Could someone guide me how to check disk IO during performance issue. I have got some idea to check the memory & cpu utilization.
But I'm not very sure how to check disk IO.
I ran iostat -x command. But I'm not sure which part I need to look in iostat output.
do we have any formula, to calculate the disk IO values. Upto what value, we can consider disk IO is normal.
If disk IO found high, what steps we need to take to improve the performance. (If at all no issues found in filesystem or disk).
For example, I have given the below output of iostat -x. Could someone guide me to learn about troubleshooting IO.
avg-cpu: %user %nice %system %iowait %steal %idle
1.61 0.14 0.65 5.32 0.00 92.28
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util
sdb 28.26 905.20 244.46 783.11 60380.59 19881.09 78.11 1.03 1.00 0.60 61.21
sda 0.10 4.55 0.78 2.53 73.40 56.62 39.34 0.00 0.87 0.58 0.19
dm-0 0.00 0.00 0.64 2.59 31.99 20.71 16.33 0.04 11.72 0.17 0.06
dm-1 0.00 0.00 0.01 0.00 0.07 0.00 8.00 0.00 0.13 0.13 0.00
dm-2 0.00 0.00 0.21 4.42 40.34 35.37 16.35 0.01 2.97 0.29 0.13
dm-3 0.00 0.00 0.45 0.08 74.92 0.60 143.86 0.00 3.34 0.10 0.01
dm-4 0.00 0.00 267.01 280.13 56234.29 5587.78 112.99 0.72 1.31 0.12 6.31
dm-5 0.00 0.00 0.08 0.13 4.07 1.05 24.09 0.00 0.42 0.17 0.00
dm-6 0.00 0.00 1.48 399.61 1269.71 3196.91 11.14 15.90 39.60 0.01 0.25
dm-7 0.00 0.00 0.09 474.21 1.01 5305.62 11.19 1.34 2.82 0.59 28.03
dm-8 0.00 0.00 3.17 474.22 2781.71 5305.63 16.94 1.35 2.83 0.59 28.31
dm-9 0.00 0.00 0.01 0.06 0.06 0.46 8.00 0.00 0.23 0.09 0.00
dm-10 0.00 0.00 0.30 59.80 11.97 478.41 8.16 0.32 5.27 0.01 0.03
dm-11 0.00 0.00 0.09 0.39 2.48 3.09 11.63 0.00 0.56 0.12 0.01
dm-12 0.00 0.00 0.01 0.06 0.07 0.46 8.00 0.00 0.39 0.14 0.00
dm-13 0.00 0.00 0.01 0.07 0.08 0.54 8.00 0.00 0.26 0.08 0.00
dm-14 0.00 0.00 0.01 0.07 0.07 0.53 8.00 0.00 0.26 0.08 0.00
But I'm not very sure how to check disk IO.
I ran iostat -x command. But I'm not sure which part I need to look in iostat output.
do we have any formula, to calculate the disk IO values. Upto what value, we can consider disk IO is normal.
If disk IO found high, what steps we need to take to improve the performance. (If at all no issues found in filesystem or disk).
For example, I have given the below output of iostat -x. Could someone guide me to learn about troubleshooting IO.
avg-cpu: %user %nice %system %iowait %steal %idle
1.61 0.14 0.65 5.32 0.00 92.28
Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util
sdb 28.26 905.20 244.46 783.11 60380.59 19881.09 78.11 1.03 1.00 0.60 61.21
sda 0.10 4.55 0.78 2.53 73.40 56.62 39.34 0.00 0.87 0.58 0.19
dm-0 0.00 0.00 0.64 2.59 31.99 20.71 16.33 0.04 11.72 0.17 0.06
dm-1 0.00 0.00 0.01 0.00 0.07 0.00 8.00 0.00 0.13 0.13 0.00
dm-2 0.00 0.00 0.21 4.42 40.34 35.37 16.35 0.01 2.97 0.29 0.13
dm-3 0.00 0.00 0.45 0.08 74.92 0.60 143.86 0.00 3.34 0.10 0.01
dm-4 0.00 0.00 267.01 280.13 56234.29 5587.78 112.99 0.72 1.31 0.12 6.31
dm-5 0.00 0.00 0.08 0.13 4.07 1.05 24.09 0.00 0.42 0.17 0.00
dm-6 0.00 0.00 1.48 399.61 1269.71 3196.91 11.14 15.90 39.60 0.01 0.25
dm-7 0.00 0.00 0.09 474.21 1.01 5305.62 11.19 1.34 2.82 0.59 28.03
dm-8 0.00 0.00 3.17 474.22 2781.71 5305.63 16.94 1.35 2.83 0.59 28.31
dm-9 0.00 0.00 0.01 0.06 0.06 0.46 8.00 0.00 0.23 0.09 0.00
dm-10 0.00 0.00 0.30 59.80 11.97 478.41 8.16 0.32 5.27 0.01 0.03
dm-11 0.00 0.00 0.09 0.39 2.48 3.09 11.63 0.00 0.56 0.12 0.01
dm-12 0.00 0.00 0.01 0.06 0.07 0.46 8.00 0.00 0.39 0.14 0.00
dm-13 0.00 0.00 0.01 0.07 0.08 0.54 8.00 0.00 0.26 0.08 0.00
dm-14 0.00 0.00 0.01 0.07 0.07 0.53 8.00 0.00 0.26 0.08 0.00