FaaS Business Context Object for Dynamic Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Function as a Service (FaaS) providers lack the ability to differentiate service-level objectives (SLOs) based on business needs, such as deadline, reliability, cost-efficiency, and latency, limiting the applicability of FaaS for business critical applications and hindering the realization of FaaS model flexibility.
Innovation Solution
Implementing a method that allows FaaS providers to optimize computations based on business goals by using a Business Context object that considers direct and indirect gains and losses, historical invocations, and infrastructure parameters to dynamically allocate resources and choose the appropriate functions for each invocation, thereby making the FaaS infrastructure 'business-centric'.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If FaaS providers offer only basic uptime guarantees with static resource choices, then device complexity is reduced and ease of operation is improved, but adaptability to different business needs deteriorates and productivity is limited
Solution Approach 1:
The patent implements dynamic resource allocation where the FaaS infrastructure automatically adjusts computing resources based on real-time business context and historical performance data. The system transitions from static resource reservations to dynamic scheduling that adapts to varying business needs, workload characteristics, and infrastructure conditions, enabling the platform to serve diverse business critical applications with differentiated SLOs.
Solution Approach 2:
The patent incorporates feedback mechanisms by continuously monitoring historical invocation performance, business context parameters, and infrastructure state. This feedback loop enables the system to learn from past executions and optimize resource allocation decisions, allowing the FaaS platform to adapt to business needs while maintaining manageable complexity through automated control.
2Manufacturing precision
If manual static resource choices are made for all invocations, then ease of operation is improved, but loss of information about specific function invocation context increases and manufacturing precision of resource allocation deteriorates
Solution Approach 1:
The patent segments the resource allocation decision-making process into distinct components: business context analysis, historical performance evaluation, infrastructure state assessment, and scheduling optimization. By dividing the overall allocation problem into these segments, the system can process specific function invocation context information systematically, achieving high resource allocation precision without overwhelming complexity.
Solution Approach 2:
The patent utilizes parameter changes by considering multiple variables including business context parameters, historical performance metrics, and infrastructure conditions. The system dynamically adjusts resource allocation based on changes in these parameters, enabling precise resource allocation that reflects the specific context of each function invocation while maintaining ease of operation through automated parameter management.
3Productivity
If FaaS SLOs are not differentiated, then device complexity is reduced, but adaptability to different business needs deteriorates and productivity is limited
Solution Approach 1:
The patent implements a universal SLO management framework that handles multiple differentiated service levels through a single integrated system. The FaaS platform provides multi-functionality by supporting various business critical applications with different SLO requirements (deadline, reliability, cost-efficiency, latency) using a unified resource allocation and scheduling mechanism, thereby improving productivity without proportionally increasing SLO management complexity.
Data Source
AI summary
Embodiments may include novel techniques to communicate user preferences to the FaaS provider so as to provide full applicability of FaaS for business critical applications and to provide full realization of the FaaS model flexibility. For example, in an embodiment, a method may be implemented in a computer system comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, and the method may comprise receiving a request for processing of a computing task and associated data indicating a context of an overall process flow for the computing task, wherein the request for processing is a function invocation for a FaaS computing system, evaluating the data indicating the context and scheduling computing resources for performing the computing task based on the data indicating the context, and performing the computing task using the scheduled computing resources.