Skip to content

feat(grouper): add Prometheus metrics #520

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Kuchizu wants to merge 3 commits into
base: master
Choose a base branch
from
+194 −77
Open

feat(grouper): add Prometheus metrics #520

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c80ce79
feat(grouper): add Prometheus metrics
Kuchizu Feb 4, 2026
b7db107
feat(grouper): OOM-debug logging
Kuchizu Feb 10, 2026
38db313
fix(grouper): handle undefined delta
Kuchizu Feb 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions lib/metrics.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
import * as client from 'prom-client';
import os from 'os';
import { nanoid } from 'nanoid';

const register = new client.Registry();

client.collectDefaultMetrics({ register });

export { register, client };

/**
* Start periodic push to pushgateway
*
* @param workerName - name of the worker for grouping
*/
export function startMetricsPushing(workerName: string): void {
const url = process.env.PROMETHEUS_PUSHGATEWAY_URL;
const interval = parseInt(process.env.PROMETHEUS_PUSHGATEWAY_INTERVAL || '10000');

if (!url) {
return;
}

const hostname = os.hostname();
const ID_SIZE = 5;
const id = nanoid(ID_SIZE);

const gateway = new client.Pushgateway(url, [], register);

console.log(`Start pushing metrics to ${url} every ${interval}ms (host: ${hostname}, id: ${id})`);

setInterval(() => {
gateway.pushAdd({ jobName: 'workers', groupings: { worker: workerName, host: hostname, id } }, (err) => {
if (err) {
console.error('Metrics push error:', err);
}
});
}, interval);
}
89 changes: 18 additions & 71 deletions runner.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@ import * as utils from './lib/utils';
import { Worker } from './lib/worker';
import HawkCatcher from '@hawk.so/nodejs';
import * as dotenv from 'dotenv';
import { startMetricsPushing } from './lib/metrics';

dotenv.config();

Expand Down Expand Up @@ -57,19 +58,17 @@ class WorkerRunner {
.then((workerConstructors) => {
this.constructWorkers(workerConstructors);
})
// .then(() => {
// try {
// this.startMetrics();
// } catch (e) {
// HawkCatcher.send(e);
// console.error(`Metrics not started: ${e}`);
// }
//
// return Promise.resolve();
// })
.then(() => {
return this.startWorkers();
})
.then(() => {
try {
this.startMetrics();
} catch (e) {
HawkCatcher.send(e);
console.error(`Metrics not started: ${e}`);
}
})
.then(() => {
this.observeProcess();
})
Expand All @@ -82,67 +81,15 @@ class WorkerRunner {
/**
* Run metrics exporter
*/
// private startMetrics(): void {
// if (!process.env.PROMETHEUS_PUSHGATEWAY_URL) {
// return;
// }
//
// const PUSH_INTERVAL = parseInt(process.env.PROMETHEUS_PUSHGATEWAY_INTERVAL);
//
// if (isNaN(PUSH_INTERVAL)) {
// throw new Error('PROMETHEUS_PUSHGATEWAY_INTERVAL is invalid or not set');
// }
//
// const collectDefaultMetrics = promClient.collectDefaultMetrics;
// const Registry = promClient.Registry;
//
// const register = new Registry();
// const startGcStats = gcStats(register);
//
// const hostname = os.hostname();
//
// const ID_SIZE = 5;
// const id = nanoid(ID_SIZE);
//
// // eslint-disable-next-line node/no-deprecated-api
// const instance = url.parse(process.env.PROMETHEUS_PUSHGATEWAY_URL).host;
//
// // Initialize metrics for workers
// this.workers.forEach((worker) => {
// // worker.initMetrics();
// worker.getMetrics().forEach((metric: promClient.Counter<string>) => register.registerMetric(metric));
// });
//
// collectDefaultMetrics({ register });
// startGcStats();
//
// this.gateway = new promClient.Pushgateway(process.env.PROMETHEUS_PUSHGATEWAY_URL, null, register);
//
// console.log(`Start pushing metrics to ${process.env.PROMETHEUS_PUSHGATEWAY_URL}`);
//
// // Pushing metrics to the pushgateway every PUSH_INTERVAL
// this.pushIntervalNumber = setInterval(() => {
// this.workers.forEach((worker) => {
// if (!this.gateway || !instance) {
// return;
// }
// // Use pushAdd not to overwrite previous metrics
// this.gateway.pushAdd({
// jobName: 'workers',
// groupings: {
// worker: worker.type.replace('/', '_'),
// host: hostname,
// id,
// },
// }, (err?: Error) => {
// if (err) {
// HawkCatcher.send(err);
// console.log(`Error of pushing metrics to gateway: ${err}`);
// }
// });
// });
// }, PUSH_INTERVAL);
// }
private startMetrics(): void {
if (!process.env.PROMETHEUS_PUSHGATEWAY_URL) {
return;
}

this.workers.forEach((worker) => {
startMetricsPushing(worker.type.replace('/', '_'));
});
}

/**
* Dynamically loads workers through the yarn workspaces
Expand Down
Loading