetUInt64(hash_any_extended(jstate->jumble, + jstate->jumble_len, + 0)); + + /* + * If we are unlucky enough to get a hash of zero, use 1 instead, to + * prevent confusion with the utility-statement case. + */ + if (query->queryId == UINT64CONST(0)) + query->queryId = UINT64CONST(1); + } + + return jstate; +} + +/* + * Compute a query identifier for the given utility query string. + */ +static uint64 +compute_utility_queryid(const char *str, int query_len) +{ + uint64 queryId; + + queryId = DatumGetUInt64(hash_any_extended((const unsigned char *) str, + query_len, 0)); + + /* + * If we are unlucky enough to get a hash of zero(invalid), use + * queryID as 2 instead, queryID 1 is already in use for normal + * statements. + */ + if (queryId == UINT64CONST(0)) + queryId = UINT64CONST(2); + + return queryId; +} + +/* + * AppendJumble: Append a value that is substantive in a given query to + * the current jumble. + */ +static void +AppendJumble(JumbleState *jstate, const unsigned char *item, Size size) +{ + unsigned char *jumble = jstate->jumble; + Size jumble_len = jstate->jumble_len; + + /* + * Whenever the jumble buffer is full, we hash the current contents and + * reset the buffer to contain just that hash value, thus relying on the + * hash to summarize everything so far. + */ + while (size > 0) + { + Size part_size; + + if (jumble_len >= JUMBLE_SIZE) + { + uint64 start_hash; + + start_hash = DatumGetUInt64(hash_any_extended(jumble, + JUMBLE_SIZE, 0)); + memcpy(jumble, &start_hash, sizeof(start_hash)); + jumble_len = sizeof(start_hash); + } + part_size = Min(size, JUMBLE_SIZE - jumble_len); + memcpy(jumble + jumble_len, item, part_size); + jumble_len += part_size; + item += part_size; + size -= part_size; + } + jstate->jumble_len = jumble_len; +} + +/* + * Wrappers around AppendJumble to encapsulate details of serialization + * of individual local variable elements. + */ +#define APP_JUMB(item) \ + AppendJumble(jstate, (const unsigned char *) &(item), sizeof(item)) +#define APP_JUMB_STRING(str) \ + AppendJumble(jstate, (const unsigned char *) (str), strlen(str) + 1) + +/* + * JumbleQueryInternal: Selectively serialize the query tree, appending + * significant data to the "query jumble" while ignoring nonsignificant data. + * + * Rule of thumb for what to include is that we should ignore anything not + * semantically significant (such as alias names) as well as anything that can + * be deduced from child nodes (else we'd just be double-hashing that piece + * of information). + */ +static void +JumbleQueryInternal(JumbleState *jstate, Query *query) +{ + Assert(IsA(query, Query)); + Assert(query->utilityStmt == NULL); + + APP_JUMB(query->commandType); + /* resultRelation is usually predictable from commandType */ + JumbleExpr(jstate, (Node *) query->cteList); + JumbleRangeTable(jstate, query->rtable); + JumbleExpr(jstate, (Node *) query->jointree); + JumbleExpr(jstate, (Node *) query->targetList); + JumbleExpr(jstate, (Node *) query->onConflict); + JumbleExpr(jstate, (Node *) query->returningList); + JumbleExpr(jstate, (Node *) query->groupClause); + JumbleExpr(jstate, (Node *) query->groupingSets); + JumbleExpr(jstate, query->havingQual); + JumbleExpr(jstate, (Node *) query->windowClause); + JumbleExpr(jstate, (Node *) query->distinctClause); + JumbleExpr(jstate, (Node *) query->sortClause); + JumbleExpr(jstate, query->limitOffset); + JumbleExpr(jstate, query->limitCount); + JumbleRowMarks(jstate, query->rowMarks); + JumbleExpr(jstate, query->setOperations); +} + +/* + * Jumble a range table + */ +static void +JumbleRangeTable(JumbleState *jstate, List *rtable) +{ + ListCell *lc; + + foreach(lc, rtable) + { + RangeTblEntry *rte = lfirst_node(RangeTblEntry, lc); + + APP_JUMB(rte->rtekind); + switch (rte->rtekind) + { + case RTE_RELATION: + APP_JUMB(rte->relid); + JumbleExpr(jstate, (Node *) rte->tablesample); + break; + case RTE_SUBQUERY: + JumbleQueryInternal(jstate, rte->subquery); + break; + case RTE_JOIN: + APP_JUMB(rte->jointype); + break; + case RTE_FUNCTION: + JumbleExpr(jstate, (Node *) rte->functions); + break; + case RTE_TABLEFUNC: + JumbleExpr(jstate, (Node *) rte->tablefunc); + break; + case RTE_VALUES: + JumbleExpr(jstate, (Node *) rte->values_lists); + break; + case RTE_CTE: + + /* + * Depending on the CTE name here isn't ideal, but it's the + * only info we have to identify the referenced WITH item. + */ + APP_JUMB_STRING(rte->ctename); + APP_JUMB(rte->ctelevelsup); + break; + case RTE_NAMEDTUPLESTORE: + APP_JUMB_STRING(rte->enrname); + break; + case RTE_RESULT: + break; + default: + elog(ERROR, "unrecognized RTE kind: %d", (int) rte->rtekind); + break; + } + } +} + +/* + * Jumble a rowMarks list + */ +static void +JumbleRowMarks(JumbleState *jstate, List *rowMarks) +{ + ListCell *lc; + + foreach(lc, rowMarks) + { + RowMarkClause *rowmark = lfirst_node(RowMarkClause, lc); + + if (!rowmark->pushedDown) + { + APP_JUMB(rowmark->rti); + APP_JUMB(rowmark->strength); + APP_JUMB(rowmark->waitPolicy); + } + } +} + +/* + * Jumble an expression tree + * + * In general this function should handle all the same node types that + * expression_tree_walker() does, and therefore it's coded to be as parallel + * to that function as possible. However, since we are only invoked on + * queries immediately post-parse-analysis, we need not handle node types + * that only appear in planning. + * + * Note: the reason we don't simply use expression_tree_walker() is that the + * point of that function is to support tree walkers that don't care about + * most tree node types, but here we care about all types. We should complain + * about any unrecognized node type. + */ +static void +JumbleExpr(JumbleState *jstate, Node *node) +{ + ListCell *temp; + + if (node == NULL) + return; + + /* Guard against stack overflow due to overly complex expressions */ + check_stack_depth(); + + /* + * We always emit the node's NodeTag, then any additional fields that are + * considered significant, and then we recurse to any child nodes. + */ + APP_JUMB(node->type); + + switch (nodeTag(node)) + { + case T_Var: + { + Var *var = (Var *) node; + + APP_JUMB(var->varno); + APP_JUMB(var->varattno); + APP_JUMB(var->varlevelsup); + } + break; + case T_Const: + { + Const *c = (Const *) node; + + /* We jumble only the constant's type, not its value */ + APP_JUMB(c->consttype); + /* Also, record its parse location for query normalization */ + RecordConstLocation(jstate, c->location); + } + break; + case T_Param: + { + Param *p = (Param *) node; + + APP_JUMB(p->paramkind); + APP_JUMB(p->paramid); + APP_JUMB(p->paramtype); + /* Also, track the highest external Param id */ + if (p->paramkind == PARAM_EXTERN && + p->paramid > jstate->highest_extern_param_id) + jstate->highest_extern_param_id = p->paramid; + } + break; + case T_Aggref: + { + Aggref *expr = (Aggref *) node; + + APP_JUMB(expr->aggfnoid); + JumbleExpr(jstate, (Node *) expr->aggdirectargs); + JumbleExpr(jstate, (Node *) expr->args); + JumbleExpr(jstate, (Node *) expr->aggorder); + JumbleExpr(jstate, (Node *) expr->aggdistinct); + JumbleExpr(jstate, (Node *) expr->aggfilter); + } + break; + case T_GroupingFunc: + { + GroupingFunc *grpnode = (GroupingFunc *) node; + + JumbleExpr(jstate, (Node *) grpnode->refs); + } + break; + case T_WindowFunc: + { + WindowFunc *expr = (WindowFunc *) node; + + APP_JUMB(expr->winfnoid); + APP_JUMB(expr->winref); + JumbleExpr(jstate, (Node *) expr->args); + JumbleExpr(jstate, (Node *) expr->aggfilter); + } + break; + case T_SubscriptingRef: + { + SubscriptingRef *sbsref = (SubscriptingRef *) node; + + JumbleExpr(jstate, (Node *) sbsref->refupperindexpr); + JumbleExpr(jstate, (Node *) sbsref->reflowerindexpr); + JumbleExpr(jstate, (Node *) sbsref->refexpr); + JumbleExpr(jstate, (Node *) sbsref->refassgnexpr); + } + break; + case T_FuncExpr: + { + FuncExpr *expr = (FuncExpr *) node; + + APP_JUMB(expr->funcid); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_NamedArgExpr: + { + NamedArgExpr *nae = (NamedArgExpr *) node; + + APP_JUMB(nae->argnumber); + JumbleExpr(jstate, (Node *) nae->arg); + } + break; + case T_OpExpr: + case T_DistinctExpr: /* struct-equivalent to OpExpr */ + case T_NullIfExpr: /* struct-equivalent to OpExpr */ + { + OpExpr *expr = (OpExpr *) node; + + APP_JUMB(expr->opno); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_ScalarArrayOpExpr: + { + ScalarArrayOpExpr *expr = (ScalarArrayOpExpr *) node; + + APP_JUMB(expr->opno); + APP_JUMB(expr->useOr); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_BoolExpr: + { + BoolExpr *expr = (BoolExpr *) node; + + APP_JUMB(expr->boolop); + JumbleExpr(jstate, (Node *) expr->args); + } + break; + case T_SubLink: + { + SubLink *sublink = (SubLink *) node; + + APP_JUMB(sublink->subLinkType); + APP_JUMB(sublink->subLinkId); + JumbleExpr(jstate, (Node *) sublink->testexpr); + JumbleQueryInternal(jstate, castNode(Query, sublink->subselect)); + } + break; + case T_FieldSelect: + { + FieldSelect *fs = (FieldSelect *) node; + + APP_JUMB(fs->fieldnum); + JumbleExpr(jstate, (Node *) fs->arg); + } + break; + case T_FieldStore: + { + FieldStore *fstore = (FieldStore *) node; + + JumbleExpr(jstate, (Node *) fstore->arg); + JumbleExpr(jstate, (Node *) fstore->newvals); + } + break; + case T_RelabelType: + { + RelabelType *rt = (RelabelType *) node; + + APP_JUMB(rt->resulttype); + JumbleExpr(jstate, (Node *) rt->arg); + } + break; + case T_CoerceViaIO: + { + CoerceViaIO *cio = (CoerceViaIO *) node; + + APP_JUMB(cio->resulttype); + JumbleExpr(jstate, (Node *) cio->arg); + } + break; + case T_ArrayCoerceExpr: + { + ArrayCoerceExpr *acexpr = (ArrayCoerceExpr *) node; + + APP_JUMB(acexpr->resulttype); + JumbleExpr(jstate, (Node *) acexpr->arg); + JumbleExpr(jstate, (Node *) acexpr->elemexpr); + } + break; + case T_ConvertRowtypeExpr: + { + ConvertRowtypeExpr *crexpr = (ConvertRowtypeExpr *) node; + + APP_JUMB(crexpr->resulttype); + JumbleExpr(jstate, (Node *) crexpr->arg); + } + break; + case T_CollateExpr: + { + CollateExpr *ce = (CollateExpr *) node; + + APP_JUMB(ce->collOid); + JumbleExpr(jstate, (Node *) ce->arg); + } + break; + case T_CaseExpr: + { + CaseExpr *caseexpr = (CaseExpr *) node; + + JumbleExpr(jstate, (Node *) caseexpr->arg); + foreach(temp, caseexpr->args) + { + CaseWhen *when = lfirst_node(CaseWhen, temp); + + JumbleExpr(jstate, (Node *) when->expr); + JumbleExpr(jstate, (Node *) when->result); + } + JumbleExpr(jstate, (Node *) caseexpr->defresult); + } + break; + case T_CaseTestExpr: + { + CaseTestExpr *ct = (CaseTestExpr *) node; + + APP_JUMB(ct->typeId); + } + break; + case T_ArrayExpr: + JumbleExpr(jstate, (Node *) ((ArrayExpr *) node)->elements); + break; + case T_RowExpr: + JumbleExpr(jstate, (Node *) ((RowExpr *) node)->args); + break; + case T_RowCompareExpr: + { + RowCompareExpr *rcexpr = (RowCompareExpr *) node; + + APP_JUMB(rcexpr->rctype); + JumbleExpr(jstate, (Node *) rcexpr->largs); + JumbleExpr(jstate, (Node *) rcexpr->rargs); + } + break; + case T_CoalesceExpr: + JumbleExpr(jstate, (Node *) ((CoalesceExpr *) node)->args); + break; + case T_MinMaxExpr: + { + MinMaxExpr *mmexpr = (MinMaxExpr *) node; + + APP_JUMB(mmexpr->op); + JumbleExpr(jstate, (Node *) mmexpr->args); + } + break; + case T_SQLValueFunction: + { + SQLValueFunction *svf = (SQLValueFunction *) node; + + APP_JUMB(svf->op); + /* type is fully determined by op */ + APP_JUMB(svf->typmod); + } + break; + case T_XmlExpr: + { + XmlExpr *xexpr = (XmlExpr *) node; + + APP_JUMB(xexpr->op); + JumbleExpr(jstate, (Node *) xexpr->named_args); + JumbleExpr(jstate, (Node *) xexpr->args); + } + break; + case T_NullTest: + { + NullTest *nt = (NullTest *) node; + + APP_JUMB(nt->nulltesttype); + JumbleExpr(jstate, (Node *) nt->arg); + } + break; + case T_BooleanTest: + { + BooleanTest *bt = (BooleanTest *) node; + + APP_JUMB(bt->booltesttype); + JumbleExpr(jstate, (Node *) bt->arg); + } + break; + case T_CoerceToDomain: + { + CoerceToDomain *cd = (CoerceToDomain *) node; + + APP_JUMB(cd->resulttype); + JumbleExpr(jstate, (Node *) cd->arg); + } + break; + case T_CoerceToDomainValue: + { + CoerceToDomainValue *cdv = (CoerceToDomainValue *) node; + + APP_JUMB(cdv->typeId); + } + break; + case T_SetToDefault: + { + SetToDefault *sd = (SetToDefault *) node; + + APP_JUMB(sd->typeId); + } + break; + case T_CurrentOfExpr: + { + CurrentOfExpr *ce = (CurrentOfExpr *) node; + + APP_JUMB(ce->cvarno); + if (ce->cursor_name) + APP_JUMB_STRING(ce->cursor_name); + APP_JUMB(ce->cursor_param); + } + break; + case T_NextValueExpr: + { + NextValueExpr *nve = (NextValueExpr *) node; + + APP_JUMB(nve->seqid); + APP_JUMB(nve->typeId); + } + break; + case T_InferenceElem: + { + InferenceElem *ie = (InferenceElem *) node; + + APP_JUMB(ie->infercollid); + APP_JUMB(ie->inferopclass); + JumbleExpr(jstate, ie->expr); + } + break; + case T_TargetEntry: + { + TargetEntry *tle = (TargetEntry *) node; + + APP_JUMB(tle->resno); + APP_JUMB(tle->ressortgroupref); + JumbleExpr(jstate, (Node *) tle->expr); + } + break; + case T_RangeTblRef: + { + RangeTblRef *rtr = (RangeTblRef *) node; + + APP_JUMB(rtr->rtindex); + } + break; + case T_JoinExpr: + { + JoinExpr *join = (JoinExpr *) node; + + APP_JUMB(join->jointype); + APP_JUMB(join->isNatural); + APP_JUMB(join->rtindex); + JumbleExpr(jstate, join->larg); + JumbleExpr(jstate, join->rarg); + JumbleExpr(jstate, join->quals); + } + break; + case T_FromExpr: + { + FromExpr *from = (FromExpr *) node; + + JumbleExpr(jstate, (Node *) from->fromlist); + JumbleExpr(jstate, from->quals); + } + break; + case T_OnConflictExpr: + { + OnConflictExpr *conf = (OnConflictExpr *) node; + + APP_JUMB(conf->action); + JumbleExpr(jstate, (Node *) conf->arbiterElems); + JumbleExpr(jstate, conf->arbiterWhere); + JumbleExpr(jstate, (Node *) conf->onConflictSet); + JumbleExpr(jstate, conf->onConflictWhere); + APP_JUMB(conf->constraint); + APP_JUMB(conf->exclRelIndex); + JumbleExpr(jstate, (Node *) conf->exclRelTlist); + } + break; + case T_List: + foreach(temp, (List *) node) + { + JumbleExpr(jstate, (Node *) lfirst(temp)); + } + break; + case T_IntList: + foreach(temp, (List *) node) + { + APP_JUMB(lfirst_int(temp)); + } + break; + case T_SortGroupClause: + { + SortGroupClause *sgc = (SortGroupClause *) node; + + APP_JUMB(sgc->tleSortGroupRef); + APP_JUMB(sgc->eqop); + APP_JUMB(sgc->sortop); + APP_JUMB(sgc->nulls_first); + } + break; + case T_GroupingSet: + { + GroupingSet *gsnode = (GroupingSet *) node; + + JumbleExpr(jstate, (Node *) gsnode->content); + } + break; + case T_WindowClause: + { + WindowClause *wc = (WindowClause *) node; + + APP_JUMB(wc->winref); + APP_JUMB(wc->frameOptions); + JumbleExpr(jstate, (Node *) wc->partitionClause); + JumbleExpr(jstate, (Node *) wc->orderClause); + JumbleExpr(jstate, wc->startOffset); + JumbleExpr(jstate, wc->endOffset); + } + break; + case T_CommonTableExpr: + { + CommonTableExpr *cte = (CommonTableExpr *) node; + + /* we store the string name because RTE_CTE RTEs need it */ + APP_JUMB_STRING(cte->ctename); + APP_JUMB(cte->ctematerialized); + JumbleQueryInternal(jstate, castNode(Query, cte->ctequery)); + } + break; + case T_SetOperationStmt: + { + SetOperationStmt *setop = (SetOperationStmt *) node; + + APP_JUMB(setop->op); + APP_JUMB(setop->all); + JumbleExpr(jstate, setop->larg); + JumbleExpr(jstate, setop->rarg); + } + break; + case T_RangeTblFunction: + { + RangeTblFunction *rtfunc = (RangeTblFunction *) node; + + JumbleExpr(jstate, rtfunc->funcexpr); + } + break; + case T_TableFunc: + { + TableFunc *tablefunc = (TableFunc *) node; + + JumbleExpr(jstate, tablefunc->docexpr); + JumbleExpr(jstate, tablefunc->rowexpr); + JumbleExpr(jstate, (Node *) tablefunc->colexprs); + } + break; + case T_TableSampleClause: + { + TableSampleClause *tsc = (TableSampleClause *) node; + + APP_JUMB(tsc->tsmhandler); + JumbleExpr(jstate, (Node *) tsc->args); + JumbleExpr(jstate, (Node *) tsc->repeatable); + } + break; + default: + /* Only a warning, since we can stumble along anyway */ + elog(WARNING, "unrecognized node type: %d", + (int) nodeTag(node)); + break; + } +} + +/* + * Record location of constant within query string of query tree + * that is currently being walked. + */ +static void +RecordConstLocation(JumbleState *jstate, int location) +{ + /* -1 indicates unknown or undefined location */ + if (location >= 0) + { + /* enlarge array if needed */ + if (jstate->clocations_count >= jstate->clocations_buf_size) + { + jstate->clocations_buf_size *= 2; + jstate->clocations = (LocationLen *) + repalloc(jstate->clocations, + jstate->clocations_buf_size * + sizeof(LocationLen)); + } + jstate->clocations[jstate->clocations_count].location = location; + /* initialize lengths to -1 to simplify third-party module usage */ + jstate->clocations[jstate->clocations_count].length = -1; + jstate->clocations_count++; + } +} diff --git a/src/include/parser/analyze.h b/src/include/parser/analyze.h index 4a3c9686f9..6716db6c13 100644 --- a/src/include/parser/analyze.h +++ b/src/include/parser/analyze.h @@ -15,10 +15,12 @@ #define ANALYZE_H #include "parser/parse_node.h" +#include "utils/queryjumble.h" /* Hook for plugins to get control at end of parse analysis */ typedef void (*post_parse_analyze_hook_type) (ParseState *pstate, - Query *query); + Query *query, + JumbleState *jstate); extern PGDLLIMPORT post_parse_analyze_hook_type post_parse_analyze_hook; diff --git a/src/include/utils/guc.h b/src/include/utils/guc.h index 5004ee4177..9b6552b25b 100644 --- a/src/include/utils/guc.h +++ b/src/include/utils/guc.h @@ -248,6 +248,7 @@ extern bool log_btree_build_stats; extern PGDLLIMPORT bool check_function_bodies; extern bool session_auth_is_superuser; +extern bool compute_query_id; extern bool log_duration; extern int log_parameter_max_length; extern int log_parameter_max_length_on_error; diff --git a/src/include/utils/queryjumble.h b/src/include/utils/queryjumble.h new file mode 100644 index 0000000000..83ba7339fa --- /dev/null +++ b/src/include/utils/queryjumble.h @@ -0,0 +1,58 @@ +/*------------------------------------------------------------------------- + * + * queryjumble.h + * Query normalization and fingerprinting. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/include/utils/queryjumble.h + * + *------------------------------------------------------------------------- + */ +#ifndef QUERYJUBLE_H +#define QUERYJUBLE_H + +#include "nodes/parsenodes.h" + +#define JUMBLE_SIZE 1024 /* query serialization buffer size */ + +/* + * Struct for tracking locations/lengths of constants during normalization + */ +typedef struct LocationLen +{ + int location; /* start offset in query text */ + int length; /* length in bytes, or -1 to ignore */ +} LocationLen; + +/* + * Working state for computing a query jumble and producing a normalized + * query string + */ +typedef struct JumbleState +{ + /* Jumble of current query tree */ + unsigned char *jumble; + + /* Number of bytes used in jumble[] */ + Size jumble_len; + + /* Array of locations of constants that should be removed */ + LocationLen *clocations; + + /* Allocated length of clocations array */ + int clocations_buf_size; + + /* Current number of valid entries in clocations array */ + int clocations_count; + + /* highest Param id we've seen, in order to start normalization correctly */ + int highest_extern_param_id; +} JumbleState; + +const char *CleanQuerytext(const char *query, int *location, int *len); +JumbleState *JumbleQuery(Query *query, const char *querytext); + +#endif /* QUERYJUMBLE_H */ -- 2.30.1 --oiinmuy4hl4wyl46 Content-Type: text/x-diff; charset=us-ascii Content-Disposition: attachment; filename="v20-0002-Expose-queryid-in-pg_stat_activity-and-log_line_.patch" ^ permalink raw reply [nested|flat] 4+ messages in thread
* [PATCH v1] Add REPACK command. @ 2025-07-26 17:57 Álvaro Herrera <alvherre@kurilemu.de> 0 siblings, 0 replies; 4+ messages in thread From: Álvaro Herrera @ 2025-07-26 17:57 UTC (permalink / raw) The existing CLUSTER command as well as VACUUM with the FULL option both reclaim unused space by rewriting table. Now that we want to enhance this functionality (in particular, by adding a new option CONCURRENTLY), we should enhance both commands because they are both implemented by the same function (cluster.c:cluster_rel). However, adding the same option to two different commands is not very user-friendly. Therefore it was decided to create a new command and to declare both CLUSTER command and the FULL option of VACUUM deprecated. Future enhancements to this rewriting code will only affect the new command. Like CLUSTER, the REPACK command reorders the table according to the specified index. Unlike CLUSTER, REPACK does not require the index: if only table is specified, the command acts as VACUUM FULL. As we don't want to remove CLUSTER and VACUUM FULL yet, there are three callers of the cluster_rel() function now: REPACK, CLUSTER and VACUUM FULL. When we need to distinguish who is calling this function (mostly for logging, but also for progress reporting), we can no longer use the OID of the clustering index: both REPACK and VACUUM FULL can pass InvalidOid. Therefore, this patch introduces a new enumeration type ClusterCommand, and adds an argument of this type to the cluster_rel() function and to all the functions that need to distinguish the caller. Like CLUSTER and VACUUM FULL, the REPACK COMMAND without arguments processes all the tables on which the current user has the MAINTAIN privilege. A new view pg_stat_progress_repack view is added to monitor the progress of REPACK. Currently it displays the same information as pg_stat_progress_cluster (except that column names might differ), but it'll also display the status of the REPACK CONCURRENTLY command in the future, so the view definitions will eventually diverge. Regarding user documentation, the patch moves the information on clustering from cluster.sgml to the new file repack.sgml. cluster.sgml now contains a link that points to the related section of repack.sgml. A note on deprecation and a link to repack.sgml are added to both cluster.sgml and vacuum.sgml. Author: Antonin Houska <ah@cybertec.at> Discussion: https://postgr.es/m/82651.1720540558@antos --- doc/src/sgml/monitoring.sgml | 223 ++++++- doc/src/sgml/ref/allfiles.sgml | 1 + doc/src/sgml/ref/cluster.sgml | 82 +-- doc/src/sgml/ref/repack.sgml | 254 ++++++++ doc/src/sgml/ref/vacuum.sgml | 9 + doc/src/sgml/reference.sgml | 1 + src/backend/access/heap/heapam_handler.c | 32 +- src/backend/catalog/index.c | 2 +- src/backend/catalog/system_views.sql | 26 + src/backend/commands/cluster.c | 723 +++++++++++++++-------- src/backend/commands/vacuum.c | 3 +- src/backend/parser/gram.y | 77 ++- src/backend/tcop/utility.c | 20 +- src/backend/utils/adt/pgstatfuncs.c | 2 + src/bin/psql/tab-complete.in.c | 33 +- src/include/commands/cluster.h | 7 +- src/include/commands/progress.h | 61 +- src/include/nodes/parsenodes.h | 20 +- src/include/parser/kwlist.h | 1 + src/include/tcop/cmdtaglist.h | 1 + src/include/utils/backend_progress.h | 1 + src/test/regress/expected/cluster.out | 125 +++- src/test/regress/expected/rules.out | 23 + src/test/regress/sql/cluster.sql | 59 ++ src/tools/pgindent/typedefs.list | 2 + 25 files changed, 1407 insertions(+), 381 deletions(-) create mode 100644 doc/src/sgml/ref/repack.sgml diff --git a/doc/src/sgml/monitoring.sgml b/doc/src/sgml/monitoring.sgml index 823afe1b30b..924e1b1fa99 100644 --- a/doc/src/sgml/monitoring.sgml +++ b/doc/src/sgml/monitoring.sgml @@ -405,6 +405,14 @@ postgres 27093 0.0 0.0 30096 2752 ? Ss 11:34 0:00 postgres: ser </entry> </row> + <row> + <entry><structname>pg_stat_progress_repack</structname><indexterm><primary>pg_stat_progress_repack</primary></indexterm></entry> + <entry>One row for each backend running + <command>REPACK</command>, showing current progress. See + <xref linkend="repack-progress-reporting"/>. + </entry> + </row> + <row> <entry><structname>pg_stat_progress_basebackup</structname><indexterm><primary>pg_stat_progress_basebackup</primary></indexterm></entry> <entry>One row for each WAL sender process streaming a base backup, @@ -5495,7 +5503,8 @@ FROM pg_stat_get_backend_idset() AS backendid; certain commands during command execution. Currently, the only commands which support progress reporting are <command>ANALYZE</command>, <command>CLUSTER</command>, - <command>CREATE INDEX</command>, <command>VACUUM</command>, + <command>CREATE INDEX</command>, <command>REPACK</command>, + <command>VACUUM</command>, <command>COPY</command>, and <xref linkend="protocol-replication-base-backup"/> (i.e., replication command that <xref linkend="app-pgbasebackup"/> issues to take @@ -5954,6 +5963,218 @@ FROM pg_stat_get_backend_idset() AS backendid; </table> </sect2> + <sect2 id="repack-progress-reporting"> + <title>REPACK Progress Reporting</title> + + <indexterm> + <primary>pg_stat_progress_repack</primary> + </indexterm> + + <para> + Whenever <command>REPACK</command> is running, + the <structname>pg_stat_progress_repack</structname> view will contain a + row for each backend that is currently running the command. The tables + below describe the information that will be reported and provide + information about how to interpret it. + </para> + + <table id="pg-stat-progress-repack-view" xreflabel="pg_stat_progress_repack"> + <title><structname>pg_stat_progress_repack</structname> View</title> + <tgroup cols="1"> + <thead> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + Column Type + </para> + <para> + Description + </para></entry> + </row> + </thead> + + <tbody> + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>pid</structfield> <type>integer</type> + </para> + <para> + Process ID of backend. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>datid</structfield> <type>oid</type> + </para> + <para> + OID of the database to which this backend is connected. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>datname</structfield> <type>name</type> + </para> + <para> + Name of the database to which this backend is connected. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>relid</structfield> <type>oid</type> + </para> + <para> + OID of the table being repacked. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>phase</structfield> <type>text</type> + </para> + <para> + Current processing phase. See <xref linkend="repack-phases"/>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>repack_index_relid</structfield> <type>oid</type> + </para> + <para> + If the table is being scanned using an index, this is the OID of the + index being used; otherwise, it is zero. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>heap_tuples_scanned</structfield> <type>bigint</type> + </para> + <para> + Number of heap tuples scanned. + This counter only advances when the phase is + <literal>seq scanning heap</literal>, + <literal>index scanning heap</literal> + or <literal>writing new heap</literal>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>heap_tuples_written</structfield> <type>bigint</type> + </para> + <para> + Number of heap tuples written. + This counter only advances when the phase is + <literal>seq scanning heap</literal>, + <literal>index scanning heap</literal> + or <literal>writing new heap</literal>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>heap_blks_total</structfield> <type>bigint</type> + </para> + <para> + Total number of heap blocks in the table. This number is reported + as of the beginning of <literal>seq scanning heap</literal>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>heap_blks_scanned</structfield> <type>bigint</type> + </para> + <para> + Number of heap blocks scanned. This counter only advances when the + phase is <literal>seq scanning heap</literal>. + </para></entry> + </row> + + <row> + <entry role="catalog_table_entry"><para role="column_definition"> + <structfield>index_rebuild_count</structfield> <type>bigint</type> + </para> + <para> + Number of indexes rebuilt. This counter only advances when the phase + is <literal>rebuilding index</literal>. + </para></entry> + </row> + </tbody> + </tgroup> + </table> + + <table id="repack-phases"> + <title>REPACK Phases</title> + <tgroup cols="2"> + <colspec colname="col1" colwidth="1*"/> + <colspec colname="col2" colwidth="2*"/> + <thead> + <row> + <entry>Phase</entry> + <entry>Description</entry> + </row> + </thead> + + <tbody> + <row> + <entry><literal>initializing</literal></entry> + <entry> + The command is preparing to begin scanning the heap. This phase is + expected to be very brief. + </entry> + </row> + <row> + <entry><literal>seq scanning heap</literal></entry> + <entry> + The command is currently scanning the table using a sequential scan. + </entry> + </row> + <row> + <entry><literal>index scanning heap</literal></entry> + <entry> + <command>REPACK</command> is currently scanning the table using an index scan. + </entry> + </row> + <row> + <entry><literal>sorting tuples</literal></entry> + <entry> + <command>REPACK</command> is currently sorting tuples. + </entry> + </row> + <row> + <entry><literal>writing new heap</literal></entry> + <entry> + <command>REPACK</command> is currently writing the new heap. + </entry> + </row> + <row> + <entry><literal>swapping relation files</literal></entry> + <entry> + The command is currently swapping newly-built files into place. + </entry> + </row> + <row> + <entry><literal>rebuilding index</literal></entry> + <entry> + The command is currently rebuilding an index. + </entry> + </row> + <row> + <entry><literal>performing final cleanup</literal></entry> + <entry> + The command is performing final cleanup. When this phase is + completed, <command>REPACK</command> will end. + </entry> + </row> + </tbody> + </tgroup> + </table> + </sect2> + <sect2 id="copy-progress-reporting"> <title>COPY Progress Reporting</title> diff --git a/doc/src/sgml/ref/allfiles.sgml b/doc/src/sgml/ref/allfiles.sgml index f5be638867a..c0ef654fcb4 100644 --- a/doc/src/sgml/ref/allfiles.sgml +++ b/doc/src/sgml/ref/allfiles.sgml @@ -167,6 +167,7 @@ Complete list of usable sgml source files in this directory. <!ENTITY refreshMaterializedView SYSTEM "refresh_materialized_view.sgml"> <!ENTITY reindex SYSTEM "reindex.sgml"> <!ENTITY releaseSavepoint SYSTEM "release_savepoint.sgml"> +<!ENTITY repack SYSTEM "repack.sgml"> <!ENTITY reset SYSTEM "reset.sgml"> <!ENTITY revoke SYSTEM "revoke.sgml"> <!ENTITY rollback SYSTEM "rollback.sgml"> diff --git a/doc/src/sgml/ref/cluster.sgml b/doc/src/sgml/ref/cluster.sgml index 8811f169ea0..ee4fd965928 100644 --- a/doc/src/sgml/ref/cluster.sgml +++ b/doc/src/sgml/ref/cluster.sgml @@ -42,18 +42,6 @@ CLUSTER [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <r <replaceable class="parameter">table_name</replaceable>. </para> - <para> - When a table is clustered, it is physically reordered - based on the index information. Clustering is a one-time operation: - when the table is subsequently updated, the changes are - not clustered. That is, no attempt is made to store new or - updated rows according to their index order. (If one wishes, one can - periodically recluster by issuing the command again. Also, setting - the table's <literal>fillfactor</literal> storage parameter to less than - 100% can aid in preserving cluster ordering during updates, since updated - rows are kept on the same page if enough space is available there.) - </para> - <para> When a table is clustered, <productname>PostgreSQL</productname> remembers which index it was clustered by. The form @@ -78,6 +66,25 @@ CLUSTER [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <r database operations (both reads and writes) from operating on the table until the <command>CLUSTER</command> is finished. </para> + + <warning> + <para> + The <command>CLUSTER</command> command is deprecated in favor of + <xref linkend="sql-repack"/>. + </para> + </warning> + + <note> + <para> + <xref linkend="sql-repack-notes-on-clustering"/> explain how clustering + works, whether it is initiated by <command>CLUSTER</command> or + by <command>REPACK</command>. The notable difference between the two is + that <command>REPACK</command> does not remember the index used last + time. Thus if you don't specify an index, <command>REPACK</command> + rewrites the table but does not try to cluster it. + </para> + </note> + </refsect1> <refsect1> @@ -136,63 +143,12 @@ CLUSTER [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <r on the table. </para> - <para> - In cases where you are accessing single rows randomly - within a table, the actual order of the data in the - table is unimportant. However, if you tend to access some - data more than others, and there is an index that groups - them together, you will benefit from using <command>CLUSTER</command>. - If you are requesting a range of indexed values from a table, or a - single indexed value that has multiple rows that match, - <command>CLUSTER</command> will help because once the index identifies the - table page for the first row that matches, all other rows - that match are probably already on the same table page, - and so you save disk accesses and speed up the query. - </para> - - <para> - <command>CLUSTER</command> can re-sort the table using either an index scan - on the specified index, or (if the index is a b-tree) a sequential - scan followed by sorting. It will attempt to choose the method that - will be faster, based on planner cost parameters and available statistical - information. - </para> - <para> While <command>CLUSTER</command> is running, the <xref linkend="guc-search-path"/> is temporarily changed to <literal>pg_catalog, pg_temp</literal>. </para> - <para> - When an index scan is used, a temporary copy of the table is created that - contains the table data in the index order. Temporary copies of each - index on the table are created as well. Therefore, you need free space on - disk at least equal to the sum of the table size and the index sizes. - </para> - - <para> - When a sequential scan and sort is used, a temporary sort file is - also created, so that the peak temporary space requirement is as much - as double the table size, plus the index sizes. This method is often - faster than the index scan method, but if the disk space requirement is - intolerable, you can disable this choice by temporarily setting <xref - linkend="guc-enable-sort"/> to <literal>off</literal>. - </para> - - <para> - It is advisable to set <xref linkend="guc-maintenance-work-mem"/> to - a reasonably large value (but not more than the amount of RAM you can - dedicate to the <command>CLUSTER</command> operation) before clustering. - </para> - - <para> - Because the planner records statistics about the ordering of - tables, it is advisable to run <link linkend="sql-analyze"><command>ANALYZE</command></link> - on the newly clustered table. - Otherwise, the planner might make poor choices of query plans. - </para> - <para> Because <command>CLUSTER</command> remembers which indexes are clustered, one can cluster the tables one wants clustered manually the first time, diff --git a/doc/src/sgml/ref/repack.sgml b/doc/src/sgml/ref/repack.sgml new file mode 100644 index 00000000000..a612c72d971 --- /dev/null +++ b/doc/src/sgml/ref/repack.sgml @@ -0,0 +1,254 @@ +<!-- +doc/src/sgml/ref/repack.sgml +PostgreSQL documentation +--> + +<refentry id="sql-repack"> + <indexterm zone="sql-repack"> + <primary>REPACK</primary> + </indexterm> + + <refmeta> + <refentrytitle>REPACK</refentrytitle> + <manvolnum>7</manvolnum> + <refmiscinfo>SQL - Language Statements</refmiscinfo> + </refmeta> + + <refnamediv> + <refname>REPACK</refname> + <refpurpose>rewrite a table to reclaim disk space</refpurpose> + </refnamediv> + + <refsynopsisdiv> +<synopsis> +REPACK [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <replaceable class="parameter">table_name</replaceable> [ USING INDEX <replaceable class="parameter">index_name</replaceable> ] ] + +<phrase>where <replaceable class="parameter">option</replaceable> can be one of:</phrase> + + VERBOSE [ <replaceable class="parameter">boolean</replaceable> ] +</synopsis> + </refsynopsisdiv> + + <refsect1> + <title>Description</title> + + <para> + <command>REPACK</command> reclaims storage occupied by dead + tuples. Unlike <command>VACUUM</command>, it does so by rewriting the + entire contents of the table specified + by <replaceable class="parameter">table_name</replaceable> into a new disk + file with no extra space (except for the space guaranteed by + the <literal>fillfactor</literal> storage parameter), allowing unused space + to be returned to the operating system. + </para> + + <para> + Without + a <replaceable class="parameter">table_name</replaceable>, <command>REPACK</command> + processes every table and materialized view in the current database that + the current user has the <literal>MAINTAIN</literal> privilege on. This + form of <command>REPACK</command> cannot be executed inside a transaction + block. + </para> + + <para> + If <replaceable class="parameter">index_name</replaceable> is specified, + the table is clustered by this index. Please see the notes on clustering + below. + </para> + + <para> + When a table is being repacked, an <literal>ACCESS EXCLUSIVE</literal> lock + is acquired on it. This prevents any other database operations (both reads + and writes) from operating on the table until the <command>REPACK</command> + is finished. + </para> + + <refsect2 id="sql-repack-notes-on-clustering" xreflabel="Notes on Clustering"> + <title>Notes on Clustering</title> + + <para> + When a table is clustered, it is physically reordered based on the index + information. Clustering is a one-time operation: when the table is + subsequently updated, the changes are not clustered. That is, no attempt + is made to store new or updated rows according to their index order. (If + one wishes, one can periodically recluster by issuing the command again. + Also, setting the table's <literal>fillfactor</literal> storage parameter + to less than 100% can aid in preserving cluster ordering during updates, + since updated rows are kept on the same page if enough space is available + there.) + </para> + + <para> + In cases where you are accessing single rows randomly within a table, the + actual order of the data in the table is unimportant. However, if you tend + to access some data more than others, and there is an index that groups + them together, you will benefit from using <command>REPACK</command>. If + you are requesting a range of indexed values from a table, or a single + indexed value that has multiple rows that match, + <command>REPACK</command> will help because once the index identifies the + table page for the first row that matches, all other rows that match are + probably already on the same table page, and so you save disk accesses and + speed up the query. + </para> + + <para> + <command>REPACK</command> can re-sort the table using either an index scan + on the specified index (if the index is a b-tree), or a sequential scan + followed by sorting. It will attempt to choose the method that will be + faster, based on planner cost parameters and available statistical + information. + </para> + + <para> + Because the planner records statistics about the ordering of tables, it is + advisable to + run <link linkend="sql-analyze"><command>ANALYZE</command></link> on the + newly repacked table. Otherwise, the planner might make poor choices of + query plans. + </para> + </refsect2> + + <refsect2 id="sql-repack-notes-on-resources" xreflabel="Notes on Resources"> + <title>Notes on Resources</title> + + <para> + When an index scan or a sequential scan without sort is used, a temporary + copy of the table is created that contains the table data in the index + order. Temporary copies of each index on the table are created as well. + Therefore, you need free space on disk at least equal to the sum of the + table size and the index sizes. + </para> + + <para> + When a sequential scan and sort is used, a temporary sort file is also + created, so that the peak temporary space requirement is as much as double + the table size, plus the index sizes. This method is often faster than + the index scan method, but if the disk space requirement is intolerable, + you can disable this choice by temporarily setting + <xref linkend="guc-enable-sort"/> to <literal>off</literal>. + </para> + + <para> + It is advisable to set <xref linkend="guc-maintenance-work-mem"/> to a + reasonably large value (but not more than the amount of RAM you can + dedicate to the <command>REPACK</command> operation) before repacking. + </para> + </refsect2> + + </refsect1> + + <refsect1> + <title>Parameters</title> + + <variablelist> + <varlistentry> + <term><replaceable class="parameter">table_name</replaceable></term> + <listitem> + <para> + The name (possibly schema-qualified) of a table. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><replaceable class="parameter">index_name</replaceable></term> + <listitem> + <para> + The name of an index. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><literal>VERBOSE</literal></term> + <listitem> + <para> + Prints a progress report as each table is repacked + at <literal>INFO</literal> level. + </para> + </listitem> + </varlistentry> + + <varlistentry> + <term><replaceable class="parameter">boolean</replaceable></term> + <listitem> + <para> + Specifies whether the selected option should be turned on or off. + You can write <literal>TRUE</literal>, <literal>ON</literal>, or + <literal>1</literal> to enable the option, and <literal>FALSE</literal>, + <literal>OFF</literal>, or <literal>0</literal> to disable it. The + <replaceable class="parameter">boolean</replaceable> value can also + be omitted, in which case <literal>TRUE</literal> is assumed. + </para> + </listitem> + </varlistentry> + </variablelist> + </refsect1> + + <refsect1> + <title>Notes</title> + + <para> + To repack a table, one must have the <literal>MAINTAIN</literal> privilege + on the table. + </para> + + <para> + While <command>REPACK</command> is running, the <xref + linkend="guc-search-path"/> is temporarily changed to <literal>pg_catalog, + pg_temp</literal>. + </para> + + <para> + Each backend running <command>REPACK</command> will report its progress + in the <structname>pg_stat_progress_repack</structname> view. See + <xref linkend="repack-progress-reporting"/> for details. + </para> + + <para> + Repacking a partitioned table repacks each of its partitions. If an index + is specified, each partition is repacked using the partition of that + index. <command>REPACK</command> on a partitioned table cannot be executed + inside a transaction block. + </para> + + </refsect1> + + <refsect1> + <title>Examples</title> + + <para> + Repack the table <literal>employees</literal>: +<programlisting> +REPACK employees; +</programlisting> + </para> + + <para> + Repack the table <literal>employees</literal> on the basis of its + index <literal>employees_ind</literal> (Since index is used here, this is + effectively clustering): +<programlisting> +REPACK employees USING INDEX employees_ind; +</programlisting> + </para> + + <para> + Repack all tables in the database on which you have + the <literal>MAINTAIN</literal> privilege: +<programlisting> +REPACK; +</programlisting></para> + </refsect1> + + <refsect1> + <title>Compatibility</title> + + <para> + There is no <command>REPACK</command> statement in the SQL standard. + </para> + + </refsect1> + +</refentry> diff --git a/doc/src/sgml/ref/vacuum.sgml b/doc/src/sgml/ref/vacuum.sgml index bd5dcaf86a5..cee1cf3926c 100644 --- a/doc/src/sgml/ref/vacuum.sgml +++ b/doc/src/sgml/ref/vacuum.sgml @@ -98,6 +98,7 @@ VACUUM [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <re <varlistentry> <term><literal>FULL</literal></term> <listitem> + <para> Selects <quote>full</quote> vacuum, which can reclaim more space, but takes much longer and exclusively locks the table. @@ -106,6 +107,14 @@ VACUUM [ ( <replaceable class="parameter">option</replaceable> [, ...] ) ] [ <re the operation is complete. Usually this should only be used when a significant amount of space needs to be reclaimed from within the table. </para> + + <warning> + <para> + The <option>FULL</option> parameter is deprecated in favor of + <xref linkend="sql-repack"/>. + </para> + </warning> + </listitem> </varlistentry> diff --git a/doc/src/sgml/reference.sgml b/doc/src/sgml/reference.sgml index ff85ace83fc..229912d35b7 100644 --- a/doc/src/sgml/reference.sgml +++ b/doc/src/sgml/reference.sgml @@ -195,6 +195,7 @@ &refreshMaterializedView; &reindex; &releaseSavepoint; + &repack; &reset; &revoke; &rollback; diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index cb4bc35c93e..0b03070d394 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -741,13 +741,13 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, if (OldIndex != NULL && !use_sort) { const int ci_index[] = { - PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_INDEX_RELID + PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_INDEX_RELID }; int64 ci_val[2]; /* Set phase and OIDOldIndex to columns */ - ci_val[0] = PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP; + ci_val[0] = PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP; ci_val[1] = RelationGetRelid(OldIndex); pgstat_progress_update_multi_param(2, ci_index, ci_val); @@ -759,15 +759,15 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, else { /* In scan-and-sort mode and also VACUUM FULL, set phase */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP); tableScan = table_beginscan(OldHeap, SnapshotAny, 0, (ScanKey) NULL); heapScan = (HeapScanDesc) tableScan; indexScan = NULL; /* Set total heap blocks */ - pgstat_progress_update_param(PROGRESS_CLUSTER_TOTAL_HEAP_BLKS, + pgstat_progress_update_param(PROGRESS_REPACK_TOTAL_HEAP_BLKS, heapScan->rs_nblocks); } @@ -809,7 +809,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, * is manually updated to the correct value when the table * scan finishes. */ - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED, heapScan->rs_nblocks); break; } @@ -825,7 +825,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, */ if (prev_cblock != heapScan->rs_cblock) { - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_BLKS_SCANNED, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_BLKS_SCANNED, (heapScan->rs_cblock + heapScan->rs_nblocks - heapScan->rs_startblock @@ -912,14 +912,14 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, * In scan-and-sort mode, report increase in number of tuples * scanned */ - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_SCANNED, *num_tuples); } else { const int ct_index[] = { - PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED, - PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN + PROGRESS_REPACK_HEAP_TUPLES_SCANNED, + PROGRESS_REPACK_HEAP_TUPLES_WRITTEN }; int64 ct_val[2]; @@ -952,14 +952,14 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, double n_tuples = 0; /* Report that we are now sorting tuples */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_SORT_TUPLES); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_SORT_TUPLES); tuplesort_performsort(tuplesort); /* Report that we are now writing new heap */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_WRITE_NEW_HEAP); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP); for (;;) { @@ -977,7 +977,7 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, values, isnull, rwstate); /* Report n_tuples */ - pgstat_progress_update_param(PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN, + pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_WRITTEN, n_tuples); } diff --git a/src/backend/catalog/index.c b/src/backend/catalog/index.c index c4029a4f3d3..3063abff9a5 100644 --- a/src/backend/catalog/index.c +++ b/src/backend/catalog/index.c @@ -4079,7 +4079,7 @@ reindex_relation(const ReindexStmt *stmt, Oid relid, int flags, Assert(!ReindexIsProcessingIndex(indexOid)); /* Set index rebuild count */ - pgstat_progress_update_param(PROGRESS_CLUSTER_INDEX_REBUILD_COUNT, + pgstat_progress_update_param(PROGRESS_REPACK_INDEX_REBUILD_COUNT, i); i++; } diff --git a/src/backend/catalog/system_views.sql b/src/backend/catalog/system_views.sql index f6eca09ee15..02f091c3ed6 100644 --- a/src/backend/catalog/system_views.sql +++ b/src/backend/catalog/system_views.sql @@ -1279,6 +1279,32 @@ CREATE VIEW pg_stat_progress_cluster AS FROM pg_stat_get_progress_info('CLUSTER') AS S LEFT JOIN pg_database D ON S.datid = D.oid; +CREATE VIEW pg_stat_progress_repack AS + SELECT + S.pid AS pid, + S.datid AS datid, + D.datname AS datname, + S.relid AS relid, + -- param1 is currently unused + CASE S.param2 WHEN 0 THEN 'initializing' + WHEN 1 THEN 'seq scanning heap' + WHEN 2 THEN 'index scanning heap' + WHEN 3 THEN 'sorting tuples' + WHEN 4 THEN 'writing new heap' + WHEN 5 THEN 'swapping relation files' + WHEN 6 THEN 'rebuilding index' + WHEN 7 THEN 'performing final cleanup' + END AS phase, + CAST(S.param3 AS oid) AS repack_index_relid, + S.param4 AS heap_tuples_scanned, + S.param5 AS heap_tuples_written, + S.param6 AS heap_blks_total, + S.param7 AS heap_blks_scanned, + S.param8 AS index_rebuild_count + FROM pg_stat_get_progress_info('REPACK') AS S + LEFT JOIN pg_database D ON S.datid = D.oid; + + CREATE VIEW pg_stat_progress_create_index AS SELECT S.pid AS pid, S.datid AS datid, D.datname AS datname, diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index b55221d44cd..752c83d4391 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -67,18 +67,41 @@ typedef struct Oid indexOid; } RelToCluster; - -static void cluster_multiple_rels(List *rtcs, ClusterParams *params); -static void rebuild_relation(Relation OldHeap, Relation index, bool verbose); +static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, + Oid indexOid, Oid userid, int options); +static void rebuild_relation(RepackCommand cmd, bool usingindex, + Relation OldHeap, Relation index, bool verbose); static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, bool verbose, bool *pSwapToastByContent, TransactionId *pFreezeXid, MultiXactId *pCutoffMulti); -static List *get_tables_to_cluster(MemoryContext cluster_context); -static List *get_tables_to_cluster_partitioned(MemoryContext cluster_context, - Oid indexOid); -static bool cluster_is_permitted_for_relation(Oid relid, Oid userid); +static List *get_tables_to_repack(RepackCommand cmd, bool usingindex, + MemoryContext permcxt); +static List *get_tables_to_repack_partitioned(RepackCommand cmd, + MemoryContext cluster_context, + Oid relid, bool rel_is_index); +static bool cluster_is_permitted_for_relation(RepackCommand cmd, + Oid relid, Oid userid); +static Relation process_single_relation(RepackStmt *stmt, + ClusterParams *params); +static Oid determine_clustered_index(Relation rel, bool usingindex, + const char *indexname); +static const char * +RepackCommandAsString(RepackCommand cmd) +{ + switch (cmd) + { + case REPACK_COMMAND_REPACK: + return "REPACK"; + case REPACK_COMMAND_VACUUMFULL: + return "VACUUM"; + case REPACK_COMMAND_CLUSTER: + return "VACUUM"; + } + return "???"; +} + /*--------------------------------------------------------------------------- * This cluster code allows for clustering multiple tables at once. Because * of this, we cannot just run everything on a single transaction, or we @@ -104,101 +127,39 @@ static bool cluster_is_permitted_for_relation(Oid relid, Oid userid); *--------------------------------------------------------------------------- */ void -cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel) +ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel) { - ListCell *lc; ClusterParams params = {0}; bool verbose = false; Relation rel = NULL; - Oid indexOid = InvalidOid; - MemoryContext cluster_context; + MemoryContext repack_context; List *rtcs; /* Parse option list */ - foreach(lc, stmt->params) + foreach_node(DefElem, opt, stmt->params) { - DefElem *opt = (DefElem *) lfirst(lc); - if (strcmp(opt->defname, "verbose") == 0) verbose = defGetBoolean(opt); else ereport(ERROR, (errcode(ERRCODE_SYNTAX_ERROR), - errmsg("unrecognized CLUSTER option \"%s\"", + errmsg("unrecognized %s option \"%s\"", + RepackCommandAsString(stmt->command), opt->defname), parser_errposition(pstate, opt->location))); } params.options = (verbose ? CLUOPT_VERBOSE : 0); + /* + * If a single relation is specified, process it and we're done ... unless + * the relation is a partitioned table, in which case we fall through. + */ if (stmt->relation != NULL) { - /* This is the single-relation case. */ - Oid tableOid; - - /* - * Find, lock, and check permissions on the table. We obtain - * AccessExclusiveLock right away to avoid lock-upgrade hazard in the - * single-transaction case. - */ - tableOid = RangeVarGetRelidExtended(stmt->relation, - AccessExclusiveLock, - 0, - RangeVarCallbackMaintainsTable, - NULL); - rel = table_open(tableOid, NoLock); - - /* - * Reject clustering a remote temp table ... their local buffer - * manager is not going to cope. - */ - if (RELATION_IS_OTHER_TEMP(rel)) - ereport(ERROR, - (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot cluster temporary tables of other sessions"))); - - if (stmt->indexname == NULL) - { - ListCell *index; - - /* We need to find the index that has indisclustered set. */ - foreach(index, RelationGetIndexList(rel)) - { - indexOid = lfirst_oid(index); - if (get_index_isclustered(indexOid)) - break; - indexOid = InvalidOid; - } - - if (!OidIsValid(indexOid)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("there is no previously clustered index for table \"%s\"", - stmt->relation->relname))); - } - else - { - /* - * The index is expected to be in the same namespace as the - * relation. - */ - indexOid = get_relname_relid(stmt->indexname, - rel->rd_rel->relnamespace); - if (!OidIsValid(indexOid)) - ereport(ERROR, - (errcode(ERRCODE_UNDEFINED_OBJECT), - errmsg("index \"%s\" for table \"%s\" does not exist", - stmt->indexname, stmt->relation->relname))); - } - - /* For non-partitioned tables, do what we came here to do. */ - if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE) - { - cluster_rel(rel, indexOid, ¶ms); - /* cluster_rel closes the relation, but keeps lock */ - + rel = process_single_relation(stmt, ¶ms); + if (rel == NULL) return; - } } /* @@ -207,88 +168,103 @@ cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel) * transaction. This forces us to disallow running inside a user * transaction block. */ - PreventInTransactionBlock(isTopLevel, "CLUSTER"); + PreventInTransactionBlock(isTopLevel, RepackCommandAsString(stmt->command)); /* Also, we need a memory context to hold our list of relations */ - cluster_context = AllocSetContextCreate(PortalContext, - "Cluster", - ALLOCSET_DEFAULT_SIZES); + repack_context = AllocSetContextCreate(PortalContext, + "Repack", + ALLOCSET_DEFAULT_SIZES); + + params.options |= CLUOPT_RECHECK; /* - * Either we're processing a partitioned table, or we were not given any - * table name at all. In either case, obtain a list of relations to - * process. - * - * In the former case, an index name must have been given, so we don't - * need to recheck its "indisclustered" bit, but we have to check that it - * is an index that we can cluster on. In the latter case, we set the - * option bit to have indisclustered verified. - * - * Rechecking the relation itself is necessary here in all cases. + * If we don't have a relation yet, determine a relation list. If we do, + * then it must be a partitioned table, and we want to process its + * partitions. */ - params.options |= CLUOPT_RECHECK; - if (rel != NULL) + if (rel == NULL) { - Assert(rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE); - check_index_is_clusterable(rel, indexOid, AccessShareLock); - rtcs = get_tables_to_cluster_partitioned(cluster_context, indexOid); - - /* close relation, releasing lock on parent table */ - table_close(rel, AccessExclusiveLock); + Assert(stmt->indexname == NULL); + rtcs = get_tables_to_repack(stmt->command, stmt->usingindex, + repack_context); } else { - rtcs = get_tables_to_cluster(cluster_context); - params.options |= CLUOPT_RECHECK_ISCLUSTERED; + Oid relid; + bool rel_is_index; + + Assert(rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE); + + /* + * If an index name was specified, resolve it now and pass it down. + */ + if (stmt->usingindex) + { + /* + * XXX how should this behave? Passing no index to a partitioned + * table could be useful to have certain partitions clustered by + * some index, and other partitions by a different index. + */ + if (!stmt->indexname) + ereport(ERROR, + errmsg("there is no previously clustered index for table \"%s\"", + RelationGetRelationName(rel))); + + relid = determine_clustered_index(rel, true, stmt->indexname); + /* XXX is this the right place for this? */ + check_index_is_clusterable(rel, relid, AccessExclusiveLock); + rel_is_index = true; + } + else + { + relid = RelationGetRelid(rel); + rel_is_index = false; + } + + rtcs = get_tables_to_repack_partitioned(stmt->command, repack_context, + relid, rel_is_index); + + /* close parent relation, releasing lock on it */ + table_close(rel, AccessExclusiveLock); + rel = NULL; } - /* Do the job. */ - cluster_multiple_rels(rtcs, ¶ms); - - /* Start a new transaction for the cleanup work. */ - StartTransactionCommand(); - - /* Clean up working storage */ - MemoryContextDelete(cluster_context); -} - -/* - * Given a list of relations to cluster, process each of them in a separate - * transaction. - * - * We expect to be in a transaction at start, but there isn't one when we - * return. - */ -static void -cluster_multiple_rels(List *rtcs, ClusterParams *params) -{ - ListCell *lc; - /* Commit to get out of starting transaction */ PopActiveSnapshot(); CommitTransactionCommand(); /* Cluster the tables, each in a separate transaction */ - foreach(lc, rtcs) + Assert(rel == NULL); + foreach_ptr(RelToCluster, rtc, rtcs) { - RelToCluster *rtc = (RelToCluster *) lfirst(lc); - Relation rel; - /* Start a new transaction for each relation. */ StartTransactionCommand(); /* functions in indexes may want a snapshot set */ PushActiveSnapshot(GetTransactionSnapshot()); - rel = table_open(rtc->tableOid, AccessExclusiveLock); + /* + * Open the target table, coping with the case where it has been + * dropped. + */ + rel = try_table_open(rtc->tableOid, AccessExclusiveLock); + if (rel == NULL) + continue; /* Process this table */ - cluster_rel(rel, rtc->indexOid, params); + cluster_rel(stmt->command, stmt->usingindex, + rel, rtc->indexOid, ¶ms); /* cluster_rel closes the relation, but keeps lock */ PopActiveSnapshot(); CommitTransactionCommand(); } + + /* Start a new transaction for the cleanup work. */ + StartTransactionCommand(); + + /* Clean up working storage */ + MemoryContextDelete(repack_context); } /* @@ -304,11 +280,14 @@ cluster_multiple_rels(List *rtcs, ClusterParams *params) * them incrementally while we load the table. * * If indexOid is InvalidOid, the table will be rewritten in physical order - * instead of index order. This is the new implementation of VACUUM FULL, - * and error messages should refer to the operation as VACUUM not CLUSTER. + * instead of index order. + * + * 'cmd' indicates which command is being executed, to be used for error + * messages. */ void -cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params) +cluster_rel(RepackCommand cmd, bool usingindex, + Relation OldHeap, Oid indexOid, ClusterParams *params) { Oid tableOid = RelationGetRelid(OldHeap); Oid save_userid; @@ -323,13 +302,25 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params) /* Check for user-requested abort. */ CHECK_FOR_INTERRUPTS(); - pgstat_progress_start_command(PROGRESS_COMMAND_CLUSTER, tableOid); - if (OidIsValid(indexOid)) - pgstat_progress_update_param(PROGRESS_CLUSTER_COMMAND, - PROGRESS_CLUSTER_COMMAND_CLUSTER); + if (cmd == REPACK_COMMAND_REPACK) + pgstat_progress_start_command(PROGRESS_COMMAND_REPACK, tableOid); else - pgstat_progress_update_param(PROGRESS_CLUSTER_COMMAND, + pgstat_progress_start_command(PROGRESS_COMMAND_CLUSTER, tableOid); + + if (cmd == REPACK_COMMAND_REPACK) + pgstat_progress_update_param(PROGRESS_REPACK_COMMAND, + PROGRESS_REPACK_COMMAND_REPACK); + else if (cmd == REPACK_COMMAND_CLUSTER) + { + pgstat_progress_update_param(PROGRESS_REPACK_COMMAND, + PROGRESS_CLUSTER_COMMAND_CLUSTER); + } + else + { + Assert(cmd == REPACK_COMMAND_VACUUMFULL); + pgstat_progress_update_param(PROGRESS_REPACK_COMMAND, PROGRESS_CLUSTER_COMMAND_VACUUM_FULL); + } /* * Switch to the table owner's userid, so that any index functions are run @@ -351,63 +342,21 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params) * to cluster a not-previously-clustered index. */ if (recheck) - { - /* Check that the user still has privileges for the relation */ - if (!cluster_is_permitted_for_relation(tableOid, save_userid)) - { - relation_close(OldHeap, AccessExclusiveLock); + if (!cluster_rel_recheck(cmd, OldHeap, indexOid, save_userid, + params->options)) goto out; - } - - /* - * Silently skip a temp table for a remote session. Only doing this - * check in the "recheck" case is appropriate (which currently means - * somebody is executing a database-wide CLUSTER or on a partitioned - * table), because there is another check in cluster() which will stop - * any attempt to cluster remote temp tables by name. There is - * another check in cluster_rel which is redundant, but we leave it - * for extra safety. - */ - if (RELATION_IS_OTHER_TEMP(OldHeap)) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - - if (OidIsValid(indexOid)) - { - /* - * Check that the index still exists - */ - if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid))) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - - /* - * Check that the index is still the one with indisclustered set, - * if needed. - */ - if ((params->options & CLUOPT_RECHECK_ISCLUSTERED) != 0 && - !get_index_isclustered(indexOid)) - { - relation_close(OldHeap, AccessExclusiveLock); - goto out; - } - } - } /* - * We allow VACUUM FULL, but not CLUSTER, on shared catalogs. CLUSTER - * would work in most respects, but the index would only get marked as - * indisclustered in the current database, leading to unexpected behavior - * if CLUSTER were later invoked in another database. + * We allow repacking shared catalogs only when not using an index. + * It would work to use an index in most respects, but the index would + * only get marked as indisclustered in the current database, leading to + * unexpected behavior if CLUSTER were later invoked in another database. */ - if (OidIsValid(indexOid) && OldHeap->rd_rel->relisshared) + if (usingindex && OldHeap->rd_rel->relisshared) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), - errmsg("cannot cluster a shared catalog"))); + errmsg("cannot run \"%s\" on a shared catalog", + RepackCommandAsString(cmd)))); /* * Don't process temp tables of other backends ... their local buffer @@ -415,21 +364,30 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params) */ if (RELATION_IS_OTHER_TEMP(OldHeap)) { - if (OidIsValid(indexOid)) + if (cmd == REPACK_COMMAND_CLUSTER) ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), errmsg("cannot cluster temporary tables of other sessions"))); + else if (cmd == REPACK_COMMAND_REPACK) + { + ereport(ERROR, + (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot repack temporary tables of other sessions"))); + } else + { + Assert (cmd == REPACK_COMMAND_VACUUMFULL); ereport(ERROR, (errcode(ERRCODE_FEATURE_NOT_SUPPORTED), errmsg("cannot vacuum temporary tables of other sessions"))); + } } /* * Also check for active uses of the relation in the current transaction, * including open scans and pending AFTER trigger events. */ - CheckTableNotInUse(OldHeap, OidIsValid(indexOid) ? "CLUSTER" : "VACUUM"); + CheckTableNotInUse(OldHeap, RepackCommandAsString(cmd)); /* Check heap and index are valid to cluster on */ if (OidIsValid(indexOid)) @@ -469,7 +427,7 @@ cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params) TransferPredicateLocksToHeapRelation(OldHeap); /* rebuild_relation does all the dirty work */ - rebuild_relation(OldHeap, index, verbose); + rebuild_relation(cmd, usingindex, OldHeap, index, verbose); /* rebuild_relation closes OldHeap, and index if valid */ out: @@ -482,6 +440,64 @@ out: pgstat_progress_end_command(); } +/* + * Check if the table (and its index) still meets the requirements of + * cluster_rel(). + */ +static bool +cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, + Oid userid, int options) +{ + Oid tableOid = RelationGetRelid(OldHeap); + + /* Check that the user still has privileges for the relation */ + if (!cluster_is_permitted_for_relation(tableOid, userid, + CLUSTER_COMMAND_CLUSTER)) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + + /* + * Silently skip a temp table for a remote session. Only doing this check + * in the "recheck" case is appropriate (which currently means somebody is + * executing a database-wide CLUSTER or on a partitioned table), because + * there is another check in cluster() which will stop any attempt to + * cluster remote temp tables by name. There is another check in + * cluster_rel which is redundant, but we leave it for extra safety. + */ + if (RELATION_IS_OTHER_TEMP(OldHeap)) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + + if (OidIsValid(indexOid)) + { + /* + * Check that the index still exists + */ + if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(indexOid))) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + + /* + * Check that the index is still the one with indisclustered set, if + * needed. + */ + if ((options & CLUOPT_RECHECK_ISCLUSTERED) != 0 && + !get_index_isclustered(indexOid)) + { + relation_close(OldHeap, AccessExclusiveLock); + return false; + } + } + + return true; +} + /* * Verify that the specified heap and index are valid to cluster on * @@ -626,7 +642,8 @@ mark_index_clustered(Relation rel, Oid indexOid, bool is_internal) * On exit, they are closed, but locks on them are not released. */ static void -rebuild_relation(Relation OldHeap, Relation index, bool verbose) +rebuild_relation(RepackCommand cmd, bool usingindex, + Relation OldHeap, Relation index, bool verbose) { Oid tableOid = RelationGetRelid(OldHeap); Oid accessMethod = OldHeap->rd_rel->relam; @@ -642,8 +659,8 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose) Assert(CheckRelationLockedByMe(OldHeap, AccessExclusiveLock, false) && (index == NULL || CheckRelationLockedByMe(index, AccessExclusiveLock, false))); - if (index) - /* Mark the correct index as clustered */ + /* for CLUSTER or REPACK USING INDEX, mark the index as the one to use */ + if (usingindex) mark_index_clustered(OldHeap, RelationGetRelid(index), true); /* Remember info about rel before closing OldHeap */ @@ -1458,8 +1475,8 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, int i; /* Report that we are now swapping relation files */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_SWAP_REL_FILES); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_SWAP_REL_FILES); /* Zero out possible results from swapped_relation_files */ memset(mapped_tables, 0, sizeof(mapped_tables)); @@ -1509,14 +1526,14 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, reindex_flags |= REINDEX_REL_FORCE_INDEXES_PERMANENT; /* Report that we are now reindexing relations */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_REBUILD_INDEX); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_REBUILD_INDEX); reindex_relation(NULL, OIDOldHeap, reindex_flags, &reindex_params); /* Report that we are now doing clean up */ - pgstat_progress_update_param(PROGRESS_CLUSTER_PHASE, - PROGRESS_CLUSTER_PHASE_FINAL_CLEANUP); + pgstat_progress_update_param(PROGRESS_REPACK_PHASE, + PROGRESS_REPACK_PHASE_FINAL_CLEANUP); /* * If the relation being rebuilt is pg_class, swap_relation_files() @@ -1632,69 +1649,136 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, } } - /* - * Get a list of tables that the current user has privileges on and - * have indisclustered set. Return the list in a List * of RelToCluster - * (stored in the specified memory context), each one giving the tableOid - * and the indexOid on which the table is already clustered. + * Determine which relations to process, when REPACK/CLUSTER is called + * without specifying a table name. The exact process depends on whether + * USING INDEX was given or not, and in any case we only return tables and + * materialized views that the current user has privileges to repack/cluster. + * + * If USING INDEX was given, we scan pg_index to find those that have + * indisclustered set; if it was not given, scan pg_class and return all + * tables. + * + * Return it as a list of RelToCluster in the given memory context. */ static List * -get_tables_to_cluster(MemoryContext cluster_context) +get_tables_to_repack(RepackCommand command, bool usingindex, + MemoryContext permcxt) { - Relation indRelation; + Relation catalog; TableScanDesc scan; - ScanKeyData entry; - HeapTuple indexTuple; - Form_pg_index index; + HeapTuple tuple; MemoryContext old_context; List *rtcs = NIL; - /* - * Get all indexes that have indisclustered set and that the current user - * has the appropriate privileges for. - */ - indRelation = table_open(IndexRelationId, AccessShareLock); - ScanKeyInit(&entry, - Anum_pg_index_indisclustered, - BTEqualStrategyNumber, F_BOOLEQ, - BoolGetDatum(true)); - scan = table_beginscan_catalog(indRelation, 1, &entry); - while ((indexTuple = heap_getnext(scan, ForwardScanDirection)) != NULL) + if (usingindex) { - RelToCluster *rtc; + ScanKeyData entry; - index = (Form_pg_index) GETSTRUCT(indexTuple); + catalog = table_open(IndexRelationId, AccessShareLock); + ScanKeyInit(&entry, + Anum_pg_index_indisclustered, + BTEqualStrategyNumber, F_BOOLEQ, + BoolGetDatum(true)); + scan = table_beginscan_catalog(catalog, 1, &entry); + while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL) + { + RelToCluster *rtc; + Form_pg_index index; - if (!cluster_is_permitted_for_relation(index->indrelid, GetUserId())) - continue; + index = (Form_pg_index) GETSTRUCT(tuple); + /* + * XXX I think the only reason there's no test failure here is + * that we seldom have clustered indexes that would be affected + * by concurrency. Maybe we should also do the + * ConditionalLockRelationOid+SearchSysCacheExists dance that + * we do below. + */ + if (!cluster_is_permitted_for_relation(command, index->indrelid, + GetUserId())) + continue; - /* Use a permanent memory context for the result list */ - old_context = MemoryContextSwitchTo(cluster_context); + /* Use a permanent memory context for the result list */ + old_context = MemoryContextSwitchTo(permcxt); - rtc = (RelToCluster *) palloc(sizeof(RelToCluster)); - rtc->tableOid = index->indrelid; - rtc->indexOid = index->indexrelid; - rtcs = lappend(rtcs, rtc); + rtc = (RelToCluster *) palloc(sizeof(RelToCluster)); + rtc->tableOid = index->indrelid; + rtc->indexOid = index->indexrelid; + rtcs = lappend(rtcs, rtc); - MemoryContextSwitchTo(old_context); + MemoryContextSwitchTo(old_context); + } } - table_endscan(scan); + else + { + catalog = table_open(RelationRelationId, AccessShareLock); + scan = table_beginscan_catalog(catalog, 0, NULL); - relation_close(indRelation, AccessShareLock); + while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL) + { + RelToCluster *rtc; + Form_pg_class class; + + class = (Form_pg_class) GETSTRUCT(tuple); + + /* + * Try to obtain a light lock on the table, to ensure it doesn't + * go away while we collect the list. If we cannot, just + * disregard the table. XXX we could release at the bottom of the + * loop, but for now just hold it until this transaction is + * finished. + */ + if (!ConditionalLockRelationOid(class->oid, AccessShareLock)) + continue; + + /* Verify that the table still exists. */ + if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(class->oid))) + { + /* Release useless lock */ + UnlockRelationOid(class->oid, AccessShareLock); + continue; + } + + /* Can only process plain tables and matviews */ + if (class->relkind != RELKIND_RELATION && + class->relkind != RELKIND_MATVIEW) + continue; + + if (!cluster_is_permitted_for_relation(command, class->oid, + GetUserId())) + continue; + + /* Use a permanent memory context for the result list */ + old_context = MemoryContextSwitchTo(permcxt); + + rtc = (RelToCluster *) palloc(sizeof(RelToCluster)); + rtc->tableOid = class->oid; + rtc->indexOid = InvalidOid; + rtcs = lappend(rtcs, rtc); + + MemoryContextSwitchTo(old_context); + } + } + + table_endscan(scan); + relation_close(catalog, AccessShareLock); return rtcs; } /* - * Given an index on a partitioned table, return a list of RelToCluster for + * Given a partitioned table or its index, return a list of RelToCluster for * all the children leaves tables/indexes. * * Like expand_vacuum_rel, but here caller must hold AccessExclusiveLock * on the table containing the index. + * + * 'rel_is_index' tells whether 'relid' is that of an index (true) or of the + * owning relation. */ static List * -get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid) +get_tables_to_repack_partitioned(RepackCommand cmd, MemoryContext cluster_context, + Oid relid, bool rel_is_index) { List *inhoids; ListCell *lc; @@ -1702,17 +1786,33 @@ get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid) MemoryContext old_context; /* Do not lock the children until they're processed */ - inhoids = find_all_inheritors(indexOid, NoLock, NULL); + inhoids = find_all_inheritors(relid, NoLock, NULL); foreach(lc, inhoids) { - Oid indexrelid = lfirst_oid(lc); - Oid relid = IndexGetRelation(indexrelid, false); + Oid inhoid = lfirst_oid(lc); + Oid inhrelid, + inhindid; RelToCluster *rtc; - /* consider only leaf indexes */ - if (get_rel_relkind(indexrelid) != RELKIND_INDEX) - continue; + if (rel_is_index) + { + /* consider only leaf indexes */ + if (get_rel_relkind(inhoid) != RELKIND_INDEX) + continue; + + inhrelid = IndexGetRelation(inhoid, false); + inhindid = inhoid; + } + else + { + /* consider only leaf relations */ + if (get_rel_relkind(inhoid) != RELKIND_RELATION) + continue; + + inhrelid = inhoid; + inhindid = InvalidOid; + } /* * It's possible that the user does not have privileges to CLUSTER the @@ -1720,15 +1820,15 @@ get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid) * table. We skip any partitions which the user is not permitted to * CLUSTER. */ - if (!cluster_is_permitted_for_relation(relid, GetUserId())) + if (!cluster_is_permitted_for_relation(cmd, inhrelid, GetUserId())) continue; /* Use a permanent memory context for the result list */ old_context = MemoryContextSwitchTo(cluster_context); rtc = (RelToCluster *) palloc(sizeof(RelToCluster)); - rtc->tableOid = relid; - rtc->indexOid = indexrelid; + rtc->tableOid = inhrelid; + rtc->indexOid = inhindid; rtcs = lappend(rtcs, rtc); MemoryContextSwitchTo(old_context); @@ -1742,13 +1842,134 @@ get_tables_to_cluster_partitioned(MemoryContext cluster_context, Oid indexOid) * function emits a WARNING. */ static bool -cluster_is_permitted_for_relation(Oid relid, Oid userid) +cluster_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid) { if (pg_class_aclcheck(relid, userid, ACL_MAINTAIN) == ACLCHECK_OK) return true; + Assert(cmd == REPACK_COMMAND_CLUSTER || cmd == REPACK_COMMAND_REPACK); ereport(WARNING, - (errmsg("permission denied to cluster \"%s\", skipping it", - get_rel_name(relid)))); + errmsg("permission denied to execute %s on \"%s\", skipping it", + cmd == REPACK_COMMAND_CLUSTER ? "CLUSTER" : "REPACK", + get_rel_name(relid))); + return false; } + + +/* + * Given a RepackStmt with an indicated relation name, resolve the relation + * name, obtain lock on it, then determine what to do based on the relation + * type: if it's not a partitioned table, repack it as indicated (using an + * existing clustered index, or following the indicated index), and return + * NULL. + * + * On the other hand, if the table is partitioned, do nothing further and + * instead return the opened relcache entry, so that caller can process the + * partitions using the multiple-table handling code. The index name is not + * resolve in this case. + */ +static Relation +process_single_relation(RepackStmt *stmt, ClusterParams *params) +{ + Relation rel; + Oid tableOid; + + Assert(stmt->relation != NULL); + Assert(stmt->command == REPACK_COMMAND_CLUSTER || + stmt->command == REPACK_COMMAND_REPACK); + + /* + * Find, lock, and check permissions on the table. We obtain + * AccessExclusiveLock right away to avoid lock-upgrade hazard in the + * single-transaction case. + */ + tableOid = RangeVarGetRelidExtended(stmt->relation, + AccessExclusiveLock, + 0, + RangeVarCallbackMaintainsTable, + NULL); + rel = table_open(tableOid, NoLock); + + /* + * Reject clustering a remote temp table ... their local buffer manager is + * not going to cope. + */ + if (RELATION_IS_OTHER_TEMP(rel)) + { + ereport(ERROR, + errcode(ERRCODE_FEATURE_NOT_SUPPORTED), + errmsg("cannot execute %s on temporary tables of other sessions", + RepackCommandAsString(stmt->command))); + } + + /* + * For partitioned tables, let caller handle this. Otherwise, process + * it here and we're done. + */ + if (rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE) + return rel; + else + { + Oid indexOid; + + indexOid = determine_clustered_index(rel, stmt->usingindex, + stmt->indexname); + check_index_is_clusterable(rel, indexOid, AccessExclusiveLock); + cluster_rel(stmt->command, stmt->usingindex, rel, indexOid, params); + return NULL; + } +} + +/* + * Given a relation and the usingindex/indexname options in a + * REPACK USING INDEX or CLUSTER command, return the OID of the index to use + * for clustering the table. + * + * Caller must hold lock on the relation so that the set of indexes doesn't + * change, and must call check_index_is_clusterable. + */ +static Oid +determine_clustered_index(Relation rel, bool usingindex, const char *indexname) +{ + Oid indexOid; + + if (indexname == NULL && usingindex) + { + ListCell *lc; + + /* Find an index with indisclustered set, or report error */ + foreach(lc, RelationGetIndexList(rel)) + { + indexOid = lfirst_oid(lc); + + if (get_index_isclustered(indexOid)) + break; + indexOid = InvalidOid; + } + + if (!OidIsValid(indexOid)) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("there is no previously clustered index for table \"%s\"", + RelationGetRelationName(rel))); + } + else if (indexname != NULL) + { + /* + * An index was specified; figure out its name. It must be in the + * same namespace as the relation. + */ + indexOid = get_relname_relid(indexname, + rel->rd_rel->relnamespace); + if (!OidIsValid(indexOid)) + ereport(ERROR, + errcode(ERRCODE_UNDEFINED_OBJECT), + errmsg("index \"%s\" for table \"%s\" does not exist", + indexname, RelationGetRelationName(rel))); + } + else + indexOid = InvalidOid; + + return indexOid; +} diff --git a/src/backend/commands/vacuum.c b/src/backend/commands/vacuum.c index 733ef40ae7c..8863ad0e8bd 100644 --- a/src/backend/commands/vacuum.c +++ b/src/backend/commands/vacuum.c @@ -2287,7 +2287,8 @@ vacuum_rel(Oid relid, RangeVar *relation, VacuumParams params, cluster_params.options |= CLUOPT_VERBOSE; /* VACUUM FULL is now a variant of CLUSTER; see cluster.c */ - cluster_rel(rel, InvalidOid, &cluster_params); + cluster_rel(REPACK_COMMAND_VACUUMFULL, false, rel, InvalidOid, + &cluster_params); /* cluster_rel closes the relation, but keeps lock */ rel = NULL; diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y index db43034b9db..062235817f4 100644 --- a/src/backend/parser/gram.y +++ b/src/backend/parser/gram.y @@ -280,7 +280,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); AlterCompositeTypeStmt AlterUserMappingStmt AlterRoleStmt AlterRoleSetStmt AlterPolicyStmt AlterStatsStmt AlterDefaultPrivilegesStmt DefACLAction - AnalyzeStmt CallStmt ClosePortalStmt ClusterStmt CommentStmt + AnalyzeStmt CallStmt ClosePortalStmt CommentStmt ConstraintsSetStmt CopyStmt CreateAsStmt CreateCastStmt CreateDomainStmt CreateExtensionStmt CreateGroupStmt CreateOpClassStmt CreateOpFamilyStmt AlterOpFamilyStmt CreatePLangStmt @@ -297,7 +297,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); GrantStmt GrantRoleStmt ImportForeignSchemaStmt IndexStmt InsertStmt ListenStmt LoadStmt LockStmt MergeStmt NotifyStmt ExplainableStmt PreparableStmt CreateFunctionStmt AlterFunctionStmt ReindexStmt RemoveAggrStmt - RemoveFuncStmt RemoveOperStmt RenameStmt ReturnStmt RevokeStmt RevokeRoleStmt + RemoveFuncStmt RemoveOperStmt RenameStmt RepackStmt ReturnStmt RevokeStmt RevokeRoleStmt RuleActionStmt RuleActionStmtOrEmpty RuleStmt SecLabelStmt SelectStmt TransactionStmt TransactionStmtLegacy TruncateStmt UnlistenStmt UpdateStmt VacuumStmt @@ -316,7 +316,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); %type <str> opt_single_name %type <list> opt_qualified_name -%type <boolean> opt_concurrently +%type <boolean> opt_concurrently opt_usingindex %type <dbehavior> opt_drop_behavior %type <list> opt_utility_option_list %type <list> utility_option_list @@ -763,7 +763,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query); QUOTE QUOTES RANGE READ REAL REASSIGN RECURSIVE REF_P REFERENCES REFERENCING - REFRESH REINDEX RELATIVE_P RELEASE RENAME REPEATABLE REPLACE REPLICA + REFRESH REINDEX RELATIVE_P RELEASE RENAME REPACK REPEATABLE REPLACE REPLICA RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP ROUTINE ROUTINES ROW ROWS RULE @@ -1025,7 +1025,6 @@ stmt: | CallStmt | CheckPointStmt | ClosePortalStmt - | ClusterStmt | CommentStmt | ConstraintsSetStmt | CopyStmt @@ -1099,6 +1098,7 @@ stmt: | RemoveFuncStmt | RemoveOperStmt | RenameStmt + | RepackStmt | RevokeStmt | RevokeRoleStmt | RuleStmt @@ -1135,6 +1135,11 @@ opt_concurrently: | /*EMPTY*/ { $$ = false; } ; +opt_usingindex: + USING INDEX { $$ = true; } + | /* EMPTY */ { $$ = false; } + ; + opt_drop_behavior: CASCADE { $$ = DROP_CASCADE; } | RESTRICT { $$ = DROP_RESTRICT; } @@ -11912,38 +11917,80 @@ CreateConversionStmt: /***************************************************************************** * * QUERY: + * REPACK [ (options) ] [ <qualified_name> [ USING INDEX <index_name> ] ] + * + * obsolete variants: * CLUSTER (options) [ <qualified_name> [ USING <index_name> ] ] * CLUSTER [VERBOSE] [ <qualified_name> [ USING <index_name> ] ] * CLUSTER [VERBOSE] <index_name> ON <qualified_name> (for pre-8.3) * *****************************************************************************/ -ClusterStmt: - CLUSTER '(' utility_option_list ')' qualified_name cluster_index_specification +RepackStmt: + REPACK opt_utility_option_list qualified_name USING INDEX name { - ClusterStmt *n = makeNode(ClusterStmt); + RepackStmt *n = makeNode(RepackStmt); + n->command = REPACK_COMMAND_REPACK; + n->relation = $3; + n->indexname = $6; + n->usingindex = true; + n->params = $2; + $$ = (Node *) n; + } + | REPACK opt_utility_option_list qualified_name opt_usingindex + { + RepackStmt *n = makeNode(RepackStmt); + + n->command = REPACK_COMMAND_REPACK; + n->relation = $3; + n->indexname = NULL; + n->usingindex = $4; + n->params = $2; + $$ = (Node *) n; + } + | REPACK opt_usingindex + { + RepackStmt *n = makeNode(RepackStmt); + + n->command = REPACK_COMMAND_REPACK; + n->relation = NULL; + n->indexname = NULL; + n->usingindex = $2; + n->params = NIL; + $$ = (Node *) n; + } + | CLUSTER '(' utility_option_list ')' qualified_name cluster_index_specification + { + RepackStmt *n = makeNode(RepackStmt); + + n->command = REPACK_COMMAND_CLUSTER; n->relation = $5; n->indexname = $6; + n->usingindex = true; n->params = $3; $$ = (Node *) n; } | CLUSTER opt_utility_option_list { - ClusterStmt *n = makeNode(ClusterStmt); + RepackStmt *n = makeNode(RepackStmt); + n->command = REPACK_COMMAND_CLUSTER; n->relation = NULL; n->indexname = NULL; + n->usingindex = true; n->params = $2; $$ = (Node *) n; } /* unparenthesized VERBOSE kept for pre-14 compatibility */ | CLUSTER opt_verbose qualified_name cluster_index_specification { - ClusterStmt *n = makeNode(ClusterStmt); + RepackStmt *n = makeNode(RepackStmt); + n->command = REPACK_COMMAND_CLUSTER; n->relation = $3; n->indexname = $4; + n->usingindex = true; if ($2) n->params = list_make1(makeDefElem("verbose", NULL, @2)); $$ = (Node *) n; @@ -11951,20 +11998,24 @@ ClusterStmt: /* unparenthesized VERBOSE kept for pre-17 compatibility */ | CLUSTER VERBOSE { - ClusterStmt *n = makeNode(ClusterStmt); + RepackStmt *n = makeNode(RepackStmt); + n->command = REPACK_COMMAND_CLUSTER; n->relation = NULL; n->indexname = NULL; + n->usingindex = true; n->params = list_make1(makeDefElem("verbose", NULL, @2)); $$ = (Node *) n; } /* kept for pre-8.3 compatibility */ | CLUSTER opt_verbose name ON qualified_name { - ClusterStmt *n = makeNode(ClusterStmt); + RepackStmt *n = makeNode(RepackStmt); + n->command = REPACK_COMMAND_CLUSTER; n->relation = $5; n->indexname = $3; + n->usingindex = true; if ($2) n->params = list_make1(makeDefElem("verbose", NULL, @2)); $$ = (Node *) n; @@ -17960,6 +18011,7 @@ unreserved_keyword: | RELATIVE_P | RELEASE | RENAME + | REPACK | REPEATABLE | REPLACE | REPLICA @@ -18592,6 +18644,7 @@ bare_label_keyword: | RELATIVE_P | RELEASE | RENAME + | REPACK | REPEATABLE | REPLACE | REPLICA diff --git a/src/backend/tcop/utility.c b/src/backend/tcop/utility.c index babc34d0cbe..f26440a9b79 100644 --- a/src/backend/tcop/utility.c +++ b/src/backend/tcop/utility.c @@ -277,9 +277,9 @@ ClassifyUtilityCommandAsReadOnly(Node *parsetree) return COMMAND_OK_IN_RECOVERY | COMMAND_OK_IN_READ_ONLY_TXN; } - case T_ClusterStmt: case T_ReindexStmt: case T_VacuumStmt: + case T_RepackStmt: { /* * These commands write WAL, so they're not strictly @@ -854,14 +854,14 @@ standard_ProcessUtility(PlannedStmt *pstmt, ExecuteCallStmt(castNode(CallStmt, parsetree), params, isAtomicContext, dest); break; - case T_ClusterStmt: - cluster(pstate, (ClusterStmt *) parsetree, isTopLevel); - break; - case T_VacuumStmt: ExecVacuum(pstate, (VacuumStmt *) parsetree, isTopLevel); break; + case T_RepackStmt: + ExecRepack(pstate, (RepackStmt *) parsetree, isTopLevel); + break; + case T_ExplainStmt: ExplainQuery(pstate, (ExplainStmt *) parsetree, params, dest); break; @@ -2850,10 +2850,6 @@ CreateCommandTag(Node *parsetree) tag = CMDTAG_CALL; break; - case T_ClusterStmt: - tag = CMDTAG_CLUSTER; - break; - case T_VacuumStmt: if (((VacuumStmt *) parsetree)->is_vacuumcmd) tag = CMDTAG_VACUUM; @@ -2861,6 +2857,10 @@ CreateCommandTag(Node *parsetree) tag = CMDTAG_ANALYZE; break; + case T_RepackStmt: + tag = CMDTAG_REPACK; + break; + case T_ExplainStmt: tag = CMDTAG_EXPLAIN; break; @@ -3498,7 +3498,7 @@ GetCommandLogLevel(Node *parsetree) lev = LOGSTMT_ALL; break; - case T_ClusterStmt: + case T_RepackStmt: lev = LOGSTMT_DDL; break; diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c index 1c12ddbae49..b2ad8ba45cd 100644 --- a/src/backend/utils/adt/pgstatfuncs.c +++ b/src/backend/utils/adt/pgstatfuncs.c @@ -268,6 +268,8 @@ pg_stat_get_progress_info(PG_FUNCTION_ARGS) cmdtype = PROGRESS_COMMAND_ANALYZE; else if (pg_strcasecmp(cmd, "CLUSTER") == 0) cmdtype = PROGRESS_COMMAND_CLUSTER; + else if (pg_strcasecmp(cmd, "REPACK") == 0) + cmdtype = PROGRESS_COMMAND_REPACK; else if (pg_strcasecmp(cmd, "CREATE INDEX") == 0) cmdtype = PROGRESS_COMMAND_CREATE_INDEX; else if (pg_strcasecmp(cmd, "BASEBACKUP") == 0) diff --git a/src/bin/psql/tab-complete.in.c b/src/bin/psql/tab-complete.in.c index dbc586c5bc3..cca12fb058b 100644 --- a/src/bin/psql/tab-complete.in.c +++ b/src/bin/psql/tab-complete.in.c @@ -1244,7 +1244,7 @@ static const char *const sql_commands[] = { "DELETE FROM", "DISCARD", "DO", "DROP", "END", "EXECUTE", "EXPLAIN", "FETCH", "GRANT", "IMPORT FOREIGN SCHEMA", "INSERT INTO", "LISTEN", "LOAD", "LOCK", "MERGE INTO", "MOVE", "NOTIFY", "PREPARE", - "REASSIGN", "REFRESH MATERIALIZED VIEW", "REINDEX", "RELEASE", + "REASSIGN", "REFRESH MATERIALIZED VIEW", "REINDEX", "RELEASE", "REPACK", "RESET", "REVOKE", "ROLLBACK", "SAVEPOINT", "SECURITY LABEL", "SELECT", "SET", "SHOW", "START", "TABLE", "TRUNCATE", "UNLISTEN", "UPDATE", "VACUUM", "VALUES", "WITH", @@ -4991,6 +4991,37 @@ match_previous_words(int pattern_id, COMPLETE_WITH_QUERY(Query_for_list_of_tablespaces); } +/* REPACK */ + else if (Matches("REPACK")) + COMPLETE_WITH_SCHEMA_QUERY(Query_for_list_of_clusterables); + else if (Matches("REPACK", "(*)")) + COMPLETE_WITH_SCHEMA_QUERY(Query_for_list_of_clusterables); + /* If we have REPACK <sth>, then add "USING INDEX" */ + else if (Matches("REPACK", MatchAnyExcept("("))) + COMPLETE_WITH("USING INDEX"); + /* If we have REPACK (*) <sth>, then add "USING INDEX" */ + else if (Matches("REPACK", "(*)", MatchAny)) + COMPLETE_WITH("USING INDEX"); + /* If we have REPACK <sth> USING, then add the index as well */ + else if (Matches("REPACK", MatchAny, "USING", "INDEX")) + { + set_completion_reference(prev3_wd); + COMPLETE_WITH_SCHEMA_QUERY(Query_for_index_of_table); + } + else if (HeadMatches("REPACK", "(*") && + !HeadMatches("REPACK", "(*)")) + { + /* + * This fires if we're in an unfinished parenthesized option list. + * get_previous_words treats a completed parenthesized option list as + * one word, so the above test is correct. + */ + if (ends_with(prev_wd, '(') || ends_with(prev_wd, ',')) + COMPLETE_WITH("VERBOSE"); + else if (TailMatches("VERBOSE")) + COMPLETE_WITH("ON", "OFF"); + } + /* SECURITY LABEL */ else if (Matches("SECURITY")) COMPLETE_WITH("LABEL"); diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 60088a64cbb..7f4138c7b36 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -31,8 +31,11 @@ typedef struct ClusterParams bits32 options; /* bitmask of CLUOPT_* */ } ClusterParams; -extern void cluster(ParseState *pstate, ClusterStmt *stmt, bool isTopLevel); -extern void cluster_rel(Relation OldHeap, Oid indexOid, ClusterParams *params); + +extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); + +extern void cluster_rel(RepackCommand command, bool usingindex, + Relation OldHeap, Oid indexOid, ClusterParams *params); extern void check_index_is_clusterable(Relation OldHeap, Oid indexOid, LOCKMODE lockmode); extern void mark_index_clustered(Relation rel, Oid indexOid, bool is_internal); diff --git a/src/include/commands/progress.h b/src/include/commands/progress.h index 7c736e7b03b..5f102743af4 100644 --- a/src/include/commands/progress.h +++ b/src/include/commands/progress.h @@ -56,24 +56,51 @@ #define PROGRESS_ANALYZE_PHASE_COMPUTE_EXT_STATS 4 #define PROGRESS_ANALYZE_PHASE_FINALIZE_ANALYZE 5 -/* Progress parameters for cluster */ -#define PROGRESS_CLUSTER_COMMAND 0 -#define PROGRESS_CLUSTER_PHASE 1 -#define PROGRESS_CLUSTER_INDEX_RELID 2 -#define PROGRESS_CLUSTER_HEAP_TUPLES_SCANNED 3 -#define PROGRESS_CLUSTER_HEAP_TUPLES_WRITTEN 4 -#define PROGRESS_CLUSTER_TOTAL_HEAP_BLKS 5 -#define PROGRESS_CLUSTER_HEAP_BLKS_SCANNED 6 -#define PROGRESS_CLUSTER_INDEX_REBUILD_COUNT 7 +/* + * Progress parameters for REPACK. + * + * Note: Since REPACK shares some code with CLUSTER, these values are also + * used by CLUSTER. (CLUSTER is now deprecated, so it makes little sense to + * introduce a separate set of constants.) + */ +#define PROGRESS_REPACK_COMMAND 0 +#define PROGRESS_REPACK_PHASE 1 +#define PROGRESS_REPACK_INDEX_RELID 2 +#define PROGRESS_REPACK_HEAP_TUPLES_SCANNED 3 +#define PROGRESS_REPACK_HEAP_TUPLES_WRITTEN 4 +#define PROGRESS_REPACK_TOTAL_HEAP_BLKS 5 +#define PROGRESS_REPACK_HEAP_BLKS_SCANNED 6 +#define PROGRESS_REPACK_INDEX_REBUILD_COUNT 7 -/* Phases of cluster (as advertised via PROGRESS_CLUSTER_PHASE) */ -#define PROGRESS_CLUSTER_PHASE_SEQ_SCAN_HEAP 1 -#define PROGRESS_CLUSTER_PHASE_INDEX_SCAN_HEAP 2 -#define PROGRESS_CLUSTER_PHASE_SORT_TUPLES 3 -#define PROGRESS_CLUSTER_PHASE_WRITE_NEW_HEAP 4 -#define PROGRESS_CLUSTER_PHASE_SWAP_REL_FILES 5 -#define PROGRESS_CLUSTER_PHASE_REBUILD_INDEX 6 -#define PROGRESS_CLUSTER_PHASE_FINAL_CLEANUP 7 +/* + * Phases of repack (as advertised via PROGRESS_REPACK_PHASE). + */ +#define PROGRESS_REPACK_PHASE_SEQ_SCAN_HEAP 1 +#define PROGRESS_REPACK_PHASE_INDEX_SCAN_HEAP 2 +#define PROGRESS_REPACK_PHASE_SORT_TUPLES 3 +#define PROGRESS_REPACK_PHASE_WRITE_NEW_HEAP 4 +#define PROGRESS_REPACK_PHASE_SWAP_REL_FILES 5 +#define PROGRESS_REPACK_PHASE_REBUILD_INDEX 6 +#define PROGRESS_REPACK_PHASE_FINAL_CLEANUP 7 + +/* + * Commands of PROGRESS_REPACK + * + * Currently we only have one command, so the PROGRESS_REPACK_COMMAND + * parameter is not necessary. However it makes cluster.c simpler if we have + * the same set of parameters for CLUSTER and REPACK - see the note on REPACK + * parameters above. + */ +#define PROGRESS_REPACK_COMMAND_REPACK 1 + +/* + * Progress parameters for cluster. + * + * Although we need to report REPACK and CLUSTER in separate views, the + * parameters and phases of CLUSTER are a subset of those of REPACK. Therefore + * we just use the appropriate values defined for REPACK above instead of + * defining a separate set of constants here. + */ /* Commands of PROGRESS_CLUSTER */ #define PROGRESS_CLUSTER_COMMAND_CLUSTER 1 diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h index 86a236bd58b..fcc25a0c592 100644 --- a/src/include/nodes/parsenodes.h +++ b/src/include/nodes/parsenodes.h @@ -3949,16 +3949,26 @@ typedef struct AlterSystemStmt } AlterSystemStmt; /* ---------------------- - * Cluster Statement (support pbrown's cluster index implementation) + * Repack Statement * ---------------------- */ -typedef struct ClusterStmt +typedef enum RepackCommand +{ + REPACK_COMMAND_CLUSTER, + REPACK_COMMAND_REPACK, + REPACK_COMMAND_VACUUMFULL, +} RepackCommand; + +typedef struct RepackStmt { NodeTag type; - RangeVar *relation; /* relation being indexed, or NULL if all */ - char *indexname; /* original index defined */ + RepackCommand command; /* type of command being run */ + RangeVar *relation; /* relation being repacked */ + char *indexname; /* order tuples by this index */ + bool usingindex; /* whether USING INDEX is specified */ List *params; /* list of DefElem nodes */ -} ClusterStmt; +} RepackStmt; + /* ---------------------- * Vacuum and Analyze Statements diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h index a4af3f717a1..22559369e2c 100644 --- a/src/include/parser/kwlist.h +++ b/src/include/parser/kwlist.h @@ -374,6 +374,7 @@ PG_KEYWORD("reindex", REINDEX, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("relative", RELATIVE_P, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("release", RELEASE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("rename", RENAME, UNRESERVED_KEYWORD, BARE_LABEL) +PG_KEYWORD("repack", REPACK, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("repeatable", REPEATABLE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("replace", REPLACE, UNRESERVED_KEYWORD, BARE_LABEL) PG_KEYWORD("replica", REPLICA, UNRESERVED_KEYWORD, BARE_LABEL) diff --git a/src/include/tcop/cmdtaglist.h b/src/include/tcop/cmdtaglist.h index d250a714d59..cceb312f2b3 100644 --- a/src/include/tcop/cmdtaglist.h +++ b/src/include/tcop/cmdtaglist.h @@ -196,6 +196,7 @@ PG_CMDTAG(CMDTAG_REASSIGN_OWNED, "REASSIGN OWNED", false, false, false) PG_CMDTAG(CMDTAG_REFRESH_MATERIALIZED_VIEW, "REFRESH MATERIALIZED VIEW", true, false, false) PG_CMDTAG(CMDTAG_REINDEX, "REINDEX", true, false, false) PG_CMDTAG(CMDTAG_RELEASE, "RELEASE", false, false, false) +PG_CMDTAG(CMDTAG_REPACK, "REPACK", false, false, false) PG_CMDTAG(CMDTAG_RESET, "RESET", false, false, false) PG_CMDTAG(CMDTAG_REVOKE, "REVOKE", true, false, false) PG_CMDTAG(CMDTAG_REVOKE_ROLE, "REVOKE ROLE", false, false, false) diff --git a/src/include/utils/backend_progress.h b/src/include/utils/backend_progress.h index dda813ab407..e69e366dcdc 100644 --- a/src/include/utils/backend_progress.h +++ b/src/include/utils/backend_progress.h @@ -28,6 +28,7 @@ typedef enum ProgressCommandType PROGRESS_COMMAND_CREATE_INDEX, PROGRESS_COMMAND_BASEBACKUP, PROGRESS_COMMAND_COPY, + PROGRESS_COMMAND_REPACK, } ProgressCommandType; #define PGSTAT_NUM_PROGRESS_PARAM 20 diff --git a/src/test/regress/expected/cluster.out b/src/test/regress/expected/cluster.out index 4d40a6809ab..5256628b51d 100644 --- a/src/test/regress/expected/cluster.out +++ b/src/test/regress/expected/cluster.out @@ -254,6 +254,63 @@ ORDER BY 1; clstr_tst_pkey (3 rows) +-- REPACK handles individual tables identically to CLUSTER, but it's worth +-- checking if it handles table hierarchies identically as well. +REPACK clstr_tst USING INDEX clstr_tst_c; +-- Verify that inheritance link still works +INSERT INTO clstr_tst_inh VALUES (0, 100, 'in child table 2'); +SELECT a,b,c,substring(d for 30), length(d) from clstr_tst; + a | b | c | substring | length +----+-----+------------------+--------------------------------+-------- + 10 | 14 | catorce | | + 18 | 5 | cinco | | + 9 | 4 | cuatro | | + 26 | 19 | diecinueve | | + 12 | 18 | dieciocho | | + 30 | 16 | dieciseis | | + 24 | 17 | diecisiete | | + 2 | 10 | diez | | + 23 | 12 | doce | | + 11 | 2 | dos | | + 25 | 9 | nueve | | + 31 | 8 | ocho | | + 1 | 11 | once | | + 28 | 15 | quince | | + 32 | 6 | seis | xyzzyxyzzyxyzzyxyzzyxyzzyxyzzy | 500000 + 29 | 7 | siete | | + 15 | 13 | trece | | + 22 | 30 | treinta | | + 17 | 32 | treinta y dos | | + 3 | 31 | treinta y uno | | + 5 | 3 | tres | | + 20 | 1 | uno | | + 6 | 20 | veinte | | + 14 | 25 | veinticinco | | + 21 | 24 | veinticuatro | | + 4 | 22 | veintidos | | + 19 | 29 | veintinueve | | + 16 | 28 | veintiocho | | + 27 | 26 | veintiseis | | + 13 | 27 | veintisiete | | + 7 | 23 | veintitres | | + 8 | 21 | veintiuno | | + 0 | 100 | in child table | | + 0 | 100 | in child table 2 | | +(34 rows) + +-- Verify that foreign key link still works +INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail'); +ERROR: insert or update on table "clstr_tst" violates foreign key constraint "clstr_tst_con" +DETAIL: Key (b)=(1111) is not present in table "clstr_tst_s". +SELECT conname FROM pg_constraint WHERE conrelid = 'clstr_tst'::regclass +ORDER BY 1; + conname +---------------------- + clstr_tst_a_not_null + clstr_tst_con + clstr_tst_pkey +(3 rows) + SELECT relname, relkind, EXISTS(SELECT 1 FROM pg_class WHERE oid = c.reltoastrelid) AS hastoast FROM pg_class c WHERE relname LIKE 'clstr_tst%' ORDER BY relname; @@ -381,6 +438,35 @@ SELECT * FROM clstr_1; 2 (2 rows) +-- REPACK w/o argument performs no ordering, so we can only check which tables +-- have the relfilenode changed. +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_old AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); +SET SESSION AUTHORIZATION regress_clstr_user; +SET client_min_messages = ERROR; -- order of "skipping" warnings may vary +REPACK; +RESET client_min_messages; +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_new AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); +-- Do the actual comparison. Unlike CLUSTER, clstr_3 should have been +-- processed because there is nothing like clustering index here. +SELECT o.relname FROM relnodes_old o +JOIN relnodes_new n ON o.relname = n.relname +WHERE o.relfilenode <> n.relfilenode +ORDER BY o.relname; + relname +--------- + clstr_1 + clstr_3 +(2 rows) + +SET SESSION AUTHORIZATION regress_clstr_user; -- Test MVCC-safety of cluster. There isn't much we can do to verify the -- results with a single backend... CREATE TABLE clustertest (key int PRIMARY KEY); @@ -495,6 +581,43 @@ ALTER TABLE clstrpart SET WITHOUT CLUSTER; ERROR: cannot mark index clustered in partitioned table ALTER TABLE clstrpart CLUSTER ON clstrpart_idx; ERROR: cannot mark index clustered in partitioned table +-- Check that REPACK sets new relfilenodes: it should process exactly the same +-- tables as CLUSTER did. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +REPACK clstrpart USING INDEX clstrpart_idx; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C"; + relname | level | relkind | ?column? +-------------+-------+---------+---------- + clstrpart | 0 | p | t + clstrpart1 | 1 | p | t + clstrpart11 | 2 | r | f + clstrpart12 | 2 | p | t + clstrpart2 | 1 | r | f + clstrpart3 | 1 | p | t + clstrpart33 | 2 | r | f +(7 rows) + +-- And finally the same for REPACK w/o index. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +REPACK clstrpart; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C"; + relname | level | relkind | ?column? +-------------+-------+---------+---------- + clstrpart | 0 | p | t + clstrpart1 | 1 | p | t + clstrpart11 | 2 | r | f + clstrpart12 | 2 | p | t + clstrpart2 | 1 | r | f + clstrpart3 | 1 | p | t + clstrpart33 | 2 | r | f +(7 rows) + DROP TABLE clstrpart; -- Ownership of partitions is checked CREATE TABLE ptnowner(i int unique) PARTITION BY LIST (i); @@ -513,7 +636,7 @@ CREATE TEMP TABLE ptnowner_oldnodes AS JOIN pg_class AS c ON c.oid=tree.relid; SET SESSION AUTHORIZATION regress_ptnowner; CLUSTER ptnowner USING ptnowner_i_idx; -WARNING: permission denied to cluster "ptnowner2", skipping it +WARNING: permission denied to execute CLUSTER on "ptnowner2", skipping it RESET SESSION AUTHORIZATION; SELECT a.relname, a.relfilenode=b.relfilenode FROM pg_class a JOIN ptnowner_oldnodes b USING (oid) ORDER BY a.relname COLLATE "C"; diff --git a/src/test/regress/expected/rules.out b/src/test/regress/expected/rules.out index dce8c672b40..84ae47080f5 100644 --- a/src/test/regress/expected/rules.out +++ b/src/test/regress/expected/rules.out @@ -2066,6 +2066,29 @@ pg_stat_progress_create_index| SELECT s.pid, s.param15 AS partitions_done FROM (pg_stat_get_progress_info('CREATE INDEX'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20) LEFT JOIN pg_database d ON ((s.datid = d.oid))); +pg_stat_progress_repack| SELECT s.pid, + s.datid, + d.datname, + s.relid, + CASE s.param2 + WHEN 0 THEN 'initializing'::text + WHEN 1 THEN 'seq scanning heap'::text + WHEN 2 THEN 'index scanning heap'::text + WHEN 3 THEN 'sorting tuples'::text + WHEN 4 THEN 'writing new heap'::text + WHEN 5 THEN 'swapping relation files'::text + WHEN 6 THEN 'rebuilding index'::text + WHEN 7 THEN 'performing final cleanup'::text + ELSE NULL::text + END AS phase, + (s.param3)::oid AS repack_index_relid, + s.param4 AS heap_tuples_scanned, + s.param5 AS heap_tuples_written, + s.param6 AS heap_blks_total, + s.param7 AS heap_blks_scanned, + s.param8 AS index_rebuild_count + FROM (pg_stat_get_progress_info('REPACK'::text) s(pid, datid, relid, param1, param2, param3, param4, param5, param6, param7, param8, param9, param10, param11, param12, param13, param14, param15, param16, param17, param18, param19, param20) + LEFT JOIN pg_database d ON ((s.datid = d.oid))); pg_stat_progress_vacuum| SELECT s.pid, s.datid, d.datname, diff --git a/src/test/regress/sql/cluster.sql b/src/test/regress/sql/cluster.sql index b7115f86104..cfcc3dc9761 100644 --- a/src/test/regress/sql/cluster.sql +++ b/src/test/regress/sql/cluster.sql @@ -76,6 +76,19 @@ INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail'); SELECT conname FROM pg_constraint WHERE conrelid = 'clstr_tst'::regclass ORDER BY 1; +-- REPACK handles individual tables identically to CLUSTER, but it's worth +-- checking if it handles table hierarchies identically as well. +REPACK clstr_tst USING INDEX clstr_tst_c; + +-- Verify that inheritance link still works +INSERT INTO clstr_tst_inh VALUES (0, 100, 'in child table 2'); +SELECT a,b,c,substring(d for 30), length(d) from clstr_tst; + +-- Verify that foreign key link still works +INSERT INTO clstr_tst (b, c) VALUES (1111, 'this should fail'); + +SELECT conname FROM pg_constraint WHERE conrelid = 'clstr_tst'::regclass +ORDER BY 1; SELECT relname, relkind, EXISTS(SELECT 1 FROM pg_class WHERE oid = c.reltoastrelid) AS hastoast @@ -159,6 +172,34 @@ INSERT INTO clstr_1 VALUES (1); CLUSTER clstr_1; SELECT * FROM clstr_1; +-- REPACK w/o argument performs no ordering, so we can only check which tables +-- have the relfilenode changed. +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_old AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); + +SET SESSION AUTHORIZATION regress_clstr_user; +SET client_min_messages = ERROR; -- order of "skipping" warnings may vary +REPACK; +RESET client_min_messages; + +RESET SESSION AUTHORIZATION; +CREATE TEMP TABLE relnodes_new AS +(SELECT relname, relfilenode +FROM pg_class +WHERE relname IN ('clstr_1', 'clstr_2', 'clstr_3')); + +-- Do the actual comparison. Unlike CLUSTER, clstr_3 should have been +-- processed because there is nothing like clustering index here. +SELECT o.relname FROM relnodes_old o +JOIN relnodes_new n ON o.relname = n.relname +WHERE o.relfilenode <> n.relfilenode +ORDER BY o.relname; + +SET SESSION AUTHORIZATION regress_clstr_user; + -- Test MVCC-safety of cluster. There isn't much we can do to verify the -- results with a single backend... @@ -229,6 +270,24 @@ SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM o CLUSTER clstrpart; ALTER TABLE clstrpart SET WITHOUT CLUSTER; ALTER TABLE clstrpart CLUSTER ON clstrpart_idx; + +-- Check that REPACK sets new relfilenodes: it should process exactly the same +-- tables as CLUSTER did. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +REPACK clstrpart USING INDEX clstrpart_idx; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C"; + +-- And finally the same for REPACK w/o index. +DROP TABLE old_cluster_info; +DROP TABLE new_cluster_info; +CREATE TEMP TABLE old_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +REPACK clstrpart; +CREATE TEMP TABLE new_cluster_info AS SELECT relname, level, relfilenode, relkind FROM pg_partition_tree('clstrpart'::regclass) AS tree JOIN pg_class c ON c.oid=tree.relid ; +SELECT relname, old.level, old.relkind, old.relfilenode = new.relfilenode FROM old_cluster_info AS old JOIN new_cluster_info AS new USING (relname) ORDER BY relname COLLATE "C"; + DROP TABLE clstrpart; -- Ownership of partitions is checked diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 3daba26b237..dc562ca662c 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -426,6 +426,7 @@ ClientCertName ClientConnectionInfo ClientData ClientSocket +ClusterCommand ClonePtrType ClosePortalStmt ClosePtrType @@ -2536,6 +2537,7 @@ ReorderBufferTupleCidKey ReorderBufferUpdateProgressTxnCB ReorderTuple RepOriginId +RepackStmt ReparameterizeForeignPathByChild_function ReplaceVarsFromTargetList_context ReplaceVarsNoMatchOption base-commit: db6461b1c9aae122b90bb52430f06efb306b371a -- 2.39.5 --v55yi6h5s6effx24-- ^ permalink raw reply [nested|flat] 4+ messages in thread
end of thread, other threads:[~2025-07-26 17:57 UTC | newest] Thread overview: 4+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2020-10-13 18:11 [PATCH v19 1/3] Move pg_stat_statements query jumbling to core. Julien Rouhaud <julien.rouhaud@free.fr> 2021-03-22 21:43 [PATCH v23 1/3] Move pg_stat_statements query jumbling to core. Bruce Momjian <bruce@momjian.us> 2021-03-22 21:43 [PATCH v20 1/3] Move pg_stat_statements query jumbling to core. Bruce Momjian <bruce@momjian.us> 2025-07-26 17:57 [PATCH v1] Add REPACK command. Álvaro Herrera <alvherre@kurilemu.de>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox