Protected-Memory-Aware Request Distribution Across Cluster Hosts

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional load balancers fail to consider the protected memory area when distributing processing requests, leading to depletion and increased error responses in computer clusters with encrypted protected areas.

Innovation Solution

A distribution device that tracks the remaining capacity of protected areas across multiple host computers and allocates processing requests based on this information to prevent depletion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional load balancers distribute processing requests without considering protected area capacity, then request distribution is simple and fast, but protected area depletion occurs and error responses increase

Engineering Contradiction:
Improveprotected area availabilityVSAvoidload balancing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The load balancer implements feedback by continuously monitoring the remaining capacity information of protected areas on each host computer and using this information to dynamically adjust request distribution decisions, preventing protected area depletion while maintaining system reliability

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary actions by collecting and storing remaining capacity information of protected areas in advance before distribution decisions are made, allowing the load balancer to proactively prevent depletion rather than reactively responding to errors

Inventive Principle:
Principle #10Preliminary action

2Reliability

If the load balancer monitors protected area capacity for each host, then protected area depletion is prevented, but information processing complexity increases

Engineering Contradiction:
Improveprotected area depletion preventionVSAvoidinformation processing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

Each host computer autonomously generates and transmits its own remaining capacity information to the load balancer, eliminating the need for complex centralized monitoring mechanisms and reducing overall system information processing complexity while maintaining reliable depletion prevention

Inventive Principle:
Principle #25Self-service

3Productivity

If remaining capacity information is collected from each host computer, then accurate distribution decisions can be made, but communication overhead increases

Engineering Contradiction:
Improverequest distribution efficiencyVSAvoidcommunication overhead
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

Host computers transmit remaining capacity information periodically rather than continuously or on every state change, reducing communication overhead while providing the load balancer with sufficiently current data to make accurate distribution decisions and maintain high productivity

Inventive Principle:
Principle #19Periodic action

Data Source

PatentUS20250298545A1Distributing device, distributing system, distributing method and program
Publication Date: 2025.09.25 NT T INC
  • US20250298545A1 patent drawing
  • US20250298545A1 patent drawing
  • US20250298545A1 patent drawing

AI summary

A distribution device stores, in a storage unit, remaining capacity information of a protected area received from each of a plurality of host computers forming a computer cluster. Each time a processing request is received from one of the plurality of terminals, requesting execution of processing using an encrypted protected area on the memory of the host computer, the distribution device refers to the remaining capacity information of each of the plurality of host computers stored in the storage unit in accordance with the processing request to select a destination to which the processing request is to be distributed.