RHEL IO Monitoring

Community post

Shared by the Applicare community. It has not been re-checked against Applicare 10.0, so confirm the steps in your environment or contact Support.

Commands for IO performance counters

rrqm/s: the number of read requests merged per second that were queued to the device

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 2

wrqm/s: the number of write requests merged per second that were queued to the device

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 3

r/s: the number (after merges) of read requests completed per second for the device

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 4

w/s: the number (after merges) of write requests completed per second for the device
iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 5

rsec/s (rkB/s, rMB/s): the number of sectors (kilobytes or megabytes) read from the device per second

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 6

wsec/s (wkB/s, wMB/s): the number of sectors (kilobytes or megabytes) written to the device per second

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 7

avgrq-sz: the average size (in sectors) of the requests that were issued to the device

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 8

avgqu-sz: the average queue length of the requests that were issued to the device

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 9

await: the average time (in milliseconds) for I/O requests issued to the device to be served. This includes the time spent by the requests in queue and the time spent servicing them

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 10

svctm: the average service time (in milliseconds) for I/O requests that were issued to the device. Warning! Do not continue to rely upon this field, as it will be removed in a future sysstat version

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 11

%util: percentage of elapsed time during which I/O requests were issued to the device (bandwidth utilization for the device). Device saturation occurs when this value is close to 100% for devices serving requests serially. But for devices serving requests in parallel, such as RAID arrays and modern SSDs, this number does not reflect their performance limits

iostat -x |grep "sda " | tr -s ' ' | cut -d ' ' -f 12

Join the discussion

Comments, voting and following are kept by Zendesk and need a Help Center account. This button opens the original discussion there.

Opens Zendesk · needs internet and sign-in

Still stuck? Contact support