Installation guide

188
EMC Host Connectivity with QLogic Fibre Channel HBAs and CNAs in the Windows Environment
Troubleshooting
Understanding queue depth
Each port on EMC storage arrays has a maximum queue depth. The
performance implications in a large fabric environment with many
HBAs (initiators) generating I/Os is that a storage port's queue can
quickly fill up to the maximum. When this happens, the HBA will be
notified by the array with queue full (QFULL) messages and result in
very poor response times. Various operating systems deal with queue
full differently.
Windows operating systems with STORPort drivers will throttle I/Os
down to a minimum in an attempt to prevent filling the queue. When
the queue full messages subside, STORPort will increase the queue
depth again. This could take up to around a minute in some
instances, depending on the load. The performance of the server's
applications will be impacted, sometimes to the point of hanging or
crashing if it happens repeatedly or for a prolonged amount of time.
In order to avoid overloading the storage array's ports, you can
calculate the maximum queue depth using a combination of the
number of initiators per storage port and the number of LUNs ESX
uses. Other initiators are likely to be sharing the same SP ports, so
these will also need to have their queue depths limited. The math to
calculate the maximum queue depth is:
QD = Maximum Port Queue Length / (Initiators * LUNs)
For example, there are 4 servers with single HBA ports connected to a
single port on the storage array, with 5 LUNs masked to each server.
The storage port's maximum queue length is 1600 outstanding
commands. This leads to the following queue depth calculation:
HBA Queue Depth = 1600 / (4 * 20)
In this example, the calculated HBA queue depth would be 20. A
certain amount of over-subscription can be tolerated because all
LUNs assigned to the servers are unlikely to be busy at the same
time, especially if additional HBA ports and load balancing software
is used. So in the example above, a queue depth of 32 should not
cause queue full. However, a queue depth value of 256 or higher
could cause performance issues.
Using this example, it is easy to extrapolate the potential performance
implications of large server environments with large numbers of
servers and initiators. This includes virtualized environments like
Hyper-V that use synthetic/virtual Fibre Channel adapters and NPIV