Re:How we built Uber Engineering's highest query-per-second ...
by spookthesunset on Thursday November 14, 2019 @03:03PM
(#21538840)
Sure but now your "100th percentile" would be nothing but the timeout.
Quantifying things like service latency isn't a one-size fits all thing. Every service has its nuances and use cases that make it more meaningful to measure 99%, 99.9%, 99.99% or something else.
.... just don't measure average like I've seen naive junior devs do. Average latency is the worst of all metrics to use as it will include all the outliers at the very tippy top of the spectrum and basically render the metric meaningless.
Quantifying things like service latency isn't a one-size fits all thing. Every service has its nuances and use cases that make it more meaningful to measure 99%, 99.9%, 99.99% or something else.
.... just don't measure average like I've seen naive junior devs do. Average latency is the worst of all metrics to use as it will include all the outliers at the very tippy top of the spectrum and basically render the metric meaningless.