Aggregate and update MongoDB

Question

I have 2 collections:

• Clients (6 000 000 documents)
• Orders (50 000 000 documents)

Once a day, i would like to calculate the number of o

Answer 1

For improved performance especially when dealing with large collections, take advantage of using the Bulk() API for bulk updates as you will be sending the operations to the server in batches (for example, say a batch size of 1000) which gives you much better performance since you won't be sending every request to the server (as you are currently doing with the update statement within the forEach() loop) but just once in every 1000 requests, thus making your updates more efficient and quicker than currently is.

The following examples demonstrate this approach, the first one uses the Bulk() API available in MongoDB versions >= 2.6 and < 3.2. It updates all the documents in the clients collection by changing the nb_orders_1year fields with values from the aggregation results.

Since the aggregate() method returns a cursor, You can use the aggregation output collection's forEach() method to iterate it and access each document thus setting up the bulk update operations in batches to then send across the server efficiently with the API:

var bulk = db.clients.initializeUnorderedBulkOp(),
    pipeline = [
        {
            "$match": { "date_order": { "$gt": v_date1year } }
        },
        {
            "$group": {
                "_id": "$id_client", 
                "count": { "$sum" : 1 }
            }
        },
        { "$out": "tmp_indicators" }        
    ],
    counter = 0;

db.orders.aggregate(pipeline);  
db.tmp_indicators.find().forEach(function (doc) {       
    bulk.find({ "_id": doc._id }).updateOne({ 
        "$set": { "nb_orders_1year": doc.count }
    });

    counter++;
    if (counter % 1000 == 0) {
        bulk.execute(); // Execute per 1000 operations and re-initialize every 1000 update statements
        bulk = db.clients.initializeUnorderedBulkOp();
    }
});
// Clean up remaining operations in queue
if (counter % 1000 != 0) { bulk.execute(); }

The next example applies to the new MongoDB version 3.2 which has since deprecated the Bulk API and provided a newer set of apis using bulkWrite().

It uses the same cursor as above but instead of iterating the result, create the array with the bulk operations by using its map() method:

 var pipeline = [
        {
            "$match": { "date_order": { "$gt": v_date1year } }
        },
        {
            "$group": {
                "_id": "$id_client", 
                "count": { "$sum" : 1 }
            }
        },
        { "$out": "tmp_indicators" }        
    ];
db.orders.aggregate(pipeline);
var bulkOps = db.tmp_indicators.find().map(function (doc) { 
        return { 
            "updateOne": { 
                "filter": { "_id": doc._id } ,              
                "update": { "$set": { "nb_orders_1year": doc.count } } 
            }         
        };
    });

db.clients.bulkWrite(bulkOps, { "ordered": true });