Low Cost Multi-Server Array Using Exact-Match Packet Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current multi-server arrays face high costs due to the use of optical transceivers and complex SDN flow table packet switching, which increases manufacturing costs and power consumption.
Innovation Solution
The system employs a matrix of host server devices connected via non-optical metal conductor cables for short distances and optical cables for longer distances, using an exact-match packet switching integrated circuit (NFX) without TCAM or wildcard flow entries, controlled by a central controller to manage packet switching efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If optical transceivers and optical networking cables are used for all inter-server connections, then data communication reliability is improved, but system cost increases significantly
Solution Approach 1:
The patent applies different cable types based on distance requirements: non-optical metal conductor cables for short distances (≤7 meters) and optical cables for longer distances. This local differentiation allows the system to use cheaper copper cables where sufficient while reserving optical cables only where needed, reducing overall system cost while maintaining adequate communication reliability for each specific connection scenario.
2Adaptability or versatility
If TCAM and wildcard flow entries are used for packet switching, then packet routing flexibility is improved, but device complexity and power consumption increase
Solution Approach 1:
The patent extracts and removes the TCAM component and wildcard flow entry functionality from the packet switching architecture. By eliminating these complex elements, the system achieves simpler device implementation and lower power consumption while maintaining adequate packet routing flexibility through alternative mechanisms that do not require TCAM's specialized content-addressable memory structure.
Solution Approach 2:
The patent replaces expensive, complex TCAM hardware with simpler, more economical packet switching mechanisms. The system uses standard memory structures and processing approaches that are cheaper and less complex than TCAM, achieving the necessary packet routing functionality without the high cost and complexity of wildcard flow table implementations.
3Adaptability or versatility
If TCAM and wildcard flow table are used for packet switching, then packet routing versatility is improved, but power consumption increases
Solution Approach 1:
The patent extracts and removes the power-consuming TCAM component and wildcard flow entry processing from the system. By eliminating these energy-intensive elements, the patent achieves significant power consumption reduction while maintaining packet routing versatility through alternative, more energy-efficient mechanisms that do not rely on TCAM's continuous power requirements.
Data Source
AI summary
An array of columns and rows of host server devices is mounted in a row of racks. Each device has a host processor and an exact-match packet switching integrated circuit. Packets are switched within the system using exact-match flow tables that are provisioned by a central controller. Each device is coupled by a first cable to a device to its left, by a second cable to a device to its right, by a third cable to a device above, and by a fourth cable to a device below. In one example, substantially all cables that are one meter or less in length are non-optical cables, whereas substantially all cables that are seven meters or more in length are optical cables. Advantageously, each device of a majority of the devices has four and only four cable ports, and connects only to non-optical cables, and the connections involve no optical transceiver.