Https://Linuxczar.Net/Blog/2017/06/15/Prometheus-Histogram-2/ > To make matters worse, Prometheus uses a binary search

Question

Https://Linuxczar.Net/Blog/2017/06/15/Prometheus-Histogram-2/ > To make matters worse, Prometheus uses a binary search

algorithm (because the data monotonically increases, right?) to find the correct bucket holding the q percentile. As this search jumps around to efficiently search the array, it could return any one of the buckets that match this criteria. This shows itself on your graphs as large spikes in your percentile data, probably up into the highest boundary you have configured. This obscures the real values/trend of the percentile data, and indicates a false problem.

> Histograms (Summary types too) are potentially always in an invalid or racy state that produce completely erroneous percentile estimates. The more buckets used the more likely one is to hit this problem.

А ситуация как-то поменялась с 2017го года?

#metrics #programming #russian

0

22.01.2022

1 ответов

22 просмотра

Aleksey Shirokikh · Accepted Answer

Aleksey Shirokikh

я не сталкивался с таким поведением

0

22.01.2022

171 похожих чатов

Https://Linuxczar.Net/Blog/2017/06/15/Prometheus-Histogram-2/ > To make matters worse, Prometheus uses a binary search

1 ответов

Похожие вопросы