在mongodb中多个嵌套数组中使用展开
在mongodb中多个嵌套数组中使用展开
提问于 2016-12-22 18:23:57
我已经将对象存储在我的mongodb(版本3.2)集合中，
{
"_id" : ObjectId("585a42b5b7e79d1c0c533f1f"),
"instanceId" : "i-b385a9bd",
"DiskSpaceAvailable" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:14:00.000Z"),
"Average" : 4.32112884521484,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:32:00.000Z"),
"Average" : 4.32107543945312,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:50:00.000Z"),
"Average" : 4.32101821899414,
"Unit" : "Gigabytes"
}
]
},
"DiskSpaceUsed" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:14:00.000Z"),
"Average" : 3.33073806762695,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:32:00.000Z"),
"Average" : 3.33079147338867,
"Unit" : "Gigabytes"
}
]
},
"MemoryUsed" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:14:00.000Z"),
"Average" : 0.753532409667969,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:32:00.000Z"),
"Average" : 0.753063201904297,
"Unit" : "Gigabytes"
}
]
},
"MemoryUtilization" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:18:00.000Z"),
"Average" : 19.5049320125989,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T12:36:00.000Z"),
"Average" : 19.5078950721357,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T12:54:00.000Z"),
"Average" : 19.5068086169722,
"Unit" : "Percent"
}
]
},
"DiskSpaceUtilization" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:18:00.000Z"),
"Average" : 42.9914921714092,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T12:36:00.000Z"),
"Average" : 42.9921815029693,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T12:54:00.000Z"),
"Average" : 42.992920072498,
"Unit" : "Percent"
}
]
},
"SwapUtilization" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:18:00.000Z"),
"Average" : 0,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T12:36:00.000Z"),
"Average" : 0,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T12:54:00.000Z"),
"Average" : 0,
"Unit" : "Percent"
},
{
"Timestamp" : ISODate("2016-12-20T13:12:00.000Z"),
"Average" : 0,
"Unit" : "Percent"
}
]
},
"SwapUsed" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T13:06:00.000Z"),
"Average" : 0,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T13:24:00.000Z"),
"Average" : 0,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:36:00.000Z"),
"Average" : 0,
"Unit" : "Gigabytes"
}
]
},
"MemoryAvailable" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:14:00.000Z"),
"Average" : 3.10872268676758,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:32:00.000Z"),
"Average" : 3.10919189453125,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:50:00.000Z"),
"Average" : 3.10895538330078,
"Unit" : "Gigabytes"
}
]
}
}我正在尝试使用mongodb聚合，下面是我的查询
db.collectionSchema.aggregate([
{
$match :{ "instanceId" : "i-b385a9bd" }
},
{
$unwind : "$DiskSpaceAvailable.Datapoints"
},
{
$unwind : "$DiskSpaceUtilization.Datapoints"
},
{
$unwind : "$DiskSpaceUsed.Datapoints"
},
{
$unwind : "$MemoryUsed.Datapoints"
},
{
$unwind : "$SwapUtilization.Datapoints"
},
{
$unwind : "$MemoryAvailable.Datapoints"
},
{
$unwind : "$MemoryUtilization.Datapoints"
},
{
$unwind : "$SwapUsed.Datapoints"
},
{
$group : { _id : "$instanceId" ,
DiskSpaceAvailable : { "$avg" : "$DiskSpaceAvailable.Datapoints.Average" } ,
DiskSpaceAvailableUnit : { "$addToSet" : "$DiskSpaceAvailable.Datapoints.Unit" },
DiskSpaceUtilization : {"$avg" : "$DiskSpaceUtilization.Datapoints.Average"},
DiskSpaceUtilizationUnit : {"$addToSet" : "$DiskSpaceUtilization.Datapoints.Unit"},
DiskSpaceUsed : {"$avg" : "$DiskSpaceUsed.Datapoints.Average"},
DiskSpaceUsedUnit : {"$addToSet" : "$DiskSpaceUsed.Datapoints.Unit"},
MemoryUsed :{"$avg" : "$MemoryUsed.Datapoints.Average"},
MemoryUsedUnit:{"$addToSet" : "$MemoryUsed.Datapoints.Unit"},
SwapUtilization:{"$avg" : "$SwapUtilization.Datapoints.Average"},
SwapUtilizationUnit:{"$addToSet" : "$SwapUtilization.Datapoints.Unit"},
MemoryAvailable:{"$avg" : "$MemoryAvailable.Datapoints.Average"},
MemoryAvailableUnit:{"$addToSet" : "$MemoryAvailable.Datapoints.Unit"},
MemoryUtilization:{"$avg" : "$MemoryUtilization.Datapoints.Average"},
MemoryUtilizationUnit: {"$addToSet" : "$MemoryUtilization.Datapoints.Unit"},
SwapUsed:{"$avg" : "$SwapUsed.Datapoints.Average"},
SwapUsedUnit: {"$addToSet" : "$SwapUsed.Datapoints.Unit"}
}
},
{
$project : { _id:1 ,
DiskSpaceAvailable:1 ,
DiskSpaceAvailableUnit : 1,
DiskSpaceUtilization : 1,
DiskSpaceUtilizationUnit : 1,
DiskSpaceUsed : 1,
DiskSpaceUsedUnit : 1,
MemoryUsed :1,
MemoryUsedUnit:1,
SwapUtilization:1,
SwapUtilizationUnit:1,
MemoryAvailable:1,
MemoryAvailableUnit:1,
MemoryUtilization:1,
MemoryUtilizationUnit: 1,
SwapUsed:1,
SwapUsedUnit:1
}
}
]);这个查询不会返回并无限期运行，我尝试过使用前4个展开操作符，它的工作时间大约为3-4秒，但是在添加了第5个展开操作符之后，查询就会被抛出，而不会返回。我肯定我做错了什么，但不能指手画脚，有人能指出我是否犯了错误吗？
任何类型的建议都是最受欢迎的，我也愿意改变模式。
谢谢您:)
回答 1
Stack Overflow用户
回答已采纳
发布于 2017-02-17 11:03:06
一份文件里有很多数据。展开这许多嵌套的文档并计算相同的平均值，不仅会增加响应时间，而且还会增加所消耗的资源！
为了随后快速进行聚合查询，我坚持认为您应该尝试在插入文档时执行平均，而不是在检索时执行。
例如，当添加第一个文档(平均值为5)时，DiskSpaceAvailable的总体平均值为5&当添加第二个子文档(平均为2)时，总平均值计算为5+2/2 = 3.5。
数据设计将类似于 :-
{
"_id" : ObjectId("585a42b5b7e79d1c0c533f1f"),
"instanceId" : "i-b385a9bd",
"DiskSpaceAvailableUnit": "Gigabytes",
"DiskSpaceAvailableAverage": <The computed average value>,
"DiskSpaceAvailable" : {
"Datapoints" : [
{
"Timestamp" : ISODate("2016-12-20T12:14:00.000Z"),
"Average" : 4.32112884521484,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:32:00.000Z"),
"Average" : 4.32107543945312,
"Unit" : "Gigabytes"
},
{
"Timestamp" : ISODate("2016-12-20T12:50:00.000Z"),
"Average" : 4.32101821899414,
"Unit" : "Gigabytes"
}
]
},
....
}因此，您只需在不执行任何计算的情况下获取数据&响应也会相当快(与当前的响应时间相比要少得多)。
但是，这样的结构随后会增加插入/更新的计算时间&复杂性。但是，如果更快的检索是最重要的，那么您应该考虑到这个结构。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/41289534
复制相关文章
相似问题
腾讯云开发者
