Cross-Network Bridging for Disaggregated Server Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud computing systems face challenges in efficiently disaggregating remote server resources over communication networks, limiting flexibility and scalability in handling diverse computing demands from multiple users.
Innovation Solution
A cross-network bridging apparatus and method that translates system-bus transactions into network packets for transmission between local devices and remote processors, using bridging circuitry to manage Queue Pairs and maintain work-queue elements, enabling efficient device disaggregation with low CPU overhead and good response time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If device disaggregation is implemented to flexibly allocate server resources to multiple remote clients, then resource allocation flexibility and scalability are improved, but system complexity and network overhead increase
Solution Approach 1:
The patent segments the server system into local components (system bus, local devices) and remote components (remote processors across the network), connected through a bridging apparatus. This segmentation allows independent optimization of each component while maintaining flexible resource allocation, resolving the contradiction between adaptability and complexity by organizing the disaggregated system into manageable modular units.
Solution Approach 2:
The bridging apparatus acts as an intermediary between the local system bus and remote processors across the network. It translates system-bus transactions into network packets and manages Queue Pairs, serving as a mediator that simplifies the complexity of direct network communication while enabling flexible resource allocation to multiple remote clients.
2Adaptability or versatility
If system-bus transactions are translated into network packets for remote transmission, then resource accessibility across networks is improved, but translation overhead and processing time increase
Solution Approach 1:
The bridging apparatus performs preliminary actions by pre-configuring Queue Pairs and maintaining work-queue elements that map system-bus transactions to network packets. This preliminary setup allows for efficient translation without repeated complex processing, reducing translation overhead while maintaining broad resource accessibility across networks.
Solution Approach 2:
The patent creates a copy of the system-bus transaction protocol in the network layer through work-queue elements that mirror transaction structures. This copying approach allows efficient translation by reusing established protocol patterns rather than implementing complex real-time conversion, reducing processing time while enabling remote resource access.
3Adaptability or versatility
If multiple Queue Pairs are maintained for different local system bus devices, then device connection versatility is improved, but memory requirements and management complexity increase
Solution Approach 1:
The bridging apparatus implements a universal Queue Pair management structure where each Queue Pair can serve multiple local system bus devices through a standardized interface. This multi-functional design allows the same memory management mechanisms to handle diverse device connections, increasing versatility while controlling memory requirements through resource sharing.
Data Source
AI summary
A cross-network bridging apparatus includes a bus interface and bridging circuitry. The bus interface is configured for connecting to a system bus. The bridging circuitry is configured to translate between (i) system-bus transactions that are exchanged between one or more local devices that are coupled to the system bus and served by the system bus and one or more remote processors located across a network from the apparatus, and (ii) data units that convey the system-bus transactions, for transmitting and receiving as network packets over the network to and from the remote processors.