怎么查看linux的哪个进程占用磁盘io较多？

[太乙]

怎么查看linux的哪个进程占用磁盘io较多？

iotop没装（不考虑）
iopp不好使（没响应）
pid rchar wchar syscr syscw rkb wkb cwkb command
pid rchar wchar syscr syscw rkb wkb cwkb command
pid rchar wchar syscr syscw rkb wkb cwkb command

iostat不能查看哪个进程！！

[hallowwar]

Mark。

[do_fork]

/proc/$PID/io

[happybeginner]

/proc/进程号/stat下面不是有么?
好像vmstat也能显示io次数

[do_fork]

io不一定是磁盘io，这个很难区分

[playmud]

python

#!/usr/bin/python
# Monitoring per-process disk I/O activity
# written by http://www.vpsee.com 

import sys, os, time, signal, re

class DiskIO:
    def __init__(self, pname=None, pid=None, reads=0, writes=0):
        self.pname = pname
        self.pid = pid
        self.reads = 0
        self.writes = 0

def main():
    argc = len(sys.argv)
    if argc != 1:
        print "usage: ./iotop"
        sys.exit(0)

    if os.getuid() != 0:
        print "must be run as root"
        sys.exit(0)

    signal.signal(signal.SIGINT, signal_handler)
    os.system('echo 1 > /proc/sys/vm/block_dump')
    print "TASK              PID       READ      WRITE"
    while True:
        os.system('dmesg -c > /tmp/diskio.log')
        l = []
        f = open('/tmp/diskio.log', 'r')
        line = f.readline()
        while line:
            m = re.match(\
                '^(\S+)\((\d+)\): (READ|WRITE) block (\d+) on (\S+)', line)
            if m != None:
                if not l:
                    l.append(DiskIO(m.group(1), m.group(2)))
                    line = f.readline()
                    continue
                found = False
                for item in l:
                    if item.pid == m.group(2):
                        found = True
                        if m.group(3) == "READ":
                            item.reads = item.reads + 1
                        elif m.group(3) == "WRITE":
                            item.writes = item.writes + 1
                if not found:
                    l.append(DiskIO(m.group(1), m.group(2)))
            line = f.readline()
        time.sleep(1)
        for item in l:
            print "%-10s %10s %10d %10d" % \
                (item.pname, item.pid, item.reads, item.writes)

def signal_handler(signal, frame):
    os.system('echo 0 > /proc/sys/vm/block_dump')
    sys.exit(0)

if __name__=="__main__":
    main()

[太乙]

[Quote=引用 2 楼 do_fork 的回复:]
/proc/$PID/io
[/Quote]

这个是不行的，没有这个东西~~~

我用的是linux 2.6.9-42.ELsmp

[太乙]

[Quote=引用 5 楼 playmud 的回复:]
pythonPython code#!/usr/bin/python
# Monitoring per-process disk I/O activity
# written by http://www.vpsee.comimport sys, os, time, signal, reclass DiskIO:def__init__(self, pname=None, pid=None, read?-
[/Quote]

这个需要iotop，我这里没有这个命令（没装）

请看我的帖子内容，上面说了，iotop不考虑~~~

[太乙]

[Quote=引用 5 楼 playmud 的回复:]
pythonPython code#!/usr/bin/python
# Monitoring per-process disk I/O activity
# written by http://www.vpsee.comimport sys, os, time, signal, reclass DiskIO:def__init__(self, pname=None, pid=None, read?-
[/Quote]

怎么使用？？

我使用 chmod +x 或者python 都不行！！！
File "py.sh", line 8
def __init__(self, pname=None, pid=None, reads=0, writes=0):
^
IndentationError: expected an indented block

[playmud]

没有调用iotop，没有看iotop的代码，这个python脚本核心就是

echo 1 > /proc/sys/vm/block_dump

然后对生成的数据用python处理，你可以改成shell的。

[root@playmud ~]# python 1.py
TASK              PID       READ      WRITE
kjournald         973          0         28
pdflush            90          0          0
kjournald         262          0         18
kjournald         973          0         28
kjournald         262          0         13
kjournald         971          0          5
[root@playmud ~]# uname -r
2.6.18.1

[Wenxy1]

top命令，看CPU的占用率，一般IO是比较占CPU资源的。