Kioxia Demonstrates RAID Offload Scheme for NVMe Drives

At FMS 2024, Kioxia had a proof-of-concept demonstration of their proposed a brand new RAID offload methodology for enterprise SSDs. The impetus for that is fairly clear: as SSDs get quicker in every technology, RAID arrays have a significant downside of sustaining (and scaling up) efficiency. Even in instances the place the RAID operations are dealt with by a devoted RAID card, a easy write request in, say, a RAID 5 array would contain two reads and two writes to completely different drives. In instances the place there is no such thing as a {hardware} acceleration, the info from the reads must journey all the best way again to the CPU and fundamental reminiscence for additional processing earlier than the writes could be finished.

Kioxia has proposed the usage of the PCIe direct reminiscence entry characteristic together with the SSD controller’s controller reminiscence buffer (CMB) to keep away from the motion of knowledge as much as the CPU and again. The required parity computation is completed by an accelerator block resident throughout the SSD controller.

In Kioxia’s PoC implementation, the DMA engine can entry your complete host deal with area (together with the peer SSD’s BAR-mapped CMB), permitting it to obtain and switch information as required from neighboring SSDs on the bus. Kioxia famous that their offload PoC noticed near 50% discount in CPU utilization and upwards of 90% discount in system DRAM utilization in comparison with software program RAID finished on the CPU. The proposed offload scheme may deal with scrubbing operations with out taking over the host CPU cycles for the parity computation process.

Kioxia has already taken steps to contribute these options to the NVM Specific working group. If accepted, the proposed offload scheme might be a part of an ordinary that might turn out to be extensively out there throughout a number of SSD distributors.