Shulou(Shulou.com)06/01 Report--

How to understand the IO command iostat, many novices are not very clear about this, in order to help you solve this problem, the following editor will explain for you in detail, people with this need can come to learn, I hope you can gain something.

The% wa (wa = I waiting O waiting) in TOP can also see the utilization rate of IO to CPU time.

Iostat [- c] [- d] [- N] [- n] [- h] [- k |-m] [- t] [- V] [- x] [- y] [- z] [- j {ID |

LABEL | PATH | UUID |.} [device [...] | ALL]] [device [...] | ALL] [- p [device [,...] |

ALL]] [interval [count]]

The last two digits of the iostat command indicate the interval time, how many times it is displayed, and the interval time is indicated when the command takes a number at the end.

-k: disk read and write speed is measured in KB

-m: disk read and write speed is measured in MB

-x: view device usage (% util), response time (await, in in milliseconds)

-c: view cpu status

Tps

Indicate the number of transfers per second that were issued to the device. A transfer is an I/O request to the device.

Multiple logical requests can be combined into a sin-gle I/O request to the device. A transfer is of indeterminate size.

IOPS (Input/Output Per Second), which is the amount of input and output per second (or the number of reads and writes), is one of the main indicators of disk performance.

The following is purely personal understanding:

Under the pure IO pressure, the data of tps can be regarded as the iops that represents the processing power of the disk.

When IO is distributed, there will be request and response. The difference between tps and IOPS is that if 100 IO is issued, tps is 100. if IO merge occurs at the bottom, then the number of IOPS will be less than 100. for example, there are only 80 IO left.

[root@dwdb] # iostat-d-k 1 2

Linux 2.6.32-431.el6.x86_64 (tdb.huddk.com) 04 pound 10 CPU 2017 _ x86 pound 6416)

Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn

Sda 0.46 2.28 3.93 49388899 84928316

Sdb 5.77 48.92 81.68 1057519869 1765689376

Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn

Sda 0.46 2.28 3.93 49388899 84928316

Sdb 6.00 50.00 78.00 0 48

The above shows that it is displayed every 1 second, a total of 2 times. It shows that the average number of KB,sdb disk transfers per second is 6, disk reads per second is about 50KB, and disk writes per second is about 80KB.

[oraprod@ebsdba] $iostat-d-x-m 1 3

Linux 2.6.32-431.el6.x86_64 (ebsdba) 10 / 04 / 2017 _ x86 CPU 6496)

Device: rrqm/s wrqm/s rUnip s wdeband s rMB/s wMB/s avgrq-sz avgqu-sz await svctm% util

Sdb 0.00 0.00 133.75 1567.41 13.35 32.25 45.58 0.27 0.38 0.15 60.77

Device: rrqm/s wrqm/s rUnip s wdeband s rMB/s wMB/s avgrq-sz avgqu-sz await svctm% util

Sdb 0.00 0.00 200.00 8692.00 10.34 33.95 8.06 2.74 0.31 0.09 79.00

Device: rrqm/s wrqm/s rUnip s wdeband s rMB/s wMB/s avgrq-sz avgqu-sz await svctm% util

Sdb 0.00 0.00 100.00 8686.00 11.15 33.93 8.03 3.22 0.37 0.07 60.20

As seen above, it is displayed every second for a total of 3 times, showing that the MB,sdb disk reads about 10m per second and writes about 33m per second. The average disk response time is 60%. Although the response is very fast, it is already very busy.

Is it helpful for you to read the above content? If you want to know more about the relevant knowledge or read more related articles, please follow the industry information channel, thank you for your support.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.