DAVG/cmd show high values for shorts periods. Is "normal"?

[JPReyes]

Hi,

   Reviewing performance the LUN's of storage with esxtop, observed with for short periods the DAVG/cmd value increases until 200 ms around. But this value not constant, generally remained between 10 and 15 ms.

   Is time of calling the Storage Group and raise a alert for this behavior or it may be considered "normal"?

   For my side, the HBA of ESX Server is firmware update and KAVG/cmd value is between 0.01 and 0.44 ms at most.

   Thanks for your help to clarify this question.

[Troy_Clavell]

I would confirm with your Enterprise Storage Team they are no seeing high latency on their side.  200ms is not so good.

• DAVG

This is the latency seen at the device driver level. It includes the roundtrip time between the HBA and the storage.

DAVG  is a good indicator of performance of the backend storage. If IO  latencies are suspected to be causing performance problems, DAVG should  be examined. Compare IO latencies with corresponding data from the  storage array. If they are close, check the array for misconfiguration  or faults. If not, compare DAVG with corresponding data from points in  between the array and the ESX Server, e.g., FC switches. If this  intermediate data also matches DAVG values, it is likely that the  storage is under-configured for the application. Adding disk spindles or  changing the RAID level may help in such cases.