Hello there,
In vSAN the counter "Outstanding I/O", which is well explained in this great paper :
"In general terms, outstanding I/O is a measurement of I/O that is pending to be processed in a given queue. There are a number of queues throughout any storage stack, including at the VM, the hypervisor (internal vSAN queues and other ESXi queues) at the storage controller, within the cache tier, and at the physical disk. The maximum depths of these queues may vary."
Is it possible to identify which queue is the one where the I/O are the most stuck ?
I mean, if I look OIO number outside the VM (vcenter numbers), I can safely assume the queues inside the guests are out of the equation.
But now, how to identify which device is slowing the whole path ? Could be at the vSAN internal queues, network adapters queues, whatever...
Is it possible to "break" outstanding IO per device in the chain from the VM to the disks ?
