缓慢的*初始* mysql 查询

Slow *initial* mysql query

运行 Mysql V5.6.22,运行 正确索引数据库上的复杂查询,响应时间最初非常慢(10 秒)。随后的查询(针对不同的项目)非常敏感(50 毫秒)。所以我想查询缓存正在做它们的工作——但我如何最大限度地减少初始缓慢响应?

该数据库是一个外部维护的医学数据库 (SNOMED),我使用当前快照的推荐视图 - 我 认为这些视图是速度限制。

奇怪地重新启动 mysql 并没有什么不同 - 这似乎是一个时间问题 - 如果数据库有一段时间不使用,它只需要很长时间才能启动。

所以我的问题是,是否有一个 mysql 设置用于这些缓存的保留时间,或者我应该使用不同的方法而不使用视图(SNOMED 的数据每年更新 2 倍,在另一个类似的药物数据库中,每月都会发布。?

有些人希望看到查询,所以这里开始。警告它确实有点棘手,基本查询的行数在评论中给出......;-)

SELECT DISTINCT concat(c.id, '::', c.effectiveTime) as id, `d1`.`term` as label, `d2`.`term`
FROM (`snomed`.`rf2_ss_refset` as refset)
JOIN `snomed`.`rf2_ss_concepts` as c ON `c`.`id` = `refset`.`referencedCOmponentId`
JOIN `snomed`.`rf2_ss_descriptions` as d1 ON `d1`.`conceptId` = `refset`.`referencedComponentId`
JOIN `snomed`.`rf2_ss_descriptions` as d2 ON `d2`.`conceptId` = `d1`.`conceptId`
JOIN `snomed`.`rf2_ss_language_refset` as lang ON `lang`.`referencedComponentId` = `d1`.`id`
WHERE `refset`.`refSetId` =  32570071000036102
AND `refset`.`active` =  1
AND `d2`.`typeId` =  900000000000013009
AND `d1`.`active` =  1
AND `d2`.`active` =  1
AND `d1`.`moduleId` =  900000000000207008
AND `d2`.`moduleId` =  900000000000207008
AND `lang`.`active` =  1
AND `lang`.`acceptabilityId` =  900000000000548007
AND `d2`.`term` like "hypertension%"
ORDER BY `d1`.`term`, `d2`.`term`

哪里:

CREATE TABLE `rf2_ss_refset` (
  `id` char(36) COLLATE utf8_unicode_ci NOT NULL,
  `effectiveTime` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
  `active` smallint(1) NOT NULL,
  `moduleId` bigint(20) unsigned NOT NULL,
  `refSetId` bigint(20) unsigned NOT NULL,
  `referencedComponentId` bigint(20) unsigned NOT NULL,
  PRIMARY KEY (`id`,`effectiveTime`),
  KEY `moduleId_idx` (`moduleId`),
  KEY `refSetId_idx` (`refSetId`),
  KEY `referencedComponentId_idx` (`referencedComponentId`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

CREATE ALGORITHM=UNDEFINED DEFINER=`snomed`@`localhost` SQL SECURITY DEFINER VIEW `rf2_ss_concepts`
AS SELECT
   `t1`.`id` AS `id`,
   `t1`.`effectiveTime` AS `effectiveTime`,
   `t1`.`active` AS `active`,
   `t1`.`moduleId` AS `moduleId`,
   `t1`.`definitionStatusId` AS `definitionStatusId`
FROM `rf2_full_concepts` `t1` where (`t1`.`effectiveTime` = (select max(`t2`.`effectiveTime`) from `rf2_full_concepts` `t2` where (`t1`.`id` = `t2`.`id`)));

CREATE ALGORITHM=UNDEFINED DEFINER=`snomed`@`localhost` SQL SECURITY DEFINER VIEW `rf2_ss_descriptions`
AS SELECT
   `t1`.`id` AS `id`,
   `t1`.`effectiveTime` AS `effectiveTime`,
   `t1`.`active` AS `active`,
   `t1`.`moduleID` AS `moduleID`,
   `t1`.`conceptId` AS `conceptId`,
   `t1`.`languageCode` AS `languageCode`,
   `t1`.`typeID` AS `typeID`,
   `t1`.`term` AS `term`,
   `t1`.`caseSignificanceId` AS `caseSignificanceId`
FROM `rf2_full_descriptions` `t1` where (`t1`.`effectiveTime` = (select max(`t2`.`effectiveTime`) from `rf2_full_descriptions` `t2` where (`t1`.`id` = `t2`.`id`)));

CREATE ALGORITHM=UNDEFINED DEFINER=`snomed`@`localhost` SQL SECURITY DEFINER VIEW `rf2_ss_language_refset`
AS SELECT
   `t1`.`id` AS `id`,
   `t1`.`effectiveTime` AS `effectiveTime`,
   `t1`.`active` AS `active`,
   `t1`.`moduleId` AS `moduleId`,
   `t1`.`refSetId` AS `refSetId`,
   `t1`.`referencedComponentId` AS `referencedComponentId`,
   `t1`.`acceptabilityId` AS `acceptabilityId`
FROM `rf2_full_language_refset` `t1` where (`t1`.`effectiveTime` = (select max(`t2`.`effectiveTime`) from `rf2_full_language_refset` `t2` where (`t1`.`id` = `t2`.`id`)));

CREATE ALGORITHM=UNDEFINED DEFINER=`snomed`@`localhost` SQL SECURITY DEFINER VIEW `rf2_ss_relationships`
AS SELECT
   `t1`.`id` AS `id`,
   `t1`.`effectiveTime` AS `effectiveTime`,
   `t1`.`active` AS `active`,
   `t1`.`moduleId` AS `moduleId`,
   `t1`.`sourceId` AS `sourceId`,
   `t1`.`destinationId` AS `destinationId`,
   `t1`.`relationshipGroup` AS `relationshipGroup`,
   `t1`.`typeId` AS `typeId`,
   `t1`.`characteristicTypeId` AS `characteristicTypeId`,
   `t1`.`modifierId` AS `modifierId`
FROM `rf2_full_relationships` `t1` where (`t1`.`effectiveTime` = (select max(`t2`.`effectiveTime`) from `rf2_full_relationships` `t2` where (`t1`.`id` = `t2`.`id`)));

#select count(*) from rf2_full_concepts # 507046
CREATE TABLE `rf2_full_concepts` (
  `id` bigint(20) unsigned NOT NULL,
  `effectiveTime` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
  `active` tinyint(4) DEFAULT NULL,
  `moduleId` bigint(20) unsigned NOT NULL,
  `definitionStatusId` bigint(20) unsigned NOT NULL,
  PRIMARY KEY (`id`,`effectiveTime`),
  KEY `moduleId_idx` (`moduleId`),
  KEY `definitionStatusId_idx` (`definitionStatusId`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

#select count(*) from rf2_full_descriptions # 1486373
CREATE TABLE `rf2_full_descriptions` (
  `id` bigint(20) unsigned NOT NULL,
  `effectiveTime` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
  `active` tinyint(4) DEFAULT NULL,
  `moduleID` bigint(20) unsigned NOT NULL,
  `conceptId` bigint(20) unsigned NOT NULL,
  `languageCode` char(2) COLLATE utf8_unicode_ci NOT NULL DEFAULT 'en',
  `typeID` bigint(20) unsigned NOT NULL,
  `term` varchar(255) COLLATE utf8_unicode_ci DEFAULT NULL,
  `caseSignificanceId` bigint(20) unsigned NOT NULL,
  PRIMARY KEY (`id`,`effectiveTime`),
  KEY `moduleID_idx` (`moduleID`),
  KEY `conceptId_idx` (`conceptId`),
  KEY `typeID_idx` (`typeID`),
  KEY `caseSignificanceId_idx` (`caseSignificanceId`),
  KEY `term_idx` (`term`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

#select count(*) from rf2_full_relationships = 4582286 
CREATE TABLE `rf2_full_relationships` (
  `id` bigint(20) unsigned NOT NULL,
  `effectiveTime` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
  `active` tinyint(4) DEFAULT '1',
  `moduleId` bigint(20) unsigned NOT NULL,
  `sourceId` bigint(20) unsigned NOT NULL,
  `destinationId` bigint(20) unsigned NOT NULL,
  `relationshipGroup` bigint(20) unsigned NOT NULL,
  `typeId` bigint(20) unsigned NOT NULL,
  `characteristicTypeId` bigint(20) unsigned NOT NULL,
  `modifierId` bigint(20) unsigned NOT NULL,
  PRIMARY KEY (`id`,`effectiveTime`),
  KEY `moduleId_idx` (`moduleId`),
  KEY `sourceId_idx` (`sourceId`),
  KEY `destinationId_idx` (`destinationId`),
  KEY `relationshipGroup_idx` (`relationshipGroup`),
  KEY `typeId_idx` (`typeId`),
  KEY `characteristicTypeId_idx` (`characteristicTypeId`),
  KEY `modifierId_idx` (`modifierId`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

#select count(*) from rf2_full_language_refset # 624467
CREATE TABLE `rf2_full_language_refset` (
  `id` char(36) COLLATE utf8_unicode_ci NOT NULL,
  `effectiveTime` timestamp NOT NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
  `active` smallint(1) NOT NULL,
  `moduleId` bigint(20) unsigned NOT NULL,
  `refSetId` bigint(20) unsigned NOT NULL,
  `referencedComponentId` bigint(20) unsigned NOT NULL,
  `acceptabilityId` bigint(20) unsigned NOT NULL,
  PRIMARY KEY (`id`,`effectiveTime`),
  KEY `moduleId` (`moduleId`),
  KEY `refSetId` (`refSetId`),
  KEY `referencedComponentId` (`referencedComponentId`),
  KEY `acceptabilityId` (`acceptabilityId`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

在没有拼图的所有部分的情况下诊断别人的服务器是困难的,所以我将做出以下假设(如果我错了请纠正我):

  1. 这不是 运行 在数据库级服务器上
  2. MySQL 配置尚未专门针对此任务进行配置

对于您展示的示例,您的 table 看起来索引过多,并且由于数据集很大,我可以想象最大的索引文件太大而无法放入 MySQL 中索引缓存。

没有关于环境的更多信息,您描述的行为似乎取决于配置的缓冲区。此时,OS 介入并在内存中缓冲数据库。

当您重新启动 MySQL 时,它会很好且快速地查询,因为 OS 仍在其缓冲区中保存文件。当您停止访问数据库时,OS 最终将取消缓冲文件,您将回到缓慢的初始查询。

我在超过配置的缓冲区大小的大型索引上看到了相同的行为,但这是一组更大的数据。配置数据库为索引和 table 数据提供更大的缓冲区解决了我的特殊问题。在我的例子中,查询速度从 10-15 秒下降到毫秒。

http://dev.mysql.com/doc/refman/5.6/en/innodb-parameters.html#sysvar_innodb_buffer_pool_size

如果您有一些空闲 RAM,请尝试稍微增加缓冲池大小。 默认大小为 128Mb,最大的索引文件大约为 279Mb(64 字节 * 4,582,286 行)。 首先,尝试将配置中的值设置为 512Mb。重新启动,重新测试。如果它仍然不是很好,再添加 128Mb 并重复直到它起作用。 如果此数据库位于专用机器上,则根据您的设置将值设置得相当高(总 RAM 的 50-75%)应该是安全的。

快速 Google 提出了一个很好的指南,说明 fiddle 的配置值。 http://www.tocker.ca/2013/09/17/what-to-tune-in-mysql-56-after-installation.html