I have written a cloud function that runs every 5 minutes on my Firebase app. In essence, the function gathers trends data from the Google Trends website and parses the JSON into a variable.
After doing so I want to then connect to the Twitter API and search for tweets using the trending topics fetched in the first part.
My Issue seems to lie with the second part. It fetches the data but the remainder of the function does not wait for the result before writing to Firebase.
I have tried two different methods but both don't seem to work as intended. I am struggling to understand how the function should wait for the second part to gather and store the information before writing to Firebase.
Method 1
exports.callTo = functions.pubsub.schedule("5 * * * *").onRun((context) => {
let searchTrends;
const ts = Date.now();
const dateOb = new Date(ts);
const date = dateOb.getDate();
const month = dateOb.getMonth() + 1;
const year = dateOb.getFullYear();
const twitterTrends = [];
googleTrends.dailyTrends({
trendDate: new Date(year + "-" + month + "-" + date),
geo: "CA",
}, function(err, res) {
if (err) {
functions.logger.error(err);
} else {
searchTrends = JSON.parse(res).default.trendingSearchesDays[0]
.trendingSearches;
functions.logger.info(searchTrends);
for (let i = 0; i < searchTrends.length; i++) {
functions.logger.log(searchTrends[i].title.query);
T.get("search/tweets", {q: searchTrends[i].title.query, count: 1},
function(err, data, response) {
if (err) {
functions.logger.error(err);
}
functions.logger.info("Twitter data" +
JSON.stringify(data.statuses));
twitterTrends[i] = JSON.stringify(data.statuses);
});
}
const dbRef = admin.database().ref("searchTrends");
dbRef.set({google: searchTrends, twitter: twitterTrends});
}
});
});
Method 2
exports.callTo = functions.pubsub.schedule("5 * * * *").onRun((context) => {
let searchTrends;
const ts = Date.now();
const dateOb = new Date(ts);
const date = dateOb.getDate();
const month = dateOb.getMonth() + 1;
const year = dateOb.getFullYear();
const twitterTrends = [];
async function getTrends(){
googleTrends.dailyTrends({
trendDate: new Date(year + "-" + month + "-" + date),
geo: "CA",
}, function(err, res) {
if (err) {
functions.logger.error(err);
} else {
searchTrends = JSON.parse(res).default.trendingSearchesDays[0]
.trendingSearches;
functions.logger.info(searchTrends);
}
});
await getTwitterTrends();
}
async function getTwitterTrends(){
for (let i = 0; i < 1; i++) {
functions.logger.log(searchTrends[i].title.query);
T.get("search/tweets", {q: searchTrends[i].title.query, count: 1},
function(err, data, response) {
if (err) {
functions.logger.error(err);
} else {
functions.logger.info("Twitter data" +
JSON.stringify(data.statuses));
twitterTrends[i] = JSON.stringify(data.statuses);
}
});
}
return "done";
}
const dbRef = admin.database().ref("searchTrends");
dbRef.set({google: searchTrends, twitter: twitterTrends});
});
After checking your function it looks like a Promises issue. The reason you are seeing only the searchTrends data in Firestore is because the Firestore reference and upload is being done inside the callback for the dailyTrends method (taking for reference the method 1 code). However this does not wait for each request to the Twitter API to be resolved before writing to Firestore.
Based on the documentation for twit (which seems to be the wrapper you are using), it also supports standard promises. You could add each promise to an array, and then use Promise.all() to wait until they are all resolved to then write the data into Firestore. It would look something like this (which I haven’t tested since I don’t have Twitter API access).
exports.callTo = functions.pubsub.schedule("5 * * * *").onRun((context) => {
const ts = Date.now();
const dateOb = new Date(ts);
const date = dateOb.getDate();
const month = dateOb.getMonth() + 1;
const year = dateOb.getFullYear();
let searchTrends;
const twitterTrends = [];
const twPromises = [];
googleTrends.dailyTrends({
trendDate: new Date(year + "-" + month + "-" + date),
geo: "CA",
}, function(err, res) {
if (err) {
functions.logger.error(err);
} else {
searchTrends = JSON.parse(res).default.trendingSearchesDays[0]
.trendingSearches;
functions.logger.info(searchTrends);
for (let i = 0; i < searchTrends.length; i++) {
functions.logger.log(searchTrends[i].title.query);
twPromises.push(T.get("search/tweets", {q: searchTrends[i].title.query, count: 1})); // adds promises to the array
}
Promise.all(twPromises).then((responses) => { // runs when all promises from the array are resolved
responses.forEach((response) => {
twitterTrends.push(JSON.stringify(response.statuses));
})
const dbRef = admin.database().ref("searchTrends");
dbRef.set({google: searchTrends, twitter: twitterTrends});
})
}
});
});
I want to access shopify api using Node.js with request method. I get first 50 items but i need to send the last id of the products i get as a response so it can loop through all the products until we don't have another id (i check that if the last array is not 50 in length.)
So when i get the response of lastID i want to feed that again to the same function until the Parraylength is not 50 or not 0.
Thing is request works asynchronously and i don't know how to feed the same function with the result lastID in node.js.
Here is my code
let importedData = JSON.parse(body);
//for ( const product in importedData.products ){
// console.log(`${importedData.products[product].id}`);
//}
lastID = importedData.products[importedData.products.length-1].id;
let lastIDD = lastID;
console.log(`This is ${lastID}`);
importedData ? console.log('true') : console.log('false');
let Prarraylength = importedData.products.length;
console.log(Prarraylength);
//console.log(JSON.stringify(req.headers));
return lastIDD;
});```
You can use a for loop and await to control the flow of your script in this case.
I'd suggest using the request-native-promise module to get items, since it has a promise based interface, but you could use node-fetch or axios (or any other http client) too.
In this case, to show you the logic, I've created a mock rp which normally you'd create as follows:
const rp = require("request-promise-native");
You can see we're looping through the items, 50 at a time. We're passing the last id as a url parameter to the next rp call. Now this is obviously going to be different in reality, but I believe you can easily change the logic as you require.
const totalItems = 155;
const itemsPerCall = 50;
// Mock items array...
const items = Array.from({ length: totalItems}, (v,n) => { return { id: n+1, name: `item #${n+1}` } });
// Mock of request-promise (to show logic..)
// Replace with const rp = require("request-promise-native");
const rp = function(url) {
let itemPointer = parseInt(url.split("/").slice(-1)[0]);
return new Promise((resolve, reject) => {
setTimeout(() => {
let slice = items.slice(itemPointer, itemPointer + itemsPerCall);
itemPointer += itemsPerCall;
resolve( { products: slice });
}, 500);
})
}
async function getMultipleRequests() {
let callIndex = 0;
let lastID = 0;
const MAX_CALLS = 20;
const EXPECTED_ARRAY_LENGTH = 50;
for(let callCount = 1; callCount < MAX_CALLS; callCount++) {
// Replace with the actual url..
let url = "/products/" + lastID;
let importedData = await rp(url);
lastID = importedData.products[importedData.products.length - 1].id;
console.log("Call #: " + ++callIndex + ", Item count: " + importedData.products.length + ", lastID: " + lastID);
if (importedData.products.length < EXPECTED_ARRAY_LENGTH) {
console.log("Reached the end of products...exiting loop...");
break;
}
}
}
getMultipleRequests();
Im using bluebirds Promise.map() method to run 100,000 firebase queries as shown below and the function takes about 10 seconds to run.. If I set the concurrency higher than 1000 then I receive the error
Maximum call stack size exceeded
Any ideas on how to fix this and also how to speed this up. It seems to me that perhaps Promise.map() may not be the right function to use or maybe I am mismanaging the memory some how. Any ideas thank you.
exports.postMadeByFriend = functions.https.onCall(async (data, context) => {
const mainUserID = "hJwyTHpoxuMmcJvyR6ULbiVkqzH3";
const follwerID = "Rr3ePJc41CTytOB18puGl4LRN1R2"
const otherUserID = "q2f7RFwZFoMRjsvxx8k5ryNY3Pk2"
var refs = [];
for (var x = 0; x < 100000; x += 1) {
if (x === 999) {
const ref = admin.database().ref(`Followers`).child(mainUserID).child(follwerID)
refs.push(ref);
continue;
}
const ref = admin.database().ref(`Followers`).child(mainUserID).child(otherUserID);
refs.push(ref);
}
await Promise.map(refs, (ref) => {
return ref.once('value')
}, {
concurrency: 10000
}).then((val) => {
console.log("Something happened: " + JSON.stringify(val));
return val;
}).catch((error) => {
console.log("an error occured: " + error);
return error;
})
Edits
const runtimeOpts = {
timeoutSeconds: 300,
memory: '2GB'
}
exports.postMadeByFriend = functions.runWith(runtimeOpts).https.onCall(async (data, context) => {
const mainUserID = "hJwyTHpoxuMmcJvyR6ULbiVkqzH3";
const follwerID = "Rr3ePJc41CTytOB18puGl4LRN1R2"
const otherUserID = "q2f7RFwZFoMRjsvxx8k5ryNY3Pk2"
var refs = [];
for (var x = 0; x < 100000; x += 1) {
if (x === 999) {
const ref = admin.database().ref(`Followers`).child(mainUserID).child(follwerID)
refs.push(ref);
continue;
}
const ref = admin.database().ref(`Followers`).child(mainUserID).child(otherUserID);
refs.push(ref);
}
await Promise.map(refs, (ref) => {
return ref.once('value')
}, {
concurrency: 10000
}).then((val) => {
console.log("Something happened: " + JSON.stringify(val));
return val;
}).catch((error) => {
console.log("an error occured: " + error);
return error;
})
Update:
If the goal is to have a number of friends posts the better way to do it would be to have a cloud function that increments a counter on every new post saved to the DB. That way you can get the number of posts with no calculation needed.
Here is the similar answer, and a code sample with the like counter
Original answer:
You could try to increase the memory allocated to your Cloud Funciton:
In the Google Cloud Platform Console, select Cloud Functions from the left menu.
Select a function by clicking on its name in the functions list.
Click the Edit icon in the top menu.
Select a memory allocation from the drop-down menu labeled Memory allocated.
Click Save to update the function.
As described in the Manage functions deployment page
I have this firebase function which is properly deployed for testing on Firebase :
exports.testDataPoint = functions.database.ref('/testDataPoint/{uid}/{id}/')
.onCreate(event => {
if (event.data.exists()) {
return admin.database().ref("/test/"+event.params.uid+"/accumulate")
.transaction(current => {
return (current || 0) + event.data.val();
})
}
else{
return Promise.resolve(true)
}
});
When I try to write a data of 10000 entries at once the function is not triggered at all. But if the number of entries is around 1000, function triggers perfectly.
Here is the script I'm using to write data:
function testGroupWrites() {
let users = {};
for (let i = 0; i < 1000; i++) {
let id = shortId.generate();
let jobs = {};
for (let j = 0; j < 10; j++) {
let uid = shortId.generate();
console.log(uid);
jobs[uid] = 1;
}
users[id] = jobs;
}
db.ref("testDataPoint")
.set(users)
.then(() => {
console.log("written");
})
}
Is there any limit to how much data can be written at a point above which function will not gets triggered? I'm testing this scenario, because in my project firebase function will be doing the same thing to calculate values.
I'm using Admin SDK in my script to write dummy data.
Yes there is a limit, please check the below:
So the maximum is 1000 entries, more info here:
https://firebase.google.com/docs/database/usage/limits
I have a piece of JavaScript code that I am executing using the node.js interpreter.
for(var i = 1; i < LIMIT; i++) {
var user = {
id: i,
name: "MongoUser [" + i + "]"
};
db.users.save(user, function(err, saved) {
if(err || !saved) {
console.log("Error");
} else {
console.log("Saved");
}
});
}
How can I measure the time taken by these database insert operations? I could compute the difference of date values after and before this piece of code but that would be incorrect because of the asynchronous nature of the code.
Use the Node.js console.time() and console.timeEnd():
var i;
console.time("dbsave");
for(i = 1; i < LIMIT; i++){
db.users.save({id : i, name : "MongoUser [" + i + "]"}, end);
}
end = function(err, saved) {
console.log(( err || !saved )?"Error":"Saved");
if(--i === 1){
console.timeEnd("dbsave");
}
};
There is a method that is designed for this. Check out process.hrtime(); .
So, I basically put this at the top of my app.
var start = process.hrtime();
var elapsed_time = function(note){
var precision = 3; // 3 decimal places
var elapsed = process.hrtime(start)[1] / 1000000; // divide by a million to get nano to milli
console.log(process.hrtime(start)[0] + " s, " + elapsed.toFixed(precision) + " ms - " + note); // print message + time
start = process.hrtime(); // reset the timer
}
Then I use it to see how long functions take. Here's a basic example that prints the contents of a text file called "output.txt":
var debug = true;
http.createServer(function(request, response) {
if(debug) console.log("----------------------------------");
if(debug) elapsed_time("recieved request");
var send_html = function(err, contents) {
if(debug) elapsed_time("start send_html()");
response.writeHead(200, {'Content-Type': 'text/html' } );
response.end(contents);
if(debug) elapsed_time("end send_html()");
}
if(debug) elapsed_time("start readFile()");
fs.readFile('output.txt', send_html);
if(debug) elapsed_time("end readFile()");
}).listen(8080);
Here's a quick test you can run in a terminal (BASH shell):
for i in {1..100}; do echo $i; curl http://localhost:8080/; done
Invoking console.time('label') will record the current time in milliseconds, then later calling console.timeEnd('label') will display the duration from that point.
The time in milliseconds will be automatically printed alongside the label, so you don't have to make a separate call to console.log to print a label:
console.time('test');
//some code
console.timeEnd('test'); //Prints something like that-> test: 11374.004ms
For more information, see Mozilla's developer docs on console.time.
Surprised no one had mentioned yet the new built in libraries:
Available in Node >= 8.5, and should be in Modern Browers
https://developer.mozilla.org/en-US/docs/Web/API/Performance
https://nodejs.org/docs/latest-v8.x/api/perf_hooks.html#
Node 8.5 ~ 9.x (Firefox, Chrome)
// const { performance } = require('perf_hooks'); // enable for node
const delay = time => new Promise(res=>setTimeout(res,time))
async function doSomeLongRunningProcess(){
await delay(1000);
}
performance.mark('A');
(async ()=>{
await doSomeLongRunningProcess();
performance.mark('B');
performance.measure('A to B', 'A', 'B');
const measure = performance.getEntriesByName('A to B')[0];
// firefox appears to only show second precision.
console.log(measure.duration);
// apparently you should clean up...
performance.clearMarks();
performance.clearMeasures();
// Prints the number of milliseconds between Mark 'A' and Mark 'B'
})();
https://repl.it/#CodyGeisler/NodeJsPerformanceHooks
Node 12.x
https://nodejs.org/docs/latest-v12.x/api/perf_hooks.html
const { PerformanceObserver, performance } = require('perf_hooks');
const delay = time => new Promise(res => setTimeout(res, time))
async function doSomeLongRunningProcess() {
await delay(1000);
}
const obs = new PerformanceObserver((items) => {
console.log('PerformanceObserver A to B',items.getEntries()[0].duration);
// apparently you should clean up...
performance.clearMarks();
// performance.clearMeasures(); // Not a function in Node.js 12
});
obs.observe({ entryTypes: ['measure'] });
performance.mark('A');
(async function main(){
try{
await performance.timerify(doSomeLongRunningProcess)();
performance.mark('B');
performance.measure('A to B', 'A', 'B');
}catch(e){
console.log('main() error',e);
}
})();
For anyone want to get time elapsed value instead of console output :
use process.hrtime() as #D.Deriso suggestion, below is my simpler approach :
function functionToBeMeasured() {
var startTime = process.hrtime();
// do some task...
// ......
var elapsedSeconds = parseHrtimeToSeconds(process.hrtime(startTime));
console.log('It takes ' + elapsedSeconds + 'seconds');
}
function parseHrtimeToSeconds(hrtime) {
var seconds = (hrtime[0] + (hrtime[1] / 1e9)).toFixed(3);
return seconds;
}
var start = +new Date();
var counter = 0;
for(var i = 1; i < LIMIT; i++){
++counter;
db.users.save({id : i, name : "MongoUser [" + i + "]"}, function(err, saved) {
if( err || !saved ) console.log("Error");
else console.log("Saved");
if (--counter === 0)
{
var end = +new Date();
console.log("all users saved in " + (end-start) + " milliseconds");
}
});
}
Old question but for a simple API and light-weight solution; you can use perfy which uses high-resolution real time (process.hrtime) internally.
var perfy = require('perfy');
function end(label) {
return function (err, saved) {
console.log(err ? 'Error' : 'Saved');
console.log( perfy.end(label).time ); // <——— result: seconds.milliseconds
};
}
for (var i = 1; i < LIMIT; i++) {
var label = 'db-save-' + i;
perfy.start(label); // <——— start and mark time
db.users.save({ id: i, name: 'MongoUser [' + i + ']' }, end(label));
}
Note that each time perfy.end(label) is called, that instance is auto-destroyed.
Disclosure: Wrote this module, inspired by D.Deriso's answer. Docs here.
You could also try exectimer. It gives you feedback like:
var t = require("exectimer");
var myFunction() {
var tick = new t.tick("myFunction");
tick.start();
// do some processing and end this tick
tick.stop();
}
// Display the results
console.log(t.timers.myFunction.duration()); // total duration of all ticks
console.log(t.timers.myFunction.min()); // minimal tick duration
console.log(t.timers.myFunction.max()); // maximal tick duration
console.log(t.timers.myFunction.mean()); // mean tick duration
console.log(t.timers.myFunction.median()); // median tick duration
[edit] There is an even simpler way now to use exectime. Your code could be wrapped like this:
var t = require('exectimer'),
Tick = t.Tick;
for(var i = 1; i < LIMIT; i++){
Tick.wrap(function saveUsers(done) {
db.users.save({id : i, name : "MongoUser [" + i + "]"}, function(err, saved) {
if( err || !saved ) console.log("Error");
else console.log("Saved");
done();
});
});
}
// Display the results
console.log(t.timers.myFunction.duration()); // total duration of all ticks
console.log(t.timers.saveUsers.min()); // minimal tick duration
console.log(t.timers.saveUsers.max()); // maximal tick duration
console.log(t.timers.saveUsers.mean()); // mean tick duration
console.log(t.timers.saveUsers.median()); // median tick duration
You can use a wrapper function to easily report the execution time of any existing function.
A wrapper is a used to extend an existing function to do something before and after the existing function's execution - and is a convenient way to compose logic.
Here is an example of using the withDurationReporting wrapper:
// without duration reporting
const doSomethingThatMayTakeAWhile = async (someArg: string, anotherArg: number) => {
/** your logic goes here */
}
// with duration reporting
const doSomethingThatMayTakeAWhileWithReporting = withDurationReporting(
'doSomethingThatMayTakeAWhile',
doSomethingThatMayTakeAWhile
);
// note: you can define the function with duration reporting directly, too
const doSomethingThatMayTakeAWhile = withDurationReporting(
'doSomethingThatMayTakeAWhile',
async (someArg: string, anotherArg: number) => {
/** your logic goes here */
}
)
And here is the wrapper itself:
import { hrtime } from 'process';
const roundToHundredths = (num: number) => Math.round(num * 100) / 100; // https://stackoverflow.com/a/14968691/3068233
/**
* a wrapper which reports how long it took to execute a function, after the function completes
*/
export const withDurationReporting = <R extends any, T extends (...args: any[]) => Promise<R>>(
title: string,
logic: T,
options: {
reportingThresholdSeconds: number;
logMethod: (message: string, metadata?: Record<string, any>) => void;
} = {
reportingThresholdSeconds: 1, // report on anything that takes more than 1 second, by default
logMethod: console.log, // log with `console.log` by default
},
) => {
return (async (...args: Parameters<T>): Promise<R> => {
const startTimeInNanoseconds = hrtime.bigint();
const result = await logic(...args);
const endTimeInNanoseconds = hrtime.bigint();
const durationInNanoseconds = endTimeInNanoseconds - startTimeInNanoseconds;
const durationInSeconds = roundToHundredths(Number(durationInNanoseconds) / 1e9); // https://stackoverflow.com/a/53970656/3068233
if (durationInSeconds >= options.reportingThresholdSeconds)
options.logMethod(`${title} took ${durationInSeconds} seconds to execute`, { title, durationInSeconds });
return result;
}) as T;
};
I designed a simple method for this, using console.time() & console.timeEnd():
measure function definition
function measureRunningTime(func,...args){
const varToString = varObj => Object.keys(varObj)[0]
const displayName = func.name || varToString({ func })
console.time(displayName)
func(...args)
console.timeEnd(displayName)
}
To use it, pass a function without arguments, with arguments binded, or with arguments as the following parameters.
Examples:
let's say I want to check the running time of the simplest searching algorithm - SimpleSearch:
measured function definition (your code here)
const simpleSearch = (array = [1,2,3] ,item = 3) => {
for(let i = 0; i< array.length; i++){
if (array[i] === item) return i;
}
return -1
}
implementation without arguments
measureRunningTime(simpleSearch)
//Prints something like that-> simpleSearch: 0.04ms
implementation with arguments using .bind()
const array = [1,2,3]
const item = 3
measureRunningTime(simpleSearch.bind(null, array, item))
//Prints something like that-> bound simpleSearch: 0.04ms
implementation with arguments without using .bind()
const array = [1,2,3]
const item = 3
measureRunningTime(simpleSearch, array, item)
//Prints something like that-> simpleSearch: 0.04ms
-> Take notice!! this implementation is far from perfect - for example there is no error handling - but it can be used to check the running times of simple algorithms,
Moreover , I'm not an experienced programmer so take everything with a grain of salt 🧂 👌
I had same issue while moving from AWS to Azure
For express & aws, you can already use, existing time() and timeEnd()
For Azure, use this:
https://github.com/manoharreddyporeddy/my-nodejs-notes/blob/master/performance_timers_helper_nodejs_azure_aws.js
These time() and timeEnd() use the existing hrtime() function, which give high-resolution real time.
Hope this helps.
I need this to be cumulative, and to measure different stuff.
Built these functions:
function startMeasuring(key) {
measureTimers[key] = process.hrtime();
}
function stopMeasuring(key) {
if (!measures[key]) {
measures[key] = 0;
}
let hrtime = process.hrtime(measureTimers[key]);
measures[key] += hrtime[0] + hrtime[1] / 1e9;
measureTimers[key] = null;
}
Usage:
startMeasuring("first Promise");
startMeasuring("first and second Promises");
await new Promise((resolve) => {
setTimeout(resolve, 1400);
});
stopMeasuring("first Promise");
stopMeasuring("first and second Promises");
startMeasuring("first and second Promises");
await new Promise((resolve) => {
setTimeout(resolve, 600);
});
stopMeasuring("first and second Promises");
console.log("Measure Results", measures);
/*
Measusre Results {
setting: 0.00002375,
'first Promise': 1.409392916,
'first and second Promise': 2.015160376
}
*/