Não decore palavra por palavra: entenda a estrutura da resposta e refaça com as suas palavras, em inglês.
Latency percentiles describe a distribution over a stated window and request population. p95 is a value at or below which approximately 95% of observations fall, depending on the estimator. It is not the average of the slowest 5%.
If 90 requests take 100ms and 10 take 2 seconds, the mean is 290ms while the nearest-rank p95 and p99 are 2 seconds. Both the average and tail describe useful, different behavior.
Monitor latency objectives, errors, load, and saturation with appropriate windows. Low traffic makes tail estimates noisy. Do not average per-instance p95 values to obtain a global p95. Aggregate suitable histograms or observations first.
Ler é o primeiro passo. No app, essa pergunta vira flashcard com repetição espaçada, e o módulo tem quiz e simulado para testar o que ficou.
Treinar essa pergunta no app