为了减少使用OFFSET的缺点,this article描述使用JOIN当一个数字主键id可强制使用适当的指数的可能途径。需要注意的是跟踪过程中,一个“procedure_log”表中创建并逐步处理了一批又更新:
对于MySQL:
DROP PROCEDURE IF EXISTS copyTable;
DELIMITER |
CREATE PROCEDURE copyTable()
BEGIN
DECLARE batchSize INT DEFAULT 100;
DECLARE i INT DEFAULT 0;
DECLARE rowCount INT;
# Note that we use a WHERE clause to prevent a full table scan / use the index properly
SET rowCount = (SELECT COUNT(id) FROM my_table WHERE id IS NOT NULL);
CREATE TABLE IF NOT EXISTS my_table_copy LIKE my_table;
CREATE TABLE IF NOT EXISTS procedure_log ( id INT UNSIGNED NOT NULL AUTO_INCREMENT, entry TEXT, timestamp DATETIME DEFAULT CURRENT_TIMESTAMP, PRIMARY KEY (id) );
WHILE i <= rowCount DO
INSERT IGNORE INTO my_table_copy (
SELECT source.* FROM (
SELECT id FROM my_table ORDER BY id LIMIT i, batchSize
) tmp
JOIN my_table source ON source.id = tmp.id
ORDER BY source.id
);
SET i = i + batchSize;
INSERT INTO procedure_log (entry) VALUES (CONCAT('Copied batch from my_table => my_table_copy, batch: ', batchSize, ', offset: ', i, ', rowCount: ', rowCount));
END WHILE;
END |
DELIMITER ;