Decoupled Firmware Updates in Composable Compute Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current firmware update processes in computing environments require system restarts, leading to significant downtime and scheduling challenges due to the need for rebooting, which makes updating and activating new firmware difficult and costly.
Innovation Solution
Implementing decoupled firmware updates in composable compute systems by mapping devices within a resource pool, detecting needed updates, exchanging mappings transparently, and performing updates without interrupting workload execution, allowing for instantaneous address updates via a communications fabric.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If firmware updates require system restart to initialize new firmware elements, then the firmware update can be completed, but system downtime increases and workload interruption occurs
Solution Approach 1:
The system segments the firmware update process from the system operation by maintaining multiple firmware images and switching between them without requiring a restart. The compute device can apply firmware updates to one image while continuing to operate using another image, eliminating the need for system downtime during updates.
Solution Approach 2:
The system performs preliminary actions by pre-loading and validating multiple firmware images before they are needed. The firmware update mechanism prepares backup firmware images in advance, so when an update is required, the system can switch to the pre-prepared image without interruption, avoiding system restart.
2Reliability
If system restart is required for firmware updates, then new firmware elements are initialized, but scheduling complexity and cost increase
Solution Approach 1:
The system implements dynamic firmware switching capability that allows runtime changes between firmware images without restart. The firmware management system can dynamically select which firmware image to activate based on update status and system state, enabling flexible scheduling without the constraints of mandatory restarts.
Solution Approach 2:
The system introduces an intermediary firmware image management layer that mediates between the firmware update process and system operation. This intermediary layer handles the complexity of firmware validation, switching, and activation, simplifying the overall scheduling by abstracting away the restart requirement from the update process.
Data Source
AI summary
Managing composable compute system infrastructure with support for decoupled firmware updates includes mapping a device to a server, wherein the device is in a resource pool of devices including at least one idle device, and wherein the device and the server are within a pod of composable compute elements connected by a fabric in a composable system executing a workload; detecting that the device has a needed firmware update; exchanging, transparent to the workload executing in the composable system, the mapping for the device with the needed firmware update and the idle device in the resource pool; and performing the firmware update on the unmapped device as the workload executes in the composable system with the newly mapped device.


