performancelisted

# Performance Patterns Domain expertise for performance optimization and bottleneck detection. Use alongside `devflow:review-methodology` for complete performance reviews. ## Iron Law > **MEASURE BEFORE OPTIMIZING** > > Profile first, optimize second. Every performance claim requires benchmarks. Brendan > Gregg's USE Method [1] (Utilization, Saturation, Errors) and Tom Wilkie's RED Method [2] > (Rate, Errors, Duration) are the systematic starting points — not guesswork. > Gil Tene's coordinated omission warning [8]: averages lie — monitor P99, not mean latency. --- ## Measurement Foundation [1][2][7][8][9] | Method | For | Measures | |--------|-----|---------| | USE Method [1] | System resources | Utilization, Saturation, Errors per resource | | RED Method [2] | Services | Rate, Errors, Duration per endpoint | | Flame Graphs [9] | CPU hot paths | Widest frames = hottest code — optimize those | | HDR Histogram [8] | Latency | Full distribution without coordinated omission | **Latency hierarchy** [7]: L1 cache ~1ns · L2 ~4ns · L3 ~40ns · RAM ~100ns · SSD ~100µs · Network (DC) ~500µs · HDD ~10ms. Knowing these prevents optimizing the wrong layer [4]. --- ## Performance Categories ### 1. Algorithmic Issues [5][12] **N+1 Query Problem** — database query inside a loop. O(n) round-trips [5]. ```typescript // VIOLATION: 1 + N queries — O(n) round-trips [5] for (const user of users) { user.orders = await db.orders.findByUserId(user.id); } // CORRECT: Batch query with Ma