NetApp : RAID-DP

RAID-DP implements double parity within RAID 6. The performance penalty of RAID-DP is typically under 2% vs a comparable RAID 4. File system requests are first written to the battery–backed NVRAM to prevent data loss should the system lose power. Blocks are not updated in place. Writes are aggregated and the storage controller tries to write only complete stripes including both parity blocks. RAID-DP provides better protection and equal or better performance than RAID 10, and in most cases doesn't suffer from traditional RAID 6 challenges of in-place block updating and spreads reads and writes over more disks when compared to a RAID 6 group of same size.

Now part of RAID 6, double parity, sometimes known as row diagonal parity, like traditional RAID 6, features two sets of parity checks. Differently, the second set is not another set of points in the over-defined polynomial which characterizes the data. Rather, double parity calculates the extra parity against a different group of blocks. For example, in our graph both RAID 5 and RAID 6 consider all A-labeled blocks to produce one or more parity blocks. However, it is fairly easy to calculate parity against multiple groups of blocks, one can calculate all A blocks and a permuted group of blocks.