How Flash Pools work

Flash Pools enable you to add one or more RAID groups composed of SSDs to an aggregate that is otherwise composed of HDDs. The SSDs function as a high-performance cache for the working data set, increasing the performance of the aggregate without incurring the expense of using SSDs for the entire aggregate.

You create a Flash Pool by enabling the feature on an existing 64-bit aggregate composed of HDDs, and then adding SSDs to that aggregate. This results in two tiers for that aggregate: an SSD tier and an HDD tier. After you add an SSD tier to an aggregate to create a Flash Pool, you cannot remove the SSD tier to convert the aggregate back to its original configuration.

The SSD tier and the HDD tier have the same RAID type (for example, RAID-DP) and the same maximum RAID group size. The tiers can have different checksum types.

The HDD RAID groups in Flash Pools behave the same as HDD RAID groups in standard aggregates, including the rules for mixing disk types, sizes, speeds, and checksums.

The SSD tier does not contribute to the size of the aggregate as calculated against the maximum aggregate size. For example, even if an aggregate is at the maximum aggregate size, you can add an SSD tier to it.

There is a platform-dependent maximum size for the SSD tier (cache). For information about this limit for your platform, see the Hardware Universe.

There are two types of caching used by Flash Pools: read caching and write caching.You can configure your read and write caching policies to ensure optimal performance by using the Data ONTAP Command Line Interface.