offers several modes of operation to optimize the placement of data on flash drives and on HDDs in a storage pool. The system supports flash drives, which offer a number of potential benefits over magnetic hard disk drives (HDDs). The benefits can include faster data access and throughput, better performance, and less power consumption.
Determining the amount of data activity in an extent and when to move the extent to the proper storage tier is usually too complex a task to manage manually.
evaluation mode collects usage statistics for each storage extent for a storage pool where the capability of moving data from one tier to the other tier is not possible or is disabled. An example of such a storage pool is a pool of homogeneous MDisks, where all MDisks are typically HDDs. A summary file is created in the /dumps directory on the configuration node (dpa_heat.node_name.date.time.data), which can be offloaded and viewed by using the IBM Storage Tier Advisor Tool.
automatic data placement also measures the amount of data access. then acts on the measurements to automatically place the data into the appropriate tier of a storage pool that contains both MDisk tiers.
Dynamic data movement is not apparent to the host server and application users of the data, other than providing improved performance.
Volumes that are added to storage pools use extents from every type of MDisk initially. By default, the extents that are used are from the Enterprise tier, but Nearline and Flash tiers can also be used. then collects usage statistics to determine which extents to move to the MDisks.