Striping volume selection

Striping volume selection is entered only in the following situations:

During initial allocation:
If the data class specifies an extended format as either 'required' or 'preferred' and the SDR value in the storage class is nonzero. If the SDR value is zero, a nonstriped data set in extended format is allocated, and conventional volume selection is used.
Tip: A nonstriped data set in extended format may refer to a single-striped data set.
During restore/recall processing:
If the data set was a multistripe data set when it was migrated or backed-up. If the data set was single-striped when migrated or backed-up, it follows the conventional volume selection path.

Striping volume selection is very similar to conventional volume selection. Volumes that are eligible for selection are classified as primary and secondary, and assigned a volume preference weight, based on preference attributes. See Table 1 for more information on preference attributes.

Volumes are classified as follows:

Primary: For each controller, SMS randomly assigns a single volume that meets all of the requested preference attributes as the primary volume.
Secondary: For each controller, SMS classifies all eligible volumes other than the primary volume as secondary volumes.

SMS calculates the average preference weight of each storage group using the preference weights of the volumes that will be selected if the storage group is selected for allocation. Then, SMS selects the storage group that contains at least as many primary volumes as the stripe count and has the highest average weight. If there are no storage groups that meet these criteria, the storage group with the largest number of primary volumes is selected. If multiple storage groups have the largest number of primary volumes, the one with the highest average weight is selected. If there are still multiple storage groups that meet the selection criteria, SMS selects one at random.

After selecting a storage group, SMS selects volumes by their preference weight. Primary volumes are preferred over secondary volumes as they have a higher preference weight. Secondary volumes are selected when there are an insufficient number of primary volumes. If there are multiple volumes with the same preference weight, SMS selects one of the volumes at random.

Volumes that meet the requested MSR are preferred over volumes that do not meet the requested performance. A volume is considered to meet the requested performance if the volume's performance is within a predetermined range of the requested MSR.

The throughput of striped data sets is gated by the slowest device if the striped set includes devices of varying data delivery capabilities.

When allocating striped data sets, SMS prefers allocating stripes across extent pools. If this is not feasible, SMS allocates stripes across logical controllers (LCUs). When extending a stripe of a striped data set to a new volume, SMS prefers volumes in the extent pools that are not being used by other active stripes.