If you are designing a configuration for a large SAN, you must estimate the queue depth for each node in order to avoid application failures.
The queue depth is the number of I/O operations that can be run in parallel on a device.
If a SAN Volume Controller node reaches the maximum number of queued commands, many operating systems cannot recover if the situation persists for more than 15 seconds. This can result in one or more servers presenting errors to applications and application failures on the servers.
A large SAN is one in which the total number of VDisk-to-host mappings is at least 1 000. For example, 50 servers with each server addressing 20 VDisks.