Red Hat Training

A Red Hat training course is available for Red Hat Enterprise Linux

2.3. Diskdevstat and netdevstat

Diskdevstat and netdevstat are SystemTap tools that collect detailed information about the disk activity and network activity of all applications running on a system. These tools were inspired by PowerTOP, which shows the number of CPU wakeups by every application per second (refer to Section 2.2, “PowerTOP”). The statistics that these tools collect allow you to identify applications that waste power with many small I/O operations rather than fewer, larger operations. Other monitoring tools that measure only transfer speeds do not help to identify this type of usage.
Install these tools with SystemTap with the following command as root:
~]# yum install tuned-utils-systemtap kernel-debuginfo
Run the tools with the command:
~]# diskdevstat
or the command:
~]# netdevstat
Both commands can take up to three parameters, as follows:
diskdevstat update_interval total_duration display_histogram
netdevstat update_interval total_duration display_histogram
update_interval
The time in seconds between updates of the display. Default: 5
total_duration
The time in seconds for the whole run. Default: 86400 (1 day)
display_histogram
Flag whether to histogram for all the collected data at the end of the run.
The output resembles that of PowerTOP. Here is sample output from a longer diskdevstat run:
PID  UID  DEV WRITE_CNT WRITE_MIN WRITE_MAX WRITE_AVG READ_CNT READ_MIN READ_MAX READ_AVG COMMAND
 2789  2903 sda1     854     0.000   120.000    39.836      0     0.000     0.000     0.000 plasma
 5494     0 sda1       0     0.000     0.000     0.000    758     0.000     0.012     0.000 0logwatch
 5520     0 sda1       0     0.000     0.000     0.000    140     0.000     0.009     0.000 perl
 5549     0 sda1       0     0.000     0.000     0.000    140     0.000     0.009     0.000 perl
 5585     0 sda1       0     0.000     0.000     0.000    108     0.001     0.002     0.000 perl
 2573     0 sda1      63     0.033  3600.015   515.226      0     0.000     0.000     0.000 auditd
 5429     0 sda1       0     0.000     0.000     0.000     62     0.009     0.009     0.000 crond
 5379     0 sda1       0     0.000     0.000     0.000     62     0.008     0.008     0.000 crond
 5473     0 sda1       0     0.000     0.000     0.000     62     0.008     0.008     0.000 crond
 5415     0 sda1       0     0.000     0.000     0.000     62     0.008     0.008     0.000 crond
 5433     0 sda1       0     0.000     0.000     0.000     62     0.008     0.008     0.000 crond
 5425     0 sda1       0     0.000     0.000     0.000     62     0.007     0.007     0.000 crond
 5375     0 sda1       0     0.000     0.000     0.000     62     0.008     0.008     0.000 crond
 5477     0 sda1       0     0.000     0.000     0.000     62     0.007     0.007     0.000 crond
 5469     0 sda1       0     0.000     0.000     0.000     62     0.007     0.007     0.000 crond
 5419     0 sda1       0     0.000     0.000     0.000     62     0.008     0.008     0.000 crond
 5481     0 sda1       0     0.000     0.000     0.000     61     0.000     0.001     0.000 crond
 5355     0 sda1       0     0.000     0.000     0.000     37     0.000     0.014     0.001 laptop_mode
 2153     0 sda1      26     0.003  3600.029  1290.730      0     0.000     0.000     0.000 rsyslogd
 5575     0 sda1       0     0.000     0.000     0.000     16     0.000     0.000     0.000 cat
 5581     0 sda1       0     0.000     0.000     0.000     12     0.001     0.002     0.000 perl
 5582     0 sda1       0     0.000     0.000     0.000     12     0.001     0.002     0.000 perl
 5579     0 sda1       0     0.000     0.000     0.000     12     0.000     0.001     0.000 perl
 5580     0 sda1       0     0.000     0.000     0.000     12     0.001     0.001     0.000 perl
 5354     0 sda1       0     0.000     0.000     0.000     12     0.000     0.170     0.014 s  h
 5584     0 sda1       0     0.000     0.000     0.000     12     0.001     0.002     0.000 perl
 5548     0 sda1       0     0.000     0.000     0.000     12     0.001     0.014     0.001 perl
 5577     0 sda1       0     0.000     0.000     0.000     12     0.001     0.003     0.000 perl
 5519     0 sda1       0     0.000     0.000     0.000     12     0.001     0.005     0.000 perl
 5578     0 sda1       0     0.000     0.000     0.000     12     0.001     0.001     0.000 perl
 5583     0 sda1       0     0.000     0.000     0.000     12     0.001     0.001     0.000 perl
 5547     0 sda1       0     0.000     0.000     0.000     11     0.000     0.002     0.000 perl
 5576     0 sda1       0     0.000     0.000     0.000     11     0.001     0.001     0.000 perl
 5518     0 sda1       0     0.000     0.000     0.000     11     0.000     0.001     0.000 perl
 5354     0 sda1       0     0.000     0.000     0.000     10     0.053     0.053     0.005 lm_lid.sh
The columns are:
PID
the process ID of the application
UID
the user ID under which the applications is running
DEV
the device on which the I/O took place
WRITE_CNT
the total number of write operations
WRITE_MIN
the lowest time taken for two consecutive writes (in seconds)
WRITE_MAX
the greatest time taken for two consecutive writes (in seconds)
WRITE_AVG
the average time taken for two consecutive writes (in seconds)
READ_CNT
the total number of read operations
READ_MIN
the lowest time taken for two consecutive reads (in seconds)
READ_MAX
the greatest time taken for two consecutive reads (in seconds)
READ_AVG
the average time taken for two consecutive reads (in seconds)
COMMAND
the name of the process
In this example, three very obvious applications stand out:
PID  UID  DEV WRITE_CNT WRITE_MIN WRITE_MAX WRITE_AVG READ_CNT READ_MIN READ_MAX READ_AVG COMMAND
 2789  2903 sda1     854     0.000   120.000    39.836      0     0.000     0.000     0.000 plasma
2573     0 sda1      63     0.033  3600.015   515.226      0     0.000     0.000     0.000 auditd
 2153     0 sda1      26     0.003  3600.029  1290.730      0     0.000     0.000     0.000 rsyslogd
These three applications have a WRITE_CNT greater than 0, which means that they performed some form of write during the measurement. Of those, plasma was the worst offender by a large degree: it performed the most write operations, and of course the average time between writes was the lowest. Plasma would therefore be the best candidate to investigate if you were concerned about power-inefficient applications.
Use the strace and ltrace commands to examine applications more closely by tracing all system calls of the given process ID. In the present example, you could run:
~]# strace -p 2789
In this example, the output of the strace contained a repeating pattern every 45 seconds that opened the KDE icon cache file of the user for writing followed by an immediate close of the file again. This led to a necessary physical write to the hard disk as the file metadata (specifically, the modification time) had changed. The final fix was to prevent those unnecessary calls when no updates to the icons had occurred.