Backport #69886 to 24.9: Change the join_to_sort settings type to unsigned int

robot-clickhouse · robot-clickhouse · commit 430850a66712 · 2024-09-24T14:09:27.000Z
diff --git a/src/Core/Settings.cpp b/src/Core/Settings.cpp
@@ -342,8 +342,8 @@ namespace ErrorCodes
     \
     M(Bool, join_use_nulls, false, "Use NULLs for non-joined rows of outer JOINs for types that can be inside Nullable. If false, use default value of corresponding columns data type.", IMPORTANT) \
     \
-    M(Int32, join_output_by_rowlist_perkey_rows_threshold, 5, "The lower limit of per-key average rows in the right table to determine whether to output by row list in hash join.", 0) \
-    M(JoinStrictness, join_default_strictness, JoinStrictness::All, "Set default strictness in JOIN query. Possible values: empty string, 'ANY', 'ALL'. If empty, query without strictness will throw exception.", 0) \
+    M(UInt64, join_output_by_rowlist_perkey_rows_threshold, 5, "The lower limit of per-key average rows in the right table to determine whether to output by row list in hash join.", 0) \
+    M(JoinStrictness, join_default_strictness, JoinStrictness::All, "Set default strictness in JOIN query. Possible values: empty string, 'ANY', 'ALL'. If empty, query without strictness will throw an exception.", 0) \
     M(Bool, any_join_distinct_right_table_keys, false, "Enable old ANY JOIN logic with many-to-one left-to-right table keys mapping for all ANY JOINs. It leads to confusing not equal results for 't1 ANY LEFT JOIN t2' and 't2 ANY RIGHT JOIN t1'. ANY RIGHT JOIN needs one-to-many keys mapping to be consistent with LEFT one.", IMPORTANT) \
     M(Bool, single_join_prefer_left_table, true, "For single JOIN in case of identifier ambiguity prefer left table", IMPORTANT) \
     \
@@ -940,8 +940,8 @@ namespace ErrorCodes
     M(Bool, implicit_transaction, false, "If enabled and not already inside a transaction, wraps the query inside a full transaction (begin + commit or rollback)", 0) \
     M(UInt64, grace_hash_join_initial_buckets, 1, "Initial number of grace hash join buckets", 0) \
     M(UInt64, grace_hash_join_max_buckets, 1024, "Limit on the number of grace hash join buckets", 0) \
-    M(Int32, join_to_sort_minimum_perkey_rows, 40, "The lower limit of per-key average rows in the right table to determine whether to rerange the right table by key in left or inner join. This setting ensures that the optimization is not applied for sparse table keys", 0) \
-    M(Int32, join_to_sort_maximum_table_rows, 10000, "The maximum number of rows in the right table to determine whether to rerange the right table by key in left or inner join.", 0) \
+    M(UInt64, join_to_sort_minimum_perkey_rows, 40, "The lower limit of per-key average rows in the right table to determine whether to rerange the right table by key in left or inner join. This setting ensures that the optimization is not applied for sparse table keys", 0) \
+    M(UInt64, join_to_sort_maximum_table_rows, 10000, "The maximum number of rows in the right table to determine whether to rerange the right table by key in left or inner join.", 0) \
     M(Bool, allow_experimental_join_right_table_sorting, false, "If it is set to true, and the conditions of `join_to_sort_minimum_perkey_rows` and `join_to_sort_maximum_table_rows` are met, rerange the right table by key to improve the performance in left or inner hash join.", 0) \
     M(Timezone, session_timezone, "", "This setting can be removed in the future due to potential caveats. It is experimental and is not suitable for production usage. The default timezone for current session or query. The server default timezone if empty.", 0) \
     M(Bool, use_hive_partitioning, false, "Allows to use hive partitioning for File, URL, S3, AzureBlobStorage and HDFS engines.", 0)\
diff --git a/src/Interpreters/TableJoin.cpp b/src/Interpreters/TableJoin.cpp
@@ -46,10 +46,10 @@ namespace Setting
     extern const SettingsUInt64 default_max_bytes_in_join;
     extern const SettingsJoinAlgorithm join_algorithm;
     extern const SettingsUInt64 join_on_disk_max_files_to_merge;
-    extern const SettingsInt32 join_output_by_rowlist_perkey_rows_threshold;
+    extern const SettingsUInt64 join_output_by_rowlist_perkey_rows_threshold;
     extern const SettingsOverflowMode join_overflow_mode;
-    extern const SettingsInt32 join_to_sort_maximum_table_rows;
-    extern const SettingsInt32 join_to_sort_minimum_perkey_rows;
+    extern const SettingsUInt64 join_to_sort_maximum_table_rows;
+    extern const SettingsUInt64 join_to_sort_minimum_perkey_rows;
     extern const SettingsBool join_use_nulls;
     extern const SettingsUInt64 max_bytes_in_join;
     extern const SettingsUInt64 max_joined_block_size_rows;
