orderbook-rs

High-Performance Lock-Free Order Book Engine

A high-performance, thread-safe limit order book implementation written in Rust. This project provides a comprehensive order matching engine designed for low-latency trading systems, with a focus on concurrent access patterns and lock-free data structures.

Key Features

• Lock-Free Architecture: Built using atomics and lock-free data structures to minimize contention and maximize throughput in high-frequency trading scenarios.

• Multiple Order Types: Support for various order types including standard limit orders, iceberg orders, post-only, fill-or-kill, immediate-or-cancel, good-till-date, trailing stop, pegged, market-to-limit, and reserve orders with custom replenishment logic.

• Thread-Safe Price Levels: Each price level can be independently and concurrently modified by multiple threads without blocking.

• Advanced Order Matching: Efficient matching algorithm that correctly handles complex order types and partial fills.

• Performance Metrics: Built-in statistics tracking for benchmarking and monitoring system performance.

• Memory Efficient: Designed to scale to millions of orders with minimal memory overhead.

Design Goals

This order book engine is built with the following design principles:

1. Correctness: Ensure that all operations maintain the integrity of the order book, even under high concurrency.
2. Performance: Optimize for low latency and high throughput in both write-heavy and read-heavy workloads.
3. Scalability: Support for millions of orders and thousands of price levels without degradation.
4. Flexibility: Easily extendable to support additional order types and matching algorithms.

Use Cases

• Trading Systems: Core component for building trading systems and exchanges
• Market Simulation: Tool for back-testing trading strategies with realistic market dynamics
• Research: Platform for studying market microstructure and order flow
• Educational: Reference implementation for understanding modern exchange architecture

Status

This project is currently in active development and is not yet suitable for production use.

Performance Analysis of the OrderBook System

This analyzes the performance of the OrderBook system based on tests conducted on an Apple M4 Max processor. The data comes from two types of tests: a High-Frequency Trading (HFT) simulation and contention pattern tests.

1. High-Frequency Trading (HFT) Simulation

Test Configuration

• Symbol: BTC/USD
• Duration: 5000 ms (5 seconds)
• Threads: 30 threads total
  • 10 maker threads (order creators)
  • 10 taker threads (order executors)
  • 10 canceller threads (order cancellers)
• Initial orders: 1020 pre-loaded orders

Performance Results

Initial vs. Final OrderBook State

2. Contention Pattern Tests

Configuration

• Threads: 12
• Duration per test: 3000 ms (3 seconds)

Read/Write Ratio Test

Hot Spot Contention Test

3. Analysis and Conclusions

Overall Performance

The system demonstrates an impressive capability to handle nearly 1 million operations per second in the high-frequency trading simulation, distributed across order creations, matches, and cancellations.

Read/Write Behavior

• Notable observation: Performance is highest with 0% and 95% read operations, showing a U-shaped curve.
• Pure write operations (0% reads) are extremely fast (716,117 ops/s).
• Performance significantly improves when most operations are reads (95% reads = 73,484 ops/s).
• Performance is lowest in the middle range (50% reads = 29,525 ops/s), indicating that the mix of reads and writes creates more contention.

Hot Spot Contention

• Surprisingly, performance increases as more operations concentrate on a hot spot, reaching its maximum with 100% concentration (28,327,212 ops/s).
• This counter-intuitive behavior might indicate:
  1. Very efficient cache effects when operations are concentrated in one memory area
  2. Internal optimizations to handle high-contention cases
  3. Benefits of the system's lock-free architecture

OrderBook State Behavior

• During the HFT simulation, the order book handled a massive increase in order volume (from 1,020 to 87,155).
• The spread increased from 100 to 270, reflecting realistic market behavior under pressure.
• The concentration of orders changed significantly, with fewer price levels but higher volume at each level.

4. Practical Implications

• The system is suitable for high-frequency trading environments with the capacity to process nearly 1 million operations per second.
• The lock-free architecture proves to be extremely effective at handling contention, especially at hot spots.
• Optimal performance is achieved when the workload is dominated by a single type of operation (mostly reads or mostly writes).
• For real-world use cases, it would be advisable to design the workload distribution to avoid intermediate read/write ratios (25-75%), which show the lowest performance.

This analysis confirms that the system design is highly scalable and appropriate for demanding financial applications requiring high-speed processing with data consistency.

License: MIT