Node Flamegraphs on ECS: Continuous Profiling That Survives Scale

// src/profiling/guarded-profile.ts
import { Session } from "node:inspector/promises";
import { writeFile } from "node:fs/promises";

export async function captureCpuProfile(seconds = 5): Promise<Buffer> {
 const session = new Session();
 session.connect();
 await session.post("Profiler.enable");
 await session.post("Profiler.start");
 await new Promise((r) => setTimeout(r, seconds * 1000));
 const { profile } = await session.post("Profiler.stop");
 session.disconnect();
 // ✅ Scrub before persist
 const scrubbed = scrubProfile(profile);
 const buf = Buffer.from(JSON.stringify(scrubbed));
 return buf;
}

function scrubProfile(profile: any) {
 // strip absolute paths → repo-relative; drop URL query strings in frame names
 for (const node of profile.nodes ?? []) {
 if (node.callFrame?.url) {
 node.callFrame.url = node.callFrame.url.replace(/\?.*$/, "").replace(/\/home\/[^/]+/, "/home/*");
 }
 }
 return profile;
}

// ❌ Unlimited --cpu-prof on every task forever, writing to container FS
// node --cpu-prof --cpu-prof-dir=/tmp app.js

// src/profiling/trigger.ts
export function shouldCapture(metricsSnapshot: {
 eventLoopP99Ms: number;
 cpuPct: number;
 alreadyCapturing: boolean;
}) {
 if (metricsSnapshot.alreadyCapturing) return false;
 return metricsSnapshot.eventLoopP99Ms > 50 || metricsSnapshot.cpuPct > 85;
}

# ecs task snippet — ephemeral volume for profiles
MountPoints:
 - SourceVolume: profiles
 ContainerPath: /var/profiles
 ReadOnly: false

import { S3Client, PutObjectCommand } from "@aws-sdk/client-s3";

const s3 = new S3Client({});

export async function uploadProfile(key: string, body: Buffer) {
 await s3.send(new PutObjectCommand({
 Bucket: process.env.PROFILE_BUCKET!,
 Key: key,
 Body: body,
 ContentType: "application/json",
 ServerSideEncryption: "aws:kms",
 SSEKMSKeyId: process.env.PROFILE_KMS_KEY,
 }));
}