Problems / Real world, hard
The home timeline as first built: timelines read from Manhattan with no Redis cache, and the timeline API, ranker, tweet API, fan-out workers and search at an eighth of their real size. Real traffic of timeline reads, new tweets and searches arrives, and most requests fail.
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.
Grow it into the real architecture: every goal must hold at 6,000 requests a second. You may add components, connect them and resize anything.
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 6; 2 of them are hidden until then.
6,000 requests a second for 20 seconds: 80% home (reads), 10% tweet (writes), 10% search (reads).
What each component does in this design, and what calls it. The simulator mimics each one from these settings.
| Component | Its job here | Settings |
|---|---|---|
| DDoS protectionDDoS protection | Traffic enters here.Calls API gateway.Volumetric floods are absorbed at the network edge, spread over many locations, before they reach you. | 100000 slots |
| API gatewayAPI gateway | DDoS protection forwards to it.Calls Timeline API, Tweet API, Search API.Gateways centralise auth, rate limits and routing so each service does not reimplement them. | 50000 slots · 1,500,000 calls/min |
| Timeline APIApp service | API gateway forwards to it for /home.Calls Timelines (Manhattan), Timeline ranker.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 1 replicas × 100 slots · timeout 1.0 s |
| Timelines (Manhattan)Key-value store | Timeline API calls it for reads. Fan-out workers calls it.Key-value stores spread keys over partitions; one very popular key can overload a single partition. | 16 partitions × 2,000 ops/s |
| Timeline rankerRanking model | Timeline API calls it.Feeds rank a few hundred candidates per load with a learned model; retrieval narrows millions of posts first. | 128 slots |
| Tweet APIApp service | API gateway forwards to it for /tweet.Calls Tweets (MySQL, sharded), Tweet events (Kafka) (publishes).Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 1 replicas × 100 slots · timeout 1.0 s |
| Tweets (MySQL, sharded)SQL database | Tweet API calls it.Postgres runs one process per connection, which is why poolers like PgBouncer sit in front of busy databases. | 4 vCPU · 50 connections |
| Tweet events (Kafka)Event stream | Tweet API publishes to it.Calls Fan-out workers.Kafka keeps order only within a partition, so the partition key decides what stays in sequence. | 8 partitions · retention 600 s |
| Fan-out workersWorker | Tweet events (Kafka) consumes from it.Calls Timelines (Manhattan), Search index (Earlybird).Queues deliver at least once, so a worker can see the same message twice. | 32 concurrent jobs |
| Search APIApp service | API gateway forwards to it for /search.Calls Search index (Earlybird).Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 1 replicas × 100 slots · timeout 1.0 s |
| Search index (Earlybird)Search index | Fan-out workers calls it. Search API calls it.Search engines build an inverted index: each word points to the documents that contain it. | 64 slots |