Accelerating Near Real-time Analytics with High Performance Object Storage

Time: Wed Sep 14 | 3:35pm - 4:25pm


Computational storage in general can bring unique benefits in increasing the efficiency of CPU utilization in a data processing system. In this presentation we discuss the benefits of leveraging computational storage for offloading compute intensive tasks of object storage applications in a disaggregated storage environment. We demonstrate the ability of the solution to complement the CPU by taking away tasks that benefit from in-situ processing within the storage, thereby improving the overall system performance while lowering the TCO. This model has additional benefits of reducing data movement, resulting in better network utilization and decreased latency for supporting data analytics. Disaggregated storage is particularly attractive when using computational storage since scaling storage naturally yields to scaling of tasks that can be accelerated. We discuss results from our experimentation accelerating the S3 Select functionality and other use cases, using our High Performance Object Storage (HPOS) platform.

Download Presentation

Related Sessions