I have a Netware 6.5 SP7 server which boots from a Compellent SAN. It has 4 volumes. It has 2 QLogic HBAs. When I introduce new (windows) servers on the SAN, NSS deactivates volumes on my Netware server. This has been suggested to be an issue with the various QLogic HBAs known as Execution Throttle.

The following comes from QLogic's website:

"The HBA Execution Throttle is set to 16 by default. This setting specifies the maximum number of outstanding commands that can execute on any one target port. When a target ports Execution Throttle is reached, the system will not issue any new commands until one of the current commands finishes executing. To increase the number of outstanding commands to the target port, increase the Execution Throttle.
WARNING: Increasing the Execution Throttle may cause SCSI timeouts."

What I'm trying to determine is if too high a Execution Throttle setting on these newly introduced servers is monopolizing the target port and causing these SCSI timeouts.

Would a SCSI timeout manifest itself in an immediate volume deactivation?
An example of what happens when I power on a new server that uses the same target port is the following:

" CPQSHD: The COMPELNT Compellent Vol 50000D3100058D04 (0303)
disk device returned a non-supported SCSI status of 08h on
a completing I/O request. This device will be deactivated.

4-30-2008 12:21:59 pm: SERVER-5.70-2187"

When I power down the new server and I can rescan the devices/lun and it comes back up. I am going to try to lower the Execution Throttle on these newly introduced servers, but does this sound reasonable as to what could be happening?

Any advice/theories appreicated....Aaron