agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v10 1/2] Key PGSTAT_KIND_RELATION by relfile locator
252+ messages / 2 participants
[nested] [flat]

* [PATCH v10 1/2] Key PGSTAT_KIND_RELATION by relfile locator
@ 2025-10-01 09:45 Bertrand Drouvot <[email protected]>
  0 siblings, 0 replies; 252+ messages in thread

From: Bertrand Drouvot @ 2025-10-01 09:45 UTC (permalink / raw)

This patch changes the key used for the PGSTAT_KIND_RELATION statistic kind.
Instead of the relation oid, it now relies on:

- dboid (linked to RelFileLocator's dbOid)
- objoid which is the result of a new macro (namely RelFileLocatorToPgStatObjid())
that computes an objoid based on the RelFileLocator's spcOid and the
RelFileLocator's relNumber.

This is possible as, since b14e9ce7d55c, the objoid is now uint64 and spcOid
and relNumber are 32 bits.

That will allow us to add new stats (add writes counters) and ensure that some
counters (n_dead_tup and friends) are replicated.

The patch introduces pgstat_reloid_to_relfilelocator() to 1) avoid calling
RelationIdGetRelation() to get the relfilelocator based on the relation oid
and 2) handle the partitioned table case.

Please note that:

- when running pg_stat_have_stats('relation',...) we now need to be connected
to the database that hosts the relation. As pg_stat_have_stats() is not
documented publicly, then the changes done in 029_stats_restart.pl look
enough.

- this patch does not handle rewrites so some tests are failing. It's only
intent is to ease the review and should not be pushed without being
merged with the following patch that handles the rewrites.

- it can be used to test that stats are incremented correctly and that we're
able to retrieve them as long as rewrites are not involved.
---
 src/backend/postmaster/autovacuum.c          |  17 +-
 src/backend/utils/activity/pgstat_relation.c | 236 ++++++++++++++++---
 src/backend/utils/adt/pgstatfuncs.c          |  22 +-
 src/include/catalog/pg_tablespace.dat        |   4 +
 src/include/catalog/pg_tablespace.h          |   8 +
 src/include/pgstat.h                         |  15 +-
 src/include/utils/pgstat_internal.h          |   1 +
 src/test/recovery/t/029_stats_restart.pl     |  40 ++--
 8 files changed, 271 insertions(+), 72 deletions(-)
   6.1% src/backend/postmaster/
  61.6% src/backend/utils/activity/
   5.1% src/backend/utils/adt/
   3.2% src/include/catalog/
   5.6% src/include/
  18.1% src/test/recovery/t/

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 1bd3924e35e..a11174b25ad 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.c
@@ -2014,12 +2014,16 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		if (classForm->relkind != RELKIND_RELATION &&
 			classForm->relkind != RELKIND_MATVIEW)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * Check if it is a temp table (presumably, of some other backend's).
@@ -2048,8 +2052,7 @@ do_autovacuum(void)
 
 		/* Fetch reloptions and the pgstat entry for this table */
 		relopts = extract_autovac_opts(tuple, pg_class_desc);
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		/* Check if it needs vacuum or analyze */
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
@@ -2114,6 +2117,7 @@ do_autovacuum(void)
 		bool		dovacuum;
 		bool		doanalyze;
 		bool		wraparound;
+		RelFileLocator locator;
 
 		/*
 		 * We cannot safely process other backends' temp tables, so skip 'em.
@@ -2122,6 +2126,9 @@ do_autovacuum(void)
 			continue;
 
 		relid = classForm->oid;
+		locator.dbOid = classForm->relisshared ? InvalidOid : MyDatabaseId;
+		locator.spcOid = classForm->reltablespace;
+		locator.relNumber = classForm->relfilenode;
 
 		/*
 		 * fetch reloptions -- if this toast table does not have them, try the
@@ -2141,8 +2148,7 @@ do_autovacuum(void)
 		}
 
 		/* Fetch the pgstat entry for this table */
-		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-												  relid);
+		tabentry = pgstat_fetch_stat_tabentry_by_locator(locator);
 
 		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
 								  effective_multixact_freeze_max_age,
@@ -2939,8 +2945,7 @@ recheck_relation_needs_vacanalyze(Oid relid,
 	PgStat_StatTabEntry *tabentry;
 
 	/* fetch the pgstat table entry */
-	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
-											  relid);
+	tabentry = pgstat_fetch_stat_tabentry_ext(relid);
 
 	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
 							  effective_multixact_freeze_max_age,
diff --git a/src/backend/utils/activity/pgstat_relation.c b/src/backend/utils/activity/pgstat_relation.c
index 55a10c299db..a267e93f8be 100644
--- a/src/backend/utils/activity/pgstat_relation.c
+++ b/src/backend/utils/activity/pgstat_relation.c
@@ -17,12 +17,17 @@
 
 #include "postgres.h"
 
+#include "access/htup_details.h"
 #include "access/twophase_rmgr.h"
 #include "access/xact.h"
 #include "catalog/catalog.h"
+#include "catalog/pg_tablespace.h"
+#include "storage/lmgr.h"
 #include "utils/memutils.h"
 #include "utils/pgstat_internal.h"
 #include "utils/rel.h"
+#include "utils/relmapper.h"
+#include "utils/syscache.h"
 #include "utils/timestamp.h"
 
 
@@ -36,13 +41,12 @@ typedef struct TwoPhasePgStatRecord
 	PgStat_Counter inserted_pre_truncdrop;
 	PgStat_Counter updated_pre_truncdrop;
 	PgStat_Counter deleted_pre_truncdrop;
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	RelFileLocator locator;		/* table's rd_locator */
 	bool		truncdropped;	/* was the relation truncated/dropped? */
 } TwoPhasePgStatRecord;
 
 
-static PgStat_TableStatus *pgstat_prep_relation_pending(Oid rel_id, bool isshared);
+static PgStat_TableStatus *pgstat_prep_relation_pending(RelFileLocator locator);
 static void add_tabstat_xact_level(PgStat_TableStatus *pgstat_info, int nest_level);
 static void ensure_tabstat_xact_level(PgStat_TableStatus *pgstat_info);
 static void save_truncdrop_counters(PgStat_TableXactStatus *trans, bool is_drop);
@@ -60,8 +64,7 @@ pgstat_copy_relation_stats(Relation dst, Relation src)
 	PgStatShared_Relation *dstshstats;
 	PgStat_EntryRef *dst_ref;
 
-	srcstats = pgstat_fetch_stat_tabentry_ext(src->rd_rel->relisshared,
-											  RelationGetRelid(src));
+	srcstats = pgstat_fetch_stat_tabentry_ext(RelationGetRelid(src));
 	if (!srcstats)
 		return;
 
@@ -94,8 +97,10 @@ pgstat_init_relation(Relation rel)
 
 	/*
 	 * We only count stats for relations with storage and partitioned tables
+	 * and we don't count stats generated during a rewrite.
 	 */
-	if (!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE)
+	if ((!RELKIND_HAS_STORAGE(relkind) && relkind != RELKIND_PARTITIONED_TABLE) ||
+		OidIsValid(rel->rd_rel->relrewrite))
 	{
 		rel->pgstat_enabled = false;
 		rel->pgstat_info = NULL;
@@ -130,12 +135,37 @@ pgstat_init_relation(Relation rel)
 void
 pgstat_assoc_relation(Relation rel)
 {
+	RelFileLocator locator;
+
 	Assert(rel->pgstat_enabled);
 	Assert(rel->pgstat_info == NULL);
 
+	/*
+	 * Don't associate stats for relations without storage and non partitioned
+	 * tables.
+	 */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind) &&
+		rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		return;
+
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
+
 	/* Else find or make the PgStat_TableStatus entry, and update link */
-	rel->pgstat_info = pgstat_prep_relation_pending(RelationGetRelid(rel),
-													rel->rd_rel->relisshared);
+	rel->pgstat_info = pgstat_prep_relation_pending(locator);
 
 	/* don't allow link a stats to multiple relcache entries */
 	Assert(rel->pgstat_info->relation == NULL);
@@ -167,9 +197,13 @@ pgstat_unlink_relation(Relation rel)
 void
 pgstat_create_relation(Relation rel)
 {
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_create_transactional(PGSTAT_KIND_RELATION,
-								rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-								RelationGetRelid(rel));
+								rel->rd_locator.dbOid,
+								RelFileLocatorToPgStatObjid(rel->rd_locator));
 }
 
 /*
@@ -181,9 +215,13 @@ pgstat_drop_relation(Relation rel)
 	int			nest_level = GetCurrentTransactionNestLevel();
 	PgStat_TableStatus *pgstat_info;
 
+	/* don't track stats for relations without storage */
+	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
+		return;
+
 	pgstat_drop_transactional(PGSTAT_KIND_RELATION,
-							  rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId,
-							  RelationGetRelid(rel));
+							  rel->rd_locator.dbOid,
+							  RelFileLocatorToPgStatObjid(rel->rd_locator));
 
 	if (!pgstat_should_count_relation(rel))
 		return;
@@ -213,20 +251,23 @@ pgstat_report_vacuum(Relation rel, PgStat_Counter livetuples,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
 
+	locator = rel->rd_locator;
+
 	/* Store the data in the table's hash table entry. */
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel), false);
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
+											false);
 
 	shtabentry = (PgStatShared_Relation *) entry_ref->shared_stats;
 	tabentry = &shtabentry->stats;
@@ -285,9 +326,9 @@ pgstat_report_analyze(Relation rel,
 	PgStat_EntryRef *entry_ref;
 	PgStatShared_Relation *shtabentry;
 	PgStat_StatTabEntry *tabentry;
-	Oid			dboid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
 	TimestampTz ts;
 	PgStat_Counter elapsedtime;
+	RelFileLocator locator;
 
 	if (!pgstat_track_counts)
 		return;
@@ -325,9 +366,25 @@ pgstat_report_analyze(Relation rel,
 	ts = GetCurrentTimestamp();
 	elapsedtime = TimestampDifferenceMilliseconds(starttime, ts);
 
+	if (rel->rd_rel->relkind != RELKIND_PARTITIONED_TABLE)
+		locator = rel->rd_locator;
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator.dbOid = (rel->rd_rel->relisshared ? InvalidOid : MyDatabaseId);
+		locator.spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator.relNumber = rel->rd_id;
+	}
 	/* block acquiring lock for the same reason as pgstat_report_autovac() */
-	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION, dboid,
-											RelationGetRelid(rel),
+	entry_ref = pgstat_get_entry_ref_locked(PGSTAT_KIND_RELATION,
+											locator.dbOid,
+											RelFileLocatorToPgStatObjid(locator),
 											false);
 	/* can't get dropped while accessed */
 	Assert(entry_ref != NULL && entry_ref->shared_stats != NULL);
@@ -468,7 +525,16 @@ pgstat_update_heap_dead_tuples(Relation rel, int delta)
 PgStat_StatTabEntry *
 pgstat_fetch_stat_tabentry(Oid relid)
 {
-	return pgstat_fetch_stat_tabentry_ext(IsSharedRelation(relid), relid);
+	return pgstat_fetch_stat_tabentry_ext(relid);
+}
+
+PgStat_StatTabEntry *
+pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator)
+{
+	return (PgStat_StatTabEntry *) pgstat_fetch_entry(
+													  PGSTAT_KIND_RELATION,
+													  locator.dbOid,
+													  RelFileLocatorToPgStatObjid(locator));
 }
 
 /*
@@ -476,12 +542,14 @@ pgstat_fetch_stat_tabentry(Oid relid)
  * whether the to-be-accessed table is a shared relation or not.
  */
 PgStat_StatTabEntry *
-pgstat_fetch_stat_tabentry_ext(bool shared, Oid reloid)
+pgstat_fetch_stat_tabentry_ext(Oid reloid)
 {
-	Oid			dboid = (shared ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	return (PgStat_StatTabEntry *)
-		pgstat_fetch_entry(PGSTAT_KIND_RELATION, dboid, reloid);
+	if (!pgstat_reloid_to_relfilelocator(reloid, &locator))
+		return NULL;
+
+	return pgstat_fetch_stat_tabentry_by_locator(locator);
 }
 
 /*
@@ -503,14 +571,17 @@ find_tabstat_entry(Oid rel_id)
 	PgStat_TableXactStatus *trans;
 	PgStat_TableStatus *tabentry = NULL;
 	PgStat_TableStatus *tablestatus = NULL;
+	RelFileLocator locator;
+
+	if (!pgstat_reloid_to_relfilelocator(rel_id, &locator))
+		return NULL;
+
+	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION,
+										   locator.dbOid,
+										   RelFileLocatorToPgStatObjid(locator));
 
-	entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, MyDatabaseId, rel_id);
 	if (!entry_ref)
-	{
-		entry_ref = pgstat_fetch_pending_entry(PGSTAT_KIND_RELATION, InvalidOid, rel_id);
-		if (!entry_ref)
-			return tablestatus;
-	}
+		return tablestatus;
 
 	tabentry = (PgStat_TableStatus *) entry_ref->pending;
 	tablestatus = palloc_object(PgStat_TableStatus);
@@ -706,8 +777,12 @@ AtPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state)
 		record.inserted_pre_truncdrop = trans->inserted_pre_truncdrop;
 		record.updated_pre_truncdrop = trans->updated_pre_truncdrop;
 		record.deleted_pre_truncdrop = trans->deleted_pre_truncdrop;
-		record.id = tabstat->id;
-		record.shared = tabstat->shared;
+
+		if (tabstat->relation != NULL)
+			record.locator = tabstat->relation->rd_locator;
+		else
+			record.locator = tabstat->locator;
+
 		record.truncdropped = trans->truncdropped;
 
 		RegisterTwoPhaseRecord(TWOPHASE_RM_PGSTAT_ID, 0,
@@ -750,7 +825,7 @@ pgstat_twophase_postcommit(FullTransactionId fxid, uint16 info,
 	PgStat_TableStatus *pgstat_info;
 
 	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, commit case */
 	pgstat_info->counts.tuples_inserted += rec->tuples_inserted;
@@ -785,8 +860,8 @@ pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 	TwoPhasePgStatRecord *rec = (TwoPhasePgStatRecord *) recdata;
 	PgStat_TableStatus *pgstat_info;
 
-	/* Find or create a tabstat entry for the rel */
-	pgstat_info = pgstat_prep_relation_pending(rec->id, rec->shared);
+	/* Find or create a tabstat entry for the target locator */
+	pgstat_info = pgstat_prep_relation_pending(rec->locator);
 
 	/* Same math as in AtEOXact_PgStat, abort case */
 	if (rec->truncdropped)
@@ -920,17 +995,21 @@ pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts)
  * initialized if not exists.
  */
 static PgStat_TableStatus *
-pgstat_prep_relation_pending(Oid rel_id, bool isshared)
+pgstat_prep_relation_pending(RelFileLocator locator)
 {
 	PgStat_EntryRef *entry_ref;
 	PgStat_TableStatus *pending;
+	uint64		objid;
+
+	objid = RelFileLocatorToPgStatObjid(locator);
 
 	entry_ref = pgstat_prep_pending_entry(PGSTAT_KIND_RELATION,
-										  isshared ? InvalidOid : MyDatabaseId,
-										  rel_id, NULL);
+										  locator.dbOid,
+										  objid, NULL);
+
 	pending = entry_ref->pending;
-	pending->id = rel_id;
-	pending->shared = isshared;
+	pending->id = objid;
+	pending->locator = locator;
 
 	return pending;
 }
@@ -1009,3 +1088,82 @@ restore_truncdrop_counters(PgStat_TableXactStatus *trans)
 		trans->tuples_deleted = trans->deleted_pre_truncdrop;
 	}
 }
+
+/*
+ * Convert a relation OID to its corresponding RelFileLocator for statistics
+ * tracking purposes.
+ *
+ * Returns true on success, false if the relation doesn't need statistics
+ * tracking.
+ *
+ * For partitioned tables, constructs a synthetic locator using the relation
+ * OID as relNumber, since they don't have storage.
+ */
+bool
+pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator)
+{
+	HeapTuple	tuple;
+	Form_pg_class relform;
+	bool		result = true;
+
+	/* get the relation's tuple from pg_class */
+	tuple = SearchSysCache1(RELOID, ObjectIdGetDatum(reloid));
+
+	if (!HeapTupleIsValid(tuple))
+		return false;
+
+	relform = (Form_pg_class) GETSTRUCT(tuple);
+
+	/* skip relations without storage and non partitioned tables */
+	if (!RELKIND_HAS_STORAGE(relform->relkind) &&
+		relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		ReleaseSysCache(tuple);
+		return false;
+	}
+
+	if (relform->relkind != RELKIND_PARTITIONED_TABLE)
+	{
+		/* build the RelFileLocator */
+		locator->relNumber = relform->relfilenode;
+		locator->spcOid = relform->reltablespace;
+
+		/* handle default tablespace */
+		if (!OidIsValid(locator->spcOid))
+			locator->spcOid = MyDatabaseTableSpace;
+
+		/* handle dbOid for global vs local relations */
+		if (locator->spcOid == GLOBALTABLESPACE_OID)
+			locator->dbOid = InvalidOid;
+		else
+			locator->dbOid = MyDatabaseId;
+
+		/* handle mapped relations */
+		if (!RelFileNumberIsValid(locator->relNumber))
+		{
+			locator->relNumber = RelationMapOidToFilenumber(reloid,
+															relform->relisshared);
+			if (!RelFileNumberIsValid(locator->relNumber))
+			{
+				ReleaseSysCache(tuple);
+				return false;
+			}
+		}
+	}
+	else
+	{
+		/*
+		 * Partitioned tables don't have storage, so construct a synthetic
+		 * locator for statistics tracking. Use a reserved pseudo tablespace
+		 * OID that cannot conflict with real tablespaces, and the relation
+		 * OID as relNumber. This ensures no collision with regular relations
+		 * even after OID wraparound.
+		 */
+		locator->dbOid = (relform->relisshared ? InvalidOid : MyDatabaseId);
+		locator->spcOid = PSEUDO_PARTITION_TABLE_SPCOID;
+		locator->relNumber = relform->oid;
+	}
+
+	ReleaseSysCache(tuple);
+	return result;
+}
diff --git a/src/backend/utils/adt/pgstatfuncs.c b/src/backend/utils/adt/pgstatfuncs.c
index ef6fffe60b9..60ffb1679ec 100644
--- a/src/backend/utils/adt/pgstatfuncs.c
+++ b/src/backend/utils/adt/pgstatfuncs.c
@@ -23,13 +23,13 @@
 #include "common/ip.h"
 #include "funcapi.h"
 #include "miscadmin.h"
-#include "pgstat.h"
 #include "postmaster/bgworker.h"
 #include "replication/logicallauncher.h"
 #include "storage/proc.h"
 #include "storage/procarray.h"
 #include "utils/acl.h"
 #include "utils/builtins.h"
+#include "utils/pgstat_internal.h"
 #include "utils/timestamp.h"
 
 #define UINT32_ACCESS_ONCE(var)		 ((uint32)(*((volatile uint32 *)&(var))))
@@ -1949,9 +1949,14 @@ Datum
 pg_stat_reset_single_table_counters(PG_FUNCTION_ARGS)
 {
 	Oid			taboid = PG_GETARG_OID(0);
-	Oid			dboid = (IsSharedRelation(taboid) ? InvalidOid : MyDatabaseId);
+	RelFileLocator locator;
 
-	pgstat_reset(PGSTAT_KIND_RELATION, dboid, taboid);
+	/* Get the stats locator from the relation OID */
+	if (!pgstat_reloid_to_relfilelocator(taboid, &locator))
+		PG_RETURN_VOID();
+
+	pgstat_reset(PGSTAT_KIND_RELATION, locator.dbOid,
+				 RelFileLocatorToPgStatObjid(locator));
 
 	PG_RETURN_VOID();
 }
@@ -2305,5 +2310,16 @@ pg_stat_have_stats(PG_FUNCTION_ARGS)
 	uint64		objid = PG_GETARG_INT64(2);
 	PgStat_Kind kind = pgstat_get_kind_from_str(stats_type);
 
+	/* Convert relation OID to relfilenode objid */
+	if (kind == PGSTAT_KIND_RELATION)
+	{
+		RelFileLocator locator;
+
+		if (!pgstat_reloid_to_relfilelocator(objid, &locator))
+			PG_RETURN_BOOL(false);
+
+		objid = RelFileLocatorToPgStatObjid(locator);
+	}
+
 	PG_RETURN_BOOL(pgstat_have_entry(kind, dboid, objid));
 }
diff --git a/src/include/catalog/pg_tablespace.dat b/src/include/catalog/pg_tablespace.dat
index 1302a3d75cd..9430970fffd 100644
--- a/src/include/catalog/pg_tablespace.dat
+++ b/src/include/catalog/pg_tablespace.dat
@@ -10,6 +10,10 @@
 #
 #----------------------------------------------------------------------
 
+/*
+ * When adding a new one, ensure it does not conflict with
+ * PSEUDO_PARTITION_TABLE_SPCOID.
+ */
 [
 
 { oid => '1663', oid_symbol => 'DEFAULTTABLESPACE_OID',
diff --git a/src/include/catalog/pg_tablespace.h b/src/include/catalog/pg_tablespace.h
index 7816d779d8c..0e2d8051d69 100644
--- a/src/include/catalog/pg_tablespace.h
+++ b/src/include/catalog/pg_tablespace.h
@@ -21,6 +21,14 @@
 #include "catalog/genbki.h"
 #include "catalog/pg_tablespace_d.h"	/* IWYU pragma: export */
 
+/*
+ * Reserved tablespace OID for partitioned table pseudo locators.
+ * This is not an actual tablespace, just a reserved value to distinguish
+ * partitioned table statistics from regular table statistics. Ensures it does
+ * not conflict with the ones in pg_tablespace.dat.
+ */
+#define PSEUDO_PARTITION_TABLE_SPCOID 1665
+
 /* ----------------
  *		pg_tablespace definition.  cpp turns this into
  *		typedef struct FormData_pg_tablespace
diff --git a/src/include/pgstat.h b/src/include/pgstat.h
index 6714363144a..3102f86aa24 100644
--- a/src/include/pgstat.h
+++ b/src/include/pgstat.h
@@ -17,6 +17,7 @@
 #include "postmaster/pgarch.h"	/* for MAX_XFN_CHARS */
 #include "replication/conflict.h"
 #include "replication/worker_internal.h"
+#include "storage/relfilelocator.h"
 #include "utils/backend_progress.h" /* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/backend_status.h"	/* for backward compatibility */	/* IWYU pragma: export */
 #include "utils/pgstat_kind.h"
@@ -35,6 +36,12 @@
 /* Default directory to store temporary statistics data in */
 #define PG_STAT_TMP_DIR		"pg_stat_tmp"
 
+/*
+ * Build a pgstat key Objid based on a RelFileLocator.
+ */
+#define RelFileLocatorToPgStatObjid(locator) \
+	(((uint64) (locator).spcOid << 32) | (locator).relNumber)
+
 /* Values for track_functions GUC variable --- order is significant! */
 typedef enum TrackFunctionsLevel
 {
@@ -175,11 +182,11 @@ typedef struct PgStat_TableCounts
  */
 typedef struct PgStat_TableStatus
 {
-	Oid			id;				/* table's OID */
-	bool		shared;			/* is it a shared catalog? */
+	uint64		id;				/* hash of relfilelocator for stats key */
 	struct PgStat_TableXactStatus *trans;	/* lowest subxact's counts */
 	PgStat_TableCounts counts;	/* event counts to be sent */
 	Relation	relation;		/* rel that is using this entry */
+	RelFileLocator locator;		/* table's relfilelocator */
 } PgStat_TableStatus;
 
 /* ----------
@@ -735,8 +742,8 @@ extern void pgstat_twophase_postabort(FullTransactionId fxid, uint16 info,
 									  void *recdata, uint32 len);
 
 extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry(Oid relid);
-extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(bool shared,
-														   Oid reloid);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_by_locator(RelFileLocator locator);
+extern PgStat_StatTabEntry *pgstat_fetch_stat_tabentry_ext(Oid reloid);
 extern PgStat_TableStatus *find_tabstat_entry(Oid rel_id);
 
 
diff --git a/src/include/utils/pgstat_internal.h b/src/include/utils/pgstat_internal.h
index 5c1ce4d3d6a..7b24928b00d 100644
--- a/src/include/utils/pgstat_internal.h
+++ b/src/include/utils/pgstat_internal.h
@@ -764,6 +764,7 @@ extern void PostPrepare_PgStat_Relations(PgStat_SubXactStatus *xact_state);
 extern bool pgstat_relation_flush_cb(PgStat_EntryRef *entry_ref, bool nowait);
 extern void pgstat_relation_delete_pending_cb(PgStat_EntryRef *entry_ref);
 extern void pgstat_relation_reset_timestamp_cb(PgStatShared_Common *header, TimestampTz ts);
+extern bool pgstat_reloid_to_relfilelocator(Oid reloid, RelFileLocator *locator);
 
 
 /*
diff --git a/src/test/recovery/t/029_stats_restart.pl b/src/test/recovery/t/029_stats_restart.pl
index 021e2bf361f..3a9c05eaf10 100644
--- a/src/test/recovery/t/029_stats_restart.pl
+++ b/src/test/recovery/t/029_stats_restart.pl
@@ -55,10 +55,10 @@ trigger_funcrel_stat();
 
 # verify stats objects exist
 $sect = "initial";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -79,10 +79,10 @@ copy($og_stats, $statsfile) or die "Copy failed: $!";
 $node->start;
 
 $sect = "copy";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 $node->stop('immediate');
@@ -96,10 +96,10 @@ $node->start;
 
 # stats should have been discarded
 $sect = "post immediate";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 # get rid of backup statsfile
@@ -110,10 +110,10 @@ unlink $statsfile or die "cannot unlink $statsfile $!";
 trigger_funcrel_stat();
 
 $sect = "post immediate, new";
-is(have_stats('database', $dboid, 0), 't', "$sect: db stats do exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 't', "$sect: db stats do exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	't', "$sect: function stats do exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	't', "$sect: relation stats do exist");
 
 # regular shutdown
@@ -129,10 +129,10 @@ $node->start;
 
 # no stats present due to invalid stats file
 $sect = "invalid_overwrite";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -145,10 +145,10 @@ append_file($og_stats, "XYZ");
 $node->start;
 
 $sect = "invalid_append";
-is(have_stats('database', $dboid, 0), 'f', "$sect: db stats do not exist");
-is(have_stats('function', $dboid, $funcoid),
+is(have_stats($connect_db, 'database', $dboid, 0), 'f', "$sect: db stats do not exist");
+is(have_stats($db_under_test, 'function', $dboid, $funcoid),
 	'f', "$sect: function stats do not exist");
-is(have_stats('relation', $dboid, $tableoid),
+is(have_stats($db_under_test, 'relation', $dboid, $tableoid),
 	'f', "$sect: relation stats do not exist");
 
 
@@ -307,9 +307,9 @@ sub trigger_funcrel_stat
 
 sub have_stats
 {
-	my ($kind, $dboid, $objid) = @_;
+	my ($db, $kind, $dboid, $objid) = @_;
 
-	return $node->safe_psql($connect_db,
+	return $node->safe_psql($db,
 		"SELECT pg_stat_have_stats('$kind', $dboid, $objid)");
 }
 
-- 
2.34.1


--xJsrX25x3tm7Tn81
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
	filename="v10-0002-handle-relation-statistics-correctly-during-rewr.patch"



^ permalink  raw  reply  [nested|flat] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30 Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 252+ 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] 252+ messages in thread