agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v3 3/3] Replace matview WITH OLD DATA
362+ messages / 2 participants
[nested] [flat]

* [PATCH v3 3/3] Replace matview WITH OLD DATA
@ 2024-07-26 21:33  Erik Wienhold <[email protected]>
  0 siblings, 0 replies; 362+ messages in thread

From: Erik Wienhold @ 2024-07-26 21:33 UTC (permalink / raw)

---
 .../sgml/ref/create_materialized_view.sgml    | 16 +++++++++--
 src/backend/commands/createas.c               | 26 +++++++++++------
 src/backend/parser/gram.y                     | 16 +++++++++++
 src/include/nodes/primnodes.h                 |  1 +
 src/test/regress/expected/matview.out         | 28 +++++++++++++++++++
 src/test/regress/sql/matview.sql              | 15 ++++++++++
 6 files changed, 90 insertions(+), 12 deletions(-)

diff --git a/doc/src/sgml/ref/create_materialized_view.sgml b/doc/src/sgml/ref/create_materialized_view.sgml
index b5a8e3441a..65633b8bfa 100644
--- a/doc/src/sgml/ref/create_materialized_view.sgml
+++ b/doc/src/sgml/ref/create_materialized_view.sgml
@@ -27,7 +27,7 @@ CREATE [ OR REPLACE ] MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_nam
     [ WITH ( <replaceable class="parameter">storage_parameter</replaceable> [= <replaceable class="parameter">value</replaceable>] [, ... ] ) ]
     [ TABLESPACE <replaceable class="parameter">tablespace_name</replaceable> ]
     AS <replaceable>query</replaceable>
-    [ WITH [ NO ] DATA ]
+    [ WITH [ NO | OLD ] DATA ]
 </synopsis>
  </refsynopsisdiv>
 
@@ -37,7 +37,8 @@ CREATE [ OR REPLACE ] MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_nam
   <para>
    <command>CREATE MATERIALIZED VIEW</command> defines a materialized view of
    a query.  The query is executed and used to populate the view at the time
-   the command is issued (unless <command>WITH NO DATA</command> is used) and may be
+   the command is issued (unless <command>WITH NO DATA</command> or
+   <command>WITH OLD DATA</command> is used) and may be
    refreshed later using <command>REFRESH MATERIALIZED VIEW</command>.
   </para>
 
@@ -160,7 +161,7 @@ CREATE [ OR REPLACE ] MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_nam
    </varlistentry>
 
    <varlistentry>
-    <term><literal>WITH [ NO ] DATA</literal></term>
+    <term><literal>WITH [ NO | OLD ] DATA</literal></term>
     <listitem>
      <para>
       This clause specifies whether or not the materialized view should be
@@ -168,6 +169,15 @@ CREATE [ OR REPLACE ] MATERIALIZED VIEW [ IF NOT EXISTS ] <replaceable>table_nam
       flagged as unscannable and cannot be queried until <command>REFRESH
       MATERIALIZED VIEW</command> is used.
      </para>
+
+     <para>
+      The form <command>WITH OLD DATA</command> keeps the already stored data
+      when replacing an existing materialized view to keep it populated.  For
+      newly created materialized views, this has the same effect as
+      <command>WITH DATA</command>.  Use this form if you want to use
+      <command>REFRESH MATERIALIZED VIEW CONCURRENTLY</command> as it requires
+      a populated materialized view.
+     </para>
     </listitem>
    </varlistentry>
 
diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index e4ed3748f9..96e7b81966 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -331,18 +331,26 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 		/* An existing materialized view can be replaced. */
 		if (is_matview && into->replace)
 		{
-			RefreshMatViewStmt *refresh;
-
 			/* Change the relation to match the new query and other options. */
-			(void) create_ctas_nodata(query->targetList, into);
+			address = create_ctas_nodata(query->targetList, into);
 
-			/* Refresh the materialized view with a fake statement. */
-			refresh = makeNode(RefreshMatViewStmt);
-			refresh->relation = into->rel;
-			refresh->skipData = into->skipData;
-			refresh->concurrent = false;
+			/*
+			 * Refresh the materialized view with a fake statement unless we
+			 * must keep the old data.
+			 */
+			if (!into->keepData)
+			{
+				RefreshMatViewStmt *refresh;
+
+				refresh = makeNode(RefreshMatViewStmt);
+				refresh->relation = into->rel;
+				refresh->skipData = into->skipData;
+				refresh->concurrent = false;
+
+				address = ExecRefreshMatView(refresh, NULL, NULL);
+			}
 
-			return ExecRefreshMatView(refresh, NULL, NULL);
+			return address;
 		}
 
 		return InvalidObjectAddress;
diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 4b939ea7ca..e45ebb24f8 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -4808,6 +4808,22 @@ CreateMatViewStmt:
 					$7->replace = true;
 					$$ = (Node *) ctas;
 				}
+		| CREATE OR REPLACE OptNoLog MATERIALIZED VIEW create_mv_target AS SelectStmt WITH OLD DATA_P
+				{
+					CreateTableAsStmt *ctas = makeNode(CreateTableAsStmt);
+
+					ctas->query = $9;
+					ctas->into = $7;
+					ctas->objtype = OBJECT_MATVIEW;
+					ctas->is_select_into = false;
+					ctas->if_not_exists = false;
+					/* cram additional flags into the IntoClause */
+					$7->rel->relpersistence = $4;
+					$7->skipData = false;
+					$7->keepData = true;
+					$7->replace = true;
+					$$ = (Node *) ctas;
+				}
 		;
 
 create_mv_target:
diff --git a/src/include/nodes/primnodes.h b/src/include/nodes/primnodes.h
index 4b0ee5d10d..ae84cb522e 100644
--- a/src/include/nodes/primnodes.h
+++ b/src/include/nodes/primnodes.h
@@ -168,6 +168,7 @@ typedef struct IntoClause
 	/* materialized view's SELECT query */
 	Node	   *viewQuery pg_node_attr(query_jumble_ignore);
 	bool		skipData;		/* true for WITH NO DATA */
+	bool		keepData;		/* true for WITH OLD DATA */
 	bool		replace;		/* replace existing matview? */
 } IntoClause;
 
diff --git a/src/test/regress/expected/matview.out b/src/test/regress/expected/matview.out
index cefd0d442c..47dfd88bff 100644
--- a/src/test/regress/expected/matview.out
+++ b/src/test/regress/expected/matview.out
@@ -751,6 +751,23 @@ SELECT * FROM mvtest_replace;
  3
 (1 row)
 
+-- replace query but keep old data
+CREATE OR REPLACE MATERIALIZED VIEW mvtest_replace AS
+  SELECT 5 AS a
+  WITH OLD DATA;
+SELECT * FROM mvtest_replace;
+ a 
+---
+ 3
+(1 row)
+
+REFRESH MATERIALIZED VIEW mvtest_replace;
+SELECT * FROM mvtest_replace;
+ a 
+---
+ 5
+(1 row)
+
 -- add column
 CREATE OR REPLACE MATERIALIZED VIEW mvtest_replace AS
   SELECT 4 AS a, 1 b;
@@ -905,3 +922,14 @@ ERROR:  syntax error at or near "NOT"
 LINE 1: CREATE OR REPLACE MATERIALIZED VIEW IF NOT EXISTS mvtest_rep...
                                                ^
 DROP MATERIALIZED VIEW mvtest_replace;
+-- Create new matview WITH OLD DATA.  This populates the new matview as if
+-- WITH DATA had been specified.
+CREATE OR REPLACE MATERIALIZED VIEW mvtest_replace AS
+  SELECT 17 AS a
+  WITH OLD DATA;
+SELECT * FROM mvtest_replace;
+ a  
+----
+ 17
+(1 row)
+
diff --git a/src/test/regress/sql/matview.sql b/src/test/regress/sql/matview.sql
index c12f0243c9..b268237c24 100644
--- a/src/test/regress/sql/matview.sql
+++ b/src/test/regress/sql/matview.sql
@@ -338,6 +338,14 @@ SELECT * FROM mvtest_replace; -- error: not populated
 REFRESH MATERIALIZED VIEW mvtest_replace;
 SELECT * FROM mvtest_replace;
 
+-- replace query but keep old data
+CREATE OR REPLACE MATERIALIZED VIEW mvtest_replace AS
+  SELECT 5 AS a
+  WITH OLD DATA;
+SELECT * FROM mvtest_replace;
+REFRESH MATERIALIZED VIEW mvtest_replace;
+SELECT * FROM mvtest_replace;
+
 -- add column
 CREATE OR REPLACE MATERIALIZED VIEW mvtest_replace AS
   SELECT 4 AS a, 1 b;
@@ -422,3 +430,10 @@ CREATE OR REPLACE MATERIALIZED VIEW IF NOT EXISTS mvtest_replace AS
   SELECT 1 AS a;
 
 DROP MATERIALIZED VIEW mvtest_replace;
+
+-- Create new matview WITH OLD DATA.  This populates the new matview as if
+-- WITH DATA had been specified.
+CREATE OR REPLACE MATERIALIZED VIEW mvtest_replace AS
+  SELECT 17 AS a
+  WITH OLD DATA;
+SELECT * FROM mvtest_replace;
-- 
2.46.0


--muysnh7l3kienazz--





^ permalink  raw  reply  [nested|flat] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread

* [PATCH] Collapse consecutive .** accessors for jsonpath exists queries
@ 2026-06-18 20:30  Andrey Rachitskiy <[email protected]>
  0 siblings, 0 replies; 362+ 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] 362+ messages in thread