From d0db43e880be7cd2113d78ad8500660050a949e7 Mon Sep 17 00:00:00 2001 From: Andrey Rachitskiy Date: Thu, 19 Jun 2026 01:30:00 +0500 Subject: [PATCH] Collapse consecutive .** accessors for jsonpath exists queries 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 Reported-by: Andrey Rachitskiy 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