Region Mapping for Virtual Disk Object Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional virtual computing systems face challenges in efficiently managing objects with the same policy flavor, leading to higher latency, I/O usage, and resource utilization due to the need to identify and update multiple storage locations individually, resulting in bottlenecks during data migration, replication, and deletion.
Innovation Solution
The system maps buckets to regions, allowing resources associated with the region manager to partition virtual disks and allocate regions based on policy flavors, enabling region-centric actions that reduce latency and resource usage by identifying and managing regions instead of individual objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If individual objects are managed and updated separately in conventional virtual computing systems, then object-level control is achieved, but latency and resource utilization increase due to the need to identify and update multiple storage locations individually
Solution Approach 1:
The patent merges multiple objects with the same policy flavor into a single region. Instead of managing objects individually, the system creates a region that represents a set of objects sharing common policies, allowing bulk operations to be performed on the entire region rather than updating each object separately. This merging approach directly reduces the time and resources required for data management operations.
Solution Approach 2:
The region structure serves multiple functions simultaneously: it acts as a container for objects with the same policy flavor, a unit for bulk operations, and an abstraction layer that simplifies resource management. This multi-functionality allows the system to achieve both object-level control and efficient batch processing without requiring separate mechanisms for each operation type.
2Ease of operation
If individual objects are managed separately, then precise object-level control is maintained, but I/O usage and resource utilization increase during migration, replication, and deletion operations
Solution Approach 1:
The patent combines multiple objects into a single region that can be managed as one unit. During migration, replication, or deletion operations, the system operates on the region level rather than individual object level, significantly reducing the number of I/O operations required. This approach simplifies data management while lowering I/O usage and resource consumption.
3Adaptability or versatility
If objects with the same policy flavor are stored across multiple locations, then flexibility in storage allocation is achieved, but system complexity increases due to the need to track and update multiple storage locations
Solution Approach 1:
The region acts as an intermediary layer between the policy management system and the underlying storage locations. Instead of directly managing multiple storage locations, the system manages regions that represent sets of objects. This intermediary abstraction simplifies the system by providing a single point of control for operations that would otherwise require tracking multiple locations, while still maintaining the flexibility to allocate storage across different physical locations.
Data Source
AI summary
An illustrative embodiment disclosed herein is an apparatus including a processor and a memory. In some embodiments, the memory includes programmed instructions that, when executed by the processor, cause the apparatus to store a first object and a second object in a first region based on the first object and the second object having a first policy. In some embodiments, the memory includes programmed instructions that, when executed by the processor, cause the apparatus to store a third object in a second region based on the third object having a second policy. In some embodiments, a virtual disk includes the first region and the second region.