用大链接表优化mysql分组_Mysql_Group By_Many To Many

用大链接表优化mysql分组

mysql

用大链接表优化mysql分组,mysql,group-by,many-to-many,Mysql,Group By,Many To Many,我已经读了很多关于这个的文章，但是每次查询都会有30多秒的时间，而我确信它的运行速度会快很多问题是：具有如下定义的大型链接表（4000万行，数据由650MB和表示1.8GB的索引组成）： CREATE TABLE IF NOT EXISTS `glossary_entry_wordList_1` ( `idTerm` mediumint(8) unsigned NOT NULL, `idKeyword` mediumint(8) unsigned NOT NULL, `termL

我已经读了很多关于这个的文章，但是每次查询都会有30多秒的时间，而我确信它的运行速度会快很多

问题是：

具有如下定义的大型链接表（4000万行，数据由650MB和表示1.8GB的索引组成）：

CREATE TABLE IF NOT EXISTS `glossary_entry_wordList_1` (
  `idTerm` mediumint(8) unsigned NOT NULL,
  `idKeyword` mediumint(8) unsigned NOT NULL,
  `termLength` smallint(6) NOT NULL,
  `termNumberWords` tinyint(4) NOT NULL,
  `termTransliteralRFC` mediumint(9) NOT NULL,
  `keywordLength` tinyint(3) unsigned NOT NULL,
  `termLanguage` tinyint(4) NOT NULL,
  PRIMARY KEY (`idKeyword`,`idTerm`),
  KEY `termTransliteralRFC` (`termTransliteralRFC`),
  KEY `termLength` (`termLength`),
  KEY `secondPrimary` (`idTerm`,`idKeyword`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_general_ci

CREATE TEMPORARY TABLE IF NOT EXISTS `foundIDs` (
  `searchId` int(11) NOT NULL,
  `searchedKeywordId` int(11) NOT NULL,
  `similarKeywordId` mediumint(8) unsigned NOT NULL,
  `partsMatched` tinyint(4) NOT NULL,
  `sumSimliarParts` int(11) NOT NULL,
  `keywordLength` int(11) NOT NULL,
  `fuzzyMark` float NOT NULL,
  `keywordDjb2` bigint(20) NOT NULL,
  `smallKeyword` tinyint(4) NOT NULL,
  PRIMARY KEY (`similarKeywordId`),
  KEY `searchId` (`searchId`),
  KEY `searchedKeywordId` (`searchedKeywordId`),
  KEY `partsMatched` (`partsMatched`),
  KEY `keywordLength` (`keywordLength`),
  KEY `smallKeyword` (`smallKeyword`),
  KEY `keywordDjb2` (`keywordDjb2`)
) ENGINE=MEMORY DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

和一个小型临时表，定义如下：

CREATE TABLE IF NOT EXISTS `glossary_entry_wordList_1` (
  `idTerm` mediumint(8) unsigned NOT NULL,
  `idKeyword` mediumint(8) unsigned NOT NULL,
  `termLength` smallint(6) NOT NULL,
  `termNumberWords` tinyint(4) NOT NULL,
  `termTransliteralRFC` mediumint(9) NOT NULL,
  `keywordLength` tinyint(3) unsigned NOT NULL,
  `termLanguage` tinyint(4) NOT NULL,
  PRIMARY KEY (`idKeyword`,`idTerm`),
  KEY `termTransliteralRFC` (`termTransliteralRFC`),
  KEY `termLength` (`termLength`),
  KEY `secondPrimary` (`idTerm`,`idKeyword`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_general_ci

CREATE TEMPORARY TABLE IF NOT EXISTS `foundIDs` (
  `searchId` int(11) NOT NULL,
  `searchedKeywordId` int(11) NOT NULL,
  `similarKeywordId` mediumint(8) unsigned NOT NULL,
  `partsMatched` tinyint(4) NOT NULL,
  `sumSimliarParts` int(11) NOT NULL,
  `keywordLength` int(11) NOT NULL,
  `fuzzyMark` float NOT NULL,
  `keywordDjb2` bigint(20) NOT NULL,
  `smallKeyword` tinyint(4) NOT NULL,
  PRIMARY KEY (`similarKeywordId`),
  KEY `searchId` (`searchId`),
  KEY `searchedKeywordId` (`searchedKeywordId`),
  KEY `partsMatched` (`partsMatched`),
  KEY `keywordLength` (`keywordLength`),
  KEY `smallKeyword` (`smallKeyword`),
  KEY `keywordDjb2` (`keywordDjb2`)
) ENGINE=MEMORY DEFAULT CHARSET=utf8 COLLATE=utf8_unicode_ci;

我需要从

glossary\u entry\u wordList\u 1

中检索与表

foundIDs

中至少50%的

idKeyword