Proxy Virtual Machines for Isolating Faulty Processor Cores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data centers face challenges with faulty processor cores that cause errors, leading to costly downtime and increased total cost of ownership due to the complexity of removing entire computing devices, which is often unfeasible.
Innovation Solution
Implementing proxy virtual machines to isolate faulty cores from the VM scheduling and allocation scheme, managed by a hypervisor that assigns these machines to faulty cores, maintaining their availability while minimizing performance impact and reducing the need for hardware or scheduling software changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the entire computing device is removed to address faulty cores, then reliability is improved, but productivity deteriorates due to costly downtime and increased TCO
Solution Approach 1:
The system segments the computing device into individual cores, allowing the hypervisor to manage and isolate specific faulty cores independently. This enables selective disabling of only the problematic cores rather than removing the entire computing device, thus maintaining productivity while improving reliability by eliminating the source of errors.
Solution Approach 2:
The hypervisor acts as an intermediary layer between the VM allocation software and the physical cores. It receives core availability information from the computing device and can selectively report certain cores as unavailable to the VM allocation software, thereby isolating faulty cores without requiring physical removal of the entire device.
2Productivity
If faulty cores are isolated using proxy virtual machines, then productivity is maintained, but device complexity increases due to additional virtual machine management
Solution Approach 1:
The system creates proxy virtual machines as simplified copies or representations of the actual faulty cores. These proxy VMs serve as placeholders that consume minimal resources and prevent the faulty cores from being allocated to production workloads, while maintaining the appearance of normal system operation and avoiding the need for complex hardware modifications.
Data Source
AI summary
A device for disabling faulty cores using proxy virtual machines includes a processor, a faulty core, and a physical memory. The processor is responsible for executing a hypervisor that is configured to assign a proxy virtual machine to the faulty core. The assigned proxy virtual machine also includes a minimal workload. Various other methods, systems, and computer-readable media are also disclosed.