Dynamic Physical Partition Merge via Non-Overlapping Address Ranges
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern information handling systems face challenges in efficiently merging multiple physically partitioned nodes to form a single, cohesive physical partition without disrupting ongoing applications and operating systems, while maintaining non-overlapping address ranges to avoid memory conflicts.
Innovation Solution
The method involves configuring first and second nodes to operate in non-overlapping address ranges and activating a communication bus to merge them, forming a merged physical partition, with a hardware management console and flexible service processors enabling dynamic merger without powering down the nodes, allowing the nodes to communicate through each other's address ranges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple physically partitioned nodes are merged to form a single physical partition, then the workload handling capacity and resource utilization are improved, but address range conflicts and memory conflicts may occur
Solution Approach 1:
The system segments the address space by assigning non-overlapping address ranges to each physical node. Each node operates independently with its own designated address range, preventing conflicts when nodes are merged into a single physical partition.
Solution Approach 2:
Each physical node is configured with local address range assignments that are specific to that node. This local quality ensures that when nodes are merged, their respective address ranges remain distinct and non-conflicting, allowing each node to maintain its unique addressing scheme within the unified partition.
2Duration of action of stationary object
If nodes are merged dynamically without powering down, then system availability and operational continuity are improved, but system complexity and merger control difficulty increase
Solution Approach 1:
The system performs preliminary configuration of non-overlapping address ranges for each physical node before the merge operation. This preliminary action ensures that when the merge is executed dynamically, the address space is already prepared and coordinated, simplifying the actual merger process and reducing control complexity.
Solution Approach 2:
A communication bus serves as an intermediary mechanism that enables coordinated control and data exchange between physical nodes during the merge process. This intermediary facilitates the complex merger operation by providing a standardized interface for nodes to interact and synchronize their address ranges without requiring complete system shutdown.
3Reliability
If non-overlapping address ranges are assigned to physical nodes, then memory conflict prevention is improved, but address space utilization efficiency may be reduced
Solution Approach 1:
The system dynamically changes address range parameters based on the operational state of physical nodes. When nodes are merged, the address range parameters are adjusted and coordinated to eliminate conflicts while maximizing utilization. This parameter change approach allows the system to maintain non-overlapping ranges during separate operation and optimize utilization after merging.
Data Source
Figure 1
Figure 2~4
Figure 3
AI summary
An information handling system includes instruction processing nodes in respective physical partitions. A communications bus couples two information processing nodes together. Each node includes hardware resources such as CPUs, memories and I/O adapters. Prior to a command to merge the physical partitions, the communication bus exhibits a disabled state such that the two information processing nodes are effectively disconnected. After receiving a command to merge the physical partitions, the system enables the communication bus to effectively hot-plug the two nodes together. A modified master hypervisor in one node stores data structures detailing the hardware resources of the two nodes. The modified master may assign resources from one node to a logical partition in another node.