Hypervisor Exchange With In-Memory Virtual Machine Suspension
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Upgrading hypervisors often requires shutting down virtual machines, which can be costly or unacceptable, and relying on migration to a standby machine is problematic due to availability issues and high network bandwidth consumption.
Innovation Solution
The old hypervisor suspends virtual machines in memory, allowing for in-memory suspension and exchange with a new hypervisor without loading them back into memory, reducing interruption and bandwidth usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If virtual machines are migrated to a standby machine to avoid shutdown, then virtual machine availability is maintained, but network bandwidth consumption increases significantly
Solution Approach 1:
The patent extracts the virtual machine state from persistent storage and keeps it in memory during hypervisor exchange operations. By taking out only the essential state data and maintaining it in volatile memory rather than migrating entire virtual machine images over the network, the solution maintains virtual machine availability while dramatically reducing network bandwidth consumption.
Solution Approach 2:
The patent performs preliminary suspension of virtual machines in memory before the hypervisor exchange occurs. By preliminarily preparing the virtual machine state in memory and preserving it during the exchange, the system avoids the need for network migration while ensuring continuity, thus reducing bandwidth consumption while maintaining availability.
2Reliability
If virtual machines are migrated to a standby machine, then shutdown is avoided, but the required standby machine may not be available
Solution Approach 1:
The patent introduces memory as an intermediary storage medium between persistent storage and the running virtual machines. By using memory to temporarily hold virtual machine state during hypervisor exchange, the system eliminates the need for external standby machines, making the solution adaptable to environments where standby machines are unavailable.
Solution Approach 2:
The patent changes the storage parameter from persistent disk-based storage to volatile memory-based storage during the exchange process. This parameter change enables faster access and eliminates dependency on standby machine availability, as the virtual machine state remains in memory throughout the hypervisor exchange operation.
3Reliability
If virtual machines are suspended to disk, then state persistence is ensured, but resumption requires loading back into memory causing interruption
Solution Approach 1:
The patent performs preliminary suspension of virtual machines directly in memory rather than writing to disk. By preliminarily preparing the suspended state in memory and maintaining it there during exchange, the system eliminates the time-consuming load operation that would otherwise be required upon resumption, thus reducing interruption time while ensuring state persistence.
Solution Approach 2:
The patent maintains virtual machine state continuously in memory throughout the hypervisor exchange process rather than interrupting the workflow with disk I/O operations. This continuity of useful action eliminates the load-back step, reducing resumption time while maintaining state persistence through memory-based suspension.
Data Source
AI summary
A hypervisor-exchange process includes: suspending, by an “old” hypervisor, resident virtual machines; exchanging the old hypervisor for a new hypervisor, and resuming, by the new hypervisor, the resident virtual machines. The suspending can include “in-memory” suspension of the virtual machines until the virtual machines are resumed by the new hypervisor. Thus, there is no need to load the virtual machines from storage prior to the resuming. As a result, any interruption of the virtual machines is minimized. In some embodiments, the resident virtual machines are migrated onto one or more host virtual machines to reduce the number of virtual machines being suspended.