【发布时间】：2018-01-09 16:33:04
【问题描述】：
我有一个收藏产品，里面有 ~7.000.000 本书，总共有 ~40GB mongodb 3.4 数据库。以下是一本书文档的示例：
{
"_id" : ObjectId("597f17d22be7925d9a056e82"),
"ean13" : "9783891491904",
"price" : NumberInt(2100),
"name" : "My cool title",
"author_name" : "Doe, John",
"warengruppe" : "HC",
"book_category_key" : "728",
"keywords": ["fairy tale", "magic", "fantasy"]
...
}
现在我想对产品集合进行一些文本搜索：
db.products.find({
$text : {
$search: '"harry" "potter" "3" lsxger'
}
}, {
score: {
"$meta": "textScore"
},
ean13: 1,
name: 1,
author_name: 1,
price: 1,
images: 1,
warengruppe: 1
}).sort({
score: {
"$meta": "textScore"
},
name: 1
}).limit(9);
这里是解释的结果：
{
"queryPlanner" : {
"plannerVersion" : NumberInt(1),
"namespace" : "mydb.products",
"indexFilterSet" : false,
"parsedQuery" : {
"$text" : {
"$search" : "\"harry\" \"potter\" \"3\" lsxger",
"$language" : "german",
"$caseSensitive" : false,
"$diacriticSensitive" : false
}
},
"winningPlan" : {
"stage" : "PROJECTION",
"transformBy" : {
"score" : {
"$meta" : "textScore"
},
"ean13" : 1.0,
"name" : 1.0,
"author_name" : 1.0,
"price" : 1.0,
"images" : 1.0,
"warengruppe" : 1.0
},
"inputStage" : {
"stage" : "SORT",
"sortPattern" : {
"score" : {
"$meta" : "textScore"
},
"name" : 1.0
},
"limitAmount" : NumberInt(9),
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "TEXT",
"indexPrefix" : {
},
"indexName" : "fulltextsearch",
"parsedTextQuery" : {
"terms" : [
"3",
"harry",
"lsxger",
"pott"
],
"negatedTerms" : [
],
"phrases" : [
"harry",
"potter",
"3"
],
"negatedPhrases" : [
]
},
"textIndexVersion" : NumberInt(3),
"inputStage" : {
"stage" : "TEXT_MATCH",
"inputStage" : {
"stage" : "TEXT_OR",
"inputStages" : [
{
"stage" : "IXSCAN",
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
}
},
{
"stage" : "IXSCAN",
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
}
},
{
"stage" : "IXSCAN",
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
}
},
{
"stage" : "IXSCAN",
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
}
}
]
}
}
}
}
}
},
"rejectedPlans" : [
]
},
"executionStats" : {
"executionSuccess" : true,
"nReturned" : NumberInt(9),
"executionTimeMillis" : NumberInt(15441),
"totalKeysExamined" : NumberInt(1206999),
"totalDocsExamined" : NumberInt(1195069),
"executionStages" : {
"stage" : "PROJECTION",
"nReturned" : NumberInt(9),
"executionTimeMillisEstimate" : NumberInt(15294),
"works" : NumberInt(2402085),
"advanced" : NumberInt(9),
"needTime" : NumberInt(2402075),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"transformBy" : {
"score" : {
"$meta" : "textScore"
},
"ean13" : 1.0,
"name" : 1.0,
"author_name" : 1.0,
"price" : 1.0,
"images" : 1.0,
"warengruppe" : 1.0
},
"inputStage" : {
"stage" : "SORT",
"nReturned" : NumberInt(9),
"executionTimeMillisEstimate" : NumberInt(15234),
"works" : NumberInt(2402085),
"advanced" : NumberInt(9),
"needTime" : NumberInt(2402075),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"sortPattern" : {
"score" : {
"$meta" : "textScore"
},
"name" : 1.0
},
"memUsage" : NumberInt(22949),
"memLimit" : NumberInt(33554432),
"limitAmount" : NumberInt(9),
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"nReturned" : NumberInt(455),
"executionTimeMillisEstimate" : NumberInt(15074),
"works" : NumberInt(2402075),
"advanced" : NumberInt(455),
"needTime" : NumberInt(2401619),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"inputStage" : {
"stage" : "TEXT",
"nReturned" : NumberInt(455),
"executionTimeMillisEstimate" : NumberInt(15024),
"works" : NumberInt(2402074),
"advanced" : NumberInt(455),
"needTime" : NumberInt(2401618),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"indexPrefix" : {
},
"indexName" : "fulltextsearch",
"parsedTextQuery" : {
"terms" : [
"3",
"harry",
"lsxger",
"pott"
],
"negatedTerms" : [
],
"phrases" : [
"harry",
"potter",
"3"
],
"negatedPhrases" : [
]
},
"textIndexVersion" : NumberInt(3),
"inputStage" : {
"stage" : "TEXT_MATCH",
"nReturned" : NumberInt(455),
"executionTimeMillisEstimate" : NumberInt(14974),
"works" : NumberInt(2402074),
"advanced" : NumberInt(455),
"needTime" : NumberInt(2401618),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"docsRejected" : NumberInt(1194614),
"inputStage" : {
"stage" : "TEXT_OR",
"nReturned" : NumberInt(1195069),
"executionTimeMillisEstimate" : NumberInt(4500),
"works" : NumberInt(2402074),
"advanced" : NumberInt(1195069),
"needTime" : NumberInt(1207004),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"docsExamined" : NumberInt(1195069),
"inputStages" : [
{
"stage" : "IXSCAN",
"nReturned" : NumberInt(59101),
"executionTimeMillisEstimate" : NumberInt(131),
"works" : NumberInt(59102),
"advanced" : NumberInt(59101),
"needTime" : NumberInt(0),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
},
"keysExamined" : NumberInt(59101),
"seeks" : NumberInt(1),
"dupsTested" : NumberInt(59101),
"dupsDropped" : NumberInt(0),
"seenInvalidated" : NumberInt(0)
},
{
"stage" : "IXSCAN",
"nReturned" : NumberInt(9512),
"executionTimeMillisEstimate" : NumberInt(0),
"works" : NumberInt(9513),
"advanced" : NumberInt(9512),
"needTime" : NumberInt(0),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
},
"keysExamined" : NumberInt(9512),
"seeks" : NumberInt(1),
"dupsTested" : NumberInt(9512),
"dupsDropped" : NumberInt(0),
"seenInvalidated" : NumberInt(0)
},
{
"stage" : "IXSCAN",
"nReturned" : NumberInt(1134940),
"executionTimeMillisEstimate" : NumberInt(1381),
"works" : NumberInt(1134941),
"advanced" : NumberInt(1134940),
"needTime" : NumberInt(0),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
},
"keysExamined" : NumberInt(1134940),
"seeks" : NumberInt(1),
"dupsTested" : NumberInt(1134940),
"dupsDropped" : NumberInt(0),
"seenInvalidated" : NumberInt(0)
},
{
"stage" : "IXSCAN",
"nReturned" : NumberInt(3446),
"executionTimeMillisEstimate" : NumberInt(0),
"works" : NumberInt(3447),
"advanced" : NumberInt(3446),
"needTime" : NumberInt(0),
"needYield" : NumberInt(0),
"saveState" : NumberInt(18814),
"restoreState" : NumberInt(18814),
"isEOF" : NumberInt(1),
"invalidates" : NumberInt(0),
"keyPattern" : {
"_fts" : "text",
"_ftsx" : NumberInt(1)
},
"indexName" : "fulltextsearch",
"isMultiKey" : true,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : NumberInt(2),
"direction" : "backward",
"indexBounds" : {
},
"keysExamined" : NumberInt(3446),
"seeks" : NumberInt(1),
"dupsTested" : NumberInt(3446),
"dupsDropped" : NumberInt(0),
"seenInvalidated" : NumberInt(0)
}
]
}
}
}
}
}
},
"allPlansExecution" : [
]
},
"serverInfo" : {
"host" : "lvps83-169-23-14.dedicated.hosteurope.de",
"port" : NumberInt(27017),
"version" : "3.4.4",
"gitVersion" : "888390515874a9debd1b6c5d36559ca86b44babd"
},
"ok" : 1.0
}
这大约需要 25 秒或更长时间。我已经为 book_category_key、ean13、author_name、name 和 fulltextsearch 设置了一些索引：
{
"v" : 2,
"name" : "fulltextsearch",
"ns" : "mydb.products",
"background" : true,
"weights" : {
"author_name" : 5,
"ean13" : 10,
"isbn" : 10,
"keywords" : 2,
"languages.search" : 8,
"mainsubject.name" : 3,
"name" : 10
},
"default_language" : "german",
"language_override" : "language_x",
"textIndexVersion" : 3
}
如何提高速度或在哪里寻找更多信息？
【问题讨论】：
-
你能发布整个搜索命令吗？对我来说，搜索看起来不像原生 mongo.find() 或 .aggregate() ...但是，您是否在查询/聚合管道上运行了
explain()/explain:true？这应该会给你一些提示（即全扫描、索引使用等） -
同时检查你的索引（尤其是文本索引）的大小与可用内存有关。索引应该完全适合内存。没有最终的“limit(9)”返回多少个结果？
-
它是从 db.currentOp() 的结果中截取的。现在我已将其更改为本机 mongodb 代码并添加说明
-
上面的查询返回455个结果，没有限制。 Db 本身具有 >40GB 的集合 >9GB。 “indexDetails.fulltextsearch.cache.bytes 读入缓存”：“16,3 GiB”
-
你的机器有多少内存？
标签： mongodb