I'd like to do some general disk io monitoring on a debian linux server. What are the tools I should know about that monitor disk io so I can see if a disk's performance is maxed out or spikes at certain time throughout the day?


12 Answers 12


For disk I/O trending there are a few options. My personal favorite is the sar command from sysstat. By default, it gives output like this:

09:25:01 AM     CPU     %user     %nice   %system   %iowait    %steal     %idle
09:35:01 AM     all      0.11      0.00      0.01      0.00      0.00     99.88
09:45:01 AM     all      0.12      0.00      0.01      0.00      0.00     99.86
09:55:01 AM     all      0.09      0.00      0.01      0.00      0.00     99.90
10:05:01 AM     all      0.10      0.00      0.01      0.02      0.01     99.86
Average:        all      0.19      0.00      0.02      0.00      0.01     99.78

The %iowait is the time spent waiting on I/O. Using the Debian package, you must enable the stat collector via the /etc/default/sysstat config file after package installation.

To see current utilization broken out by device, you can use the iostat command, also from the sysstat package:

$ iostat -x 1
Linux 3.5.2-x86_64-linode26 (linode)    11/08/2012      _x86_64_        (4 CPU)

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           0.84    0.00    0.08    1.22    0.07   97.80

Device:         rrqm/s   wrqm/s     r/s     w/s   rsec/s   wsec/s avgrq-sz avgqu-sz   await  svctm  %util
xvda              0.09     1.02    2.58    0.49   112.79    12.11    40.74     0.15   48.56   3.88   1.19
xvdb              1.39     0.43    4.03    1.82    43.33    18.43    10.56     0.66  112.73   1.93   1.13

Some other options that can show disk usage in trending graphs is munin and cacti.

  • Munin or Cacti are more what I'm looking for. Thanks for the pointers. Commented Nov 9, 2012 at 4:00
  • 18
    Note that %iowait only shows time when the kernel had nothing else to do but wait for IO. On a 100% CPU bound server this will be zero regardless how much IO it is doing. Commented Apr 28, 2014 at 14:19
  • iostat -x dm-0 | grep Device; iostat -xd 2 -y dm-0 | grep dm-0 Commented Apr 17, 2018 at 19:02
  • 2
    to enable sar, one can simply do vim /etc/default/sysstat set "false" to "true" save the file and then do a sudo service sysstat restart
    – Hossein
    Commented Mar 2, 2021 at 3:50
  • This yields sar: command not found Commented Sep 1, 2021 at 12:47

Have a look at iotop:

Total DISK READ :       0.00 B/s | Total DISK WRITE :       0.00 B/s
Actual DISK READ:       0.00 B/s | Actual DISK WRITE:       0.00 B/s
  TID  PRIO  USER     DISK READ  DISK WRITE  SWAPIN     IO>    COMMAND                                                                                                             
    1 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % init splash
    2 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [kthreadd]
    4 be/0 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [kworker/0:0H]
    6 be/0 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [mm_percpu_wq]
    7 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [ksoftirqd/0]
    8 be/4 root        0.00 B/s    0.00 B/s  0.00 %  0.00 % [rcu_sched]

Or iodump, if that's more down your way of thinking.

Note: This requires at least kernel 2.6.20 to work.

  • This is not just Linux only, but also requires a newer (or patched) kernel.
    – jordanm
    Commented Nov 8, 2012 at 18:45
  • These look good for finding out what's going on right now, but I'm looking for bigger picture monitoring. Commented Nov 9, 2012 at 4:01
  • 15
    @camomileCase - you didn't specify that in your question ...
    – tink
    Commented Jun 17, 2016 at 10:16
  • on ubuntu 18.04 iotop crashes with messages OSError: Netlink error: No such file or directory (2) Commented Sep 1, 2021 at 12:49
  • @user7860670 - I can't confirm this; a cursory search suggests that there's a problem with iotop in containers - are you running docker or something?
    – tink
    Commented Sep 1, 2021 at 16:54

I like dstat. It can show totals and statistics per disk and even md-devices (RAID), also can use colors for better overview:

$ dstat -tdD total,sda,sdb,sdc,md1 60 
----system---- -dsk/total----dsk/sda-----dsk/sdb-----dsk/sdc-----dsk/md1--
     time     | read  writ: read  writ: read  writ: read  writ: read  writ
08-11 22:08:17|3549k  277k: 144k   28k: 851k   62k: 852k   60k:  25k   82k
08-11 22:09:17|  60k  258k:1775B   15k:  13k   63k:  15k   60k:  68B   74k
08-11 22:10:17| 176k  499k:   0    14k:  41k  122k:  41k  125k: 273B  157k
08-11 22:11:17|  42k  230k:   0    14k:9830B   54k:  14k   51k:   0    70k
08-11 22:11:52|  28k  132k:   0  5032B:5266B   33k:9479B   28k:   0    37k
  • -t for timestamps
  • -d for disk statistics
  • -D to specify the exact devices to report
  • 60 to average over 60 seconds. The display is updated every second, but only once per 60 seconds a new line will be started.

  • not used in this example, but -c can report wait IO percentage, which in most cases is related to the CPU waiting for data from the disks.

It is available for most Linux distributions, but sometimes needs to be installed from repositories.

  • I used this, and don't get the 'k' suffix, just numbers like 135 read 157 writ. What are the units here? Megabytes?
    – Bram
    Commented May 11, 2021 at 1:31
  • This yields dstat: command not found Commented Sep 1, 2021 at 12:49
  • @user7860670 that means it's not installed... Run <apt/yum/dnf> search dstat to find the package name and install it first.
    – cyqsimon
    Commented Nov 25, 2021 at 17:45

Just from files on your computer (assuming a recent kernel) you can ask /sys/block/sda/stat (documented at kernel.org) or /proc/diskstats. It will need some translating, however. But it's nice for a quick and dirty check.

  • 4
    Big advantage for this answer is that no tools need to be installed. It's just there. (Potentially :-) Commented Feb 3, 2017 at 5:36
  • 4
    e.g. echo "read io merge sectors ticks write io merges sectors ticks inflight ioticks timeinqueu";cat /sys/block/vda/vda1/stat ;sleep 10; cat /sys/block/vda/vda1/stat Commented Feb 6, 2017 at 0:07

Another option is to use: sudo iotop -aoP

-a    Will show accumulated output
-o    Will only output 
-P    Will only show processes instead of threads

This program will tell you how much a process has written to disk and read from disk since iotop was started.

  • I hear something accessing the disk, but accumulated output is increasing very slowly, sometimes not at all in a second... ???
    – Michael
    Commented Dec 11, 2018 at 1:13
  • If you hear the disk, it's probably old and/or slow. Modern HDDs tend to be very quiet. What kind of sounds is it making? Use smartctl to see whether the disk is healthy. Commented Jun 21, 2019 at 7:08

Monitoring Disk Io can be done by multiple tools like the following.

  1. Iostat
  2. Iozone
  3. SAR
  4. vmstat

Also some important operating system concepts are very much necessary to comprehend them..read the Linux IO complete tutorial

  • 3
    iozone is for testing, not monitoring: "Iozone is a filesystem benchmark tool. The benchmark generates and measures a variety of file operations." Commented Feb 16, 2016 at 22:28

I am the author of diskgraph which is a command line tool that plots the disk IO in a terminal. You select which disk, as an argument on the command-line, like sda or nvme0n1.

$ ./diskgraph nvme0n1

diskgraph screenshot

In red: the write bandwidth

In green: the read bandwidth

In orange: the number of IO operations that are in-flight.

Please note that this utility depends on features introduced in Linux 5. In other words, it will not work with Linux 4 or earlier.


Why not try nmon. It does disks and network with processes. Originally for AIX but it has been ported to Linux for some years now.


Another great tool for a quick overview where the load comes from is atop

It can show you an overview over all resources (CPU, memory/swap, network and disk I/O) or you can drill down to a single resource and sort processes by how much they consume.


If you use zfs, then there is a built in tool for this:

% zpool iostat -T d -n -H -v 1 | head -5
Sat Dec 24 23:09:49 2022
datatank    24.8T   31.6T   39  70  5.76M   4.55M
mirror-0    4.29T   4.80T   3   9   802K    765K
gpt/slot_A1 -   -   2   4   511K    403K
gpt/slot_B7 -   -   1   4   335K    405K
  • The -T d option puts the date lines (e.g Dec 24).
  • The -H enables scripted mode by omitting headers and making the data well formed.
  • The -v enables statistics for each individual vdev in the pool.
  • Finally the 1 is how many seconds to wait for the next update.
  • The head -5 is just to demonstrate you can pipe the output.

The best thing to do if you want to see performance on a long period is to use Centreon which is a powerful tools build on Nagios. Centreon make you able to monitor by drawing graphs of resource's performances and lot of other things.

  • 3
    What other things? Any screenshots? Please expand your answer. Commented Jun 24, 2019 at 18:06

The best tool is iostat. Analyzing I/O Performance in Linux." It's packed with practical insights and advanced techniques that can help boost your system's performance. Check it out here: https://techinfobest.com/analyzing-i-o-performance-in-linux/. Highly recommend it!

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .