ps 计算CPU利用率原理

最新推荐文章于 2024-08-07 20:50:54 发布

_银叶先生

最新推荐文章于 2024-08-07 20:50:54 发布

阅读量4.6k

点赞数

分类专栏： linux 工具使用

本文链接：https://blog.csdn.net/chengm8/article/details/78578385

版权

linux 工具使用专栏收录该内容

18 篇文章 1 订阅

订阅专栏

ps -o pcpu pid 可以查询进程pid所占用的CPU利用率。

top 计算CPU的利用率：

top计算进程cpu利用率: http://www.samirchen.com/linux-cpu-performance/
cat /proc/stat //查看总的CPU情况
cat /proc/[pid]/stat //查看进程的CPU情况

CPUTime1 = user1 + nice1 + system1 + idle1 + iowait1 + irq1 + softirq1 + stealstolen1 + guest1;
CPUTime2 = user2 + nice2 + system2 + idle2 + iowait2 + irq2 + softirq2 + stealstolen2 + guest2;
totalCPUTime = CPUTime2 – CPUTime1;
processTime1 = utime1 + stime1 + cutime1 + cstime1;
processTime2 = utime2 + stime2 + cutime1 + cstime2;
processTime = processTime2 – processTime1;
processCPUUse = processTime / totalCPUTime;

ps 计算CPU利用率是通过读取进程的统计数据计算出来的。

总的公式：源码参考自procps-3.2.7/ps/output.c : pr_pcpu()

进程CPU利用率= 进程在CPU上的运行时间 / 进程运行经过的系统时间。

进程运行经过的时间= 系统当前时间 - 进程启动时的时间

系统当前时间= uptime, 读/proc/uptime

进程启动时的时间= start_time , 读/proc/pid/stat

进程在CPU上运行的时间= utime+stime+cutime+cstime; 读/proc/pid/stat

(注：/proc/pid/stat下的 start_time, utime,stime, cutime,cstime的单位不是秒，要转化成秒，需要除以 sysconf(_SC_CLK_TCK))

下面是详细说明:

1，/proc/[pid]/stat -- 进程的统计信息。

cat /proc/16891/stat
16891 (cpu) R 16783 16891 16783 34817 18308 4202496 206 0 0 0 837758 10 0 0 20 0 1 0 154386088 3805184 89 2628956160 4194304 4196196 140734028402976 18446744073709551615 4195742 0 0 0 0 0 0 0 17 4 0 0 0 0 0
（详细格式可以man proc 找到）
1,pid %d 进程(包括轻量级进程，即线程)号
2,comm %s 应用程序或命令的名字。
3,state %c 任务的状态 "RSDZTW": R is running,
S ：可中断的睡眠状态 ,
D ：不可中断睡眠（等IO）,
Z ： zombie,
T ：is traced or stopped (on a signal),
W ：is paging.
4,ppid %d 父进程ID。
5,pgrp %d 进程组ID。
6,session %d 该任务所在的会话组 ID。
7,tty_nr %d 该任务的 tty 终端的设备号，INT（34817/256）= 主设备号，（34817-主设备号）= 次设备号。
The controlling terminal of the process. ( 主设备号为8到15bit, &0xff00, 次设备号0到7bit,20到31bit. &0xffff00ff
The minor device number is contained in the combination of bits 31
to 20 and 7 to 0; the major device number is in bits 15 t0 8.)
8,tpgid %d 终端的进程组号，当前运行在该任务所在终端的前台任务(包括 shell 应用程序)的 PID。
The ID of the foreground process group of the controlling
terminal of the process.

9,flags %u (%lu before Linux 2.6.22) 进程标志位，查看该任务的特性
For bit meanings,see the PF_* defines in <linux/sched.h>.

10,minflt %lu 该任务不需要从硬盘拷数据而发生的缺页（次缺页）的次数
The number of minor faults the process has made which have
not required loading a memory page from disk.

11,cminflt %lu 累计的该任务的所有的 waited-for 进程曾经发生的次缺页的次数目
The number of minor faults that the process's waited-for
children have made.

12,majflt %lu The number of major faults the process has made which have required loading a memory page from disk.

13,cmajflt %lu The number of major faults that the process's waited-for children have made.

14,utime %lu 进程在用户态运行的时间，单位是clock(除以sysconf(_SC_CLK_TCK),转成秒)
Amount of time that this process has been scheduled in
user mode, measured in clock ticks (divide by
sysconf(_SC_CLK_TCK). This includes guest time,
guest_time (time spent running a virtual CPU, see below),
so that applications that are not aware of the guest time
field do not lose that time from their calculations.

15,stime %lu 进程在内核态运行的时间，单位是clock,

16,cutime %ld
Amount of time that this process's waited-for children
have been scheduled in user mode, measured in clock ticks
(divide by sysconf(_SC_CLK_TCK). (See also times(2).)
This includes guest time, cguest_time (time spent running
a virtual CPU, see below).
17,cstime %ld Amount of time that this process's waited-for children
have been scheduled in kernel mode, measured in clock
ticks (divide by sysconf(_SC_CLK_TCK).

18,priority %ld
19, nice %ld
20, num_thread %ld
21, itrealvalue %ld
22, starttime %llu (was %lu before Linux 2.6)
...