Partial Memory Updating in Distributed Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multiple computer systems, the volume of data that needs to be updated can be substantial, leading to inefficiencies and delays due to the need to replicate and update memory locations across interconnected machines, especially as the number of machines and complexity of applications increase.
Innovation Solution
The system categorizes memory locations into two groups: one group is replicated across all machines, while the other is unique to each machine. Changes to the first group are updated simultaneously across all machines, and memory locations in the second group are promoted to the first group only when referenced, reducing unnecessary data transmission and updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all memory locations are replicated across all computers, then data consistency is improved, but the volume of data to be transmitted and updated increases substantially
Solution Approach 1:
The patent segments memory locations into two distinct groups: first group memory locations that are replicated across all computers and second group memory locations that are unique to specific computers. This segmentation allows the system to maintain data consistency for shared data while avoiding unnecessary replication and transmission of local-only data, thereby resolving the contradiction between data consistency and data volume.
Solution Approach 2:
The patent applies local quality by treating different memory locations differently based on their accessibility. First group memory locations are replicated and updated across all computers since they are accessed by multiple computers, while second group memory locations remain local to specific computers. This differentiated approach optimizes both data consistency for shared data and reduces unnecessary data transmission for local data.
2Reliability
If memory locations are updated simultaneously across all computers, then data consistency is improved, but the speed of operation decreases due to transmission delays
Solution Approach 1:
By segmenting memory locations into replicated first group and local-only second group, the system can update only the necessary first group locations across all computers simultaneously, while local computers can independently operate on second group locations without waiting for network transmission. This segmentation reduces transmission delays and improves overall operation speed while maintaining data consistency for shared data.
Solution Approach 2:
The patent applies partial action by updating only the first group memory locations that are actually needed across multiple computers, rather than attempting to update all memory locations. This partial updating approach maintains data consistency for shared data while avoiding unnecessary transmission delays associated with updating local-only data across the network.
3Productivity
If the number of computers in the system increases, then computing capability is improved, but the complexity of memory management increases
Solution Approach 1:
The patent segments memory locations into two groups with distinct management rules: first group locations are replicated across all computers and updated simultaneously, while second group locations remain local to specific computers. This segmentation provides a simple, scalable approach to memory management that does not become more complex as the number of computers increases, thereby resolving the contradiction between computing capability and management complexity.
Solution Approach 2:
The patent creates a universal memory management mechanism that works consistently regardless of the number of computers in the system. The same categorization into first and second groups applies whether there are two computers or hundreds, providing a multi-functional approach that scales from small to large distributed systems without increasing management complexity.
4Reliability
If more memory locations are replicated, then data availability is improved, but network traffic increases
Solution Approach 1:
The patent segments memory locations into first group (replicated) and second group (local-only) to optimize the balance between data availability and network traffic. By replicating only the first group locations that are accessed by multiple computers, the system ensures data availability where needed while minimizing unnecessary network traffic that would result from replicating all memory locations across all computers.
Solution Approach 2:
The patent applies local quality by making different memory locations have different replication characteristics. First group memory locations are replicated across all computers to ensure availability for multiple computers, while second group memory locations remain local to avoid unnecessary network traffic. This differentiated approach optimizes both data availability and network efficiency.
Data Source
AI summary
The updating of only some memory locations in a multiple computer environment in which at least one applications program (50) executes simultaneously on a plurality of computers M1, M2 . . . Mn each of which has a local memory, is disclosed. Memory locations (A, B, D, E, X) in said local memory are categorized into two groups. The first group of memory locations (X1, X2, . . . Xn, A1, A2 . . . An) are each accessible by other computers. The second group of memory locations (B, E) are each accessible only by the computer having the local memory including the memory location. Changes to the values of memory locations in the first group only are transmitted to all other computers. A promotion mechanism is disclosed to promote memory locations in the second group into the first group in the event that application program execution means that a memory location in said second group is referred to by a memory location in the first group (ie the first group location now points to the second group location).