Node.js Readable stream slows over time, CPU usage falls - node.js

Question

I am trying to launch a cluster that will stream files (new line delimited JSON) from google cloud storage and transform each row after fetching data from MongoDB. After transforming the row, i want to store it in Google's bigquery - 10000 rows at a time. All of this is working fine but the issue is that the rate at which the streamed files are being processed decreases significantly over time.
I have setup the node application on one server and mongodb on another. Both 8 core machines with 30GB RAM. When the script is executed, initially the CPU usage for the application server and mongodb server is around 70%-75%. After 30 minutes, the CPU usage falls down to 10% and then finally 1%. The application generates no exceptions. I can see the application log and find that it finished processing a few files and took up new files for processing. One execution can be observered below a little later than 3:00PM and a almost upto 5:20PM.
var cluster = require('cluster'),
os = require('os'),
numCPUs = os.cpus().length,
async = require('async'),
fs = require('fs'),
google = require('googleapis'),
bigqueryV2 = google.bigquery('v2'),
gcs = require('#google-cloud/storage')({
projectId: 'someproject',
keyFilename: __dirname + '/auth.json'
}),
dataset = bigquery.dataset('somedataset'),
bucket = gcs.bucket('somebucket.appspot.com'),
JSONStream = require('JSONStream'),
Transform = require('stream').Transform,
MongoClient = require('mongodb').MongoClient,
mongoUrl = 'mongodb://localhost:27017/bigquery',
mDb,
groupA,
groupB;
var rows = [],
rowsLen = 0;
function transformer() {
var t = new Transform({ objectMode: true });
t._transform = function(row, encoding, cb) {
// Get some information from mongodb and attach it to the row
if (row) {
groupA.findOne({
'geometry': { $geoIntersects: { $geometry: { type: 'Point', coordinates: [row.lon, row.lat] } } }
}, {
fields: { 'properties.OA_SA': 1, _id: 0 }
}, function(err, a) {
if (err) return cb();
groupB.findOne({
'geometry': { $geoIntersects: { $geometry: { type: 'Point', coordinates: [row.lon, row.lat] } } }
}, {
fields: { 'properties.WZ11CD': 1, _id: 0 }
}, function(err, b) {
if (err) return cb();
row.groupA = a ? a.properties.OA_SA : null;
row.groupB = b ? b.properties.WZ11CD : null;
// cache processed rows in memory
rows[rowsLen++] = { json: row };
if (rowsLen >= 10000) {
// batch insert rows in bigquery table
// and free memory
log('inserting 10000')
insertRowsAsStream(rows.splice(0, 10000));
rowsLen = rows.length;
}
cb();
});
});
} else {
cb();
}
};
return t;
}
var log = function(str) {
console.log(str);
}
function insertRowsAsStream(rows, callback) {
bigqueryV2.tabledata.insertAll({
"projectId": 'someproject',
"datasetId": 'somedataset',
"tableId": 'sometable',
"resource": {
"kind": "bigquery#tableDataInsertAllRequest",
"rows": rows
}
}, function(err, res) {
if (res && res.insertErrors && res.insertErrors.length) {
console.log(res.insertErrors[0].errors)
err = err || new Error(JSON.stringify(res.insertErrors));
}
});
}
function startStream(fileName, cb) {
// stream a file from Google cloud storage
var file = bucket.file(fileName),
called = false;
log(`Processing file ${fileName}`);
file.createReadStream()
.on('data', noop)
.on('end', function() {
if (!called) {
called = true;
cb();
}
})
.pipe(JSONStream.parse())
.pipe(transformer())
.on('finish', function() {
log('transformation ended');
if (!called) {
called = true;
cb();
}
});
}
function processFiles(files, cpuIdentifier) {
if (files.length == 0) return;
var fn = [];
for (var i = 0; i < files.length; i++) {
fn.push(function(cb) {
startStream(files.pop(), cb);
});
}
// process 3 files in parallel
async.parallelLimit(fn, 3, function() {
log(`child process ${cpuIdentifier} completed the task`);
fs.appendFile(__dirname + '/complete_count.txt', '1');
});
}
if (cluster.isMaster) {
for (var ii = 0; ii < numCPUs; ii++) {
cluster.fork();
}
} else {
MongoClient.connect(mongoUrl, function(err, db) {
if (err) throw (err);
mDb = db;
groupA = mDb.collection('groupageo');
groupB = mDb.collection('groupbgeo');
processFiles(files, process.pid);
// `files` is an array of file names
// each file is in newline json delimited format
// ["1478854974993/000000000000.json","1478854974993/000000000001.json","1478854974993/000000000002.json","1478854974993/000000000003.json","1478854974993/000000000004.json","1478854974993/000000000005.json"]
});
}

Answer 1

Okay, I have found the culprit! Google APIs Node.js client library makes use of a module called "stream-events" which implements Streams 0.8. Streams 0.8 do not control the rate at which it emits the 'data' event based on the consumer's ability to consume data. The rate controlling feature was introduced in Streams 1.0. So this essentially meant that the readable stream was throwing data at MongoDB at a rate that it was not able to process.
Solution:
I used the 'request' module instead of Google's client library. I supplied a signed URL to the request module which in turn fetched results as a stream which I could pipe into my transformer.
Take Away:
Always check the modules you use for the stream versions they are using.