Pod Manager Composes High-Availability Nodes from Rack Resources
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for a mechanism to compose a collection of nodes and provision necessary components to implement a high-availability node in cloud computing networks, where pooled and configurable computing resources are allocated to meet user requests for workload execution.
Innovation Solution
A pod manager receives a data object indicating high-availability requirements and composes a collection of composed-nodes, configuring them to function as a target composed-node by allocating resources from computing racks, including compute, memory, and storage modules, and provisions high-availability operation components to ensure redundancy and load balancing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If pooled and configurable computing resources are allocated to compose nodes, then resource utilization and flexibility are improved, but system complexity and management overhead increase
Solution Approach 1:
The pod manager acts as an intermediary between users and the pooled computing resources. It receives user requests for high-availability nodes, automatically composes appropriate collections of composed-nodes from available resources, and manages the provisioning process. This mediator approach simplifies user interaction while maintaining flexible resource allocation, resolving the contradiction between adaptability and management complexity.
2Reliability
If a collection of composed-nodes is composed to implement high-availability, then system reliability is improved, but resource consumption and cost increase
Solution Approach 1:
Multiple composed-nodes are merged into a collection that functions as a single high-availability node. The pod manager combines individual nodes with specific resources (compute, memory, storage, networking) into a unified high-availability system. This merging allows the system to achieve high-availability through resource pooling and coordination, optimizing resource utilization while meeting reliability requirements.
3Adaptability or versatility
If necessary components are provisioned to composed-nodes, then functionality and service capability are improved, but provisioning time and operational complexity increase
Solution Approach 1:
The pod manager performs preliminary actions by pre-composing collections of nodes and pre-provisioning necessary components before actual workload deployment. When a user requests a high-availability node, the system has already prepared the collection of composed-nodes with required resources and configurations, enabling rapid provisioning and reducing operational delays.
Data Source
AI summary
In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a pod manager. The pod manager receives a data object for composing a target composed-node. The pod manager determines that the data object includes an indication for high-availability. The pod manager accordingly composes a collection of composed-nodes based on the data object. The pod manager further configures the collection of composed-nodes to function as the target composed-node.