agora inbox for [email protected]  
help / color / mirror / Atom feed
[PATCH v33 07/11] Add DISTINCT support for IVM
32+ messages / 2 participants
[nested] [flat]

* [PATCH v33 07/11] Add DISTINCT support for IVM
@ 2023-05-31 10:08  Yugo Nagata <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Yugo Nagata @ 2023-05-31 10:08 UTC (permalink / raw)

When IMMV is created with DISTINCT, multiplicity of tuples is
counted and stored in  "__ivm_count__" column, which is a hidden
column of IMMV.  The value in __ivm_count__ is updated when IMMV
is maintained incrementally. A tuple in IMMV can be removed if
and only if the count becomes zero.
---
 src/backend/commands/createas.c     | 141 ++++++++++++++++++++------
 src/backend/commands/indexcmds.c    |  40 ++++++++
 src/backend/commands/matview.c      | 148 ++++++++++++++++++++++++++--
 src/backend/commands/tablecmds.c    |   9 ++
 src/backend/nodes/outfuncs.c        |   1 +
 src/backend/nodes/readfuncs.c       |   1 +
 src/backend/parser/parse_relation.c |  18 +++-
 src/backend/rewrite/rewriteDefine.c |   3 +-
 src/include/commands/createas.h     |   2 +
 src/include/nodes/parsenodes.h      |   2 +
 10 files changed, 320 insertions(+), 45 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index a424abbd32..7138dd59ce 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -50,6 +50,7 @@
 #include "parser/parser.h"
 #include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "rewrite/rewriteHandler.h"
 #include "tcop/tcopprot.h"
 #include "utils/builtins.h"
@@ -305,6 +306,9 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 					 errhint("functions must be marked IMMUTABLE")));
 
 		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
 	}
 
 	if (into->skipData)
@@ -409,6 +413,49 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		TargetEntry *tle;
+
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -532,7 +579,8 @@ intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
 		ColumnDef  *col;
 		char	   *colname;
 
-		if (lc)
+		/* Don't override hidden columns added for IVM */
+		if (lc && !isIvmName(NameStr(attribute->attname)))
 		{
 			colname = strVal(lfirst(lc));
 			lc = lnext(into->colNames, lc);
@@ -936,10 +984,6 @@ check_ivm_restriction_walker(Node *node, void *context)
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
-				if (qry->distinctClause)
-					ereport(ERROR,
-							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
 				if (qry->hasDistinctOn)
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -1086,12 +1130,18 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	char		idxname[NAMEDATALEN];
 	List	   *indexoidlist = RelationGetIndexList(matviewRel);
 	ListCell   *indexoidscan;
-	Bitmapset *key_attnos;
 
 	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
 
 	index = makeNode(IndexStmt);
 
+	/*
+	 * We consider null values not distinct to make sure that views with DISTINCT
+	 * or GROUP BY don't contain multiple NULL rows when NULL is inserted to
+	 * a base table concurrently.
+	 */
+	index->nulls_not_distinct = true;
+
 	index->unique = true;
 	index->primary = false;
 	index->isconstraint = false;
@@ -1118,41 +1168,68 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	index->concurrent = false;
 	index->if_not_exists = false;
 
-	/* create index on the base tables' primary key columns */
-	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
-	if (key_attnos)
+	if (query->distinctClause)
 	{
+		/* create unique constraint on all columns */
 		foreach(lc, query->targetList)
 		{
 			TargetEntry *tle = (TargetEntry *) lfirst(lc);
 			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
-
-			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
-			{
-				IndexElem  *iparam;
-
-				iparam = makeNode(IndexElem);
-				iparam->name = pstrdup(NameStr(attr->attname));
-				iparam->expr = NULL;
-				iparam->indexcolname = NULL;
-				iparam->collation = NIL;
-				iparam->opclass = NIL;
-				iparam->opclassopts = NIL;
-				iparam->ordering = SORTBY_DEFAULT;
-				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
-				index->indexParams = lappend(index->indexParams, iparam);
-			}
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
 		}
 	}
 	else
 	{
-		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
-		ereport(NOTICE,
-				(errmsg("could not create an index on materialized view \"%s\" automatically",
-						RelationGetRelationName(matviewRel)),
-				 errdetail("This target list does not have all the primary key columns. "),
-				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
-		return;
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+		if (key_attnos)
+		{
+			foreach(lc, query->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
 	}
 
 	/* If we have a compatible index, we don't need to create another. */
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index 2caab88aa5..462c15f9c8 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -40,6 +40,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1120,6 +1121,45 @@ DefineIndex(Oid tableId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (int i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 1061c37b2c..f2e8aa02a3 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -148,11 +148,15 @@ static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *
 
 static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
-			Query *query);
+			Query *query, bool use_count, char *count_colname);
 static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
 static char *get_matching_condition_string(List *keys);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
@@ -267,6 +271,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	Oid			matviewOid;
 	Relation	matviewRel;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -329,8 +334,13 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 						"CONCURRENTLY", "WITH NO DATA")));
 
 
-	dataQuery = get_matview_query(matviewRel);
+	viewQuery = get_matview_query(matviewRel);
 
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(viewQuery,NIL);
+	else
+		dataQuery = viewQuery;
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -510,8 +520,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
 	{
-		CreateIndexOnIMMV(dataQuery, matviewRel);
-		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(viewQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(viewQuery, matviewOid);
 	}
 
 	table_close(matviewRel, NoLock);
@@ -1533,6 +1543,13 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 			int	rte_index = lfirst_int(lc2);
 			TupleDesc		tupdesc_old;
 			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
 
 			/* calculate delta tables */
 			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
@@ -1545,7 +1562,8 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 			{
 				/* apply the delta tables to the materialized view */
 				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
-							tupdesc_old, tupdesc_new, query);
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
 			}
 			PG_CATCH();
 			{
@@ -2018,7 +2036,7 @@ rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte
 static void
 apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
-			Query *query)
+			Query *query, bool use_count, char *count_colname)
 {
 	StringInfoData querybuf;
 	StringInfoData target_list_buf;
@@ -2094,7 +2112,12 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 		if (rc != SPI_OK_REL_REGISTER)
 			elog(ERROR, "SPI_register failed");
 
-		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
 	}
 	/* For tuple insertion */
@@ -2116,7 +2139,11 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			elog(ERROR, "SPI_register failed");
 
 		/* apply new delta */
-		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
 	}
 
 	/* We're done maintaining the materialized view. */
@@ -2129,6 +2156,51 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 		elog(ERROR, "SPI_finish failed");
 }
 
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					")"
+					/* delete a tuple if this is to be deleted */
+					"DELETE FROM %s AS mv USING t "
+					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
 /*
  * apply_old_delta
  *
@@ -2178,6 +2250,66 @@ apply_old_delta(const char *matviewname, const char *deltaname_old,
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
 }
 
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s) "	/* insert a new tuple if this doesn't exist */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
 /*
  * apply_new_delta
  *
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 9e9dc5c2c1..ddb0732542 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -57,6 +57,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/sequence.h"
 #include "commands/tablecmds.h"
@@ -3696,6 +3697,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/nodes/outfuncs.c b/src/backend/nodes/outfuncs.c
index 3337b77ae6..c191f70a6f 100644
--- a/src/backend/nodes/outfuncs.c
+++ b/src/backend/nodes/outfuncs.c
@@ -510,6 +510,7 @@ _outRangeTblEntry(StringInfo str, const RangeTblEntry *node)
 			WRITE_INT_FIELD(rellockmode);
 			WRITE_UINT_FIELD(perminfoindex);
 			WRITE_NODE_FIELD(tablesample);
+			WRITE_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			WRITE_NODE_FIELD(subquery);
diff --git a/src/backend/nodes/readfuncs.c b/src/backend/nodes/readfuncs.c
index c4d01a441a..ffcab8cda2 100644
--- a/src/backend/nodes/readfuncs.c
+++ b/src/backend/nodes/readfuncs.c
@@ -361,6 +361,7 @@ _readRangeTblEntry(void)
 			READ_INT_FIELD(rellockmode);
 			READ_UINT_FIELD(perminfoindex);
 			READ_NODE_FIELD(tablesample);
+			READ_BOOL_FIELD(relisivm);
 			break;
 		case RTE_SUBQUERY:
 			READ_NODE_FIELD(subquery);
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index 2f64eaf0e3..a39358f125 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -97,7 +98,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool rte_visible_if_lateral(ParseState *pstate, RangeTblEntry *rte);
 static bool rte_visible_if_qualified(ParseState *pstate, RangeTblEntry *rte);
@@ -1503,6 +1504,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->inh = inh;
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1588,6 +1590,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->inh = inh;
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2757,7 +2760,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -3025,7 +3028,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -3042,7 +3045,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -3055,6 +3058,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3217,6 +3223,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index 6cc9a8d8bf..5d22dbcfcf 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -614,7 +614,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 396ad1bb4c..6b47e66bfd 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -29,6 +29,8 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
 extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
 
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index 85a62b538e..1366946bb4 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1106,6 +1106,8 @@ typedef struct RangeTblEntry
 	Index		perminfoindex pg_node_attr(query_jumble_ignore);
 	/* sampling info, or NULL */
 	struct TableSampleClause *tablesample;
+	/* incrementally maintainable materialized view? */
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
-- 
2.25.1


--Multipart=_Tue__2_Jul_2024_17_03_11_+0900_6OrVBZxOB4o_k6A1
Content-Type: text/x-diff;
 name="v33-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Disposition: attachment;
 filename="v33-0006-Add-Incremental-View-Maintenance-support.patch"
Content-Transfer-Encoding: 7bit



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 6cc2acb..7dfc311 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -310,6 +312,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -739,6 +742,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -1017,16 +1021,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1039,8 +1064,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1978,6 +2003,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 81efebc..21f1362 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index c1f4ab5..92abe13 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg15.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index ba9bbb6..74fc499 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -107,6 +107,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -199,6 +201,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -567,6 +570,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -920,16 +924,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -942,8 +967,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1373,6 +1398,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg16.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index a758e1a..d08b122 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -108,6 +108,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -200,6 +202,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -568,6 +571,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -921,16 +925,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -943,8 +968,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1374,6 +1399,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg17.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 9b7187e..21d21ea 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -115,6 +115,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -284,6 +286,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -703,6 +706,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -983,16 +987,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1005,8 +1030,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1924,6 +1949,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 8cf6ecf..0bbad25 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index acb508c..1d867d8 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg18.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index eedc5c8..c4d5cb1 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -282,6 +284,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -701,6 +704,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -981,16 +985,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1003,8 +1028,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1923,6 +1948,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 4bcd4e9..03fbd97 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 3e8929a..db2a21d 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc--






^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 6cc2acb..7dfc311 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -310,6 +312,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -739,6 +742,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -1017,16 +1021,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1039,8 +1064,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1978,6 +2003,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 81efebc..21f1362 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index c1f4ab5..92abe13 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg15.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index ba9bbb6..74fc499 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -107,6 +107,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -199,6 +201,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -567,6 +570,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -920,16 +924,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -942,8 +967,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1373,6 +1398,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg16.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index a758e1a..d08b122 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -108,6 +108,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -200,6 +202,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -568,6 +571,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -921,16 +925,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -943,8 +968,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1374,6 +1399,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg17.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 9b7187e..21d21ea 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -115,6 +115,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -284,6 +286,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -703,6 +706,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -983,16 +987,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1005,8 +1030,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1924,6 +1949,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 8cf6ecf..0bbad25 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index acb508c..1d867d8 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg18.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index eedc5c8..c4d5cb1 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -282,6 +284,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -701,6 +704,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -981,16 +985,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1003,8 +1028,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1923,6 +1948,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 4bcd4e9..03fbd97 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 3e8929a..db2a21d 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc--






^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 6cc2acb..7dfc311 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -310,6 +312,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -739,6 +742,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -1017,16 +1021,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1039,8 +1064,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1978,6 +2003,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 81efebc..21f1362 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index c1f4ab5..92abe13 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg15.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index ba9bbb6..74fc499 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -107,6 +107,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -199,6 +201,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -567,6 +570,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -920,16 +924,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -942,8 +967,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1373,6 +1398,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg16.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index a758e1a..d08b122 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -108,6 +108,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -200,6 +202,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -568,6 +571,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -921,16 +925,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -943,8 +968,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1374,6 +1399,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg17.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 9b7187e..21d21ea 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -115,6 +115,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -284,6 +286,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -703,6 +706,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -983,16 +987,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1005,8 +1030,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1924,6 +1949,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 8cf6ecf..0bbad25 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index acb508c..1d867d8 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg18.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index eedc5c8..c4d5cb1 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -282,6 +284,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -701,6 +704,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -981,16 +985,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1003,8 +1028,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1923,6 +1948,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 4bcd4e9..03fbd97 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 3e8929a..db2a21d 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc--






^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 6cc2acb..7dfc311 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -310,6 +312,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -739,6 +742,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -1017,16 +1021,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1039,8 +1064,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1978,6 +2003,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 81efebc..21f1362 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index c1f4ab5..92abe13 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg15.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index ba9bbb6..74fc499 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -107,6 +107,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -199,6 +201,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -567,6 +570,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -920,16 +924,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -942,8 +967,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1373,6 +1398,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg16.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index a758e1a..d08b122 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -108,6 +108,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -200,6 +202,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -568,6 +571,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -921,16 +925,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -943,8 +968,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1374,6 +1399,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg17.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 9b7187e..21d21ea 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -115,6 +115,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -284,6 +286,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -703,6 +706,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -983,16 +987,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1005,8 +1030,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1924,6 +1949,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 8cf6ecf..0bbad25 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index acb508c..1d867d8 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg18.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index eedc5c8..c4d5cb1 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -282,6 +284,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -701,6 +704,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -981,16 +985,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1003,8 +1028,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1923,6 +1948,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 4bcd4e9..03fbd97 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 3e8929a..db2a21d 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc--






^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 6cc2acb..7dfc311 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -310,6 +312,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -739,6 +742,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -1017,16 +1021,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1039,8 +1064,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1978,6 +2003,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 81efebc..21f1362 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index c1f4ab5..92abe13 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg15.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index ba9bbb6..74fc499 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -107,6 +107,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -199,6 +201,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -567,6 +570,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -920,16 +924,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -942,8 +967,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1373,6 +1398,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg16.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index a758e1a..d08b122 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -108,6 +108,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -200,6 +202,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -568,6 +571,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -921,16 +925,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -943,8 +968,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1374,6 +1399,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg17.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 9b7187e..21d21ea 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -115,6 +115,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -284,6 +286,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -703,6 +706,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -983,16 +987,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1005,8 +1030,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1924,6 +1949,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 8cf6ecf..0bbad25 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index acb508c..1d867d8 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg18.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index eedc5c8..c4d5cb1 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -282,6 +284,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -701,6 +704,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -981,16 +985,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1003,8 +1028,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1923,6 +1948,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 4bcd4e9..03fbd97 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 3e8929a..db2a21d 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc--






^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 6cc2acb..7dfc311 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -310,6 +312,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -739,6 +742,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -1017,16 +1021,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1039,8 +1064,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1978,6 +2003,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 81efebc..21f1362 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index c1f4ab5..92abe13 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg15.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index ba9bbb6..74fc499 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -107,6 +107,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -199,6 +201,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -567,6 +570,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -920,16 +924,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -942,8 +967,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1373,6 +1398,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg16.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index a758e1a..d08b122 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -108,6 +108,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -200,6 +202,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -568,6 +571,7 @@ executeJsonPath(JsonPath *path, Jsonb *vars, Jsonb *json, bool throwErrors,
 	cxt.lastGeneratedObjectId = vars ? 2 : 1;
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenseOfErrors(&cxt) && !result)
@@ -921,16 +925,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -943,8 +968,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1374,6 +1399,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index eafb421..5e1bd19 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -792,6 +792,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 8163fc6..4c62fe2 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -155,6 +155,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg17.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index 9b7187e..21d21ea 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -115,6 +115,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -284,6 +286,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -703,6 +706,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -983,16 +987,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1005,8 +1030,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1924,6 +1949,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 8cf6ecf..0bbad25 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index acb508c..1d867d8 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc
Content-Type: text/x-patch
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename=0001-collapse-consecutive-jsonpath-any-pg18.patch



^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-06-18 20:30 UTC (permalink / raw)

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in executeAnyItem().
k consecutive .** operators can degrade performance to O(N^k) on a document
with N nodes, even though a chain like $.**.**.** is redundant for existence
semantics and equivalent to a single $.** with merged level bounds.

This was reported as a performance problem when expressions such as
$.**.**.**.**.* are evaluated with @? against deeply nested JSON: the same
query without the trailing .* completes in sub-millisecond time, while the
form with redundant .** segments can run for many minutes.  A similar pattern
in strict mode can also provoke very large memory allocation attempts.

Collapse consecutive jpiAny nodes at execution time for existence queries
(@? and jsonb_path_exists), merging their level bounds and performing a
single executeAnyItem() pass.

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Andrey Rachitskiy <[email protected]>
Backpatch-through: 15
---
 src/backend/utils/adt/jsonpath_exec.c     | 47 +++++++++++++++++++---
 .../src/test/regress/expected/jsonb_jsonpath.out   | 40 ++++++++++++++++++
 src/test/regress/sql/jsonb_jsonpath.sql   | 11 +++++
 3 files changed, 93 insertions(+), 5 deletions(-)

diff --git a/src/backend/utils/adt/jsonpath_exec.c b/src/backend/utils/adt/jsonpath_exec.c
index eedc5c8..c4d5cb1 100644
--- a/src/backend/utils/adt/jsonpath_exec.c
+++ b/src/backend/utils/adt/jsonpath_exec.c
@@ -113,6 +113,8 @@ typedef struct JsonPathExecContext
 										 * ignored */
 	bool		throwErrors;	/* with "false" all suppressible errors are
 								 * suppressed */
+	bool		existsOnly;		/* @? / jsonb_path_exists: may collapse
+							 * redundant consecutive .** accessors */
 	bool		useTz;
 } JsonPathExecContext;
 
@@ -282,6 +284,7 @@ static JsonPathExecResult executeAnyItem(JsonPathExecContext *cxt,
 										 JsonPathItem *jsp, JsonbContainer *jbc, JsonValueList *found,
 										 uint32 level, uint32 first, uint32 last,
 										 bool ignoreStructuralErrors, bool unwrapNext);
+static uint32 mergeAnyBound(uint32 a, uint32 b);
 static JsonPathBool executePredicate(JsonPathExecContext *cxt,
 									 JsonPathItem *pred, JsonPathItem *larg, JsonPathItem *rarg,
 									 JsonbValue *jb, bool unwrapRightArg,
@@ -701,6 +704,7 @@ executeJsonPath(JsonPath *path, void *vars, JsonPathGetVarCallback getVar,
 	cxt.lastGeneratedObjectId = 1 + countVars(vars);
 	cxt.innermostArraySize = -1;
 	cxt.throwErrors = throwErrors;
+	cxt.existsOnly = (result == NULL);
 	cxt.useTz = useTz;
 
 	if (jspStrictAbsenceOfErrors(&cxt) && !result)
@@ -981,16 +985,37 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 
 		case jpiAny:
 			{
-				bool		hasNext = jspGetNext(jsp, &elem);
+				JsonPathItem elem;
+				bool		hasNext;
+				uint32		first;
+				uint32		last;
+
+				hasNext = jspGetNext(jsp, &elem);
+				first = jsp->content.anybounds.first;
+				last = jsp->content.anybounds.last;
+
+				/*
+				 * Consecutive .** accessors are redundant for existence
+				 * queries and multiply traversal cost.
+				 */
+				if (cxt->existsOnly)
+				{
+					while (hasNext && elem.type == jpiAny)
+					{
+						first = mergeAnyBound(first, elem.content.anybounds.first);
+						last = mergeAnyBound(last, elem.content.anybounds.last);
+						hasNext = jspGetNext(&elem, &elem);
+					}
+				}
 
 				/* first try without any intermediate steps */
-				if (jsp->content.anybounds.first == 0)
+				if (first == 0)
 				{
 					bool		savedIgnoreStructuralErrors;
 
 					savedIgnoreStructuralErrors = cxt->ignoreStructuralErrors;
 					cxt->ignoreStructuralErrors = true;
-					res = executeNextItem(cxt, jsp, &elem,
+					res = executeNextItem(cxt, jsp, hasNext ? &elem : NULL,
 										  jb, found, true);
 					cxt->ignoreStructuralErrors = savedIgnoreStructuralErrors;
 
@@ -1003,8 +1028,8 @@ executeItemOptUnwrapTarget(JsonPathExecContext *cxt, JsonPathItem *jsp,
 						(cxt, hasNext ? &elem : NULL,
 						 jb->val.binary.data, found,
 						 1,
-						 jsp->content.anybounds.first,
-						 jsp->content.anybounds.last,
+						 first,
+						 last,
 						 true, jspAutoUnwrap(cxt));
 				break;
 			}
@@ -1923,6 +1948,18 @@ executeNestedBoolItem(JsonPathExecContext *cxt, JsonPathItem *jsp,
 	return res;
 }
 
+
+/*
+ * Merge level bounds of two consecutive .** accessors.
+ */
+static uint32
+mergeAnyBound(uint32 a, uint32 b)
+{
+	if (a == PG_UINT32_MAX || b == PG_UINT32_MAX)
+		return PG_UINT32_MAX;
+	return a + b;
+}
+
 /*
  * Implementation of several jsonpath nodes:
  *  - jpiAny (.** accessor),
diff --git a/src/test/regress/expected/jsonb_jsonpath.out b/src/test/regress/expected/jsonb_jsonpath.out
index 4bcd4e9..03fbd97 100644
--- a/src/test/regress/expected/jsonb_jsonpath.out
+++ b/src/test/regress/expected/jsonb_jsonpath.out
@@ -785,6 +785,46 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
  t
 (1 row)
 
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+ ?column? 
+----------
+ t
+(1 row)
+
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+ ?column? 
+----------
+ f
+(1 row)
+
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+ jsonb_path_exists 
+-------------------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+ ?column? 
+----------
+ t
+(1 row)
+
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
  jsonb_path_query 
 ------------------
diff --git a/src/test/regress/sql/jsonb_jsonpath.sql b/src/test/regress/sql/jsonb_jsonpath.sql
index 3e8929a..db2a21d 100644
--- a/src/test/regress/sql/jsonb_jsonpath.sql
+++ b/src/test/regress/sql/jsonb_jsonpath.sql
@@ -150,6 +150,17 @@ select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{0 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to last}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{1 to 2}.b ? ( @ > 0)';
 select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**{2 to 3}.b ? ( @ > 0)';
+-- Redundant consecutive .** accessors are collapsed for existence queries
+-- (@? and jsonb_path_exists), avoiding multiplicative traversal cost.
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 0)';
+select jsonb '{"a": {"c": {"b": 1}}}' @? '$.**.**.b ? (@ > 99)';
+select jsonb_path_exists('{"a": {"c": {"b": 1}}}', '$.**.**.b ? (@ > 0)');
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'lax $.**.**.**.**';
+select ('[' || repeat('[', 50) || '0' || repeat(']', 50) || ']')::jsonb
+	@? 'strict $.**.**.**';
+
 
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.x))');
 select jsonb_path_query('{"g": {"x": 2}}', '$.g ? (exists (@.y))');
-- 
2.47.3

--MP_/BlgiDE/t55y8Vb7V2uvNybc--






^ permalink  raw  reply  [nested|flat] 32+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-07-06 18:50  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 32+ messages in thread

From: Andrey Rachitskiy @ 2026-07-06 18:50 UTC (permalink / raw)
  To: PostgreSQL Hackers <[email protected]>; +Cc: Nikolay Shaplov <[email protected]>; Amit Langote <[email protected]>; Andrey Borodin <[email protected]>


Hi, Hackers!

When a jsonpath expression contains multiple consecutive .** (jpiAny)
accessors, each one triggers a full subtree traversal in
executeAnyItem().  A chain of k such accessors can cost O(N^k) on a
document with N nodes, even though for existence semantics it is
equivalent to a single .** with merged level bounds.


Background
----------

We originally reported this as BUG #19362 [1], with a follow-up
analysis [2].  The original report used a fuzzer-generated sql
statement; the follow-up gave a clearer reproduction. For example, on
a JSON array nested 1000 levels deep:
  SELECT data @? '$.**.**.**.**' FROM test_json;     -- ~0.5 ms
  SELECT data @? '$.**.**.**.**.*' FROM test_json;   -- >23 min
  (cancelled)

Andrey Borodin replied that this looks like a performance optimization
opportunity rather than a bug, and asked for a more realistic example of
what a user might want but not get in reasonable time [3].  We agree,
and are sending this to pgsql-hackers.

A developer searching semi-structured JSON (nested categories, comment
threads, task lists) might use @? / jsonb_path_exists with paths such as
$.**.b ? (@ > 0) — "does key b exist anywhere, with this predicate?"
Templates, copy-paste, or auto-generated paths can accidentally
accumulate redundant .** segments (.**.**.b), which is semantically the
same as $.**.b for existence checks but much slower.

If an application accepts user-supplied jsonpath for @?, a path with
many consecutive .** operators also becomes an easy DoS vector: no
special privileges beyond the ability to run a query.


Proposal
--------

Collapse consecutive jpiAny nodes at execution time for existence
queries (@? and jsonb_path_exists): merge level bounds and perform a
single executeAnyItem() pass (.** {a,b} .** {c,d} -> .** {a+c,b+d}).

For existence checks this bounds the cost of a k-deep .** chain to
O(N) instead of O(N^k), so paths that previously hung the backend for
many minutes on the BUG #19362 reproduction now finish in under a
millisecond. That closes a practical DoS vector for applications that
pass user-supplied jsonpath to @?.

This patch intentionally does NOT change jsonb_path_query or @@: those
functions collect item sequences, and consecutive .** affects result
multiplicity (e.g. lax $.**.** vs $.**).  The optimization is gated on
existsOnly (result == NULL in executeJsonPath()).

jsonb_jsonpath regress tests are included.

Backpatch-through: 15.
Separate patches for REL_15_STABLE through master are attached.

[1] https://postgr.es/m/[email protected]
[2] https://postgr.es/m/[email protected]
[3]
https://postgr.es/m/[email protected]

Author: Andrey Rachitskiy <[email protected]>
Reported-by: Nikolay Shaplov <[email protected]>
Tested-on: REL_15_STABLE .. master

-- 
Regards,
Andrey Rachitskiy



^ permalink  raw  reply  [nested|flat] 32+ messages in thread


end of thread, other threads:[~2026-07-06 18:50 UTC | newest]

Thread overview: 32+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2023-05-31 10:08 [PATCH v33 07/11] Add DISTINCT support for IVM Yugo Nagata <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-06-18 20:30 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>
2026-07-06 18:50 [PATCH] Collapse consecutive .** accessors for jsonpath exists queries Andrey Rachitskiy <[email protected]>

This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox