Use when traffic is growing or about to spike and the system bends under concurrency — deciding what to add and in what order (cache, connection pool, async queue, read replica, more instances) and proving it with a load test against explicit RPS and p95 targets rather than guessing. NOT making one slow request faster or profiling an N+1 (that is `performance`), NOT race-free Redis caches, locks and queue semantics (that is `redis`).
