Performance Benchmarks

tileserver-rs is designed for high-performance vector tile serving. This page documents benchmark results for both PMTiles and MBTiles sources.

Test Environment

• Hardware: Apple Silicon (M-series) MacBook
• Runtime: All servers running in Docker containers (ARM64 native)
• Test Tool: autocannon (Node.js HTTP benchmarking)
• Configuration: 100 concurrent connections, 10 seconds per endpoint

Test Data

Summary Results

Both formats deliver ~93 MB/s throughput with 1,000+ requests/second under heavy load (100 concurrent connections).

Detailed Results by Zoom Level

PMTiles (Florence, Italy)

MBTiles (Zurich, Switzerland)

Analysis

Key Insights

• Throughput is consistent at ~90-100 MB/s regardless of zoom level
• Latency scales with tile size - low zoom (large tiles) = higher latency
• High zoom requests are fastest - z10-z14 achieve 1,000-3,400 req/s

PMTiles Performance

• Consistent performance across zoom levels
• Best at city zoom (z12-z14): 1,600+ req/s with 62ms latency
• Memory-mapped file access provides predictable performance

MBTiles Performance

• Fastest at z0: 3,441 req/s with only 29ms latency
• SQLite overhead more visible at high-detail tiles (z14: 425ms)
• Good for local development and smaller datasets

Format Comparison

Running Benchmarks

To reproduce these benchmarks with fair Docker-to-Docker comparison:

# Build tileserver-rs Docker image for your platform
docker build -t tileserver-rs:local .

# Update benchmarks/docker-compose.yml to use local image
# Then start all servers
docker compose -f benchmarks/docker-compose.yml up -d

# Run benchmarks
cd benchmarks
bun install
node run-benchmarks.js --duration 10 --connections 100

Benchmark Options

# Test only PMTiles
node run-benchmarks.js --format pmtiles

# Test only MBTiles  
node run-benchmarks.js --format mbtiles

# Test specific server
node run-benchmarks.js --server tileserver-rs

# Longer test with more connections
node run-benchmarks.js --duration 30 --connections 200

# Generate markdown report
node run-benchmarks.js --markdown

Server Comparison

We benchmarked tileserver-rs against martin and tileserver-gl using the same test data. All servers ran in Docker containers on ARM64 for a fair apples-to-apples comparison.

PMTiles Performance (Florence, Italy)

tileserver-rs is ~20% faster than tileserver-gl and ~17x faster than martin for PMTiles serving.

MBTiles Performance (Zurich, Switzerland)

All three servers perform similarly for MBTiles (within ~5% of each other).

Feature Comparison

tileserver-rs provides the best balance: fastest PMTiles performance (~20% faster than tileserver-gl, 17x faster than martin), native MapLibre rendering for raster tiles, and static image generation - all in a single binary.

Optimization Tips

1. Use release builds - cargo build --release is 10-50x faster than debug
2. Use PMTiles for production - cloud-native, HTTP range request friendly
3. Use MBTiles for development - easy to generate and inspect with SQLite tools
4. Enable compression - gzipped tiles reduce bandwidth significantly
5. Use CDN caching - tiles are immutable, cache with long TTLs
6. Match connections to cores - more connections than CPU cores adds overhead