Greetings all!
We're running a nimble and NetApp SAN over iSCSI to 10 esxi 6.5 UCS hosts. Have a queue depth of 128 set on the iscsi HBAs. We're seeing a bunch of iSCSI aborts here and there, coupled with vmkernel latency. I know if i increase the Q depth to 256, the aborts will go down, but have concerns about high wait time and latency on vmkernel.. Any suggestions?
You can use the information in Using esxtop to identify storage performance issues for ESX / ESXi (multiple versions) (1008205) to see the difference in latency between the settings. Also check Performance Best Practices for VMware vSphere 6.5 for any possible configuration issues.
With the Nimble option I would suggest you raise a support call, you'll get an answer really quickly and will give you the comfort that it's a supported option