Routing Switch Direct Memory Access Cross-Node Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current server hardware systems face inefficiencies in cross-node memory and IO space access due to the need for proxy-mediated communication, leading to low efficiency and speed, which affects system performance in applications requiring high processing and memory capabilities.
Innovation Solution
A routing switch apparatus with direct memory access (DMA) modules and protocol conversion interfaces that enable direct, proxy-free communication between network nodes through a fast bus link, allowing for efficient data transmission and conversion of communication protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple processors are connected through a general network protocol with proxy-mediated communication, then system scalability and flexibility are improved, but access speed and efficiency of cross-node memory and IO space deteriorate
Solution Approach 1:
The patent introduces a routing switch as an intermediary device that enables direct peer-to-peer communication between network nodes. The routing switch includes protocol conversion interfaces that convert between network protocols (for external communication) and a fast bus protocol (for internal high-speed communication). This mediator architecture allows nodes to maintain scalability through standard network protocols while achieving high-speed direct access through the routing switch's fast bus link, resolving the contradiction between scalability and access speed.
2Adaptability or versatility
If proxy-mediated communication is used for cross-node access, then protocol compatibility and system flexibility are improved, but access delay and system performance deteriorate
Solution Approach 1:
The patent segments the communication path into two distinct parts: the external network interface using standard protocols for compatibility, and the internal fast bus link using a dedicated high-speed protocol for low-latency communication. The routing switch performs protocol conversion at its interfaces, separating the concerns of protocol compatibility (handled at the interface level) from speed optimization (handled at the internal bus level). This segmentation allows the system to maintain protocol compatibility while eliminating proxy-mediated delays through direct fast bus communication.
3Productivity
If direct memory access is implemented through fast bus link, then data transmission efficiency is improved, but device complexity increases
Solution Approach 1:
The routing switch is designed as a multi-functional device that simultaneously performs protocol conversion, routing, and direct memory access operations. The fast bus link is configured to support both general data transmission and direct memory access operations. By making the routing switch universal in its capabilities, the patent achieves high data transmission efficiency through direct access while consolidating multiple functions into a single device rather than adding separate complexity for each function.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to a routing switch apparatus, a network switch system, and a routing switch method. The routing switch apparatus includes one or more direct memory access modules and at least two protocol conversion interfaces. The direct memory access module is configured to generate a continuous access request of a cross network node, and control data transmission in the at least two protocol conversion interfaces; each protocol conversion interface is configured to convert a communication protocol of data transmitted inside and outside the routing switch apparatus and connect the routing switch module and an external network node. Therefore, in the present invention, the routing switch apparatus may be introduced to replace a network switch, so that cross-node memory access and IO space access can be performed directly rather than through a proxy, thereby reducing delay of the cross-node memory access and IO space access and improving overall performance of a system.