How to find how often Ubuntu frequently refers to hard disk drive (for read / write purposes) and how to adjust it?
Asked
Active
Viewed 256 times
1 Answers
2
The command to make these observations is iostat
and is contained in the package sysstat. Install it [ for systems that don't have it ] with:
sudo apt-get -y install sysstat
It can be used accordingly:
$ iostat
Linux 4.4.0-64-generic (george-HP-Pavilion-17-Notebook-PC) 04/03/2017 _x86_64_ (4 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
4.56 0.02 2.17 1.67 0.00 91.59
Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn
loop0 0.00 0.02 0.00 1093 0
loop1 0.04 0.04 0.00 1799 0
loop2 0.18 0.20 0.00 9607 0
loop3 0.00 0.02 0.00 1079 0
loop4 0.00 0.00 0.00 108 0
sda 7.70 87.28 178.21 4194476 8564449
scd1 0.00 0.00 0.00 166 0
Capture in megabytes:
$ iostat -m
Linux 4.4.0-64-generic (george-HP-Pavilion-17-Notebook-PC) 04/03/2017 _x86_64_ (4 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
4.56 0.02 2.17 1.67 0.00 91.59
Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn
loop0 0.00 0.00 0.00 1 0
loop1 0.04 0.00 0.00 1 0
loop2 0.18 0.00 0.00 9 0
loop3 0.00 0.00 0.00 1 0
loop4 0.00 0.00 0.00 0 0
sda 7.69 0.09 0.17 4096 8370
scd1 0.00 0.00 0.00 0 0
Extend report with -x parameter:
$ iostat -x
Linux 4.4.0-64-generic (george-HP-Pavilion-17-Notebook-PC) 04/03/2017 _x86_64_ (4 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
4.56 0.02 2.17 1.67 0.00 91.59
Device: rrqm/s wrqm/s r/s w/s rkB/s wkB/s avgrq-sz avgqu-sz await r_await w_await svctm %util
loop0 0.00 0.00 0.00 0.00 0.02 0.00 28.76 0.00 53.89 53.89 0.00 28.74 0.00
loop1 0.00 0.00 0.04 0.00 0.04 0.00 2.09 0.00 76.24 76.24 0.00 3.18 0.01
loop2 0.00 0.00 0.18 0.00 0.20 0.00 2.23 0.00 20.97 20.97 0.00 1.22 0.02
loop3 0.00 0.00 0.00 0.00 0.02 0.00 25.69 0.00 47.00 47.00 0.00 32.43 0.01
loop4 0.00 0.00 0.00 0.00 0.00 0.00 6.55 0.00 42.30 42.30 0.00 28.97 0.00
sda 0.36 7.68 3.05 4.64 87.12 178.06 68.95 0.29 37.84 35.88 39.14 4.88 3.75
scd1 0.00 0.00 0.00 0.00 0.00 0.00 9.49 0.00 11.20 11.20 0.00 10.17 0.00
Add delay to result ouput. This will produce 3 reports with 2 seconds interval:
$ iostat -k 2 3
Linux 4.4.0-64-generic (george-HP-Pavilion-17-Notebook-PC) 04/03/2017 _x86_64_ (4 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
4.56 0.02 2.17 1.67 0.00 91.59
Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn
loop0 0.00 0.00 0.00 1 0
loop1 0.04 0.00 0.00 1 0
loop2 0.18 0.00 0.00 9 0
loop3 0.00 0.00 0.00 1 0
loop4 0.00 0.00 0.00 0 0
sda 7.69 0.09 0.17 4096 8375
scd1 0.00 0.00 0.00 0 0
avg-cpu: %user %nice %system %iowait %steal %idle
4.03 0.00 1.64 0.63 0.00 93.70
Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn
loop0 0.00 0.00 0.00 0 0
loop1 0.00 0.00 0.00 0 0
loop2 0.00 0.00 0.00 0 0
loop3 0.00 0.00 0.00 0 0
loop4 0.00 0.00 0.00 0 0
sda 1.50 0.00 0.01 0 0
scd1 0.00 0.00 0.00 0 0
avg-cpu: %user %nice %system %iowait %steal %idle
3.16 0.00 2.28 0.51 0.00 94.06
Device: tps MB_read/s MB_wrtn/s MB_read MB_wrtn
loop0 0.00 0.00 0.00 0 0
loop1 0.00 0.00 0.00 0 0
loop2 0.00 0.00 0.00 0 0
loop3 0.00 0.00 0.00 0 0
loop4 0.00 0.00 0.00 0 0
sda 0.50 0.00 0.00 0 0
scd1 0.00 0.00 0.00 0 0
Now to see it continuously with 2 seconds interval:
$ iostat 2
Here's how to read iostat reports
The first section contains CPU report
%user : show the percentage of CPU utilization that occured while executing at the user (application) level
%nice : show the percentage of CPU utilization that occured while executing at the user level with nice priority
%system : show the percentage of CPU utilization that occured while executing at the system (kernel) level
%iowait : show the percentage of the time that the CPU or CPUs were idle during whcih the system had an outstanding disk I/O request
%steal : show the percentage of time spent in involuntary wait by the virtual CPU or CPUs while the hypervisor was servicing another virtual processor
%idle : show the percentage of time that the CPU or CPUs were idle and the system did not have an outstanding disk I/O request
The second section contains device utilization report
Device : device / partition name as listed in /dev directory
tps : show the number of transfers per second that were issued to the device. Higher tps means the processor is busier
Blk_read/s : show the amount of data read from the device expressed in a number of blocks (kilobytes, megabytes) per second
Blk_wrtn/s : show the amount of data written to the device expressed in a number of blocks (kilobytes, megabytes) per second
Blk_read : show the total number of blocks read
Blk_wrtn : show the total number of blocks written
For the second part of your question:
I/O schedulers are used to alter or optimize I/O operations on Linux and the various types includes:
CFQ [cfq] (Completely Fair Queuing) is an I/O scheduler for the Linux kernel and default under many Linux distributions.
Noop scheduler (noop) is the simplest I/O scheduler for the Linux kernel based upon FIFO queue concept.
Anticipatory scheduler (anticipatory) is an algorithm for scheduling hard disk input/output as well as old scheduler which is replaced by CFQ
Deadline scheduler (deadline) – it attempt to guarantee a start service time for a request.
To see your current disk scheduler:
sudo cat /sys/block/{DEVICE-NAME}/queue/scheduler
# where device name is [sda | sdb | ...]
# The one with the "[ ]" around it the one in use.
Each of these have their various pros and cons. To change to any of them they two methods:
At run time:
# echo scheduler_type_name > /sys/block/sda/queue/scheduler # echo noop > /sys/block/sda/queue/schedulerFor persistence after
reboot:a. Edit
vi /etc/default/grub, andb. Add this line:
GRUB_CMDLINE_LINUX="elevator=noop"c. Reboot
d. See here for the difference performances using a
postgresql
Source:
https://blog.codeship.com/linux-io-scheduler-tuning/
https://www.cyberciti.biz/faq/linux-change-io-scheduler-for-harddisk/
https://unix.stackexchange.com/questions/48138/how-to-throttle-per-process-i-o-to-a-max-limit
George Udosen
- 36,677