MongoDB$或对自身的查询速度要快得多
我有一个mongo实例，集合中有16m个文档。我写了一个查询来搜索一个（索引的）字段，我得到了一些奇怪的结果，我无法解释 如果我直接执行查询，如：MongoDB$或对自身的查询速度要快得多,mongodb,mongodb-query,Mongodb,Mongodb Query,我有一个mongo实例，集合中有16m个文档。我写了一个查询来搜索一个（索引的）字段，我得到了一些奇怪的结果，我无法解释 如果我直接执行查询，如： find({ "$and" : [ { "ipAddr" : { "$regex" : "^01:172"}} , { "active" : true}]}).limit(100).sort({ "_id" : 1}) 甚至在查询中添加一个毫无意义的$or： find({ "$and" : [ { "$or" : [ { "ipAddr" : {
find({ "$and" : [ { "ipAddr" : { "$regex" : "^01:172"}} , { "active" : true}]}).limit(100).sort({ "_id" : 1})
find({ "$and" : [ { "$or" : [ { "ipAddr" : { "$regex" : "^01:172"}}]} , { "active" : true}]}).limit(100).sort({ "_id" : 1})
find({ "$and" : [ { "$or" : [ { "ipAddr" : { "$regex" : "^01:172"}} , { "ipAddr" : { "$regex" : "^01:172"}}]} , { "active" : true}]}).limit(100).sort({ "_id" : 1})
find({ "$and" : [ { "$or" : [ { "ipAddr" : { "$regex" : "^01:172"}}]} , { "active" : true}]}).limit(100).sort({ "_id" : 1}).explain()
{
"queryPlanner" : {
"plannerVersion" : 1,
"namespace" : "CLS-TEST.Leases",
"indexFilterSet" : false,
"parsedQuery" : {
"$and" : [
{
"active" : {
"$eq" : true
}
},
{
"ipAddr" : /^01:172/
}
]
},
"winningPlan" : {
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"active" : {
"$eq" : true
}
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"ipAddr" : 1
},
"indexName" : "ipAddr_1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"ipAddr" : [
"[\"01:172\", \"01:173\")",
"[/^01:172/, /^01:172/]"
]
}
}
}
}
},
"rejectedPlans" : [
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"ipAddr" : /^01:172/
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"sessionId" : 1,
"updateTime" : 1
},
"indexName" : "active_1_sessionId_1_updateTime_1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"sessionId" : [
"[MinKey, MaxKey]"
],
"updateTime" : [
"[MinKey, MaxKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"ipAddr" : /^01:172/
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"clientId" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_clientId_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"clientId" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"ipAddr" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_ipAddr_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"ipAddr" : [
"[\"01:172\", \"01:173\")",
"[/^01:172/, /^01:172/]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"ipAddr" : /^01:172/
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"macAddress" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_macAddress_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"macAddress" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"ipAddr" : /^01:172/
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"remoteId" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_remoteId_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"remoteId" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "LIMIT",
"limitAmount" : 100,
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$and" : [
{
"active" : {
"$eq" : true
}
},
{
"ipAddr" : /^01:172/
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"_id" : 1
},
"indexName" : "_id_",
"isMultiKey" : false,
"isUnique" : true,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"_id" : [
"[MinKey, MaxKey]"
]
}
}
}
}
]
},
"serverInfo" : {
"host" : "",
"port" : 27017,
"version" : "3.2.3",
"gitVersion" : "b326ba837cf6f49d65c2f85e1b70f6f31ece7937"
},
"ok" : 1
}
Explain（）在$上或对其本身进行解释，这需要您可能会注意到，没有任何索引选择包括
“active”“ipAddr”“ipAddr”{“active”：true}“active”“ipAddr”$或“active”$或语句之外的任何条件都将是最佳选择索引的逻辑选择
由于从这些结果返回的结果可能较小，因此“筛选”出正则表达式匹配比查看所有正则表达式结果并筛选出“活动”值更快
因此，为该查询定义的“最佳”索引为：
.createIndex（{“活动”：1，“ipAddr”：1}）
然后，两个查询的结果都是一致的，当然前提是优化者不会被其他索引所迷惑，而是选择了那个索引。要强制选择索引，请使用您可能会注意到，所有索引选择都不包括“active”
和“ipAddr”
的组合，这将是此处要定义的有用索引
简而言之，“较慢”查询只使用“ipAddr”
的索引，因此需要更多的工作才能“过滤”出{“active”：true}
条目
显然，当其他索引选择使用带有这些边界的“active”
键时，传递给regex模式上后续过滤器的结果较少。这里似乎有很多索引，但没有一个真正适合查询
我将为您提供至少在任一查询上运行“explain”输出的道具，但如果仔细观察，您会发现“slow”查询“错误地”选择了“ipAddr”
索引，认为它是最佳的。可能不是，但乐观主义者考虑使用“锚定”正则表达式是一个合理的假设
当$或
中只有“一”个参数时，它就不会这样做了。“两个”参数可以实现这一点，而优化者通过查找在其他查询条件之前的索引（“active”
值）进行另一个“猜测”
这是有道理的，因为它现在正在运行“两个”查询，从中它将“相交”结果，因此$或语句之外的任何条件都将是最佳选择索引的逻辑选择
由于从这些结果返回的结果可能较小，因此“筛选”出正则表达式匹配比查看所有正则表达式结果并筛选出“活动”值更快
因此，为该查询定义的“最佳”索引为：
.createIndex（{“活动”：1，“ipAddr”：1}）
然后，两个查询的结果都是一致的，当然前提是优化者不会被其他索引所迷惑，而是选择了那个索引。要强制选择索引，请使用感谢详细的响应和指向“索引交点”的指针。我希望避免创建额外的索引，因为其他索引可以减少维护开销，但这可能是必需的。@caverman关于索引的数量，您可能希望仔细查看所有查询模式（并解释输出），然后决定是否真的需要它们。最好只使用复合索引，其中索引键被“最佳地”使用，因此在使用最常见的组合和它们可能过滤的结果之前。这里的教训主要是，“active”
是减少可能结果的实际值，对于此查询，至少该值将作为索引中的前一项发挥最大的作用。感谢详细的响应和指向“索引交叉点”的指针。我希望避免创建额外的索引，因为其他索引可以减少维护开销，但这可能是必需的。@caverman关于索引的数量，您可能需要
find({ "$and" : [ { "$or" : [ { "ipAddr" : { "$regex" : "^01:172"}} , { "ipAddr" : { "$regex" : "^01:172"}}]} , { "active" : true}]}).limit(100).sort({ "_id" : 1}).explain()
{
"queryPlanner" : {
"plannerVersion" : 1,
"namespace" : "CLS-TEST.Leases",
"indexFilterSet" : false,
"parsedQuery" : {
"$and" : [
{
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
{
"active" : {
"$eq" : true
}
}
]
},
"winningPlan" : {
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"active" : {
"$eq" : true
}
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"ipAddr" : 1
},
"indexName" : "ipAddr_1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"ipAddr" : [
"[\"01:172\", \"01:173\")",
"[/^01:172/, /^01:172/]"
]
}
}
}
}
},
"rejectedPlans" : [
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"sessionId" : 1,
"updateTime" : 1
},
"indexName" : "active_1_sessionId_1_updateTime_1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"sessionId" : [
"[MinKey, MaxKey]"
],
"updateTime" : [
"[MinKey, MaxKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"clientId" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_clientId_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"clientId" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"ipAddr" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_ipAddr_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"ipAddr" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"macAddress" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_macAddress_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"macAddress" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "SORT",
"sortPattern" : {
"_id" : 1
},
"limitAmount" : 100,
"inputStage" : {
"stage" : "SORT_KEY_GENERATOR",
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"active" : 1,
"remoteId" : 1,
"startTime" : -1,
"_id" : -1
},
"indexName" : "active_1_remoteId_1_startTime_-1__id_-1",
"isMultiKey" : false,
"isUnique" : false,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"active" : [
"[true, true]"
],
"remoteId" : [
"[MinKey, MaxKey]"
],
"startTime" : [
"[MaxKey, MinKey]"
],
"_id" : [
"[MaxKey, MinKey]"
]
}
}
}
}
},
{
"stage" : "LIMIT",
"limitAmount" : 100,
"inputStage" : {
"stage" : "FETCH",
"filter" : {
"$and" : [
{
"$or" : [
{
"ipAddr" : /^01:172/
},
{
"ipAddr" : /^01:172/
}
]
},
{
"active" : {
"$eq" : true
}
}
]
},
"inputStage" : {
"stage" : "IXSCAN",
"keyPattern" : {
"_id" : 1
},
"indexName" : "_id_",
"isMultiKey" : false,
"isUnique" : true,
"isSparse" : false,
"isPartial" : false,
"indexVersion" : 1,
"direction" : "forward",
"indexBounds" : {
"_id" : [
"[MinKey, MaxKey]"
]
}
}
}
}
]
},
"serverInfo" : {
"host" : "",
"port" : 27017,
"version" : "3.2.3",
"gitVersion" : "b326ba837cf6f49d65c2f85e1b70f6f31ece7937"
},
"ok" : 1
}