Elastic Compute Resource Management Between Web Server and On-Demand Environment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current on-demand computing environments face challenges in efficiently and flexibly utilizing additional resources to handle workload peaks, due to inflexibility in hardware and resource manager compatibility, leading to delays and unnecessary costs for users.
Innovation Solution
The system enables the creation of a virtual private cluster within an on-demand compute environment, allowing for dynamic provisioning of resources and transparent workload transfer from a local environment, using a workload manager to detect events and automatically provision resources based on demand, ensuring seamless scalability and cost-effectiveness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If on-demand centers require participating parties to align to certain hardware, operating systems or resource manager environments, then resource compatibility and reliability are improved, but device complexity and ease of operation deteriorate
Solution Approach 1:
The patent introduces a gateway as an intermediary component that sits between the user's local environment and the on-demand compute environment. This gateway handles protocol translation, authentication, and resource provisioning, allowing users to access on-demand resources without modifying their local hardware or software infrastructure. The gateway mediates the interaction between heterogeneous environments, maintaining compatibility while simplifying user operations.
2Reliability
If on-demand centers require participating parties to align to certain hardware, operating systems or resource manager environments, then resource compatibility is improved, but ease of operation deteriorates
Solution Approach 1:
The system implements self-service capabilities where users can dynamically provision and manage their own compute resources through the gateway interface. Users can submit job descriptions, select from available resource templates, and automatically receive allocated resources without requiring manual infrastructure configuration or alignment with specific on-demand center environments. This self-service model eliminates the burden of making infrastructure changes while maintaining resource compatibility.
3Productivity
If resources are provisioned in advance to handle peak loads, then productivity is improved, but loss of substance deteriorates due to unwanted charges
Solution Approach 1:
The patent implements dynamic resource provisioning where compute resources are allocated based on real-time demand rather than static pre-provisioning. The gateway monitors workload conditions and automatically provisions additional resources when peak loads are detected, then deallocates them when demand subsides. This dynamic approach allows the system to handle peak loads effectively while charging users only for the resources actually consumed, eliminating unwanted charges for idle pre-provisioned capacity.
4Reliability
If hardware alignment is required with on-demand centers, then reliability is improved, but adaptability deteriorates
Solution Approach 1:
The gateway is designed as a universal interface that can translate between multiple different hardware architectures, operating systems, and resource manager environments. Instead of requiring users to align their local environments with specific on-demand center requirements, the gateway provides multi-functional adaptation layers that handle compatibility translations. This allows the system to maintain reliable resource execution while supporting diverse and flexible user environments.
Data Source
AI summary
Disclosed are systems, methods and non-transitory computer-readable storage media for managing resources between a web server and an on-demand compute environment. A system configured to practice the method receives, at the on-demand compute environment, an indication that web traffic directed to a web server should at least be partially served via the on-demand compute environment, provisions compute resources within the on-demand compute environment to respond to web traffic for the web server based on the indication to yield a provisioned on-demand compute environment. The system serves web traffic at the provisioned on-demand compute environment based on an established routing of the web traffic from the web server to the provisioned on-demand compute environment such that the use of the provisioned on-demand compute environment for the web traffic is transparent. After serving the web traffic via the provisioned resources, the system can release the provisioned compute resources for other uses.