Linux进程及其子进程读取/写入的总字节数 [英] Total number of bytes read/written by a Linux process and its children

问题描述

我想打印Linux进程读取/写入的总字节数。例如，我运行

I would like to print the total number of bytes read/written by a Linux process. For example, I run

gcc -c a.c

并希望看到GCC（包括其子代）从Linux内核请求了多少字节以及它们发送到内核的字节数。

and would like to see how many bytes in total did GCC, including its children, request from the Linux kernel and how many bytes they sent to the kernel.

此问题的不完整解决方案是：

Incomplete solutions to this problem are:

• 字段 rchar 和 wchar 在 / proc / PID / io 中显示读/写字节数至今。它不考虑子进程。一旦流程终止，它就会丢失。

• The fields rchar and wchar in /proc/PID/io show the number of read/written bytes so far. It does not account for child processes. It is lost as soon as the process terminates.

可以使用诸如 strace 之类的工具打印出进程及其子进程的系统调用（例如：读取，写入系统调用），但它无法聚合读/写的字节数。

A tool such as strace can be used to print out the syscalls of a process and its children (such as: read, write syscalls), but it is unable to aggregate the number of bytes read/written.

如何打印读取/写入的总字节数Linux进程及其子进程？

How to print the total number of bytes read/written by a Linux process and its child processes?

推荐答案

有点awk，strace就是你想要的。

A little awk, and strace is what you want.

strace -e trace=read,write -o ls.log ls

为您提供读写系统调用的日志。现在你可以把这个日志和这样的最后一列相加

gives you a log of the read and write syscalls. Now you can take this log and sum the last column like this

cat ls.log | grep read | awk 'BEGIN {FS="="}{ sum += $2} END {print sum}'

您可能不想更改grep以仅匹配行开头的读数。

You might wan't to change the grep to match only a read at the beginning of the line.

这篇关于Linux进程及其子进程读取/写入的总字节数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！