IBM Easy Tier

Easy Tier® is an optional feature that is provided at no cost. It can greatly increase the performance of your system by ensuring frequently accessed data is put on faster storage. Its capabilities include manual provisioned capacity rebalance, auto performance rebalancing in both single-tier and multiple-tier pools, hot spot management, rank depopulation, manual volume migration, and thin provisioning support (ESE volumes only). Easy Tier determines the appropriate tier of storage that is based on data access requirements and then automatically and non-disruptively moves data, at the subvolume or sub-LUN level, to the appropriate tier in the storage system.

Use Easy Tier to dynamically move your data to the appropriate drive tier in your storage system with its automatic performance monitoring algorithms. You can use this feature to increase the efficiency of your flash drives and the efficiency of all the tiers in your storage system.

You can use the features of Easy Tier between three tiers of storage within a DS8900F.

Easy Tier features help you to effectively manage your system health, storage performance, and storage capacity automatically. Easy Tier uses system configuration and workload analysis with warm demotion to achieve effective overall system health. Simultaneously, data promotion and auto-rebalancing address performance while cold demotion works to address capacity.

Easy Tier data in memory persists in local storage or storage in the peer server, ensuring the Easy Tier configurations are available at failover, cold start, or Easy Tier restart.

With Easy Tier Application, you can also assign logical volumes to a specific tier. This feature can be useful when certain data is accessed infrequently, but needs to always be highly available.

Easy Tier Application is enhanced by two related functions:
  • Easy Tier Application for IBM® Z provides comprehensive data-placement management policy support from application to storage.
  • Easy Tier application controls over workload learning and data migration provides a granular pool-level and volume-level Easy Tier control as well as volume-level tier assignment where a volume can be assigned to a tier.

The Easy Tier Heat Map Transfer utility replicates Easy Tier primary storage workload learning results to secondary storage sites, synchronizing performance characteristics across all storage systems. In the event of data recovery, storage system performance is not sacrificed.

Easy Tier helps manage thin provisioned volumes. If the initial allocation of new extents is set to the highest performance tier in the pool, as thin provisioned volumes grow, Easy Tier automatically detects if the data placed in these new extents should remain in the higher performance tier, or if they should be demoted to a capacity tier.

An additional feature provides the capability for you to use Easy Tier manual processing for thin provisioning. Rank depopulation is supported on ranks with ESE volumes allocated (extent space-efficient) or auxiliary volumes.

Use the capabilities of Easy Tier to support:
Drive classes
The following drive classes are available, in order from highest to lowest performance. A pool can contain up to three drive classes.
Flash Tier 0 drives
The highest performance drives, which provide high I/O throughput and low latency.
Flash Tier 1 drives
The first tier of high capacity drives.
Flash Tier 2 drives
The second tier of high capacity drives.
Three tiers
Using three tiers (each representing a separate drive class) and efficient algorithms improves system performance and cost effectiveness.

You can select from four drive classes to create up to three tiers. The drives within a tier must be single-tier.

The following table lists the possible tier assignments for the drive classes. The tiers are listed according to the following values:
Hot data tier, which contain the most active data. This tier can also serve as the home tier for new data allocations.
Mid-data tier, which can be combined with one or both of the other tiers and will contain data not moved to either of these tiers. This is by default the home tier for new data allocations.
Cold data tier, which contains the least active data.
Table 1. Drive class combinations and tiers for systems with Flash Tier 0 drives as the highest performance drive class
Drive classes Drive class combinations
Flash Tier 0 Flash Tier 0 + Flash Tier 1 Flash Tier 0 + Flash Tier 2 Flash Tier 0 + Flash Tier 1 + Flash Tier 2
Flash Tier 0 0 0 0 0
Flash Tier 1   1   1
Flash Tier 2     1 2
Table 2. Drive class combinations and tiers for systems with Flash Tier 1 drives as the highest performance drive class
Drive classes Drive class combinations
Flash Tier 1 Flash Tier 1 + Flash Tier 2
Flash Tier 1 0 0
Flash Tier 2   1
Cold demotion
Cold data (or extents) stored on a higher-performance tier is demoted to a more appropriate tier. Cold demotion will occur with both two-tier and three-tier pools. Sequential bandwidth is moved to the lower tier to increase the efficient use of your tiers.
Warm demotion
Active data that has larger bandwidth is demoted to the next lowest tier. Warm demotion is triggered whenever the higher tier is over its bandwidth capacity. Selected warm extents are demoted to allow the higher tier to operate at its optimal load. Warm demotes do not follow a predetermined schedule.
Warm promotion
Active data that has higher IOPS is promoted to the next highest tier. Warm promotion is triggered whenever the lower tier is over its IOPS capacity. Selected warm extents are promoted to allow the lower tier to operate at its optimal load. Warm promotes do not follow a predetermined schedule.
Manual volume or pool rebalance
Volume rebalancing relocates the smallest number of extents of a volume and restripes those extents on all available ranks of the extent pool.
Automatically balances the workload of the same storage tier to improve system performance and resource use. Auto-rebalncing will occur in both single-tier and multiple-tier pools.
Rank depopulations
Allows ranks that have extents (data) allocated to them to be unassigned from an extent pool by using extent migration to move extents from the specified ranks to other ranks within the pool.

Easy Tier provides a performance monitoring capability, regardless of whether the Easy Tier feature is activated. Easy Tier uses the monitoring process to determine what data to move and when to move it when you use automatic mode. You can enable monitoring independently (with or without the Easy Tier feature activated) for information about the behavior and benefits that can be expected if automatic mode were enabled.

Data from the monitoring process is included in a summary report that you can download to your local system.