SailsJS + Waterline concurrent db requests with promises - node.js

I'm a bit confused about concurrency in SailsJS's waterline.
Currently I'm doing data retrieval like this;
var results = {};
// Get user by id 5
User.find('5', function(err, user) {
results.user = user;
// when it resolves, get messages
Message.find({userId: '5'}, function(err, messages) {
results.messages = messages;
// when message query resolves, get other stuff
OtherStuff.find({userId: '5'}, function(err, otherStuff) {
results.otherStuff = otherStuff;
res.view({results});
});
});
});
The problem is that the DB calls are not concurrent. Every request launches after previous one's promise has been fulfilled. I'd like to launch all requests at the same time and then see somehow if all promises are fulfilled and if so, proceed to pass results to the view.
How am I gonna achieve this concurrency with db requests?
Thanks!

Use async.auto. The async module is globalized in Sails:
async.auto({
user: function(cb) {
// Note--use findOne here, not find! "find" doesn't accept
// an ID argument, only an object.
User.findOne('5').exec(cb);
},
messages: function(cb) {
Message.find({userId: '5'}).exec(cb);
},
otherStuff: function(cb) {
OtherStuff.find({userId: '5'}).exec(cb);
}
},
// This will be called when all queries are complete, or immediately
// if any of them returns an error
function allDone (err, results) {
// If any of the queries returns an error,
// it'll populate the "err" var
if (err) {return res.serverError(err);}
// Otherwise "results" will be an object whose keys are
// "user", "messages" and "otherStuff", and whose values
// are the results of those queries
res.view(results);
}
);

Related

Mongoose Promise not populating in script

I have an api server and some script jobs. They are using the same function to pull a roster using mongoose and populate the players in the roster.
On the api server, this function is called normally. Using the script, it doesn't.
API example
function getRoster(id) {
var deferred = Q.defer();
Roster.find({_id:id}, 'playerRoster userId tournamentId').populate('playerRoster').exec(
function(err, roster) {
if (err) {
deferred.resolve(err);
}
deferred.resolve(roster[0]);
});
return deferred.promise;
}
api.post('/get_roster', function(req, res) {
// get tournament
var id = req.body._id;
var playerId = req.body.playerId;
getRoster(id).then(function(data) {
var roster=data;
res.json(roster);
});
});
Script
module.exports = function(config) {
this.getRoster=function(id) {
//return Roster.find({_id:id}, 'playerRoster userId tournamentId').exec( - THIS RETURNS
return Roster.find({_id:id}, 'playerRoster userId tournamentId').populate('playerRoster').exec(
function(err, roster) {
if (err) {
return err;
}
console.log('roster[0]',roster);
return roster[0];
});
}
this.tallyPoints = function(tournamentPlayer,sportsPlayers) {
var deferred = Q.defer();
var totalPoints =0;
console.log("tallyPoints 0 ",tournamentPlayer);
var rosterId = tournamentPlayer.player.roster[0];
console.log("tallyPoints 1 ",rosterId);
this.getRoster(rosterId).then(function(roster2){
console.log("tallyPoints 2 ",roster2);
...
deferred.resolve(totalPoints);
});
return deferred.promise;
}
return this;
};
In the script, neither logging for the roster[0] or tallyPoints 2 lines print, but there is no error either.
Why doesn't Roster.find return when I add populate? The only thing I can imagine is because playerRoster collection has 2000 records searching for ~10 and it hits some timeout that isn't being caught.
Any suggestion to clean it up is also appreciated.
Thanks
Moongoose supports promises for a long time. It's unsuitable to use callback-based Mongoose API where promises are desirable and the use of Q.defer with existing promises is known as Deferred antipattern (similarly, new Promise results in promise construction antipattern).
In its current state getRoster doesn't return a promise and doesn't handle errors correctly.
function getRoster(id) {
return Roster.find({_id:id}, 'playerRoster userId tournamentId').populate('playerRoster').exec()
.then(roster => roster[0]);
}
api.post('/get_roster', function(req, res) {
// get tournament
var id = req.body._id;
var playerId = req.body.playerId;
getRoster(id)
.then(function(data) {
var roster=data;
res.json(roster);
})
.catch(err => {
// handle error
});
});
Considering that only roster[0] is used, it likely should be changed to Roster.findOne.
It doesn't matter whether getRoster is used in Express route or elsewhere, it should work. It's unknown how module.exports = function(config) {...} module is used, but this may refer to wrong context if it isn't used as class. If getRoster and tallyPoints don't use config, they shouldn't reside inside this function.

call db.loadServerScripts on connection startup

I have some server-side helper functions in system.js collection, which are then used in node.js. However sometimes, they are undefined.
Here is the scenario:
I load these functions once, on server start:
db.eval('db.loadServerScripts()', function(err, result) { ... });
So this is called only once on start, not for every request.
From now on I can call e.g.:
db.eval('getNextSequence(\'test\')', function(err, seq){});
But sometimes I get the error, that getNextSequence is undefined. I suspect those functions to exist only in current connection scope. So maybe when node receives new connection, the functions are not set.
Is there any way to use those functions in node.js, but to have them reliably available always?
Example scenario:
//1./ this function is stored in system.js
getNextSequence: function(name)
{
var ret = db.counters.findAndModify({
query: { _id: name },
update: { $inc: { seq: 1 } },
new: true,
upsert: true
});
return ret ? ret.seq : null;
}
//2./ this is called on nodejs server startup (once for server lifetime)
var mongo = require('mongoskin');
var db = mongo.db("mongodb://localhost:27017/mydb", {native_parser:true});
//...
db.eval('db.loadServerScripts()', function(err, result) {
//...crash if failed
});
//3./ this is used in node.js code, on request processing:
db.eval('getNextSequence(\'someNamespace\')', function(err, seq){
// int seq is converted to string slug
// a new entity with slugId is saved to collection
});

How can I use a cursor.forEach() in MongoDB using Node.js?

I have a huge collection of documents in my DB and I'm wondering how can I run through all the documents and update them, each document with a different value.
The answer depends on the driver you're using. All MongoDB drivers I know have cursor.forEach() implemented one way or another.
Here are some examples:
node-mongodb-native
collection.find(query).forEach(function(doc) {
// handle
}, function(err) {
// done or error
});
mongojs
db.collection.find(query).forEach(function(err, doc) {
// handle
});
monk
collection.find(query, { stream: true })
.each(function(doc){
// handle doc
})
.error(function(err){
// handle error
})
.success(function(){
// final callback
});
mongoose
collection.find(query).stream()
.on('data', function(doc){
// handle doc
})
.on('error', function(err){
// handle error
})
.on('end', function(){
// final callback
});
Updating documents inside of .forEach callback
The only problem with updating documents inside of .forEach callback is that you have no idea when all documents are updated.
To solve this problem you should use some asynchronous control flow solution. Here are some options:
async
promises (when.js, bluebird)
Here is an example of using async, using its queue feature:
var q = async.queue(function (doc, callback) {
// code for your update
collection.update({
_id: doc._id
}, {
$set: {hi: 'there'}
}, {
w: 1
}, callback);
}, Infinity);
var cursor = collection.find(query);
cursor.each(function(err, doc) {
if (err) throw err;
if (doc) q.push(doc); // dispatching doc to async.queue
});
q.drain = function() {
if (cursor.isClosed()) {
console.log('all items have been processed');
db.close();
}
}
Using the mongodb driver, and modern NodeJS with async/await, a good solution is to use next():
const collection = db.collection('things')
const cursor = collection.find({
bla: 42 // find all things where bla is 42
});
let document;
while ((document = await cursor.next())) {
await collection.findOneAndUpdate({
_id: document._id
}, {
$set: {
blu: 43
}
});
}
This results in only one document at a time being required in memory, as opposed to e.g. the accepted answer, where many documents get sucked into memory, before processing of the documents starts. In cases of "huge collections" (as per the question) this may be important.
If documents are large, this can be improved further by using a projection, so that only those fields of documents that are required are fetched from the database.
var MongoClient = require('mongodb').MongoClient,
assert = require('assert');
MongoClient.connect('mongodb://localhost:27017/crunchbase', function(err, db) {
assert.equal(err, null);
console.log("Successfully connected to MongoDB.");
var query = {
"category_code": "biotech"
};
db.collection('companies').find(query).toArray(function(err, docs) {
assert.equal(err, null);
assert.notEqual(docs.length, 0);
docs.forEach(function(doc) {
console.log(doc.name + " is a " + doc.category_code + " company.");
});
db.close();
});
});
Notice that the call .toArray is making the application to fetch the entire dataset.
var MongoClient = require('mongodb').MongoClient,
assert = require('assert');
MongoClient.connect('mongodb://localhost:27017/crunchbase', function(err, db) {
assert.equal(err, null);
console.log("Successfully connected to MongoDB.");
var query = {
"category_code": "biotech"
};
var cursor = db.collection('companies').find(query);
function(doc) {
cursor.forEach(
console.log(doc.name + " is a " + doc.category_code + " company.");
},
function(err) {
assert.equal(err, null);
return db.close();
}
);
});
Notice that the cursor returned by the find() is assigned to var cursor. With this approach, instead of fetching all data in memory and consuming data at once, we're streaming the data to our application. find() can create a cursor immediately because it doesn't actually make a request to the database until we try to use some of the documents it will provide. The point of cursor is to describe our query. The 2nd parameter to cursor.forEach shows what to do when the driver gets exhausted or an error occurs.
In the initial version of the above code, it was toArray() which forced the database call. It meant we needed ALL the documents and wanted them to be in an array.
Also, MongoDB returns data in batch format. The image below shows, requests from cursors (from application) to MongoDB
forEach is better than toArray because we can process documents as they come in until we reach the end. Contrast it with toArray - where we wait for ALL the documents to be retrieved and the entire array is built. This means we're not getting any advantage from the fact that the driver and the database system are working together to batch results to your application. Batching is meant to provide efficiency in terms of memory overhead and the execution time. Take advantage of it, if you can in your application.
None of the previous answers mentions batching the updates. That makes them extremely slow 🐌 - tens or hundreds of times slower than a solution using bulkWrite.
Let's say you want to double the value of a field in each document. Here's how to do that fast 💨 and with fixed memory consumption:
// Double the value of the 'foo' field in all documents
let bulkWrites = [];
const bulkDocumentsSize = 100; // how many documents to write at once
let i = 0;
db.collection.find({ ... }).forEach(doc => {
i++;
// Update the document...
doc.foo = doc.foo * 2;
// Add the update to an array of bulk operations to execute later
bulkWrites.push({
replaceOne: {
filter: { _id: doc._id },
replacement: doc,
},
});
// Update the documents and log progress every `bulkDocumentsSize` documents
if (i % bulkDocumentsSize === 0) {
db.collection.bulkWrite(bulkWrites);
bulkWrites = [];
print(`Updated ${i} documents`);
}
});
// Flush the last <100 bulk writes
db.collection.bulkWrite(bulkWrites);
And here is an example of using a Mongoose cursor async with promises:
new Promise(function (resolve, reject) {
collection.find(query).cursor()
.on('data', function(doc) {
// ...
})
.on('error', reject)
.on('end', resolve);
})
.then(function () {
// ...
});
Reference:
Mongoose cursors
Streams and promises
Leonid's answer is great, but I want to reinforce the importance of using async/promises and to give a different solution with a promises example.
The simplest solution to this problem is to loop forEach document and call an update. Usually, you don't need close the db connection after each request, but if you do need to close the connection, be careful. You must just close it if you are sure that all updates have finished executing.
A common mistake here is to call db.close() after all updates are dispatched without knowing if they have completed. If you do that, you'll get errors.
Wrong implementation:
collection.find(query).each(function(err, doc) {
if (err) throw err;
if (doc) {
collection.update(query, update, function(err, updated) {
// handle
});
}
else {
db.close(); // if there is any pending update, it will throw an error there
}
});
However, as db.close() is also an async operation (its signature have a callback option) you may be lucky and this code can finish without errors. It may work only when you need to update just a few docs in a small collection (so, don't try).
Correct solution:
As a solution with async was already proposed by Leonid, below follows a solution using Q promises.
var Q = require('q');
var client = require('mongodb').MongoClient;
var url = 'mongodb://localhost:27017/test';
client.connect(url, function(err, db) {
if (err) throw err;
var promises = [];
var query = {}; // select all docs
var collection = db.collection('demo');
var cursor = collection.find(query);
// read all docs
cursor.each(function(err, doc) {
if (err) throw err;
if (doc) {
// create a promise to update the doc
var query = doc;
var update = { $set: {hi: 'there'} };
var promise =
Q.npost(collection, 'update', [query, update])
.then(function(updated){
console.log('Updated: ' + updated);
});
promises.push(promise);
} else {
// close the connection after executing all promises
Q.all(promises)
.then(function() {
if (cursor.isClosed()) {
console.log('all items have been processed');
db.close();
}
})
.fail(console.error);
}
});
});
The node-mongodb-native now supports a endCallback parameter to cursor.forEach as for one to handle the event AFTER the whole iteration, refer to the official document for details http://mongodb.github.io/node-mongodb-native/2.2/api/Cursor.html#forEach.
Also note that .each is deprecated in the nodejs native driver now.
You can now use (in an async function, of course):
for await (let doc of collection.find(query)) {
await updateDoc(doc);
}
// all done
which nicely serializes all updates.
let's assume that we have the below MongoDB data in place.
Database name: users
Collection name: jobs
===========================
Documents
{ "_id" : ObjectId("1"), "job" : "Security", "name" : "Jack", "age" : 35 }
{ "_id" : ObjectId("2"), "job" : "Development", "name" : "Tito" }
{ "_id" : ObjectId("3"), "job" : "Design", "name" : "Ben", "age" : 45}
{ "_id" : ObjectId("4"), "job" : "Programming", "name" : "John", "age" : 25 }
{ "_id" : ObjectId("5"), "job" : "IT", "name" : "ricko", "age" : 45 }
==========================
This code:
var MongoClient = require('mongodb').MongoClient;
var dbURL = 'mongodb://localhost/users';
MongoClient.connect(dbURL, (err, db) => {
if (err) {
throw err;
} else {
console.log('Connection successful');
var dataBase = db.db();
// loop forEach
dataBase.collection('jobs').find().forEach(function(myDoc){
console.log('There is a job called :'+ myDoc.job +'in Database')})
});
I looked for a solution with good performance and I end up creating a mix of what I found which I think works good:
/**
* This method will read the documents from the cursor in batches and invoke the callback
* for each batch in parallel.
* IT IS VERY RECOMMENDED TO CREATE THE CURSOR TO AN OPTION OF BATCH SIZE THAT WILL MATCH
* THE VALUE OF batchSize. This way the performance benefits are maxed out since
* the mongo instance will send into our process memory the same number of documents
* that we handle in concurrent each time, so no memory space is wasted
* and also the memory usage is limited.
*
* Example of usage:
* const cursor = await collection.aggregate([
{...}, ...],
{
cursor: {batchSize: BATCH_SIZE} // Limiting memory use
});
DbUtil.concurrentCursorBatchProcessing(cursor, BATCH_SIZE, async (doc) => ...)
* #param cursor - A cursor to batch process on.
* We can get this from our collection.js API by either using aggregateCursor/findCursor
* #param batchSize - The batch size, should match the batchSize of the cursor option.
* #param callback - Callback that should be async, will be called in parallel for each batch.
* #return {Promise<void>}
*/
static async concurrentCursorBatchProcessing(cursor, batchSize, callback) {
let doc;
const docsBatch = [];
while ((doc = await cursor.next())) {
docsBatch.push(doc);
if (docsBatch.length >= batchSize) {
await PromiseUtils.concurrentPromiseAll(docsBatch, async (currDoc) => {
return callback(currDoc);
});
// Emptying the batch array
docsBatch.splice(0, docsBatch.length);
}
}
// Checking if there is a last batch remaining since it was small than batchSize
if (docsBatch.length > 0) {
await PromiseUtils.concurrentPromiseAll(docsBatch, async (currDoc) => {
return callback(currDoc);
});
}
}
An example of usage for reading many big documents and updating them:
const cursor = await collection.aggregate([
{
...
}
], {
cursor: {batchSize: BATCH_SIZE}, // Limiting memory use
allowDiskUse: true
});
const bulkUpdates = [];
await DbUtil.concurrentCursorBatchProcessing(cursor, BATCH_SIZE, async (doc: any) => {
const update: any = {
updateOne: {
filter: {
...
},
update: {
...
}
}
};
bulkUpdates.push(update);
// Updating if we read too many docs to clear space in memory
await this.bulkWriteIfNeeded(bulkUpdates, collection);
});
// Making sure we updated everything
await this.bulkWriteIfNeeded(bulkUpdates, collection, true);
...
private async bulkWriteParametersIfNeeded(
bulkUpdates: any[], collection: any,
forceUpdate = false, flushBatchSize) {
if (bulkUpdates.length >= flushBatchSize || forceUpdate) {
// concurrentPromiseChunked is a method that loops over an array in a concurrent way using lodash.chunk and Promise.map
await PromiseUtils.concurrentPromiseChunked(bulkUpsertParameters, (upsertChunk: any) => {
return techniquesParametersCollection.bulkWrite(upsertChunk);
});
// Emptying the array
bulkUpsertParameters.splice(0, bulkUpsertParameters.length);
}
}

How to make synchronous call with mongoose and nodejs

I'm designing a client/server synchronization feature. The client sends a bunch of changed events to server. The server will do creation, deletion or modification upon requested item status. After the database operation, the server need send a summary back to client.
Below is excerpt from my server side code, designed with mongoose and restify.
var EventModel = mongoose.model('Event', eventSchema);
server.post("/sync", function (req, res, next) {
var events = req.params.events;
var created = [], deleted = [], updated = [];
events.forEach(function (elem) {
if (elem.status == 0) {
// Delete
EventModel.remove({ _id: elem.uuid }, function (err, event) {
if (!err) deleted.push({uuid: elem.uuid});
});
} else if (elem.status == 1) {
// Create and update uuid
var event = new EventModel(elem);
event.save(function (err, doc) {
if (!err) {
elem.uuid = event._doc._id;
created.push(elem);
}
});
} else if (elem.status == 2) {
// Update
EventModel.findOne({ _id: elem.uuid }, function (err, event) {
event.save(function (err, doc) {
if (!err) updated.push({uuid:elem.uuid});
});
});
}
});
// Notify client what are processed.
// PROBLEM: created, deleted, updated are always empty!
res.send({processed: {created: created, deleted: deleted, updated: updated}});
});
Since mongoose do CRUD in async way, the response created,deleted and updated are always empty.
Is there any way to let the mongoose operation in series?
As stated in the comments you could use the npm async module.
Alternatively, you may prefer to nest callbacks (but this might lead to what is known as callback hell, viz many nested callbacks) or take advantage of the mongoose .then() method - see http://mongoosejs.com/docs/promises.html
Here you can do ..
EventModel.remove(args).then((removeResponse) => {
return EventModel.findOne(args);
}).then((findResponse) => {
// etc
})
These requests will happen synchronously.

rendering results of multiple DB/mongoose queries to a view in express.js

given the async nature of mongoose (or sequelize, or redis) queries, what do you do when you have multiple queries you need to make before rendering the view?
For instance, you have a user_id in a session, and want to retrieve some info about that particular user via findOne. But you also want to display a list of recently logged in users.
exports.index = function (req, res) {
var current_user = null
Player.find({last_logged_in : today()}).exec(function(err, players) {
if (err) return res.render('500');
if (req.session.user_id) {
Player.findOne({_id : req.session.user_id}).exec(function(err, player) {
if (err) return;
if (player) {
current_user = player
}
})
}
// here, current_user isn't populated until the callback fires
res.render('game/index', { title: 'Battle!',
players: players,
game_is_full: (players.length >= 6),
current_user: current_user
});
});
};
So res.render is in the first query callback, fine. But what about waiting on the response from findOne to see if we know this user? It is only called conditionally, so I can't put render inside the inner callback, unless I duplicate it for either condition. Not pretty.
I can think of some workarounds -
make it really async and use AJAX on the client side to get the current user's profile. But this seems like more work than it's worth.
use Q and promises to wait on the resolution of the findOne query before rendering. But in a way, this would be like forcing blocking to make the response wait on my operation. Doesn't seem right.
use a middleware function to get the current user info. This seems cleaner, makes the query reusable. However I'm not sure how to go about it or if it would still manifest the same problem.
Of course, in a more extreme case, if you have a dozen queries to make, things might get ugly. So, what is the usual pattern given this type of requirement?
Yep, this is a particularly annoying case in async code. What you can do is to put the code you'd have to duplicate into a local function to keep it DRY:
exports.index = function (req, res) {
var current_user = null
Player.find({last_logged_in : today()}).exec(function(err, players) {
if (err) return res.render('500');
function render() {
res.render('game/index', { title: 'Battle!',
players: players,
game_is_full: (players.length >= 6),
current_user: current_user
});
}
if (req.session.user_id) {
Player.findOne({_id : req.session.user_id}).exec(function(err, player) {
if (err) return;
if (player) {
current_user = player
}
render();
})
} else {
render();
}
});
};
However, looking at what you're doing here, you'll probably need to look up the current player information in multiple request handlers, so in that case you're better off using middleware.
Something like:
exports.loadUser = function (req, res, next) {
if (req.session.user_id) {
Player.findOne({_id : req.session.user_id}).exec(function(err, player) {
if (err) return;
if (player) {
req.player = player
}
next();
})
} else {
next();
}
}
Then you'd configure your routes to call loadUser wherever you need req.player populated and the route handler can just pull the player details right from there.
router.get("/",function(req,res){
var locals = {};
var userId = req.params.userId;
async.parallel([
//Load user Data
function(callback) {
mongoOp.User.find({},function(err,user){
if (err) return callback(err);
locals.user = user;
callback();
});
},
//Load posts Data
function(callback) {
mongoOp.Post.find({},function(err,posts){
if (err) return callback(err);
locals.posts = posts;
callback();
});
}
], function(err) { //This function gets called after the two tasks have called their "task callbacks"
if (err) return next(err); //If an error occurred, we let express handle it by calling the `next` function
//Here `locals` will be an object with `user` and `posts` keys
//Example: `locals = {user: ..., posts: [...]}`
res.render('index.ejs', {userdata: locals.user,postdata: locals.posts})
});
Nowadays you can use app.param in ExpressJS to easily establish middleware that loads needed data based on the name of parameters in the request URL.
http://expressjs.com/4x/api.html#app.param

Resources