嗨，我知道有很多关于这方面的说法，但我无法找到我的具体问题的答案。我有以下JSON文档，并尝试为questions.questionEntry.metaTags数组创建一个有效的索引：
{
"questions": [
{
"questionEntry": {
"id": 1,
"info": {
"seasonNumber": 1,
"episodeNumber": 1,
"episodeName": "Days Gone Bye"
},
"questionItem": {
"theQuestion": "",
"attachedElement": {
"type": 1,
"value": ""
}
},
"options": [
{
"type": 1,
"value": ""
},
{
"type": 1,
"value": ""
}
],
"answer": {
"questionId": 1,
"answer": 1
},
"metaTags": [
"Season 1",
"Episode 1"
]
}
}
]
}
然后我向我的数据库添加了5000,000个重复文档，并添加了一个包含不同数据字段的附加文档来运行一些测试。
我在unindexed集合上运行了以下查询，执行时间为640ms：
db.questions1.find({"questions.questionEntry.metaTags" : "Season 1"},{'questions.$':1})._addSpecial( "$explain", 1 ).pretty()
然后我创建了以下索引：
db.questions1.createIndex( { "questions.questionEntry.metaTags" : 1 })
现在我运行了相同的查询，但现在执行时间是9070毫秒......！
这是explain（），显示了500001个检查过的文件！：
{
"queryPlanner" : {
"plannerVersion" : 1,
"namespace" : "test.questions1",
"indexFilterSet" : false,
"parsedQuery" : {
"questions.questionEntry.metaTags" : {
"$eq" : "Season 1"
}
},
"winningPlan" : {
"stage" : "PROJECTION",
"transformBy" : {
"questions.$" : 1
},
"inputStage" : {
"stage" : "FETCH",
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"questions.questionEntry.metaTa
s" : 1
},
"indexName" : "questions.questionEntry.
etaTags_1",
"isMultiKey" : true,
"direction" : "forward",
"indexBounds" : {
"questions.questionEntry.metaTa
s" : [
"[\"Season 1\", \"Seaso
1\"]"
]
}
}
}
},
"rejectedPlans" : [ ]
},
"executionStats" : {
"executionSuccess" : true,
"nReturned" : 500001,
"executionTimeMillis" : 11255,
"totalKeysExamined" : 500001,
"totalDocsExamined" : 500001,
"executionStages" : {
"stage" : "PROJECTION",
"nReturned" : 500001,
"executionTimeMillisEstimate" : 10750,
"works" : 500002,
"advanced" : 500001,
"needTime" : 0,
"needFetch" : 0,
"saveState" : 3907,
"restoreState" : 3907,
"isEOF" : 1,
"invalidates" : 0,
"transformBy" : {
"questions.$" : 1
},
"inputStage" : {
"stage" : "FETCH",
"nReturned" : 500001,
"executionTimeMillisEstimate" : 9310,
"works" : 500002,
"advanced" : 500001,
"needTime" : 0,
"needFetch" : 0,
"saveState" : 3907,
"restoreState" : 3907,
"isEOF" : 1,
"invalidates" : 0,
"docsExamined" : 500001,
"alreadyHasObj" : 0,
"inputStage" : {
"stage" : "IXSCAN",
"nReturned" : 500001,
"executionTimeMillisEstimate" : 8970,
"works" : 500001,
"advanced" : 500001,
"needTime" : 0,
"needFetch" : 0,
"saveState" : 3907,
"restoreState" : 3907,
"isEOF" : 1,
"invalidates" : 0,
"keyPattern" : {
"questions.questionEntry.metaTa
s" : 1
},
"indexName" : "questions.questionEntry.
etaTags_1",
"isMultiKey" : true,
"direction" : "forward",
"indexBounds" : {
"questions.questionEntry.metaTa
s" : [
"[\"Season 1\", \"Seaso
1\"]"
]
},
"keysExamined" : 500001,
"dupsTested" : 500001,
"dupsDropped" : 0,
"seenInvalidated" : 0,
"matchTested" : 0
}
}
},
"allPlansExecution" : [ ]
},
"serverInfo" : {
"host" : "Voltage",
"port" : 27017,
"version" : "3.0.3",
"gitVersion" : "b40106b36eecd1b4407eb1ad1af6bc60593c6105"
}
}
Mongo db不是我的事，而且我很难理解为什么执行需要更长的时间？
索引字符串metaTags数组的最佳方法是什么？
非常感谢