Allocation assistance

Tape library performance can be increased by using allocation assistance to identify the subset of available clusters best suited for a given allocation (mount) request.

Device allocation assistance

Device allocation assistance (DAA) is a function that allows the host to query the TS7700 to determine which clusters should be preferred for a private (specific) mount request. When enabled, DAA returns to the host a ranked list of clusters (the preferred cluster is listed first) that determines for a specific VOLSER which cluster is best to use for device allocation.

DAA is enabled by default. DAA can be disabled by using the following LIBRARY REQUEST command.

LIBRARY REQUEST,library-name,SETTING,DEVALLOC,PRIVATE,[ENABLE|DISABLE]
where library-name = composite-library-name

The selection algorithm orders the clusters first by those having the volume already in cache, then by those having a valid copy on tape, and then by those without a valid copy. If the mount is directed to a cluster without a valid copy, then a remote mount is the result. Thus, in special cases, even if DAA is enabled remote mounts and recalls can still occur.

Scratch allocation assistance

Scratch allocation assistance (SAA) is an extension of the DAA function for scratch mount requests. SAA filters the list of clusters in a grid to return to the host a smaller list of candidate clusters specifically designated as scratch mount candidates. By identifying a subset of clusters in the grid as sole candidates for scratch mounts, SAA optimizes scratch mounts to a TS7700 Grid.

A cluster is designated as a candidate for scratch mounts using the Scratch Mount Candidate option on the management class construct, accessible from the TS7700 Management Interface (refer to the Management Classes topic in the Related information section for additional information about the management class construct). Only those clusters specified through the assigned management class are considered for the scratch mount request. When queried by the host preparing to issue a scratch mount, the TS7700 considers the candidate list associated with the management class, along with cluster availability. The TS7700 then returns to the host a filtered, but unordered, list of candidate clusters suitable for the scratch mount operation. The z/OS® allocation process then randomly chooses a device from among those candidate clusters to receive the scratch mount. If all candidate clusters are unavailable or in service, all clusters within the grid become candidates. In addition, if the filtered list returns clusters that have no devices that are configured within z/OS, all clusters in the grid become candidates.

Before SAA is visible or operational, all of the following must be true:

SAA is enabled with the host Library Request command by using the following LIBRARY REQUEST command:
```
LIBRARY REQUEST,library-name,SETTING,DEVALLOC,SCRATCH,[ENABLE|DISABLE]
where library-name = composite-library-name
```
Disabled is the default setting.
An adequate number of devices connected to the scratch mount candidate clusters are online at the host.
Note: If the clusters are online, but too few or no devices are online at the host, jobs that use SAA can go into allocation recovery. In allocation recovery, the existing MVS™ allocation options for device allocation recovery (WTOR|WAITHOLD|WAITNOH|CANCEL) are used. If all or many devices associated with the candidate clusters need to be taken offline, as when servicing a cluster, then SAA should first be disabled by using the host Library Request command. Thus, other clusters in the grid can be used for SAA during the outage. Alternatively, you can extend the list of candidate clusters to include clusters that have devices remaining online at the host during the outage. Use the management class construct to extend the list of candidate clusters.