TP50 TP90 TP99 TP999 详细说明

本文是根据自己的总结和网络总结得出

1、TP 指标说明

TP指标: 指在一个时间段内，统计该方法每次调用所消耗的时间，并将这些时间按从小到大的顺序进行排序, 并取出结果为：总次数 * 指标数 = 对应TP指标的值，在取出排序好的时间。

TP50、TP90、TP99、TP999 计算方式一致TP90，TP99，TP999则对方法性能要求很高。

2、国外资料：

在参考文章中的：
第一篇中：如下定义，也说明了上述的说明
public static final int TOTAL_RUNS = 1000000;
public static final int TP50 = (int)(TOTAL_RUNS * 0.50);
public static final int TP90 = (int)(TOTAL_RUNS * 0.90);
public static final int TP99 = (int)(TOTAL_RUNS * 0.99);
public static final int TP99_9 = (int)(TOTAL_RUNS * 0.999);
public static final int TP100 = (int)(TOTAL_RUNS * 1);

第二篇文章中的：
tp90 is a minimum time under which 90% of requests have been served. Imagine you have times:

10s
1000s
100s
2s
Calculating TP is very simple:

sort all times in ascending order: [2s, 10s, 100s, 1000s]
find latest item in portion you need to calculate.
TP50 it will ceil(4*.5)=2 requests. You need 2nd request.
TP90 it will be ceil(4*.9)=4. You need 4th request.
get time for the item found above. TP50=10s. TP90=1000s

3 疑问：为什么是去对应的取整值，为什么不是平均值，原文疑问

This doesn’t seem to match with the statistical definition of a percentile. Instead of using a ceiling to find an index, you should be averaging the two closest indices. For example, in a 4-element list, TP50 is the average of the 2nd and 3rd elements, not just the 2nd element. (This is assuming TP50 means the 50th percentile.) The exact formula is i=(k/100)(n+1) to find your desired index, where k is your percentile and n is the number of elements in your list. If i is not a whole number, average the two nearest indices.

译文：

这似乎不符合百分位的统计定义。您应该对两个最接近的指数进行平均，而不是使用上限来查找指数。例如，在4元素列表中，TP50是第二和第三元素的平均值，而不仅仅是第二元素。（这是假设TP50表示第50个百分点。）准确的公式是i =（k / 100）（n + 1）以找到您想要的指数，其中k是您的百分比，n是您列表中的元素数量。如果我不是一个整数，平均两个最接近的指数。

知道原因的朋友请留言。

参考文章：
https://stackoverflow.com/questions/12806981/after-how-many-iteration-securerandom-will-generate-all-the-number-between-given/12807589#12807589

https://stackoverflow.com/questions/17435438/what-do-we-mean-by-top-percentile-or-tp-based-latency/17458579#17458579