Aeo Performance

Use when profiling application performance, reading a flame graph, benchmarking code, identifying bottlenecks, measuring CPU usage, analyzing memory allocation, or profiling I/O and database queries. Covers profiling methodology, cProfile and how to interpret its output, py-spy sampling, line-level profiling, tracemalloc and memory_profiler, query and network I/O profiling, reading and generating flame graphs, microbenchmarking with timeit, load testing, and a decision tree for picking a profiler. Applies to measurement and diagnosis; to fix what the profile reveals, use optimization-patterns.

Use when optimizing performance, implementing caching, fixing N+1 queries, improving database queries, adding indexes, reducing latency, choosing a data structure, deciding whether to optimize at all, or reviewing code for performance anti-patterns. Covers caching strategies and the cache hierarchy, cache invalidation, the Python LRU cache and its pitfalls, N+1 detection and eager loading, index strategy, algorithmic complexity and Big-O tradeoffs, lazy loading, and connection pooling. Applies once a bottleneck is known; to find the bottleneck first, use profiling-guide.