Multi-Port Client Server Connection for Remote Desktop Latency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In remote computing systems, the repetitive traversal of data between host partitions and virtual machines leads to significant consumption of memory and CPU resources, increasing data delivery latency to clients, especially in graphics processing.
Innovation Solution
A system where a client initiates connections with a compute server and a graphics server, allowing the compute server to process user input and send processed data to the graphics server, which then directly transmits graphics output to the client, eliminating the need for data to return to the compute server and reducing redundant data traversal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data traverses repeatedly between host partition and virtual machine for processing, then authentication and resource management are maintained, but memory and CPU resources are significantly consumed and data delivery latency increases
Solution Approach 1:
The patent extracts the graphics processing function from the virtual machine and places it in a dedicated graphics processing unit (GPU) or separate processing component. This allows graphics data to be processed directly at the GPU without requiring repeated traversal to and from the virtual machine, reducing latency while maintaining system management through the host partition's coordination of resource allocation.
Solution Approach 2:
The patent introduces an intermediary component (such as a virtualization layer or gateway) that facilitates direct communication between the virtual machine and graphics processing resources. This intermediary enables authenticated data flow without requiring the virtual machine to directly traverse through the host partition for each processing operation, thus maintaining security while reducing latency.
2Reliability
If data traverses repeatedly between host partition and virtual machine, then proper data processing and authentication are ensured, but CPU and memory resources are consumed intensively
Solution Approach 1:
The patent extracts intensive graphics processing operations from the general-purpose CPU in the virtual machine and executes them on dedicated graphics processing hardware. This separation reduces CPU cycle consumption and memory bandwidth usage in the virtualized environment, allowing the host partition to allocate resources more efficiently while maintaining authentication and processing integrity.
Solution Approach 2:
The patent creates a virtual representation or copy of the graphics processing interface that resides in the virtual machine's address space, allowing the virtual machine to interact with graphics resources through a simplified interface without requiring physical data traversal to the host partition for each operation. This reduces the overhead on CPU and memory resources while maintaining proper authentication through the virtualization layer.
3Device complexity
If traditional VDI architecture is used with host partition managing all data flow, then centralized control is maintained, but data delivery latency to clients increases
Solution Approach 1:
The patent segments the data flow path into two independent channels: control plane traffic (authentication, resource management) continues to flow through the host partition, while data plane traffic (graphics data, user input) flows directly between the virtual machine and graphics processing resources. This segmentation maintains centralized control for security while enabling high-speed direct data delivery.
Solution Approach 2:
The patent adds a new dimension to the data flow architecture by introducing direct peer-to-peer communication paths between virtual machines and graphics resources, bypassing the traditional hierarchical route through the host partition. This dimensional change in the data flow topology reduces the number of hops and latency while preserving the host's centralized management capabilities for non-data traffic.
Data Source
AI summary
Methods, systems, and computer readable media are disclosed for creating a multi-port client server connection in a remote desktop environment. In an embodiment, the multi-client server connection can decouple client-server connection and client-server input from graphics delivery from the server to the client. Such embodiment provides higher server performance and enables dynamic server resource management. The multi-client server connection can be implemented in a virtual environment or between physical machines where one set of physical machines receives the graphics requests from the client and another set of physical machines generates and transmits display data to the client.