foxhunt/services/backtesting_service/tests/dbn_performance_tests.rs

//! Performance tests for DBN data loading
//!
//! These tests measure throughput, memory usage, and compare against targets
//! to ensure the DBN loading infrastructure meets HFT requirements.

use anyhow::Result;
use backtesting_service::dbn_repository::DbnMarketDataRepository;
use backtesting_service::repositories::MarketDataRepository;
use rust_decimal::Decimal;
use std::collections::HashMap;
use std::time::{Duration, Instant};

/// Helper to create a DBN repository with ES.FUT test data
async fn create_dbn_repository() -> Result<DbnMarketDataRepository> {
    // Find workspace root to get absolute path to test file
    let current_dir = std::env::current_dir()?;
    let workspace_root = current_dir
        .ancestors()
        .find(|p| p.join("Cargo.toml").exists() && p.join("test_data").exists())
        .ok_or_else(|| anyhow::anyhow!("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() {
        anyhow::bail!("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(),
    );

    DbnMarketDataRepository::new(file_mapping).await
}

#[tokio::test]
async fn test_throughput() -> Result<()> {
    let repo = create_dbn_repository().await?;

    // Load multiple times to get average
    let iterations = 10;
    let mut durations = Vec::new();

    for _ in 0..iterations {
        let start = Instant::now();

        let symbols = vec!["ES.FUT".to_string()];
        let data = repo
            .load_historical_data(
                &symbols,
                1704153600_000_000_000i64, // 2024-01-02 00:00:00
                1704240000_000_000_000i64, // 2024-01-03 00:00:00
            )
            .await?;

        let duration = start.elapsed();
        durations.push(duration);

        assert!(!data.is_empty(), "Should load data");
    }

    // Calculate statistics
    let avg_duration = durations.iter().sum::<Duration>() / iterations as u32;
    let min_duration = durations.iter().min().unwrap();
    let max_duration = durations.iter().max().unwrap();

    let bars_loaded = 390; // ES.FUT has ~390 bars on 2024-01-02
    let bars_per_sec = (bars_loaded as f64 / avg_duration.as_secs_f64()) as u64;

    println!("\n=== Throughput Analysis ({} iterations) ===", iterations);
    println!("  Min:  {:?}", min_duration);
    println!("  Avg:  {:?}", avg_duration);
    println!("  Max:  {:?}", max_duration);
    println!("  Throughput: {} bars/sec", bars_per_sec);

    // Targets:
    // - Average: <10ms
    // - Throughput: >10,000 bars/sec
    assert!(
        avg_duration.as_millis() < 10,
        "Average load time should be <10ms, got {:?}",
        avg_duration
    );
    assert!(
        bars_per_sec > 10_000,
        "Throughput should be >10K bars/sec, got {}",
        bars_per_sec
    );

    Ok(())
}

#[tokio::test]
async fn test_load_time_consistency() -> Result<()> {
    let repo = create_dbn_repository().await?;

    let iterations = 20;
    let mut durations = Vec::new();

    // Warm up
    for _ in 0..5 {
        let symbols = vec!["ES.FUT".to_string()];
        let _ = repo
            .load_historical_data(
                &symbols,
                1704153600_000_000_000i64,
                1704240000_000_000_000i64,
            )
            .await?;
    }

    // Measure
    for _ in 0..iterations {
        let start = Instant::now();

        let symbols = vec!["ES.FUT".to_string()];
        let _ = repo
            .load_historical_data(
                &symbols,
                1704153600_000_000_000i64,
                1704240000_000_000_000i64,
            )
            .await?;

        durations.push(start.elapsed().as_micros());
    }

    // Calculate statistics
    let avg: u128 = durations.iter().sum::<u128>() / iterations;
    let variance: u128 = durations
        .iter()
        .map(|d| {
            let diff = (*d as i128) - (avg as i128);
            (diff * diff) as u128
        })
        .sum::<u128>()
        / iterations;
    let stddev = (variance as f64).sqrt();
    let cv = stddev / (avg as f64); // Coefficient of variation

    println!("\n=== Load Time Consistency ({} iterations) ===", iterations);
    println!("  Avg:    {} μs", avg);
    println!("  StdDev: {:.2} μs", stddev);
    println!("  CV:     {:.2}% (lower is better)", cv * 100.0);

    // Target: CV < 20% (consistent performance)
    assert!(
        cv < 0.20,
        "Coefficient of variation should be <20%, got {:.2}%",
        cv * 100.0
    );

    Ok(())
}

#[tokio::test]
async fn test_partial_day_load() -> Result<()> {
    let repo = create_dbn_repository().await?;

    // Test loading different time windows
    let test_cases = vec![
        (
            "First hour",
            1704203400_000_000_000i64, // 2024-01-02 09:30:00 ET
            1704207000_000_000_000i64, // 2024-01-02 10:30:00 ET
        ),
        (
            "Morning session",
            1704203400_000_000_000i64, // 2024-01-02 09:30:00 ET
            1704218400_000_000_000i64, // 2024-01-02 14:00:00 ET
        ),
        (
            "Full day",
            1704153600_000_000_000i64, // 2024-01-02 00:00:00
            1704240000_000_000_000i64, // 2024-01-03 00:00:00
        ),
    ];

    println!("\n=== Partial Day Load Performance ===");

    for (name, start_time, end_time) in test_cases {
        let start = Instant::now();

        let symbols = vec!["ES.FUT".to_string()];
        let data = repo.load_historical_data(&symbols, start_time, end_time).await?;

        let duration = start.elapsed();
        let bars_per_sec = (data.len() as f64 / duration.as_secs_f64()) as u64;

        println!(
            "  {:<16} | Bars: {:>4} | Time: {:>7.2}ms | Throughput: {:>8} bars/s",
            name,
            data.len(),
            duration.as_secs_f64() * 1000.0,
            bars_per_sec
        );

        // All loads should be fast
        assert!(
            duration.as_millis() < 10,
            "{} load took too long: {:?}",
            name,
            duration
        );
    }

    Ok(())
}

#[tokio::test]
async fn test_cold_start_vs_warm() -> Result<()> {
    // Cold start
    let cold_start = Instant::now();
    let repo = create_dbn_repository().await?;
    let cold_init_duration = cold_start.elapsed();

    let symbols = vec!["ES.FUT".to_string()];
    let cold_load_start = Instant::now();
    let data = repo
        .load_historical_data(
            &symbols,
            1704153600_000_000_000i64,
            1704240000_000_000_000i64,
        )
        .await?;
    let cold_load_duration = cold_load_start.elapsed();
    let bars_loaded = data.len();

    // Warm loads (reuse repository)
    let mut warm_durations = Vec::new();
    for _ in 0..5 {
        let warm_start = Instant::now();
        let _ = repo
            .load_historical_data(
                &symbols,
                1704153600_000_000_000i64,
                1704240000_000_000_000i64,
            )
            .await?;
        warm_durations.push(warm_start.elapsed());
    }

    let avg_warm = warm_durations.iter().sum::<Duration>() / warm_durations.len() as u32;

    println!("\n=== Cold Start vs Warm Performance ===");
    println!("  Repository init: {:?}", cold_init_duration);
    println!("  Cold load:       {:?}", cold_load_duration);
    println!("  Warm load (avg): {:?}", avg_warm);
    println!(
        "  Warm speedup:    {:.2}x",
        cold_load_duration.as_secs_f64() / avg_warm.as_secs_f64()
    );
    println!("  Bars loaded:     {}", bars_loaded);

    // Warm loads should be faster or similar
    assert!(
        avg_warm <= cold_load_duration,
        "Warm loads should not be slower than cold"
    );

    Ok(())
}

#[tokio::test]
async fn test_data_correctness_at_speed() -> Result<()> {
    let repo = create_dbn_repository().await?;

    let start = Instant::now();
    let symbols = vec!["ES.FUT".to_string()];
    let data = repo
        .load_historical_data(
            &symbols,
            1704153600_000_000_000i64,
            1704240000_000_000_000i64,
        )
        .await?;
    let duration = start.elapsed();

    println!("\n=== Data Correctness at Speed ===");
    println!("  Load time: {:?}", duration);
    println!("  Bars loaded: {}", data.len());

    // Verify data quality
    assert!(!data.is_empty(), "Should load data");
    assert!(data.len() > 100, "Should load substantial data");

    // Check that bars are properly sorted
    for i in 1..data.len() {
        assert!(
            data[i].timestamp >= data[i - 1].timestamp,
            "Bars should be sorted by timestamp"
        );
    }

    // Verify all bars have valid data
    for (i, bar) in data.iter().enumerate() {
        assert!(
            bar.open > Decimal::ZERO,
            "Bar {} should have positive open price",
            i
        );
        assert!(
            bar.high >= bar.low,
            "Bar {} high should be >= low",
            i
        );
        assert!(
            bar.high >= bar.open && bar.high >= bar.close,
            "Bar {} high should be highest price",
            i
        );
        assert!(
            bar.low <= bar.open && bar.low <= bar.close,
            "Bar {} low should be lowest price",
            i
        );
        assert!(bar.volume >= Decimal::ZERO, "Bar {} should have non-negative volume", i);
    }

    println!("  ✓ All {} bars passed validation", data.len());

    Ok(())
}