只是想知道如何理解 newrelic 的前 5 个请求图。挂钟时间是如何定义的?我有一些理论,但看到超过 100% 的结果让我完全失望了。我正在使用 newrelic java 代理。
更新
根据 @lauradiane 的回答:并发请求可以使百分比超过 100% 假设我正在查看的 REST 端点有 5 个事务,每个事务 需要 12 秒才能完成。假设我正在看 60 秒 窗口。
因此,对于这 5 个事务的并发执行:
% of wall clock time = (5x12)/60 x 100 = 100%
如果它们串行执行
% of wall clock time = 12/60 x 100 = 20%
最佳答案
We look at the wall-clock time (the amount of time as recorded by the clock) for all the transactions, and we sum that across all of the transactions. Because the server can execute requests in parallel, you end up with percentages over 100. A percentage of 100 would would mean that the execution time across those 5 transactions is equal to the time expended when recording wall clock time.
关于java - 了解 newrelic 挂钟时间图的前 5 个请求(按百分比),我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/22185126/