Order Book
An order book is the list of all outstanding buy and sell orders for a financial instrument, organized by price level. It shows market depth and is constantly changing as orders are placed, filled, and cancelled.
Storing and replaying the order book
The live order book tells traders where the supply and demand sit at each price. But the harder problem is the historical one: storing every change to the book so you can replay exactly what the market looked like at any microsecond in the past.
That historical order book data is huge. Every order, modification, and cancellation is an event, and a single active instrument can generate millions of events a day. Backtesting and market microstructure research depend on being able to reconstruct and query that history fast.
This combination of extreme volume and microsecond timestamps makes order book data one of the most demanding time-series workloads in existence.
How Arc handles Order Book
Arc handles order book event data as high-volume columnar time-series. It ingests the event stream fast and stores it as Parquet you can query and replay with SQL, so you can reconstruct historical book state without a proprietary tick store.
Arc is a high-performance columnar database. Open Parquet on storage you own, single Go binary, production-ready in 30 seconds.