which field to monitor to gather total Aggr IOPS at OM?

[richardl]

Hi,

IHAC running lot of  NFS services to external client, where many of the IO belongs to nfs_other from  volume point of view.

THey are using OM to  monitor the system. 

They are asking  which fields at aggr. level (with OM) to monitor so that they can have a  historical view of how many IO in total require disk access. It is because if  they view from volume level the total IO involve nfs_read, nfs_write,  nfs_other... if they add this up it  doesn't equal to the total I/O  involve disk access (their understanding is nfs_read or nfs_other may actually  resolved in cache which doesn't request disk access).

Any input is highly appreciated!!

Thanks,

Richard

[amiller_1]

Are you using Performance Advisor? Comes free with OM and has lots of extra details around this kind of thing....

If you go into physical view and then look at the aggregate, there is a throughput in blocks/second....not exactly what you want but close.