Just interested to see what others are doing in regards to implementing QOS limits within NetApp and a virtualization stack such as VMware.
Implementing QOS iops limit on a NetApp volume that happens to be a VMware datastore will create an iops ceiling, however if this datastore consists of 10 vm's, it only takes 1 VM to consume all iops before all other 9 vm's suffer. This option also allows for adaptive QOS, so as you expand the volume the QOS expands with it.
However implementing an iops limit within vSphere - Virtual Machine - on the individual disk, is way more granular and will prevent the issue of iops blowing out on the volume QOS cap, although you can easily overprovision iops vs the max iops available in the NetApp system. This method would also use some sort of automation to go through each individual disk and check that the correct iops limit has been implemented based on the storage tier the vm disk is sitting on. If a change of vm disk storage tier occurs the automation script or tool would then adjust the iops limit of the disk.
Is this something that alot of others are using, do you do it differently ?