Breaking the Ten Millions IOps Barrier for RAID

webinar

Author(s)/Presenter(s):

Sergei Platonov

Library Content Type

Presentation

Library Release Date

Focus Areas

Abstract

Modern NVMe drives allow us to get dozens of millions of IOps in a single system. However, the current RAIDs and volume management software based on parities (aka RAID5 and beyond) limit total performance to two million IOps for reading and 0.2 million for writing. We redevelop the RAID engine for Linux using extreme parallelization of IO handling on the basis of a lock-less approach and met 10 million barrier for read and write operations. To break the barrier, we moved to the new Linux kernel that supports polling modes for NVMe drives and io_uring interface.

Learning Objectives

To demonstrate the performance impact of new io_uring interface on the storage system providing >10M IOPs,To show how polling mode for linux kernel name drives influences on overall system productivity,To demonstrate advantages of using modern algorithms and approaches in storage systems development