Defragmentation Module for Disaggregated Hardware Resource Consolidation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Disaggregated hardware systems face resource defragmentation issues, leading to performance degradation and difficulties in allocating resources to host machines, as resources become spread across multiple structures, causing gaps and latency problems.
Innovation Solution
A defragmentation module identifies structures hosting host machines and reallocates remote resources from one structure to another with available resources, consolidating them to reduce the number of structures resources are spread across, thereby improving resource utilization and reducing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If resources are allocated to host machines in disaggregated hardware systems, then resource utilization is improved, but resource defragmentation occurs causing gaps and performance degradation
Solution Approach 1:
The patent implements dynamic resource allocation by continuously monitoring resource distribution across structures and automatically triggering defragmentation operations when fragmentation thresholds are exceeded. The system adapts resource allocation patterns in real-time based on current system state, transforming the static resource allocation into a dynamic process that prevents performance degradation while maintaining high utilization.
Solution Approach 2:
The system employs feedback mechanisms by monitoring resource allocation patterns, detecting fragmentation levels, and using this information to trigger appropriate defragmentation actions. The feedback loop continuously adjusts resource allocation strategies based on observed system performance and fragmentation metrics, ensuring optimal balance between utilization and performance.
2Quantity of substance
If resources are spread across multiple structures, then resource availability increases, but latency increases due to remote resource access
Solution Approach 1:
The patent applies merging by consolidating resource allocations within the same structure whenever possible. When defragmentation is performed, the system prioritizes placing resources for the same host machine into the same structure, reducing the number of cross-structure accesses. This combining of resources locally minimizes latency while preserving overall resource availability across the distributed system.
3Ease of operation
If structures are kept active to maintain resource availability, then resource access is improved, but energy consumption increases
Solution Approach 1:
The system extracts and consolidates resource allocations into fewer active structures through defragmentation. By moving resources to be co-located within the same structure, the system enables shutdown of underutilized structures, thereby reducing the number of active components and their associated power consumption while maintaining resource accessibility through the remaining active structures.
Data Source
AI summary
A method and a defragmentation module for defragmenting resources of a hardware system. The defragmentation module identifies a set of structures. Each structure of the set of structures partially hosts a respective set of host machines. Respective resources of each host machine of the respective set of host machines are allocated in at least two structures of the set of structures. The defragmentation module selects, from the respective resources of a host machine of the respective set of host machine, a remote resource of a first structure being different from a second structure partially hosting the host machine. A remote amount of the remote resource is less than an amount of available resources of the second structure. The defragmentation module assigns the remote amount of the available resources of the second structure to the host machine instead of the remote resource.