Linux CPU 数据 Metrics 指标解读

过去从未仔细了解过使用 top 和 htop 等命令时显式的CPU信息，本文我们详解解读和标注一下各个数据项的含义，同时和 Ganglia 显式的数据做一个映射。开始前介绍一个小知识，很多查看CPU的命令行工具都是 cat /proc/stat 里的数据，所以数据来源都是一样的，区别只在于显式格式，用户体验上。本文我们以 mpstat 和 uptime 命令为主，最后介绍一下 top 和 htop 的一些细微差异。

一般来说，CPU 的性能会分成两个维度来看，一个是：利用率，另一个是：（1/5/15分钟的）平均负载，这两种指标是不同的 （具体内容，年后补啦！收工了！今年肝稿 108 篇！累死~）

%user: Percentage of CPU utilization that occurred while executing at the user level (application).
%nice: Percentage of CPU utilization that occurred while executing at the user level with nice priority.
%system: Percentage of CPU utilization that occurred while executing at the system level (kernel).
%iowait: Percentage of time that the CPU or CPUs were idle during which the system had an outstanding disk I/O request.
%idle: Percentage of time that the CPU or CPUs were idle and the system did not have an outstanding disk I/O request.

%usr – % CPU usage at the user level
%nice – % CPU usage for user processes labeled “nice”
%sys – % CPU usage at the system (Linux kernel) level
%iowait – % CPU usage idling waiting on a disk read/write
%irq – % CPU usage handling hardware interrupts
%soft – % CPU usage handing software interrupts
%steal – % CPU usage being forced to wait for a hypervisor handling other virtual processors
%guest – % CPU usage spent running a virtual processor
%idle – % CPU usage on idle time (no processes, and not waiting on a disk read/write)