Resilient External Memory via Dynamic Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing external memory systems are prone to becoming a single point of failure, which can lead to data loss and system instability due to the lack of redundancy and scalability in memory allocation.
Innovation Solution
A resilient external memory system is implemented, comprising a memory appliance, a management server, and a client, where data is dynamically allocated across multiple memory appliances, providing client-side memory access and asynchronous data resiliency operations, ensuring continued operation even under failure scenarios through replication and synchronization across multiple sites.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is stored in a single external memory appliance, then memory access performance is improved, but system reliability deteriorates due to single point of failure
Solution Approach 1:
The patent divides the memory system into multiple independent memory appliances, each capable of storing portions of the data set. This segmentation allows the system to maintain high access performance by distributing data across multiple appliances while improving reliability through redundancy, as the failure of one appliance does not result in complete data loss.
Solution Approach 2:
The system dynamically changes the parameter of data distribution by allocating different portions of the data set to different memory appliances based on accessibility. This allows the system to optimize between performance and reliability by selecting appliances with current access permissions while maintaining backup copies elsewhere.
2Reliability
If data is replicated across multiple memory appliances, then system reliability is improved, but device complexity increases due to synchronization requirements
Solution Approach 1:
The patent introduces a file access controller as an intermediary that manages data allocation and synchronization between memory appliances. This mediator handles the complexity of maintaining data consistency across multiple appliances, abstracting the synchronization requirements from the client system and simplifying the overall device complexity while maintaining high reliability.
Solution Approach 2:
The system implements feedback mechanisms where the file access controller monitors the accessibility status of memory appliances and dynamically adjusts data allocation. This feedback loop ensures that data is automatically redirected to accessible appliances while maintaining synchronization, reducing the manual complexity of managing replicated data across multiple devices.
3Quantity of substance
If memory capacity is increased using traditional hardware expansion, then storage capacity is improved, but cost increases due to expensive hardware requirements
Solution Approach 1:
The patent makes memory resources universal by allowing multiple clients to share access to the same pool of memory appliances through virtualization and dynamic allocation. This multi-functionality enables the system to provide large memory capacity to multiple users simultaneously without requiring separate hardware for each client, thereby increasing effective memory capacity while reducing overall hardware costs.
Solution Approach 2:
The system uses virtual copies and references to provide memory access rather than requiring physical hardware copies for each client. By implementing virtual memory appliances and dynamic data allocation, the system can provide the appearance of large memory capacity to multiple clients while physically storing data in a shared pool, significantly reducing the hardware cost required to achieve high memory capacity.
Data Source
AI summary
Methods and apparatuses may be provided, where data is written to a first region of memory on a first memory appliance in response to a write operation, the first region of memory is external memory to the client device, and the first region of memory is accessible by the client device over a network via client-side memory access in which a first communication interface of the first memory appliance is configured to access the first region of memory on the first memory appliance; and where the data of the write operation is caused to be written to a second region of memory on a second memory appliance, and wherein the data of the write operation is recoverable from a subset of the memory regions, the subset excluding the first region of memory or the second region of memory.