Probably because you need to divide by the average number of operations per second done in that time window.
I can't give you the specifics for windows_exporter, but I can for Linux node_exporter: https://brian-candler.medium.com/interpreting-prometheus-metrics-for-linux-disk-i-o-utilization-4db53dfedcfc The average latency for disk reads would be: rate(node_disk_read_time_seconds_total[20s]) / rate(node_disk_reads_completed_total[20s]) On Thursday 28 December 2023 at 13:53:51 UTC ضياء سامي wrote: > Hi > > I am trying to monitor Windows disk latency using windows_exporter. > I tested disk performance using two commands below : > C:\> diskspd.exe -c1G -d120 -b4K -o32 -t4 -w10 -L -D -Suw testfile.dat > PS C:\> Get-Counter -ComputerName win-node -Counter '\LogicalDisk(*)\Avg. > Disk sec/Read','\LogicalDisk(*)\Avg. Disk sec/Write' -SampleInterval 1 > > The output of both commands above shows average latency of 11 msec. > > While the prometheus query > "rate(windows_logical_disk_read_write_latency_seconds_total[20s])" prints > 125 > > Why windows_exporter showing different result ? > -- You received this message because you are subscribed to the Google Groups "Prometheus Users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/prometheus-users/a601b5dd-e0f0-4b90-aea6-4360bfa0386dn%40googlegroups.com.
