.svg)
This week I am staying on the DPU theme but addressing the typical CIO and CTO question “so what?”. Aside from network and storage performance, I believe the two most obvious use cases are Layer 3 to 7 network services and telemetry, which can be provided via a centralised controller.
The AMD DPUs provide traditional Layer 3 to 4 stateful firewalling, Layer 4 to 7 deep packet inspection, and application load balancing capabilities all at a port level within the smart switch. In the case of Cisco, this capability is currently available to the market at the same cost as a normal Top of Rack (ToR) switch. This enables the removal of expensive high-end firewalls, load balancers, and micro-segmentation solutions. In turn, this reduces complexity and cost, which both feed into a significantly reduced Total Cost of Ownership (TCO).
We should all be aware of the benefits of analytics and telemetry, so I won’t make the case for them here. The AMD DPUs will provide flow-based telemetry, stateful connection tracking and latency measurements. Having this information available directly from the DPU in the switch is invaluable operationally and adds benefits such as customer experience, security, and compliance, as well as contributing to a reduce TCO.
Finally, the AMD DPUs support a P4 data pipeline. For anyone unfamiliar with P4, put simply it allows the vendor to re-programme how the DPU handles packets. The significance is that innovations and new capabilities can be introduced far more rapidly. This provides customers with investment protection.