Compute Node Self-Provisioning via BMC for Cloud Cluster Setup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for setting up a cloud cluster require a deploy node, which is insecure, resource-intensive, and time-consuming, and lacks high availability, leading to complications in network configuration and node addition.
Innovation Solution
A method utilizing a baseboard management controller (BMC) in a compute node to receive secured information from a cloud controller, allowing direct communication and receipt of a cloud operating system image, eliminating the need for a deploy node and enhancing security and availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a deploy node is used to set up a cloud cluster, then cloud nodes can be deployed with deployment tools, but the setup process becomes complex and time-consuming
Solution Approach 1:
The compute node performs self-provisioning by automatically obtaining configuration information through PXE boot and retrieving the OS image directly from storage nodes. This eliminates the need for a deploy node to manually provision each compute node, allowing the system to configure itself automatically.
Solution Approach 2:
The invention extracts the deployment functionality from a separate deploy node and integrates it into the compute nodes themselves. Each compute node can independently obtain its configuration and OS image without requiring external deployment infrastructure, thereby removing the deploy node from the system.
2Productivity
If a deploy node is used to manage cloud cluster setup, then deployment can be centralized, but the setup time increases and high availability cannot be achieved
Solution Approach 1:
The centralized deployment function is segmented and distributed to individual compute nodes. Each compute node independently performs its own provisioning and configuration, eliminating the single point of failure represented by the deploy node and enabling parallel setup operations across multiple nodes simultaneously.
3Ease of operation
If PXE boot is used for cloud node initialization, then remote booting is enabled, but network configuration becomes complicated and security is compromised
Solution Approach 1:
The OS image and configuration information are pre-stored in the storage nodes before compute nodes need them. When a compute node boots via PXE, it can immediately retrieve the pre-prepared image without requiring real-time configuration or interaction with a deploy node, streamlining initialization while maintaining security through pre-validated images.
Data Source
AI summary
A method of setting up a cloud cluster is disclosed as providing at least one compute node with a baseboard management controller (BMC), the BMC of the compute node receiving secured information and using the secured information to establish communication with a cloud controller. Upon establishing the communication, the compute node then receives a cloud operating system (OS) image from the cloud controller via the BMC of the compute node. Finally, the cloud OS image is written to a host system in the compute node. A compute node is also disclosed.