Mongo request slow - mongodb

I'm trying Mongo with a million enties. My request is really slow.
Do you have any ideas to optimize it ?
db.financial_transaction.runCommand({
"aggregate": "financial_transaction",
"pipeline": [ {
"$match": {
"transaction_type": { "$in": [ 1, 2 ] },
"created_at": { "$gte": new ISODate("2016-03-13T00:00:00+01:00"), "$lte": new ISODate("2017-12-13T23:59:00+01:00") },
"type": { "$in": [ "A", "C", "E" ] },
"sid": { "$in": [ 1, 3, 7, 9, 11, 13 ] },
"context": { "$in": [ "CL", "RE" ] } }
}, {
"$group": { "_id": { "paymentType": "$payment_type",
"paymentMethod": "$payment_method",
"responseCode": "$response_code",
"reasonCode": "$reason_code"
},
"count": { "$sum": 1 }, "total_amount": { "$sum": "$requested_amount" } } }, { "$sort": { "count": -1 } } ]
});
Indexes:
_id_
idx_context
idx_payment_method
idx_response_code
idx_reason_code
idx_created_at
idx_transaction_type
idc_payment_method_created_at_transaction_type_origin_auth_system
idx_created_at_context_transaction_type
idx_updated_at
I made a gist with the explain result: https://gist.github.com/sanchobouillant/bd59403242ebb1ec45582dff74b457a2

Related

Filter out items from mongoDb nested array and add new field

There is a mongoDb collection, looks like this:
[
{
"_id": {
"$oid": "63110728d74738cdc48a7de0"
},
"listName": "list_name",
"alloweUidList": [
{
"uid": "prQUKkIxljVqbHlCKah7T1Rh7l22",
"role": "creator",
"boolId": 1,
"crDate": "2022-09-01 21:25",
"modDate": null
}
],
"offerModelList": [
{
"offerListenerEntity": {
"_id": "6311072ed74738cdc48a7de1",
"uid": "prQUKkIxljVqbHlCKah7T1Rh7l22",
"itemName": "sometehing",
"crDate": "2022-09-01 21:25",
"boolId": 1,
"modDate": null,
"imageColorIndex": 3,
"shoppingListId": "63110728d74738cdc48a7de0",
"checkFlag": 0,
"itemCount": 1
},
"offers": [
{
"id": "62fa7983b7f32cc089864a3b",
"itemId": 127382,
"itemName": "item_1",
"itemCleanName": "item_clean_name",
"imageUrl": "item.png",
"price": 10,
"measure": "measure",
"salesStart": "N.a",
"source": "source",
"runDate": "2022.08.15-14:11:15",
"shopName": "shop_name",
"isSales": 1,
"insertType": "automate",
"timeKey": "2022_08_15_18_51",
"imageColorIndex": 0,
"isSelectedFlag": 1,
"selectedBy": "not_selected",
"itemCount": 1
},
{
"id": "62fa7983b7f32cc089864a3b",
"itemId": 127382,
"itemName": "item_2",
"itemCleanName": "item_clean_name",
"imageUrl": "image.png",
"price": 20,
"measure": "measure",
"salesStart": "N.a",
"source": "source",
"runDate": "2022.08.15-14:11:15",
"shopName": "shop_name",
"isSales": 1,
"insertType": "automate",
"timeKey": "2022_08_15_18_51",
"imageColorIndex": 0,
"isSelectedFlag": 0,
"selectedBy": "not_selected",
"itemCount": 1
}
]
},
{
"offerListenerEntity": {
"_id": "6311a5c0d74738cdc48a7de2",
"uid": "prQUKkIxljVqbHlCKah7T1Rh7l22",
"itemName": "anything",
"crDate": "2022-09-02 08:42",
"boolId": 1,
"modDate": null,
"imageColorIndex": 1,
"shoppingListId": "63110728d74738cdc48a7de0",
"checkFlag": 0,
"itemCount": 2
},
"offers": []
}
],
"crDate": "2022-09-01 21:25",
"modDate": "2022-09-01 21:25",
"boolId": 1,
"imageColorIndex": 1
}
]
So it has an array, with a nested array.
I would like to filter out the entire item from the offerModelList array, if the offerModelList.offerListenerEntity.boolId == 0 It's working with this aggregate query:
[
{
"$match": {
"alloweUidList": {
"$elemMatch": {
"uid": "prQUKkIxljVqbHlCKah7T1Rh7l22",
"boolId": 1
}
},
"boolId": 1,
}
},
{
"$addFields": {
"offerModelList": {
"$filter": {
"input": "$offerModelList",
"as": "i",
"cond": {
"$eq": [
"$$i.offerListenerEntity.boolId",
1
]
}
}
}
},
}
]
The problem comes, when I try to filter out items from the offerModelList.offers array based on isSelectedFlag field.
I modified my query to this:
db.collection.aggregate([
{
"$match": {
"alloweUidList": {
"$elemMatch": {
"uid": "prQUKkIxljVqbHlCKah7T1Rh7l22",
"boolId": 1
}
},
"boolId": 1,
}
},
{
"$addFields": {
"offerModelList": {
"$filter": {
"input": "$offerModelList",
"as": "i",
"cond": {
"$eq": [
"$$i.offerListenerEntity.boolId",
1
]
}
}
}
},
},
{
"$addFields": {
"offerModelList.offers": {
"$filter": {
"input": "$offerModelList.offers",
"as": "x",
"cond": {
"$eq": [
"$$x.isSelectedFlag",
1
]
}
}
}
},
}
])
The problem is, it alwas return empty offers array.
Here comes an example: https://mongoplayground.net/p/kksRpoNKr1k in this specific case the offers array should cointains only 1 item.
Don't think that you are able to directly filter from offerModelList.offers.
Instead, for the last stage,
$set - Set offerModelList field.
1.1. $map - Iterate element in offerModelList array and return a new array.
1.1.1. $mergeObjects - Merge current iterated document with the document resulted from 1.1.1.1.
1.1.1.1. Document with offers array. Via $filter to filter the document(s) with isSelectedFlag: 1.
db.collection.aggregate([
{
"$match": {
"alloweUidList": {
"$elemMatch": {
"uid": "prQUKkIxljVqbHlCKah7T1Rh7l22",
"boolId": 1
}
},
"boolId": 1,
}
},
{
"$addFields": {
"offerModelList": {
"$filter": {
"input": "$offerModelList",
"as": "i",
"cond": {
"$eq": [
"$$i.offerListenerEntity.boolId",
1
]
}
}
}
},
},
{
"$set": {
"offerModelList": {
$map: {
input: "$offerModelList",
as: "offerModel",
in: {
$mergeObjects: [
"$$offerModel",
{
offers: {
$filter: {
input: "$$offerModel.offers",
as: "x",
cond: {
$eq: [
"$$x.isSelectedFlag",
1
]
}
}
}
}
]
}
}
}
}
}
])
Demo # Mongo Playground

How to get only multiple counts in Mongodb?

Im trying to get multiple count values only from multiple documents in a collection which looks like this,( basically I want to get a count of how many are from the 4 directions)
{
"empno": 1500,
"province": "North"
}
{
"empno": 1600,
"province": "West"
}
early I found a solution and implemented following query;
([
{ "$facet": {
"N": [
{ "$match": { "province": "North" }},
{ "$count": "N" }
],
"E": [
{ "$match": { "province": "East" }},
{ "$count": "E" }
],
"S": [
{ "$match": { "province": "South" }},
{ "$count": "S" }
],
"W": [
{ "$match": { "province": "West" }},
{ "$count": "W" }
]
}},
{ "$project": {
"N": { "$arrayElemAt": ["$N.N", 0] },
"E": { "$arrayElemAt": ["$E.E", 0] },
"S": { "$arrayElemAt": ["$S.S", 0] },
"W": { "$arrayElemAt": ["$W.W", 0] },
}}
])
The output I get is
{ N: 1, W: 1 }
How can I get the values only like without the keys and also I want the blank fields that are empty to be with a 0. Like this;
{1, 0, 0, 1}
Facet
Query
group by null, is the thing that you needed to add to get the count
Test code here
db.collection.aggregate([
{
"$facet": {
"g0": [
{
"$match": {
"province": {
"$eq": "North"
}
}
},
{
"$group": {
"_id": null,
"count": {
"$sum": 1
}
}
},
{
"$project": {
"_id": 0
}
}
],
"g1": [
{
"$match": {
"province": {
"$eq": "East"
}
}
},
{
"$group": {
"_id": null,
"count": {
"$sum": 1
}
}
},
{
"$project": {
"_id": 0
}
}
],
"g2": [
{
"$match": {
"province": {
"$eq": "South"
}
}
},
{
"$group": {
"_id": null,
"count": {
"$sum": 1
}
}
},
{
"$project": {
"_id": 0
}
}
],
"g3": [
{
"$match": {
"province": {
"$eq": "West"
}
}
},
{
"$group": {
"_id": null,
"count": {
"$sum": 1
}
}
},
{
"$project": {
"_id": 0
}
}
]
}
},
{
"$set": {
"data": {
"$map": {
"input": {
"$objectToArray": "$$ROOT"
},
"in": {
"$cond": [
{
"$eq": [
"$$d.v",
[]
]
},
0,
{
"$let": {
"vars": {
"m": {
"$arrayElemAt": [
"$$d.v",
0
]
}
},
"in": "$$m.count"
}
}
]
},
"as": "d"
}
}
}
},
{
"$project": {
"data": 1
}
}
])
Group
Query
group is used instead of facet (facet is like 1 aggregation per field)
each group have its index (from the array), some indexes will be missing (because no documents exist)
add a zero-data field that has all indexes and count=0 (see bellow)
add to zero-data, the data found (the ones that existed in the collection,and we have groups for them) the rest keep the count=0
Test code here
db.collection.aggregate([
{
"$group": {
"_id": {
"$switch": {
"branches": [
{
"case": {
"$eq": [
"$province",
"North"
]
},
"then": {
"index": 0,
"province": "North"
}
},
{
"case": {
"$eq": [
"$province",
"East"
]
},
"then": {
"index": 1,
"province": "East"
}
},
{
"case": {
"$eq": [
"$province",
"South"
]
},
"then": {
"index": 2,
"province": "South"
}
},
{
"case": {
"$eq": [
"$province",
"West"
]
},
"then": {
"index": 3,
"province": "West"
}
}
],
"default": {
"index": 5
}
}
},
"count": {
"$sum": 1
}
}
},
{
"$group": {
"_id": null,
"data": {
"$push": {
"index": "$_id.index",
"province": "$province",
"count": "$count"
}
}
}
},
{
"$project": {
"_id": 0
}
},
{
"$set": {
"zero-data": [
{
"index": 0,
"count": 0
},
{
"index": 1,
"count": 0
},
{
"index": 2,
"count": 0
},
{
"index": 3,
"count": 0
}
]
}
},
{
"$set": {
"data": {
"$reduce": {
"input": "$zero-data",
"initialValue": [],
"in": {
"$let": {
"vars": {
"all_data": "$$value",
"d": "$$this"
},
"in": {
"$let": {
"vars": {
"found_data": {
"$filter": {
"input": "$data",
"cond": {
"$eq": [
"$$d.index",
"$$d1.index"
]
},
"as": "d1"
}
}
},
"in": {
"$concatArrays": [
"$$all_data",
[
{
"$cond": [
{
"$eq": [
"$$found_data",
[]
]
},
{
"index": "$$d.index",
"count": 0
},
{
"$arrayElemAt": [
"$$found_data",
0
]
}
]
}
]
]
}
}
}
}
}
}
}
}
},
{
"$project": {
"data": {
"$map": {
"input": "$data",
"in": "$$this.count"
}
}
}
}
])

MongoDB match filters with grouping and get total count

My sample data:
{
"_id": "random_id_1",
"priority": "P1",
"owners": ["user-1", "user-2"],
},
{
"_id": "random_id_2",
"priority": "P1",
"owners": ["user-1", "user-2"],
},
{
"_id": "random_id_3",
"priority": "P2",
"owners": ["user-1", "user-2"],
},
I want to run an aggregation pipeline on the data involving match filters and grouping, also I want to limit the number of groups returned as well as the number of items in each group.
Essentially, if limit=2, limit_per_group=1, group_by=owner, priority=P1, I want the following results:
[
{
"data": [
{
"group_key": "user-1",
"total_items_in_group": 2,
"limited_items": [
{
"_id": "random_id_1",
"priority": "P1",
"owners": ["user-1", "user-2"],
},
],
},
{
"group_key": "user-2",
"total_items_in_group": 2,
"limited_items": [
{
"_id": "random_id_1",
"priority": "P1",
"owners": ["user-1", "user-2"],
},
],
},
]
},
{
"metadata": {
"total_items_matched": 2,
"total_groups": 2
}
},
]
Need some help on how to write an aggregation pipeline to get the required result.
My current query is as follows:
{
"$match": {
"priority": "P1"
}
},
{
"$facet": {
"data": [
{
$addFields: {
"group_by_owners": "$owners"
}
},
{
$unwind: "$group_by_owners"
},
{
$group: {
"_id": "$group_by_owners",
"total_items_in_group": {
$sum: 1
},
"items": {
$push: "$$ROOT"
}
}
},
{
$sort: {
"total": -1
}
},
{
$unset: "items.group_by_owners"
},
{
$project: {
"_id": 1,
"total_items_in_group": 1,
"limited_items": {
$slice: [
"$items",
1
]
}
}
},
{
"$limit": 2
}
],
"metadata": [
{
$count: "total_items_matched"
}
]
}
}
Mongo playground link
I am unable to calculate the total number of groups.
add new stage of $addfields at the end of pipeline
db.collection.aggregate([
{
"$match": {
"priority": "P1"
}
},
{
"$facet": {
"data": [
{
$addFields: {
"group_by_owners": "$owners"
}
},
{
$unwind: "$group_by_owners"
},
{
$group: {
"_id": "$group_by_owners",
"total_items_in_group": {
$sum: 1
},
"items": {
$push: "$$ROOT"
}
}
},
{
$sort: {
"total": -1
}
},
{
$unset: "items.group_by_owners"
},
{
$project: {
"_id": 0,
"group_key": "$_id",
"total_items_in_group": 1,
"limited_items": {
$slice: [
"$items",
1
]
}
}
},
{
"$limit": 2
}
],
"metadata": [
{
$count: "total_items_matched",
}
]
}
},
{
"$addFields": {
"metadata.total_groups": {
"$size": "$data"
}
}
}
])
https://mongoplayground.net/p/y5a0jvr6fxI

can't convert from BSON type missing to Date

I have a mongoDB aggregation which was working great when I tried it on MongoDB 4.0 but now I need to use it on MongoDB 3.4 and it's not working, I can't find why. All I suppose it that the bug occurs in the $project stage.
Here's the aggregation query :
{
"aggregate": true,
"pipeline": [
{
"$match": {
"field": {
"$exists": true
},
"field.objects": {
"$exists": true,
"$ne": []
},
"created_at": {
"$gte": {
"sec": 1551398400,
"usec": 0
},
"$lte": {
"sec": 1554076799,
"usec": 0
}
}
}
},
{
"$unwind": "$field.objects"
},
{
"$lookup": {
"from": "Object",
"localField": "field.objects.id",
"foreignField": "_id",
"as": "objects"
}
},
{
"$match": { // Some match clauses here
}
},
{
"$group": {
"_id": "$_id"
}
},
{
"$project": {
"year": {
"$year": "$created_at"
},
"month": {
"$month": "$created_at"
}
}
},
{
"$group": {
"_id": {
"date": {
"$concat": [
{
"$substr": [
"$year",
0,
4
]
},
"-",
{
"$cond": [
{
"$lte": [
"$month",
9
]
},
{
"$concat": [
"0",
{
"$substr": [
"$month",
0,
2
]
}
]
},
{
"$substr": [
"$month",
0,
2
]
}
]
},
"-01"
]
}
},
"total": {
"$sum": 1
}
}
}
],
"options": {
"cursor": true
},
"db": "db",
"collection": "Collection"
}
So, with MongoDB 4.0, I get the right result, but MongoDB 3.4 throws the following : can't convert from BSON type missing to Date. I looked a bit at changelogs but I didn't find anything.

How to get count of multiple fields based on value in mongodb?

Collection exists as below:
[
{"currentLocation": "Chennai", "baseLocation": "Bengaluru"},
{"currentLocation": "Chennai", "baseLocation": "Bengaluru"},
{"currentLocation": "Delhi", "baseLocation": "Bengaluru"},
{"currentLocation": "Chennai", "baseLocation": "Chennai"}
]
Expected Output:
[
{"city": "Chennai", "currentLocationCount": 3, "baseLocationCount": 1},
{"city": "Bengaluru", "currentLocationCount": 0, "baseLocationCount": 3},
{"city": "Delhi", "currentLocationCount": 1, "baseLocationCount": 0}
]
What I have tried is:
db.getCollection('users').aggregate([{
$group: {
"_id": "$baselocation",
baseLocationCount: {
$sum: 1
}
},
}, {
$project: {
"_id": 0,
"city": "$_id",
"baseLocationCount": 1
}
}])
Got result as:
[
{"city": "Chennai", "baseLocationCount": 1},
{"city": "Bengaluru", "baseLocationCount": "3"}
]
I'm not familiar with mongo, so any help?
MongoDB Version - 3.4
Neil Lunn and myself had a lovely argument over this topic the other day which you can read all about here: Group by day with Multiple Date Fields.
Here are two solutions to your precise problem.
The first one uses the $facet stage. Bear in mind, though, that it may not be suitable for large collections because $facet produces a single (potentially huge) document that might be bigger than the current MongoDB document size limit of 16MB (which only applies to the result document and wouldn't be a problem during pipeline processing anyway):
collection.aggregate(
{
$facet:
{
"current":
[
{
$group:
{
"_id": "$currentLocation",
"currentLocationCount": { $sum: 1 }
}
}
],
"base":
[
{
$group:
{
"_id": "$baseLocation",
"baseLocationCount": { $sum: 1 }
}
}
]
}
},
{ $project: { "result": { $setUnion: [ "$current", "$base" ] } } }, // merge results into new array
{ $unwind: "$result" }, // unwind array into individual documents
{ $replaceRoot: { newRoot: "$result" } }, // get rid of the additional field level
{ $group: { "_id": "$_id", "currentLocationCount": { $sum: "$currentLocationCount" }, "baseLocationCount": { $sum: "$baseLocationCount" } } }, // group into final result)
{ $project: { "_id": 0, "city": "$_id", "currentLocationCount": 1, "baseLocationCount": 1 } } // group into final result
)
The second one works based on the $map stage instead:
collection.aggregate(
{
"$project": {
"city": {
"$map": {
"input": [ "current", "base" ],
"as": "type",
"in": {
"type": "$$type",
"name": {
"$cond": {
"if": { "$eq": [ "$$type", "current" ] },
"then": "$currentLocation",
"else": "$baseLocation"
}
}
}
}
}
}
},
{ "$unwind": "$city" },
{
"$group": {
"_id": "$city.name",
"currentLocationCount": {
"$sum": {
"$cond": {
"if": { "$eq": [ "$city.type", "current" ] },
"then": 1,
"else": 0
}
}
},
"baseLocationCount": {
"$sum": {
"$cond": {
"if": { "$eq": [ "$city.type", "base" ] },
"then": 1,
"else": 0
}
}
}
}
}
)