Mysql 8.0.18 hash join测试(推荐)

CREATE TABLE COLUMNS_hj as select * from information_schema.`COLUMNS`;
INSERT INTO COLUMNS SELECT * FROM COLUMNS; -- 最后一次插入25万行

CREATE TABLE COLUMNS_hj2 as select * from information_schema.`COLUMNS`;

explain format=tree
SELECT 
 COUNT(c1. PRIVILEGES),
 SUM(c1.ordinal_position)
FROM
 COLUMNS_hj c1,
 COLUMNS_hj2 c2
WHERE
 c1.table_name = c2.table_name
AND c1.column_name = c2.column_name
GROUP BY
 c1.table_name,
 c1.column_name
ORDER BY
 c1.table_name,
 c1.column_name;

-> Sort: <temporary>.TABLE_NAME, <temporary>.COLUMN_NAME
 -> Table scan on <temporary>
  -> Aggregate using temporary table
   -> Inner hash join (c1.`COLUMN_NAME` = c2.`COLUMN_NAME`), (c1.`TABLE_NAME` = c2.`TABLE_NAME`) (cost=134217298.97 rows=13421218)
    -> Table scan on c1 (cost=1.60 rows=414619)
    -> Hash
     -> Table scan on c2 (cost=347.95 rows=3237)

set join_buffer_size=1048576000;

SELECT 
 COUNT(c1. PRIVILEGES),
 SUM(c1.ordinal_position)
FROM
 COLUMNS_hj c1,
 COLUMNS_hj2 c2
WHERE
 c1.table_name = c2.table_name
AND c1.column_name = c2.column_name
GROUP BY
 c1.table_name,
 c1.column_name
ORDER BY
 c1.table_name,
 c1.column_name;

alter table columns_hj drop index idx_columns_hj;
alter table columns_hj2 drop index idx_columns_hj2;
create index idx_columns_hj on columns_hj(table_name,column_name);
create index idx_columns_hj2 on columns_hj2(table_name,column_name);

-> Sort: <temporary>.TABLE_NAME, <temporary>.COLUMN_NAME
 -> Table scan on <temporary>
  -> Aggregate using temporary table
   -> Nested loop inner join (cost=454325.17 rows=412707)
    -> Filter: ((c2.`TABLE_NAME` is not null) and (c2.`COLUMN_NAME` is not null)) (cost=347.95 rows=3237)
     -> Table scan on c2 (cost=347.95 rows=3237)
    -> Index lookup on c1 using idx_COLUMNS_hj (TABLE_NAME=c2.`TABLE_NAME`, COLUMN_NAME=c2.`COLUMN_NAME`) (cost=127.50 rows=127)

mysql> select /*+ set_var(optimizer_switch='index_merge=off') set_var(join_buffer_size=4M) */ c_id from customer limit 1;

auto_increment_increment
auto_increment_offset
big_tables
bulk_insert_buffer_size
default_tmp_storage_engine
div_precision_increment
end_markers_in_json
eq_range_index_dive_limit
foreign_key_checks
group_concat_max_len
insert_id
internal_tmp_mem_storage_engine
join_buffer_size
lock_wait_timeout
max_error_count
max_execution_time
max_heap_table_size
max_join_size
max_length_for_sort_data
max_points_in_geometry
max_seeks_for_key
max_sort_length
optimizer_prune_level
optimizer_search_depth variables
optimizer_switch
range_alloc_block_size
range_optimizer_max_mem_size
read_buffer_size
read_rnd_buffer_size
sort_buffer_size
sql_auto_is_null
sql_big_selects
sql_buffer_result
sql_mode
sql_safe_updates
sql_select_limit
timestamp
tmp_table_size
updatable_views_with_limit
unique_checks
windowing_use_high_precision