Achieving Scalable High Performance for NVMe/FC

Author(s)/Presenter(s):
Library Content Type:
Publish Date: 
Thursday, September 26, 2019
Event Name: 
Event Track:
Focus Areas:
Abstract: 

Discuss the challenges of achieving scalable 5M+ IOPS on Storage with ultra low latency (~10uSec Round Trip). New workloads and Storage Class Memory (SCM) are demanding a new level of IOPs, bandwidth, and driver optimizations in Linux for storage networks. Discuss per-core WQs, hardware parallelization, interrupt handling, and shared resource management that are needed to achieve very high performance.

Watch video: