Disk load, how to find out?

Question

linux

Good afternoon, how to correctly determine the load?
Alerts are released in Zabbix
Less than 25% free in the text history cache

02/08/2016 10:59:50 AM
avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           1.65    0.00    0.25    0.15    0.00   97.95

Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s avgrq-sz avgqu-sz   await  svctm  %util
sda               0.00    18.20    0.00   32.40     0.00     0.20    12.49     0.01    0.34   0.23   0.74
dm-0              0.00     0.00    0.00   50.60     0.00     0.20     8.00     0.02    0.41   0.15   0.74
dm-1              0.00     0.00    0.00    0.00     0.00     0.00     0.00     0.00    0.00   0.00   0.00
dm-2              0.00     0.00    0.00    0.00     0.00     0.00     0.00     0.00    0.00   0.00   0.00

02/08/2016 10:59:55 AM
avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           0.60    0.00    0.20    0.75    0.00   98.45

Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s avgrq-sz avgqu-sz   await  svctm  %util
sda              20.20     1.20    3.00   24.00     0.09     0.10    14.34     0.03    1.24   1.15   3.10
dm-0              0.00     0.00    0.00   25.20     0.00     0.10     8.00     0.01    0.45   0.27   0.68
dm-1              0.00     0.00   23.20    0.00     0.09     0.00     8.00     0.17    7.24   1.04   2.42
dm-2              0.00     0.00    0.00    0.00     0.00     0.00     0.00     0.00    0.00   0.00   0.00

02/08/2016 11:00:00 AM
avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           2.15    0.00    0.40    0.20    0.00   97.25

Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s avgrq-sz avgqu-sz   await  svctm  %util
sda               4.20   191.20    0.60   28.60     0.02     0.86    61.53     0.03    1.10   0.60   1.76
dm-0              0.00     0.00    0.00  219.80     0.00     0.86     8.00     0.83    3.78   0.06   1.40
dm-1              0.00     0.00    4.80    0.00     0.02     0.00     8.00     0.03    6.00   0.75   0.36
dm-2              0.00     0.00    0.00    0.00     0.00     0.00     0.00     0.00    0.00   0.00   0.00

02/08/2016 11:00:05 AM
avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           1.15    0.00    0.55    6.02    0.00   92.27

Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s avgrq-sz avgqu-sz   await  svctm  %util
sda              33.40     4.20   24.60  246.80     0.51     0.98    11.24     0.37    1.35   0.73  19.94
dm-0              0.00     0.00   49.60  251.40     0.47     0.98     9.91     0.37    1.21   0.65  19.58
dm-1              0.00     0.00    9.00    0.00     0.04     0.00     8.00     0.11   11.87   1.71   1.54
dm-2              0.00     0.00    0.00    0.00     0.00     0.00     0.00     0.00    0.00   0.00   0.00

NAME                         MAJ:MIN RM   SIZE RO TYPE MOUNTPOINT
sr0                           11:0    1  1024M  0 rom
sda                            8:0    0   500G  0 disk
├─sda1                         8:1    0   500M  0 part /boot
└─sda2                         8:2    0 499.5G  0 part
  ├─vg_z-lv_root (dm-0) 253:0    0   400G  0 lvm  /
  ├─vg_z-lv_swap (dm-1) 253:1    0     8G  0 lvm  [SWAP]
  └─vg_z-home (dm-2)    253:2    0    10G  0 lvm  /home

             total       used       free     shared    buffers     cached
Mem:          5852       5732        120          0        128        248
-/+ buffers/cache:       5354        497
Swap:         8191       5654       2537

Answer 1

че показывает iotop -oka

Answer 2

As an option to install atop, set the statistics collection interval to 1-2 minutes.
After zabix shows an increase in load, then look in the atop logs where and what process gave the load