慢*初始* mysql查询

时间:2015-02-06 11:35:55

标签: mysql database snomed-ct

运行Mysql V5.6.22,在正确索引的数据库上运行复杂查询,响应时间最初非常慢(10秒钟的秒数)。后续查询(针对不同项目)响应非常快(50毫秒)。所以我猜查询缓存正在完成他们的工作 - 但我如何最小化最初的慢响应?

数据库是一个外部维护的医疗数据库(SNOMED),我使用推荐的视图来查看当前快照 - 我认为这些视图是速度的限制。

奇怪地重新启动mysql没有什么区别 - 这似乎是一个时间问题 - 如果数据库暂时使用它只需要很长时间就可以启动。

所以我的问题是,是否有一个mysql设置用于保存这些缓存的时间,或者我应该使用不同的方法而不使用视图(SNOMED的数据更新2年,并在另一个类似的数据库中药品有月刊。?

有些人希望看到这样的查询。警告它确实有点棘手,基本查询的行数在注释中给出......; - )

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`

其中:

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;

1 个答案:

答案 0 :(得分:2)

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

  1. 这不在DB级服务器上运行
  2. MySQL配置还没有特别配置到此任务
  3. 对于示例,您已经显示您的表看起来过度索引,并且由于大型数据集,我可以想象最大的索引文件太大而不适合MySQL的索引缓存。

    如果没有关于环境的更多信息,您所描述的行为似乎取决于配置的缓冲区。此时,操作系统介入并将DB缓存在内存中。

    当你重新启动MySQL时,它会很好地查询,因为操作系统仍然将文件保存在缓冲区中。当您停止访问数据库时,操作系统最终将取消缓冲文件,您将返回到较慢的初始查询。

    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,但这是一个更大的数据集。配置数据库以获得更大的索引和表数据缓冲区解决了我的特殊问题。就我而言,查询速度从10-15秒降低到毫秒。

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

    如果你有一些空闲的RAM,请尝试稍微提高缓冲池大小。 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。重启,重新测试。如果它仍然不好,请添加另一个128Mb并重复直到它工作。 如果此DB位于专用机器上,根据您的设置,将该值设置得相当高(50-75%总RAM)应该是安全的。

    一个快速的谷歌提出了一个很好的指南,指出要摆弄的配置值。 http://www.tocker.ca/2013/09/17/what-to-tune-in-mysql-56-after-installation.html