Open SystemDecoder on a larger screen to build systems, run simulations, and inject chaos.
What's waiting for you on desktop
Live Simulations
Watch latency spike, queues fill, and nodes fail in real time. Every slider change is instant.
Visual Architecture Canvas
Drag nodes, draw edges, and build any distributed system topology from scratch.
Chaos Engineering
Kill servers, introduce packet loss, throttle CPUs — and watch your system react.
Real-time Insights
Throughput, p99 latency, error rates — all charted live as your simulation runs.
40+
Concepts
<1s
Feedback
∞
Replays
"The best way to understand a distributed system
is to break it."
Uber
🚗
28M trips per day. Driver found in <15s.
Real-time geo search → match → dispatch
28 million trips per day. A driver must be dispatched in under 15 seconds. At peak, Uber processes 300 ride requests per second — each needs the nearest idle driver found in milliseconds.
The naive approach — SELECT drivers ORDER BY distance — does a full table scan every time. At 100K active drivers and 300 requests/second, that's 30 million distance computations per second. No database survives that.
Request Flow
Scale numbers
14 billion GPS pings per day from drivers (~162,000/second). 28 million trips dispatched. Peak of 300 match requests/second. Median match time: <10 seconds.
The spatial problem
Finding the nearest driver is a 2D nearest-neighbour problem. Geohash converts 2D coordinates into a 1D sorted key so nearby points share prefixes — turning a spatial scan into a sorted-set range query.
The dispatch problem
Geohash finds candidates. Matching scores and dispatches them. Trip Service tracks the lifecycle. Three dedicated services, each optimised for its own task.
Key Insight
Geohash is the core enabler: it converts 2D spatial search into 1D sorted-set range queries — O(1) lookup per geohash cell instead of O(n) full-fleet distance scans.
Overview