We Keep Coding

How to force sequential execution for asynchronously called functions

I'm new to the idea of asynchronous code, and am still trying to wrap my brain around how everything works.
I'm building a Node Express application which will interface with a database. When running in a development environment I want it to interface with a Sqlite database. (The production database will not use Sqlite. This only applies to creating a small development environment.)
My problem is I'm having trouble controlling the execution order and timing of queries to the database.
I would like to build my SqliteDatabase.js file such that it can only execute queries sequentially, despite the fact that functions in this file will be called by other parts of the program that are running asynchronously.
How can I acheive this?
For reference, here is how I currently have my SqliteDatabase.js file set up:
var debug = require('debug')('app:DATABASE');
var sqlite = require('sqlite3').verbose();
open = function() {
var db = new sqlite.Database('./test-database.db', sqlite.OPEN_READWRITE | sqlite.OPEN_CREATE, function(err) {
if (err) {
debug("We've encountered an error opening the sqlite database.");
debug(err);
} else {
debug("Sqlite database opened successfully.");
}
});
return db;
}
executeSQLUpdate = function(sql, next) {
var db = open();
db.serialize(function() {
console.log("executing " + sql);
db.run(sql);
db.close();
next();
});
}
exports.executeSQLUpdate = executeSQLUpdate;
Is there some way to build a queue, and make it so when the "executeSQLUpdate" function is called, the request is added to a queue, and is not started until all previous requests have been completed?
To give an example, take a look at this code which utilises my SqliteDatabase.js file:
ar database = require('../../bin/data_access/SqliteDatabase.js');
var createTestTableStmt = "CREATE TABLE IF NOT EXISTS Test(\n" +
"Name TEXT PRIMARY KEY NOT NULL UNIQUE,\n" +
"Age INT NOT NULL,\n" +
"Gender TEXT NOT NULL\n" +
");";
var clearTestTableStmt = "DELETE FROM Test;";
var testInsertStmt = "INSERT INTO Test (Name, Age, Gender)\n" +
"VALUES (\"Connor\", 23, \"Male\");";
createTable = function() {
database.executeSQLUpdate(createTestTableStmt, clearTable);
}
clearTable = function() {
database.executeSQLUpdate(clearTestTableStmt, insertRow);
}
insertRow = function() {
database.executeSQLUpdate(testInsertStmt, function() {
console.log("Done!");
});
}
createTable();
9 times out of 10 the above code works fine, but every once in a while, the "insert row" function is called before the "clearTable" function is called, which throws an error because of a violated database constraint.
How can I change my implementation of the SqliteDatabase.js file to avoid this issue?

You can use async to do this using await. This code will wait for each asynchronous database call to complete before executing the next line.
async function createTable() {
await database.executeSQLUpdate(createTestTableStmt);
await database.executeSQLUpdate(clearTestTableStmt);
await database.executeSQLUpdate(testInsertStmt);
console.log("Done!");
}
Your console.log statement will only execute once all three have completed.
I should also mention that you need a try...catch block around the three database calls to trap any errors and provide an alternate exit point if something should go wrong.

I realized why the callback function next() was sometimes being called before db.run(sql)
It turns out that db.run() is itself an asychronous function. I updated my code, and added a callback to the db.run() line to make sure we don't skip ahead until it's done.
Here's what it looks like now:
executeSQLUpdate = function(sql, next) {
var db = open();
db.run(sql, function(err) {
db.close(function() {
if (next) next(err);
});
});
}
Nesting each asynchronous function in the previous function's callback, makes each function execute in order.
Thanks to everyone who gave me hints that helped me figure out what the problem was.

MEAN Node JS requests intercourse at many requests

I have a MEAN app that works well with single requests, let's say calling /api/products?pid=500. But I recently discovered that at a "burst" of requests (i'm updating bulk around 50 products = 50 requests /api/products?pid=500 *** 550 with post data), the req.body sometimes gets a value of a new upcoming request.
The front app makes the calls in a foreach of selected products:
ds.forEach((d, key) => {
this.ApiCall.setData('products', { action: 'send-product', data: d })
.subscribe((result) => {
//we have results
});
});
//setData makes a http.post().map
Back app / mean analyses the post, tried to synthesize the code:
router.route('/')
.post(function (req, response) {
if(req.body.data){
var obj = { id: req.body.data.product_id }
if(req.body.data.linked_products){
req.body.data.linked_products.forEach(function(entry) {
obj.linked = entry; //more ifs
});
}
var async = require('async');
async.series({
q2: function(cb){
queryProducts.findOne({id: req.body.data.product_id, null).exec(cb);
},
q3: function(cb){
queryCategories.findOne({id: req.body.data.category_id, null).exec(cb);
}
}, function(err, qResults){
var alreadysent = false;
if (qResults.q3) qResults.q3.logs.forEach(function(entry) {
if(entry.sent){
alreadysent = true;
}
});
//more ifs
qResults.q3.external_codes.forEach(function(entry) {
obj.external_code = entry;//more ifs
});
if(req.body.data.price < 0){
response.json({message: "Negative price didn't sent"});
return;
}
if(qResults.q2.status=="inactive"){
response.json({message: "Inactive didn't sent"});
return;
}
req.body.data.campaigns(function(entry) {
obj.price_offers = entry;//more ifs
});
//more ifs and foreach similar
queryProducts.update({id: req.body.data.id}, {$push: { synced_products: obj }}, function (err, result) {
//HERE I found req.body.data with values of a future request
if(!err)
response.json({message: "Sent"});
return;
});
});
}
});
module.exports = router;
I understand that making requests
/api/products?pid=500
/api/products?pid=501
/api/products?pid=502
/api/products?pid=503
...
have different timings, but how is possible that a request (pid=501), calling the last req.body to have the value of req.body of new req (pid=503)?
Any ideas how to avoid? putting async first right after the post or making a
var reqbody = req.body
Thanks!

I believe this is due to the async module initialization. To quote from the node docs:
Caching
Modules are cached after the first time they are loaded. This means (among other things) that every call to require('foo') will get exactly the same object returned, if it would resolve to the same file.
Multiple calls to require('foo') may not cause the module code to be executed multiple times. This is an important feature. With it, "partially done" objects can be returned, thus allowing transitive dependencies to be loaded even when they would cause cycles.
To have a module execute code multiple times, export a function, and call that function.
When a burst of requests causes overlapping execution, you will have two (or more) uses of the async variable being modified "concurrently". I would suggest using some sort of mutex to control access to the async variable.

Do I ever need to synchronize node.js code like in Java?

I have only recently started developing for node.js, so forgive me if this is a stupid question - I come from Javaland, where objects still live happily sequentially and synchronous. ;)
I have a key generator object that issues keys for database inserts using a variant of the high-low algorithm. Here's my code:
function KeyGenerator() {
var nextKey;
var upperBound;
this.generateKey = function(table, done) {
if (nextKey > upperBound) {
require("../sync/key-series-request").requestKeys(function(err,nextKey,upperBound) {
if (err) { return done(err); }
this.nextKey = nextKey;
this.upperBound = upperBound;
done(nextKey++);
});
} else {
done(nextKey++);
}
}
}
Obviously, when I ask it for a key, I must ensure that it never, ever issues the same key twice. In Java, if I wanted to enable concurrent access, I would make make this synchronized.
In node.js, is there any similar concept, or is it unnecessary? I intend to ask the generator for a bunch of keys for a bulk insert using async.parallel. My expectation is that since node is single-threaded, I need not worry about the same key ever being issued more than once, can someone please confirm this is correct?
Obtaining a new series involves an asynchronous database operation, so if I do 20 simultaneous key requests, but the series has only two keys left, won't I end up with 18 requests for a new series? What can I do to avoid that?
UPDATE
This is the code for requestKeys:
exports.requestKeys = function (done) {
var db = require("../storage/db");
db.query("select next_key, upper_bound from key_generation where type='issue'", function(err,results) {
if (err) { done(err); } else {
if (results.length === 0) {
// Somehow we lost the "issue" row - this should never have happened
done (new Error("Could not find 'issue' row in key generation table"));
} else {
var nextKey = results[0].next_key;
var upperBound = results[0].upper_bound;
db.query("update key_generation set next_key=?, upper_bound=? where type='issue'",
[ nextKey + KEY_SERIES_WIDTH, upperBound + KEY_SERIES_WIDTH],
function (err,results) {
if (err) { done(err); } else {
done(null, nextKey, upperBound);
}
});
}
}
});
}
UPDATE 2
I should probably mention that consuming a key requires db access even if a new series doesn't have to be requested, because the consumed key will have to be marked as used in the database. The code doesn't reflect this because I ran into trouble before I got around to implementing that part.
UPDATE 3
I think I got it using event emitting:
function KeyGenerator() {
var nextKey;
var upperBound;
var emitter = new events.EventEmitter();
var requesting = true;
// Initialize the generator with the stored values
db.query("select * from key_generation where type='use'", function(err, results)
if (err) { throw err; }
if (results.length === 0) {
throw new Error("Could not get key generation parameters: Row is missing");
}
nextKey = results[0].next_key;
upperBound = results[0].upper_bound;
console.log("Setting requesting = false, emitting event");
requesting = false;
emitter.emit("KeysAvailable");
});
this.generateKey = function(table, done) {
console.log("generateKey, state is:\n nextKey: " + nextKey + "\n upperBound:" + upperBound + "\n requesting:" + requesting + " ");
if (nextKey > upperBound) {
if (!requesting) {
requesting = true;
console.log("Requesting new series");
require("../sync/key-series-request").requestSeries(function(err,newNextKey,newUpperBound) {
if (err) { return done(err); }
console.log("New series available:\n nextKey: " + newNextKey + "\n upperBound: " + newUpperBound);
nextKey = newNextKey;
upperBound = newUpperBound;
requesting = false;
emitter.emit("KeysAvailable");
done(null,nextKey++);
});
} else {
console.log("Key request is already underway, deferring");
var that = this;
emitter.once("KeysAvailable", function() { console.log("Executing deferred call"); that.generateKey(table,done); });
}
} else {
done(null,nextKey++);
}
}
}
I've peppered it with logging outputs, and it does do what I want it to.

As another answer mentions, you will potentially end up with results different from what you want. Taking things in order:
function KeyGenerator() {
// at first I was thinking you wanted these as 'class' properties
// and thus would want to proceed them with this. rather than as vars
// but I think you want them as 'private' members variables of the
// class instance. That's dandy, you'll just want to do things differently
// down below
var nextKey;
var upperBound;
this.generateKey = function (table, done) {
if (nextKey > upperBound) {
// truncated the require path below for readability.
// more importantly, renamed parameters to function
require("key-series-request").requestKeys(function(err,nKey,uBound) {
if (err) { return done(err); }
// note that thanks to the miracle of closures, you have access to
// the nextKey and upperBound variables from the enclosing scope
// but I needed to rename the parameters or else they would shadow/
// obscure the variables with the same name.
nextKey = nKey;
upperBound = uBound;
done(nextKey++);
});
} else {
done(nextKey++);
}
}
}
Regarding the .requestKeys function, you will need to somehow introduce some kind of synchronization. This isn't actually terrible in one way because with only one thread of execution, you don't need to sweat the challenge of setting your semaphore in a single operation, but it is challenging to deal with the multiple callers because you will want other callers to effectively (but not really) block waiting for the first call to requestKeys() which is going to the DB to return.
I need to think about this part a bit more. I had a basic solution in mind which involved setting a simple semaphore and queuing the callbacks, but when I was typing it up I realized I was actually introducing a more subtle potential synchronization bug when processing the queued callbacks.
UPDATE:
I was just finishing up one approach as you were writing about your EventEmitter approach, which seems reasonable. See this gist which illustrates the approach. I took. Just run it and you'll see the behavior. It has some console logging to see which calls are getting deferred for a new key block or which can be handled immediately. The primary moving part of the solution is (note that the keyManager provides the stubbed out implementation of your require('key-series-request'):
function KeyGenerator(km) {
this.nextKey = undefined;
this.upperBound = undefined;
this.imWorkingOnIt = false;
this.queuedCallbacks = [];
this.keyManager = km;
this.generateKey = function(table, done) {
if (this.imWorkingOnIt){
this.queuedCallbacks.push(done);
console.log('KG deferred call. Pending CBs: '+this.queuedCallbacks.length);
return;
};
var self=this;
if ((typeof(this.nextKey) ==='undefined') || (this.nextKey > this.upperBound) ){
// set a semaphore & add the callback to the queued callback list
this.imWorkingOnIt = true;
this.queuedCallbacks.push(done);
this.keyManager.requestKeys(function(err,nKey,uBound) {
if (err) { return done(err); }
self.nextKey = nKey;
self.upperBound = uBound;
var theCallbackList = self.queuedCallbacks;
self.queuedCallbacks = [];
self.imWorkingOnIt = false;
theCallbackList.forEach(function(f){
// rather than making the final callback directly,
// call KeyGenerator.generateKey() with the original
// callback
setImmediate(function(){self.generateKey(table,f);});
});
});
} else {
console.log('KG immediate call',self.nextKey);
var z= self.nextKey++;
setImmediate(function(){done(z);});
}
}
};

If your Node.js code to calculate the next key didn't need to execute an async operation then you wouldn't run into synchronization issues because there is only one JavaScript thread executing code. Access to the nextKey/upperBound variables will be done in sequence by only one thread (i.e. request 1 will access first, then request 2, then request 3 et cetera.) In the Java-world you will always need synchronization because multiple threads will be executing even if you didn't make a DB call.
However, in your Node.js code since you are making an async call to get the nextKey you could get strange results. There is still only one JavaScript thread executing your code, but it would be possible for request 1 to make the call to the DB, then Node.js might accept request 2 (while request 1 is getting data from the DB) and this second request will also make a request to the DB to get keys. Let's say that request 2 gets data from the DB quicker than request 1 and update nextKey/upperBound variables with values 100/150. Once request 1 gets its data (say values 50/100) then it will update nextKey/upperBound. This scenario wouldn't result in duplicate keys, but you might see gaps in your keys (for example, not all keys 100 to 150 will be used because request 1 eventually reset the values to 50/100)
This makes me think that you will need a way to sync access, but I am not exactly sure what will be the best way to achieve this.

Best method to string together variety of DB calls in Node js

I basically need to make about 3 calls to get the data for a json object.. It basically JSON array of JSON object which have some attributes, one of which is an array of other values selected using a second query, then that one also has an array inside which is selected with another db call.
I tried using asyn.concatSeries so that I can dig down into the bottom call and put together all the information I collected for one root json object but that's creating a lot of unexpected behaviour..
Example of JSON
[
{
"item" : "firstDbCall"
"children" : [ {
"name" : "itemDiscoveredWithSecondDBCall"
"children" : [ itemsDiscoveredwith3rdDBCall]
},
]
}
]
This is really difficult using node.js. I really need to figure out how to do this properly since I have to do many of these for different purposes.
EDIT
This is the code i have. There's some strange behaviour with async.concatSeries. The results get called multiple times after each one of the functions finish for each array. So i had to put a check in place. I know it's very messy code but i've been just putting band-aids all over it for the past 2 hours to make it work..
console.log("GET USERS HAREDQARE INFO _--__--_-_-_-_-_____");
var query = "select driveGroupId from tasks, driveInformation where agentId = '"
+ req.params.agentId + "' and driveInformation.taskId = tasks.id order by driveInformation.taskId desc;";
connection.query(query, function(err, rows) {
if (rows === undefined) {
res.json([]);
return;
}
if(rows.length<1) { res.send("[]"); return;}
var driveGroupId = rows[0].driveGroupId;
var physicalQuery = "select * from drives where driveGroupId = " + driveGroupId + ";";
connection.query(physicalQuery, function(err, rows) {
console.log("ROWSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS");
console.log(rows);
async.concatSeries(rows, function(row, cb) {
console.log("-------------------------------SINGLE ROW-------------------------------------");
console.log(row);
if(row.hasLogicalDrives != 0) {
console.log("HAS LOGICAL DRIVES");
console.log(row.id);
var query = "select id, name from logicalDrives where driveId = " + row.id;
connection.query(query, function(error, drives) {
console.log("QUERY RETURNED");
console.log(drives);
parseDriveInfo(row.name, row.searchable, drives, cb);
});
}
else
var driveInfo = { "driveName" : row.name, "searchable" : row.searchable};
console.log("NO SUB ITEMS");
cb(null, driveInfo);
}, function(err, results) {
console.log("GEETTTTINGHERE");
console.log(results);
if(results.length == rows.length) {
console.log("RESULTS FOR THE DRIVE SEARCH");
console.log(results);
var response = {"id": req.params.agentId};
response.driveList = results;
console.log("RESPONSE");
console.log(response);
res.json(response);
}
});
});
});
};
parseDriveInfo = function(driveName, searchable, drives, cb) {
async.concatSeries(drives, function(drive,callback) {
console.log("SERIES 2");
console.log(drive);
console.log("END OF DRIVE INFO");
var query = "select name from supportedSearchTypes where logicalDriveId = " + drive.id;
connection.query(query, function(error, searchTypes) {
drive.searchTypes = searchTypes;
var driveInfo = { "driveName" :driveName,
"searchable" : searchable,
"logicalDrives" : drive
};
callback(null, driveInfo);
});
}, function (err, results) {
console.log("THIS IS ISISIS ISISISSISISISISISISISISISIS");
console.log(results);
if(results.length === drives.length) {
console.log("GOTHERE");
cb(null, results);
}
});
}

Getting good enough with async to use exactly the right combination of methods under the right circumstances takes a fair amount of experience. Most likely your case in particular can be handled with async.waterfall if its query1 then query2(dataFoundByQuery1) then query3(dataFoundByQuery2). But depending on the circumstances you need to mix and match async methods appropriately and sometimes have 2 levels - for example a "big picture" async.waterfall where some of the steps in the waterfall do async.parallel or async.series as needed. I've never used async.concat and given your needs I think you have chosen the wrong method. The workhorses are async.each, async.eachSeries, async.waterfall, and async.map, at least for the web app & DB query use cases I mostly encounter, so make sure you really have those understood before exploring the more specific convenience methods.

EDIT: This is a more in depth example based on use of the connection library you seem to be using. Please note, some of this is javascript psuedo code. Things like adding objects to the resultsArray are clearly not complete, the only thing I took time to make sure was correct is the "flow of logic" as it pertains to callbacks. Everything else is for you to implement. In order to support multiple calls to the same callback function and maintain state from call to call, the best way is to wrap the set of callbacks in a closure. This allows the callbacks to share some state with the main event loop. This allows you to pass arguments to the callbacks, without actually having to pass them as arguments, much like class variables in c++, or even globals in javascript, but we haven't poluted the global scope :)
function queryDataBase(query) {
//wrap the whole query in a function so the callbacks can share some
//variables with similar scope. This is called a closure
int rowCounter = 0;
var dataRowsFromStep2;
var resultsArray = {};
connection.query(query, dataBaseQueryStep2);
function dataBaseQueryStep2(err, rows) {
//do something with err and rows
dataRowsFromStep2 = rows;
var query = getQueryFromRow(dataRowsFromStep2[rowCounter++]);//Always zero the first time. Might need to double check rows isn't empty!
connection.query(query, dataBaseQueryStep3);
}
function dataBaseQueryStep3(err, rows) {
//do something with err and rows
if(rowCounter < dataRowsFromStep2.size) {
resultsArray.add(rows);//Probably needs to be more interesting, but you get the idea
//since this is within the same closure, rowCounter maintains it's state
var query = getQueryFromRow(dataRowsFromStep2[rowCounter++]);
//recursive call query using dataBaseQueryStep3 as it's callback repeatedly until
//we run out of rows to call it on.
connection.query(query, dataBaseQueryStep3)
} else {
//when the if statement fails we have no more rows to run queries on so return to main program flow
returnToMainProgramLogic(resultsArray);
}
}
}
function returnToMainProgramLogic(results) {
//continue running your program here
}
I personally like the above logic better than the syntax async produces... I believe the heart of your problem rests in your nested calls to async, and the fact that ASYN itself, runs the series of functions asynchronously, but in order(confusing I know). If you write your program like this, you won't have to worry about it!

I would strongly suggest using sequelize.js It provides a really powerful orm that allows you to chain queries together. It also allows you to directly load your data into js objects, write dynamic sql, and connect to many different databases. Picture ActiveRecord from the Ruby world for Node.

Calling asynchronous function in callback

I'm having some trouble understanding asynchronous functions. I've read the chapter in Mixu's Node Book but I still can't wrap my head around it.
Basically I want to request a ressource (using the node package cheerio), parse it for valid URLs and add every match to my redis set setname.
The problem is that in the end it's only adding the first match to the redis set.
function parse(url, setname)
{
request(url, function (error, response, body)
{
if (!error && response.statusCode == 200)
{
$ = cheerio.load(body)
// For every 'a' tag in the body
$('a').each(function()
{
// Add blog URL to redis if not already there.
var blog = $(this).attr('href')
console.log("test [all]: " + blog);
// filter valid URLs
var regex = /http:\/\/[^www]*.example.com\//
var result = blog.match(regex);
if(result != null)
{
console.log("test [filtered]: " + result[0]);
redis.sismember(setname, result[0], function(err, reply)
{
if(!reply)
{
redis.sadd(setname, result[0])
console.log("Added " + result[0])
}
redis.quit()
})
}
})
}
})
}
I'd be very grateful for pointers on how I'd have to restructure this so the redis.sadd method is working with the correct result.
The output of the current implementation looks like:
test [all]: http://test1.example.com/
test [filtered]: http://test1.example.com/
...
Added http://test2.example.com/
So it's adding the test1.example.com but not printing the "added" line, and it's not adding the test2.example.com but it's printing the "added" line for it.
Thank you!

The first issue is caused by redis.sismember() being asynchronous: when its callback is called, you have already overwritten the result variable so it will point to the last value it had, and not the value at the moment at which you called redis.sismember().
One way to solve that is to create a new scoped variable by wrapping the asynchronous function in a closure:
(function(result) {
redis.sismember(setname, result[0], function(err, reply) {
...
});
})(result);
Another option is to create a partial function that's used as callback:
redis.sismember(setname, result[0], function(result, err, reply) {
...
}.bind(this, result));
The second issue is, I think, caused by redis.quit() being called, which closes the Redis connection after the first sadd(). You're not checking err, but if you do it might tell you more.