[PATCH v5 7/9] box: tune tuple_field_raw_by_path for indexed data

Kirill Shcherbatov kshcherbatov at tarantool.org
Mon Nov 26 13:49:41 MSK 2018


We don't need to parse tuple in tuple_field_raw_by_path if
required field has been indexed. We do path lookup in field
tree of JSON paths and return data by it's offset from field_map
instead of whole tuple parsing.

Part of #1012
---
 src/box/tuple_format.c     | 34 ++++++++++++++++++++++++----------
 test/engine/tuple.result   |  5 +++++
 test/engine/tuple.test.lua |  2 ++
 3 files changed, 31 insertions(+), 10 deletions(-)

diff --git a/src/box/tuple_format.c b/src/box/tuple_format.c
index 193d0d8..be89764 100644
--- a/src/box/tuple_format.c
+++ b/src/box/tuple_format.c
@@ -956,15 +956,12 @@ tuple_field_raw_by_path(struct tuple_format *format, const char *tuple,
 		goto error;
 	switch(token.key.type) {
 	case JSON_TOKEN_NUM: {
-		int index = token.key.num;
-		if (index == 0) {
+		fieldno = token.key.num;
+		if (fieldno == 0) {
 			*field = NULL;
 			return 0;
 		}
-		index -= TUPLE_INDEX_BASE;
-		*field = tuple_field_raw(format, tuple, field_map, index);
-		if (*field == NULL)
-			return 0;
+		fieldno -= TUPLE_INDEX_BASE;
 		break;
 	}
 	case JSON_TOKEN_STR: {
@@ -982,10 +979,9 @@ tuple_field_raw_by_path(struct tuple_format *format, const char *tuple,
 			name_hash = field_name_hash(token.key.str,
 						    token.key.len);
 		}
-		*field = tuple_field_raw_by_name(format, tuple, field_map,
-						 token.key.str, token.key.len,
-						 name_hash);
-		if (*field == NULL)
+		if (tuple_fieldno_by_name(format->dict, token.key.str,
+					  token.key.len, name_hash,
+					  &fieldno) != 0)
 			return 0;
 		break;
 	}
@@ -994,6 +990,24 @@ tuple_field_raw_by_path(struct tuple_format *format, const char *tuple,
 		*field = NULL;
 		return 0;
 	}
+	/* Optimize indexed JSON field data access. */
+	assert(field != NULL);
+	struct tuple_field *indexed_field =
+		unlikely(fieldno >= tuple_format_field_count(format)) ? NULL :
+		tuple_format_field_by_path(format,
+					   tuple_format_field(format, fieldno),
+					   path + lexer.offset,
+					   path_len - lexer.offset);
+	if (indexed_field != NULL &&
+	    indexed_field->offset_slot != TUPLE_OFFSET_SLOT_NIL) {
+		*field = tuple + field_map[indexed_field->offset_slot];
+		return 0;
+	}
+
+	/* No such field in index. Continue parsing JSON path. */
+	*field = tuple_field_raw(format, tuple, field_map, fieldno);
+	if (*field == NULL)
+		return 0;
 	rc = tuple_field_go_to_path(field, path + lexer.offset,
 				    path_len - lexer.offset);
 	if (rc == 0)
diff --git a/test/engine/tuple.result b/test/engine/tuple.result
index 322821e..a07e23c 100644
--- a/test/engine/tuple.result
+++ b/test/engine/tuple.result
@@ -1147,6 +1147,11 @@ assert(idx2 ~= nil)
 t = s:insert{5, 7, {town = 'Matrix', FIO = {fname = 'Agent', sname = 'Smith'}}, 4, 5}
 ---
 ...
+-- Test field_map in tuple speed-up access by indexed path.
+t["[3][\"FIO\"][\"fname\"]"]
+---
+- Agent
+...
 idx:select()
 ---
 - - [5, 7, {'town': 'Matrix', 'FIO': {'fname': 'Agent', 'sname': 'Smith'}}, 4, 5]
diff --git a/test/engine/tuple.test.lua b/test/engine/tuple.test.lua
index d53ab42..8630850 100644
--- a/test/engine/tuple.test.lua
+++ b/test/engine/tuple.test.lua
@@ -367,6 +367,8 @@ s:create_index('test2', {parts = {{2, 'number'}, {3, 'number', path = '["FIO"]["
 idx2 = s:create_index('test2', {parts = {{2, 'number'}, {3, 'str', path = '["FIO"]["fname"]'}}})
 assert(idx2 ~= nil)
 t = s:insert{5, 7, {town = 'Matrix', FIO = {fname = 'Agent', sname = 'Smith'}}, 4, 5}
+-- Test field_map in tuple speed-up access by indexed path.
+t["[3][\"FIO\"][\"fname\"]"]
 idx:select()
 idx:min()
 idx:max()
-- 
2.7.4




More information about the Tarantool-patches mailing list