Garbage Collection VM Offloading for Cloud Backup Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current garbage collection mechanisms in cloud-based data protection systems consume significant system resources, including memory and I/O operations, leading to high costs and reduced scalability, as they require constant resource reservation and high IOPS capabilities, even when garbage collection is not actively performed.
Innovation Solution
Implementing a dedicated garbage collection virtual machine (GC VM) that offloads garbage collection tasks from data protection VMs, allowing only the GC VM to reserve resources for garbage collection, and starting the GC VM on demand based on predefined policies, thereby optimizing memory and IOPS usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If garbage collection is performed within data protection VMs, then data protection functionality is maintained, but memory and IOPS resources are consumed even when not actively needed
Solution Approach 1:
The patent extracts the garbage collection function from the data protection VM and places it in a separate GC VM. This allows the data protection VM to operate without reserving memory and IOPS resources for garbage collection, while the GC VM handles all garbage collection tasks independently.
Solution Approach 2:
The system is segmented into two independent virtual machines: a data protection VM for backup operations and a GC VM for garbage collection. This segmentation allows each component to be optimized independently and eliminates resource contention between the two functions.
2Reliability
If garbage collection is performed within data protection VMs, then data protection functionality is maintained, but resource costs increase due to constant resource reservation
Solution Approach 1:
The garbage collection function is extracted from the data protection VM, allowing the data protection VM to be deployed with minimal resources. The GC VM is only instantiated when garbage collection is needed, reducing overall system resource costs.
Solution Approach 2:
The GC VM is dynamically instantiated and terminated based on garbage collection needs rather than being continuously running. This dynamic provisioning allows the system to pay only for resources when they are actually needed, reducing operational costs.
3Reliability
If garbage collection is performed within data protection VMs, then data protection functionality is maintained, but scalability is reduced due to high IOPS requirements
Solution Approach 1:
The IOPS-intensive garbage collection operations are extracted from the data protection VM and performed by a separate GC VM. This allows the data protection VM to scale without being constrained by high IOPS requirements, as the GC VM handles all IOPS-related garbage collection tasks.
4Reliability
If garbage collection is performed within data protection VMs, then data protection functionality is maintained, but processor cycles are consumed even when not actively needed
Solution Approach 1:
The garbage collection processor cycles are extracted from the data protection VM and executed in a separate GC VM. This allows the data protection VM to maintain minimal processor allocation, while the GC VM consumes processor cycles only when garbage collection is actually needed.
Data Source
AI summary
Configuring virtual machines for garbage collection in a deduplication backup system executed on a server computer in a cloud computing network, by configuring at least one virtual machine (VM) of a plurality of virtual machines in a VM cluster to be data protection virtual machines (DP VMs), by enabling only read and write operations to/from the DP VMs, interconnecting a garbage collection VM (GC VM) of the VM cluster to the DP VMs, configuring the GC VM to perform only garbage collection tasks for the DP VMs, and providing data access credentials from each DP VM to the GC VM to facilitate the garbage collection tasks.