Re:Deep inside the Linux kernel: a network latency spike
by laichzeit0 on Friday November 20, 2015 @01:07AM
(#10599882)
> To make things worse all our usual monitoring hadn't caught the problem
I suspect this is because most monitoring focuses on average instead of percentiles or maximum. Outliers are the most interesting data points. There is an almost cult-like following of the average as a KPI in monitoring tools.
Re:Deep inside the Linux kernel: a network latency spike
by luhn on Friday November 20, 2015 @01:36AM
(#10599956)
No, they explain why in the article: Their monitoring was looking at the application (nginx), so packets getting stuck in the kernel weren't reflected in that.
I suspect this is because most monitoring focuses on average instead of percentiles or maximum. Outliers are the most interesting data points. There is an almost cult-like following of the average as a KPI in monitoring tools.