Optimizing NVMe-oF Performance with Different Ethernet Transports: Host Factors
Fred Zhang, Intel; Eden Kim, Calypso Systems; David Woolf, UNH-IOL; Tom Friend, Illuminosi
About this talk
NVMe over Fabrics technology is gaining momentum and getting more tractions in data centers, but there are three kinds of Ethernet based NVMe over Fabrics transports: iWARP, RoCEv2 and TCP. How do we optimize NVMe over Fabrics performance with different Ethernet transports?
Setting aside the consideration of network infrastructure, scalability, security requirement and complete solution stack, this webcast will explore the performance of different Ethernet-based transport for NVMe over Fabrics at micro benchmark level. We will show three key performance indicators: IOPs, Throughput, and Latency with different workloads including: Sequential Read/Write, Random Read/Write, 70%Read/30%Write, with different data size. We will compare the result of three Ethernet based transports: iWARP, RoCEv2 and TCP.
Further, we will dig a little bit deeper to talk about the variables that will impact the performance of different Ethernet transports. There are a lot of variables that you can tune but these variables will impact the performance of each transport to different extents. We will cover the variables:
1.How many CPU cores are needed (I’m willing to give)?
2.Optane SSD or 3D NAND SSD?
3.How deep should the Q-Depth be?
4.Why do I need to care about MTU?
This discussion won’t tell you which transport is the best. Instead we unfold the performance of each transport and tell you what it would take for each transport to get the best performance, so that you can make the best choice for your transport for NVMe over Fabrics solutions.
After you watch the presentation, check out the Q&A blog: https://bit.ly/36A44AU
You've got data. It's time to manage it. Find information here on everything from data governance and data quality, to master and metadata management, data architecture, and the thing that was just invented ten seconds ago.…