innodb_flush_method的几个典型取值
fsync: InnoDB uses the fsync() system call to flush both the data and log files. fsync is the default setting. O_DSYNC: InnoDB uses O_SYNC to open and flush the log files, and fsync() to flush the data files. InnoDB does not use O_DSYNC directly because there have been problems with it on many varieties of Unix. O_DIRECT: InnoDB uses O_DIRECT (or directio() on Solaris) to open the data files, and uses fsync() to flush both the data and log files. This option is available on some GNU/Linux versions,FreeBSD, and Solaris.
如何取值,mysql官方文档是这么建议的
How each settings affects performance depends on hardware configuration and workload. Benchmark your particular configuration to decide which setting to use, or whether to keep the default setting. Examine the Innodb_data_fsyncs status variable to see the overall number of fsync() calls for each setting. The mix of read and write operations in your workload can affect how a setting performs. For example, on a system with a hardware RAID controller and battery-backed write cache, O_DIRECT can help to avoid double buffering between the InnoDB buffer pool and the operating system's file system cache. On some systems where InnoDB data and log files are located on a SAN, the default value or O_DSYNC might be faster for a read-heavy workload with mostly SELECT statements. Always test this parameter with hardware and workload that reflect your production environment
也就是说,具体的取值跟硬件配置和工作负载相关,最好做一次压测来决定。不过通常来说,linux环境下具有raid控制器和write-back写策略,o_direct是比较好的选择;如果存储介质是SAN,那么使用默认fsync或者osync或许更好一些。
通常来说,貌似绝大部分人都取值o_direct,底层有raid卡,读写策略设置为write-back。在使用sysbench压测oltp类型时,我发现o_direct确实比fsync性能优秀一些,看来适用于大部分场景,但是最近碰到一个这样的sql,客户反馈很慢,而在相同内存的情况下,它自己搭建的云主机执行相对快很多,后来我发现主要就是innodb_flush_method的设置值不同带来的巨大性能差异。
测试场景1
innodb_flush_method为默认值,即fsync,缓存池512M,表数据量1.2G,排除缓存池影响,稳定后的结果
mysql> show variables like '%innodb_flush_me%'; +---------------------+-------+ | Variable_name | Value | +---------------------+-------+ | innodb_flush_method | | +---------------------+-------+ 1 row in set (0.00 sec) mysql> SELECT sql_no_cache SUM(outcome)-SUM(income) FROM journal where account_id = '1c6ab4e7-main'; +--------------------------+ | SUM(outcome)-SUM(income) | +--------------------------+ | -191010.51 | +--------------------------+ 1 row in set (1.22 sec) mysql> SELECT sql_no_cache SUM(outcome)-SUM(income) FROM journal where account_id = '1c6ab4e7-main'; +--------------------------+ | SUM(outcome)-SUM(income) | +--------------------------+ | -191010.51 | +--------------------------+ 1 row in set (1.22 sec) mysql> explain SELECT sql_no_cache SUM(outcome)-SUM(income) FROM journal where account_id = '1c6ab4e7-main'; +----+-------------+---------+------+---------------+------------+---------+-------+--------+-----------------------+ | id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra | +----+-------------+---------+------+---------------+------------+---------+-------+--------+-----------------------+ | 1 | SIMPLE | journal | ref | account_id | account_id | 62 | const | 161638 | Using index condition | +----+-------------+---------+------+---------------+------------+---------+-------+--------+-----------------------+ 1 row in set (0.03 sec)
测试场景2
innodb_flush_method改为o_direct,排除缓存池影响,稳定后的结果
mysql> show variables like '%innodb_flush_me%'; +---------------------+----------+ | Variable_name | Value | +---------------------+----------+ | innodb_flush_method | O_DIRECT | +---------------------+----------+ 1 row in set (0.00 sec) mysql> SELECT sql_no_cache SUM(outcome)-SUM(income) FROM journal where account_id = '1c6ab4e7-main'; +--------------------------+ | SUM(outcome)-SUM(income) | +--------------------------+ | -191010.51 | +--------------------------+ 1 row in set (3.22 sec) mysql> SELECT sql_no_cache SUM(outcome)-SUM(income) FROM journal where account_id = '1c6ab4e7-main'; +--------------------------+ | SUM(outcome)-SUM(income) | +--------------------------+ | -191010.51 | +--------------------------+ 1 row in set (3.02 sec) mysql> explain SELECT sql_no_cache SUM(outcome)-SUM(income) FROM journal where account_id = '1c6ab4e7-main'; +----+-------------+---------+------+---------------+------------+---------+-------+--------+-----------------------+ | id | select_type | table | type | possible_keys | key | key_len | ref | rows | Extra | +----+-------------+---------+------+---------------+------------+---------+-------+--------+-----------------------+ | 1 | SIMPLE | journal | ref | account_id | account_id | 62 | const | 161638 | Using index condition | +----+-------------+---------+------+---------------+------------+---------+-------+--------+-----------------------+ 1 row in set (0.00 sec)
结果比较:
两者执行计划一摸一样,性能却差距很大。在数据库第一次启动时的查询结果也差距很大,o_direct也差很多(测试结果略)。不是很懂为啥这种情况下多了一层操作系统缓存,读取效率就高了很多,生产环境设置一定要以压测结果为准,实际效果为准,不能盲目信任经验值。
改进措施:
不改变innodb_flush_method的情况下,其实这条sql还可以进一步优化,通过添加组合索引(account_id,outcome,income),使得走覆盖索引扫描,可大大地减少响应时间
以上这篇innodb_flush_method取值方法(实例讲解)就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持。
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
稳了!魔兽国服回归的3条重磅消息!官宣时间再确认!
昨天有一位朋友在大神群里分享,自己亚服账号被封号之后居然弹出了国服的封号信息对话框。
这里面让他访问的是一个国服的战网网址,com.cn和后面的zh都非常明白地表明这就是国服战网。
而他在复制这个网址并且进行登录之后,确实是网易的网址,也就是我们熟悉的停服之后国服发布的暴雪游戏产品运营到期开放退款的说明。这是一件比较奇怪的事情,因为以前都没有出现这样的情况,现在突然提示跳转到国服战网的网址,是不是说明了简体中文客户端已经开始进行更新了呢?