- Created data/examples/download_ml_training_data.rs using reqwest + Databento HTTP API - Downloaded 90 days × 4 symbols (ES.FUT, NQ.FUT, ZN.FUT, 6E.FUT) - Files saved to test_data/real/databento/ml_training/ - Total: 360 files, 15 MB compressed DBN format - Used existing Rust pattern from download_nq_fut.rs - API key loaded from .env file - 100% success rate (360/360 files) - Ready for ML training benchmarks Next: Create simplified training benchmark for RTX 3050 Ti GPU measurements
146 lines
4.8 KiB
Rust
146 lines
4.8 KiB
Rust
//! Performance benchmarks for DBN data loading
|
|
//!
|
|
//! This benchmark measures the performance of loading real market data from DBN files
|
|
//! to ensure it meets HFT requirements.
|
|
|
|
use backtesting_service::dbn_repository::DbnMarketDataRepository;
|
|
use backtesting_service::repositories::MarketDataRepository;
|
|
use criterion::{black_box, criterion_group, criterion_main, BenchmarkId, Criterion};
|
|
use std::collections::HashMap;
|
|
use tokio::runtime::Runtime;
|
|
|
|
fn benchmark_dbn_loading(c: &mut Criterion) {
|
|
let rt = Runtime::new().unwrap();
|
|
|
|
// Find workspace root to get absolute path to test file
|
|
let current_dir = std::env::current_dir().unwrap();
|
|
let workspace_root = current_dir
|
|
.ancestors()
|
|
.find(|p| p.join("Cargo.toml").exists() && p.join("test_data").exists())
|
|
.expect("Could not find workspace root");
|
|
let test_file = workspace_root
|
|
.join("test_data/real/databento/ES.FUT_ohlcv-1m_2024-01-02.dbn");
|
|
|
|
if !test_file.exists() {
|
|
panic!("Test file not found: {}", test_file.display());
|
|
}
|
|
|
|
let mut file_mapping = HashMap::new();
|
|
file_mapping.insert(
|
|
"ES.FUT".to_string(),
|
|
test_file.to_string_lossy().to_string(),
|
|
);
|
|
|
|
let repo = rt
|
|
.block_on(async { DbnMarketDataRepository::new(file_mapping).await.unwrap() });
|
|
|
|
c.bench_function("load_es_fut_390_bars", |b| {
|
|
b.to_async(&rt).iter(|| async {
|
|
let symbols = vec!["ES.FUT".to_string()];
|
|
let start_time = 1704153600_000_000_000i64; // 2024-01-02 00:00:00
|
|
let end_time = 1704240000_000_000_000i64; // 2024-01-03 00:00:00
|
|
|
|
let data = repo
|
|
.load_historical_data(&symbols, start_time, end_time)
|
|
.await
|
|
.unwrap();
|
|
|
|
black_box(data);
|
|
});
|
|
});
|
|
}
|
|
|
|
fn benchmark_multiple_loads(c: &mut Criterion) {
|
|
let rt = Runtime::new().unwrap();
|
|
|
|
// Find workspace root to get absolute path to test file
|
|
let current_dir = std::env::current_dir().unwrap();
|
|
let workspace_root = current_dir
|
|
.ancestors()
|
|
.find(|p| p.join("Cargo.toml").exists() && p.join("test_data").exists())
|
|
.expect("Could not find workspace root");
|
|
let test_file = workspace_root
|
|
.join("test_data/real/databento/ES.FUT_ohlcv-1m_2024-01-02.dbn");
|
|
|
|
let mut file_mapping = HashMap::new();
|
|
file_mapping.insert(
|
|
"ES.FUT".to_string(),
|
|
test_file.to_string_lossy().to_string(),
|
|
);
|
|
|
|
let repo = rt
|
|
.block_on(async { DbnMarketDataRepository::new(file_mapping).await.unwrap() });
|
|
|
|
let mut group = c.benchmark_group("multiple_loads");
|
|
|
|
for iterations in [1, 5, 10].iter() {
|
|
group.bench_with_input(
|
|
BenchmarkId::from_parameter(iterations),
|
|
iterations,
|
|
|b, &iterations| {
|
|
b.to_async(&rt).iter(|| async {
|
|
for _ in 0..iterations {
|
|
let symbols = vec!["ES.FUT".to_string()];
|
|
let start_time = 1704153600_000_000_000i64;
|
|
let end_time = 1704240000_000_000_000i64;
|
|
|
|
let data = repo
|
|
.load_historical_data(&symbols, start_time, end_time)
|
|
.await
|
|
.unwrap();
|
|
|
|
black_box(data);
|
|
}
|
|
});
|
|
},
|
|
);
|
|
}
|
|
group.finish();
|
|
}
|
|
|
|
fn benchmark_partial_day_load(c: &mut Criterion) {
|
|
let rt = Runtime::new().unwrap();
|
|
|
|
// Find workspace root to get absolute path to test file
|
|
let current_dir = std::env::current_dir().unwrap();
|
|
let workspace_root = current_dir
|
|
.ancestors()
|
|
.find(|p| p.join("Cargo.toml").exists() && p.join("test_data").exists())
|
|
.expect("Could not find workspace root");
|
|
let test_file = workspace_root
|
|
.join("test_data/real/databento/ES.FUT_ohlcv-1m_2024-01-02.dbn");
|
|
|
|
let mut file_mapping = HashMap::new();
|
|
file_mapping.insert(
|
|
"ES.FUT".to_string(),
|
|
test_file.to_string_lossy().to_string(),
|
|
);
|
|
|
|
let repo = rt
|
|
.block_on(async { DbnMarketDataRepository::new(file_mapping).await.unwrap() });
|
|
|
|
c.bench_function("load_es_fut_partial_day", |b| {
|
|
b.to_async(&rt).iter(|| async {
|
|
let symbols = vec!["ES.FUT".to_string()];
|
|
// Load only first 4 hours (9:30 AM - 1:30 PM ET)
|
|
let start_time = 1704203400_000_000_000i64; // 2024-01-02 09:30:00 ET
|
|
let end_time = 1704217800_000_000_000i64; // 2024-01-02 13:30:00 ET
|
|
|
|
let data = repo
|
|
.load_historical_data(&symbols, start_time, end_time)
|
|
.await
|
|
.unwrap();
|
|
|
|
black_box(data);
|
|
});
|
|
});
|
|
}
|
|
|
|
criterion_group!(
|
|
benches,
|
|
benchmark_dbn_loading,
|
|
benchmark_multiple_loads,
|
|
benchmark_partial_day_load
|
|
);
|
|
criterion_main!(benches);
|