Problems / Real world, hard

Live comments on a celebrity stream

Asked at Meta (Facebook Live) and Twitch. Thirty thousand viewers a second poll a comments API that reads Postgres; posting writes to the same table. At 8 s a celebrity joins and traffic triples for 10 seconds.

Unlock it once for 25 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

Success ≥ 99.5%, p99 ≤ 800 ms and Apdex ≥ 0.90, for at most $44,000 a month.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 3; 1 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. A server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

30,000 requests a second for 20 seconds: 92% reads, 8% post (writes).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls Comments API.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
Comments APIApp serviceLoad balancer forwards to it.Calls Comments (Postgres).Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.20 replicas × 100 slots · timeout 1.0 s
Comments (Postgres)SQL databaseComments API calls it.Postgres runs one process per connection, which is why poolers like PgBouncer sit in front of busy databases.32 vCPU · 800 connections · 2 read replicas

More real world problems