I'm running into AggregateError: EMFILE: too many open files while streaming multiple files.
Machine Details:
MacOS Monterey,
MacBook Pro (14-inch, 2021),
Chip Apple M1 Pro,
Memory 16GB,
Node v16.13.0
I've tried increasing the limits with no luck.
Ideally I would like to be able to set the limit of the number of files open at one time or resolve by closing files as soon as they have been used.
Code below. I've tried to remove the unrelated code and replace it with '//...'.
const MultiStream = require('multistream');
const fs = require('fs-extra'); // Also tried graceful-fs and the standard fs
const { fdir } = require("fdir");
// Also have a require for the bz2 and split2 functions but editing from phone right now
//...
let files = [];
//...
(async() => {
const crawler = await new fdir()
.filter((path, isDirectory) => path.endsWith(".bz2"))
.withFullPaths()
.crawl("Dir/Sub Dir")
.withPromise();
for(const file of crawler){
files = [...files, fs.createReadStream(file)]
}
multi = await new MultiStream(files)
// Unzip
.pipe(bz2())
// Create chunks from lines
.pipe(split2())
.on('data', function (obj) {
// Code to filter data and extract what I need
//...
})
.on("error", function(error) {
// Handling parsing errors
//...
})
.on('end', function(error) {
// Output results
//...
})
})();
To prevent pre-opening a filehandle for every single file in your array, you want to only open the files upon demand when it's that particular file's turn to be streamed. And, you can do that with multi-stream.
Per the multi-stream doc, you can lazily create the readStreams by changing this:
for(const file of crawler){
files = [...files, fs.createReadStream(file)]
}
to this:
let files = crawler.map((f) => {
return function() {
return fs.createReadStream(f);
}
});
After reading over the npm page for multistream I think I have found something that will help. I have also edited where you are adding the stream to the files array as I don't see a need to instantiate a new array and spread existing elements like you are doing.
To lazily create the streams, wrap them in a function:
var streams = [
fs.createReadStream(__dirname + '/numbers/1.txt'),
function () { // will be executed when the stream is active
return fs.createReadStream(__dirname + '/numbers/2.txt')
},
function () { // same
return fs.createReadStream(__dirname + '/numbers/3.txt')
}
]
new MultiStream(streams).pipe(process.stdout) // => 123 ```
With that we can update your logic to include this functionality by simply wrapping the readStreams in functions, this way the streams will not be created until they are needed. This will prevent you from having too many open at once. We can do this by simply updating your file loop:
for(const file of crawler){
files.push(function() {
return fs.createReadStream(file)
})
}
I need some advice on how to structure this function as at the moment it is not happening in the correct order due to node being asynchronous.
This is the flow I want to achieve; I don't need help with the code itself but with the order to achieve the end results and any suggestions on how to make it efficient
Node routes a GET request to my controller.
Controller reads a .csv file on local system and opens a read stream using fs module
Then use csv-parse module to convert that to an array line by line (many 100,000's of lines)
Start a try/catch block
With the current row from the csv, take a value and try to find it in a MongoDB
If found, take the ID and store the line from the CSV and this id as a foreign ID in a separate database
If not found, create an entry into the DB and take the new ID and then do 6.
Print out to terminal the row number being worked on (ideally at some point I would like to be able to send this value to the page and have it update like a progress bar as the rows are completed)
Here is a small part of the code structure that I am currently using;
const fs = require('fs');
const parse = require('csv-parse');
function addDataOne(req, id) {
const modelOneInstance = new InstanceOne({ ...code });
const resultOne = modelOneInstance.save();
return resultOne;
}
function addDataTwo(req, id) {
const modelTwoInstance = new InstanceTwo({ ...code });
const resultTwo = modelTwoInstance.save();
return resultTwo;
}
exports.add_data = (req, res) => {
const fileSys = 'public/data/';
const parsedData = [];
let i = 0;
fs.createReadStream(`${fileSys}${req.query.file}`)
.pipe(parse({}))
.on('data', (dataRow) => {
let RowObj = {
one: dataRow[0],
two: dataRow[1],
three: dataRow[2],
etc,
etc
};
try {
ModelOne.find(
{ propertyone: RowObj.one, propertytwo: RowObj.two },
'_id, foreign_id'
).exec((err, searchProp) => {
if (err) {
console.log(err);
} else {
if (searchProp.length > 1) {
console.log('too many returned from find function');
}
if (searchProp.length === 1) {
addDataOne(RowObj, searchProp[0]).then((result) => {
searchProp[0].foreign_id.push(result._id);
searchProp[0].save();
});
}
if (searchProp.length === 0) {
let resultAddProp = null;
addDataTwo(RowObj).then((result) => {
resultAddProp = result;
addDataOne(req, resultAddProp._id).then((result) => {
resultAddProp.foreign_id.push(result._id);
resultAddProp.save();
});
});
}
}
});
} catch (error) {
console.log(error);
}
i++;
let iString = i.toString();
process.stdout.clearLine();
process.stdout.cursorTo(0);
process.stdout.write(iString);
})
.on('end', () => {
res.send('added');
});
};
I have tried to make the functions use async/await but it seems to conflict with the fs.openReadStream or csv parse functionality, probably due to my inexperience and lack of correct use of code...
I appreciate that this is a long question about the fundamentals of the code but just some tips/advice/pointers on how to get this going would be appreciated. I had it working when the data was sent one at a time via a post request from postman but can't implement the next stage which is to read from the csv file which contains many records
First of all you can make the following checks into one query:
if (searchProp.length === 1) {
if (searchProp.length === 0) {
Use upsert option in mongodb findOneAndUpdate query to update or upsert.
Secondly don't do this in main thread. Use a queue mechanism it will be much more efficient.
Queue which I personally use is Bull Queue.
https://github.com/OptimalBits/bull#basic-usage
This also provides the functionality you need of showing progress.
Also regarding using Async Await with ReadStream, a lot of example can be found on net such as : https://humanwhocodes.com/snippets/2019/05/nodejs-read-stream-promise/
I am trying to read an JSON file that I have just written with another test in the same cypress project. However when it tries to read the file it times out after 4000 milliseconds.
Has anyone experienced this before? How could I solve it?
I have tried increasing the time out by giving it a settings object but that doesn't increase the time out time. I thought it might be a file permissions issue but that doesn't seem to be it either.
I am running on Mac but tried the same project on Windows with the same result.
before('grab generated user data', function (){
let data = cy.readFile("Generated User/Cypress test 131.json", {log:true, timeout: 180000});
}
I expect it to just give back the parsed JSON object. As it says in the Cypress docs. (https://docs.cypress.io/api/commands/readfile.html#Syntax)
1.Your file should be in the project directory where cypress.json file is present.
2.Your file name should be Cypresstest131.json or Cypress-test-131.json
before('grab generated user data', function (){
let data = cy.readFile("Cypresstest131.json", {log:true, timeout: 4000});
data.its('name').should('eq', 'Eliza')
})
or
before('grab generated user data', function (){
cy.readFile("Cypress-test-131.json", {log:true, timeout: 4000}).its('name').should('eq', 'Eliza')
})
Hope this help you
I ended up creating a data.json with cy.createFileSync(). When I want to read the file instead of using cypresses cy.readFile() function I created a cypress task that uses the fs library to read the file.
I am leaving you with the code snipped of the task I used to read the file.
const fs = require('fs');
const request = require('request');
module.exports = (on, config) => {
on('task', {
// Cypress task to get the last ID
getLastId: () => {
// Make a promise to tell Cypress to wait for this task to complete
return new Promise((resolve) => {
fs.readFile("data.json", 'utf8', (err, data) => {
if (data !== null && data !== undefined) {
data = JSON.parse(data);
if (data.hasOwnProperty('last_id')) {
resolve(data.last_id);
} else {
resolve("Missing last_id");
}
} else {
resolve(err);
}
});
});
}
Calling this function would be as simple as
let id = 0;
before('grab generated user data', function (){
cy.task('getLastId').then((newID)=>{
id = newID;
});
});
I have a small problem with a nodejs program. I'm trying to use the child_process module but the following code will only trigger the data event once I remove my card from a nfc card reader.
The problem is that the output I need is available before the card is removed.
For example if I put my card on the reader it will take half a second to print some lines inculding the card UID.
Then if I don't release the card, the program nfc-poll will still be working but won't output anything. As soon as I remove my card from the reader, it will output something and then close the buffer. This is when the event data is emitted.
What I'd like is to be able to read every byte as soon as possible to emit the card id as soon as possible.
function NFCReader() {
this.reader = new events.EventEmitter()
this.start_process()
}
NFCReader.prototype = {
start_process: function () {
this._process = cp.spawn('nfc-poll', [], {})
this._process.on('close', this.restart_process.bind(this))
//this._process.stdout.on('data', this.handle_data.bind(this))
this._process.stdout.readableFlowing = true
this._process.stdout.on('data', this.handle_data.bind(this))
this._process.stderr.on('data', this.handle_error.bind(this))
},
handle_data: function (data) {
var _data = data.toString()
var uid_lines = _data
.split('\n')
.filter(function (line) {return line.search('UID') >= 0})
if (uid_lines.length != 1) {
this.reader.emit('error', 'Multiple UID found')
return
}
var card_id = uid_lines[0]
.trim()
.split(':')[1].trim()
.replace(/[ ]+/g, ':')
this.reader.emit('card', card_id)
},
}
I tried to use pipe but it doesn't seem to help.
this is a runStream function from my release tools repo:
const stdin = input ? "pipe" : "ignore";
const out = new StringStream();
const child = execspawn(cmd, Object.assign(options, {
stdio: [stdin, "pipe", 2]
}));
child.on("error", e => out.emit("error", e));
if (input) {
input.pipe(child.stdin);
}
return child.stdout.pipe(out);
You can reproduce it or if you'd care to wait a couple days I could release it as a separate module. I guess there may already be something like that though...
fs.watch( 'example.xml', function ( curr, prev ) {
// on file change we can read the new xml
fs.readFile( 'example.xml','utf8', function ( err, data ) {
if ( err ) throw err;
console.dir(data);
console.log('Done');
});
});
OUTPUT:
some data
Done X 1
some data
Done X 2
It is my usage fault or ..?
The fs.watch api:
is unstable
has known "behaviour" with regards repeated notifications. Specifically, the windows case being a result of windows design, where a single file modification can be multiple calls to the windows API
I make allowance for this by doing the following:
var fsTimeout
fs.watch('file.js', function(e) {
if (!fsTimeout) {
console.log('file.js %s event', e)
fsTimeout = setTimeout(function() { fsTimeout=null }, 5000) // give 5 seconds for multiple events
}
}
I suggest to work with chokidar (https://github.com/paulmillr/chokidar) which is much better than fs.watch:
Commenting its README.md:
Node.js fs.watch:
Doesn't report filenames on OS X.
Doesn't report events at all when using editors like Sublime on OS X.
Often reports events twice.
Emits most changes as rename.
Has a lot of other issues
Does not provide an easy way to recursively watch file trees.
Node.js fs.watchFile:
Almost as bad at event handling.
Also does not provide any recursive watching.
Results in high CPU utilization.
If you need to watch your file for changes then you can check out my small library on-file-change. It checks file sha1 hash between fired change events.
Explanation of why we have multiple fired events:
You may notice in certain situations that a single creation event generates multiple Created events that are handled by your component. For example, if you use a FileSystemWatcher component to monitor the creation of new files in a directory, and then test it by using Notepad to create a file, you may see two Created events generated even though only a single file was created. This is because Notepad performs multiple file system actions during the writing process. Notepad writes to the disk in batches that create the content of the file and then the file attributes. Other applications may perform in the same manner. Because FileSystemWatcher monitors the operating system activities, all events that these applications fire will be picked up.
Source
My custom solution
I personally like using return to prevent a block of code to run when checking something, so, here is my method:
var watching = false;
fs.watch('./file.txt', () => {
if(watching) return;
watching = true;
// do something
// the timeout is to prevent the script to run twice with short functions
// the delay can be longer to disable the function for a set time
setTimeout(() => {
watching = false;
}, 100);
};
Feel free to use this example to simplify your code. It may NOT be better than using a module from others, but it works pretty well!
Similar/same problem. I needed to do some stuff with images when they were added to a directory. Here's how I dealt with the double firing:
var fs = require('fs');
var working = false;
fs.watch('directory', function (event, filename) {
if (filename && event == 'change' && active == false) {
active = true;
//do stuff to the new file added
active = false;
});
It will ignore the second firing until if finishes what it has to do with the new file.
I'm dealing with this issue for the first time, so all of the answers so far are probably better than my solution, however none of them were 100% suitable for my case so I came up with something slightly different – I used a XOR operation to flip an integer between 0 and 1, effectively keeping track of and ignoring every second event on the file:
var targetFile = "./watchThis.txt";
var flippyBit = 0;
fs.watch(targetFile, {persistent: true}, function(event, filename) {
if (event == 'change'){
if (!flippyBit) {
var data = fs.readFile(targetFile, "utf8", function(error, data) {
gotUpdate(data);
})
} else {
console.log("Doing nothing thanks to flippybit.");
}
flipBit(); // call flipBit() function
}
});
// Whatever we want to do when we see a change
function gotUpdate(data) {
console.log("Got some fresh data:");
console.log(data);
}
// Toggling this gives us the "every second update" functionality
function flipBit() {
flippyBit = flippyBit ^ 1;
}
I didn't want to use a time-related function (like jwymanm's answer) because the file I'm watching could hypothetically get legitimate updates very frequently. And I didn't want to use a list of watched files like Erik P suggests, because I'm only watching one file. Jan Święcki's solution seemed like overkill, as I'm working on extremely short and simple files in a low-power environment. Lastly, Bernado's answer made me a little nervous – it would only ignore the second update if it arrived before I'd finished processing the first, and I can't handle that kind of uncertainty. If anyone were to find themselves in this very specific scenario, there might be some merit to the approach I used? If there's anything massively wrong with it please do let me know/edit this answer, but so far it seems to work well?
NOTE: Obviously this strongly assumes that you'll get exactly 2 events per real change. I carefully tested this assumption, obviously, and learned its limitations. So far I've confirmed that:
Modifying a file in Atom editor and saving triggers 2 updates
touch triggers 2 updates
Output redirection via > (overwriting file contents) triggers 2 updates
Appending via >> sometimes triggers 1 update!*
I can think of perfectly good reasons for the differing behaviours but we don't need to know why something is happening to plan for it – I just wanted to stress that you'll want to check for yourself in your own environment and in the context of your own use cases (duh) and not trust a self-confessed idiot on the internet. That being said, with precautions taken I haven't had any weirdness so far.
* Full disclosure, I don't actually know why this is happening, but we're already dealing with unpredictable behaviour with the watch() function so what's a little more uncertainty? For anyone following along at home, more rapid appends to a file seem to cause it to stop double-updating but honestly, I don't really know, and I'm comfortable with the behaviour of this solution in the actual case it'll be used, which is a one-line file that will be updated (contents replaced) like twice per second at the fastest.
first is change and the second is rename
we can make a difference from the listener function
function(event, filename) {
}
The listener callback gets two arguments (event, filename). event is either 'rename' or 'change', and filename is the name of the file which triggered the event.
// rm sourcefile targetfile
fs.watch( sourcefile_dir , function(event, targetfile)){
console.log( targetfile, 'is', event)
}
as a sourcefile is renamed as targetfile, it's will call three event as fact
null is rename // sourcefile not exist again
targetfile is rename
targetfile is change
notice that , if you want catch all these three evnet, watch the dir of sourcefile
I somtimes get multible registrations of the Watch event causing the Watch event to fire several times.
I solved it by keeping a list of watching files and avoid registering the event if the file allready is in the list:
var watchfiles = {};
function initwatch(fn, callback) {
if watchlist[fn] {
watchlist[fn] = true;
fs.watch(fn).on('change', callback);
}
}
......
Like others answers says... This got a lot of troubles, but i can deal with this in this way:
var folder = "/folder/path/";
var active = true; // flag control
fs.watch(folder, function (event, filename) {
if(event === 'rename' && active) { //you can remove this "check" event
active = false;
// ... its just an example
for (var i = 0; i < 100; i++) {
console.log(i);
}
// ... other stuffs and delete the file
if(!active){
try {
fs.unlinkSync(folder + filename);
} catch(err) {
console.log(err);
}
active = true
}
}
});
Hope can i help you...
Easiest solution:
const watch = (path, opt, fn) => {
var lock = false
fs.watch(path, opt, function () {
if (!lock) {
lock = true
fn()
setTimeout(() => lock = false, 1000)
}
})
}
watch('/path', { interval: 500 }, function () {
// ...
})
I was downloading file with puppeteer and once a file saved, I was sending automatic emails. Due to problem above, I noticed, I was sending 2 emails. I solved by stopping my application using process.exit() and auto-start with pm2. Using flags in code didn't saved me.
If anyone has this problem in future, one can use this solution as well. Exit from program and restart with monitor tools automatically.
Here's my simple solution. It works well every time.
// Update obj as file updates
obj = JSON.parse(fs.readFileSync('./file.json', 'utf-8'));
fs.watch('./file.json', () => {
const data = JSON.parse(fs.readFileSync('./file.json', 'utf-8') || '{}');
if(Object.entries(data).length > 0) { // This checks fs.watch() isn't false-firing
obj = data;
console.log('File actually changed: ', obj)
}
});
I came across the same issue. If you don't want to trigger multiple times, you can use a debounce function.
fs.watch( 'example.xml', _.debounce(function ( curr, prev ) {
// on file change we can read the new xml
fs.readFile( 'example.xml','utf8', function ( err, data ) {
if ( err ) throw err;
console.dir(data);
console.log('Done');
});
}, 100));
Debouncing The Observer
A solution I arrived at was that (a) there needs to be a workaround for the problem in question and, (b), there needs to be a solution to ensure multiple rapid Ctrl+s actions do not cause Race Conditions. Here's what I have...
./**/utilities.js (somewhere)
export default {
...
debounce(fn, delay) { // #thxRemySharp https://remysharp.com/2010/07/21/throttling-function-calls/
var timer = null;
return function execute(...args) {
var context = this;
clearTimeout(timer);
timer = setTimeout(fn.bind(context, ...args), delay);
};
},
...
};
./**/file.js (elsewhere)
import utilities from './**/utilities.js'; // somewhere
...
function watch(server) {
const debounced = utilities.debounce(observeFilesystem.bind(this, server), 1000 * 0.25);
const observers = new Set()
.add( fs.watch('./src', debounced) )
.add( fs.watch('./index.html', debounced) )
;
console.log(`watching... (${observers.size})`);
return observers;
}
function observeFilesystem(server, type, filename) {
if (!filename) console.warn(`Tranfer Dev Therver: filesystem observation made without filename for type ${type}`);
console.log(`Filesystem event occurred:`, type, filename);
server.close(handleClose);
}
...
This way, the observation-handler that we pass into fs.watch is [in this case a bound bunction] which gets debounced if multiple calls are made less than 1000 * 0.25 seconds (250ms) apart from one another.
It may be worth noting that I have also devised a pipeline of Promises to help avoid other types of Race Conditions as the code also leverages other callbacks. Please also note the attribution to Remy Sharp whose debounce function has repeatedly proven very useful over the years.
watcher = fs.watch( 'example.xml', function ( curr, prev ) {
watcher.close();
fs.readFile( 'example.xml','utf8', function ( err, data ) {
if ( err ) throw err;
console.dir(data);
console.log('Done');
});
});
I had similar similar problem but I was also reading the file in the callback which caused a loop.
This is where I found how to close watcher:
How to close fs.watch listener for a folder
NodeJS does not fire multiple events for a single change, it is the editor you are using updating the file multiple times.
Editors use stream API for efficiency, they read and write data in chunks which causes multiple updates depending on the chunks size and the amount of content. Here is a snippet to test if fs.watch fires multiple events:
const http = require('http');
const fs = require('fs');
const path = require('path');
const host = 'localhost';
const port = 3000;
const file = path.join(__dirname, 'config.json');
const requestListener = function (req, res) {
const data = new Date().toString();
fs.writeFileSync(file, data, { encoding: 'utf-8' });
res.end(data);
};
const server = http.createServer(requestListener);
server.listen(port, host, () => {
fs.watch(file, (eventType, filename) => {
console.log({ eventType });
});
console.log(`Server is running on http://${host}:${port}`);
});
I believe a simple solution would be checking for the last modified timestamp:
let lastModified;
fs.watch(file, (eventType, filename) => {
stat(file).then(({ mtimeMs }) => {
if (lastModified !== mtimeMs) {
lastModified = mtimeMs;
console.log({ eventType, filename });
}
});
});
Please note that you need to use all-sync or all-async methods otherwise you will have issues:
Update the file in a editor, you will see only single event is logged:
const http = require('http');
const host = 'localhost';
const port = 3000;
const fs = require('fs');
const path = require('path');
const file = path.join(__dirname, 'config.json');
let lastModified;
const requestListener = function (req, res) {
const data = Date.now().toString();
fs.writeFileSync(file, data, { encoding: 'utf-8' });
lastModified = fs.statSync(file).mtimeMs;
res.end(data);
};
const server = http.createServer(requestListener);
server.listen(port, host, () => {
fs.watch(file, (eventType, filename) => {
const mtimeMs = fs.statSync(file).mtimeMs;
if (lastModified !== mtimeMs) {
lastModified = mtimeMs;
console.log({ eventType });
}
});
console.log(`Server is running on http://${host}:${port}`);
});
Few notes on the alternative solutions: Storing files for comparison will be memory inefficient especially if you have large files, taking file hashes will be expensive, custom flags are hard to keep track of, especially if you are going to detect changes made by other applications, and lastly unsubscribing and re-subscribing requires unnecessary juggling.
If you don't need an instant result, you can use setTimout to debounce successive events:
let timeoutId;
fs.watch(file, (eventType, filename) => {
clearTimeout(timeoutId);
timeoutId = setTimeout(() => {
console.log({ eventType });
}, 100);
});