Partition Identification for Multi-Node Packet Isolation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing multi-partition computer systems face challenges in quickly and reliably identifying and preventing incorrect packets from propagating to normal partitions, with existing methods being costly, complex, and prone to errors as the system scales, especially when partition borders change dynamically.

Innovation Solution

Incorporating a packet identification unit in each node that compares unique partition identification information within received packets to determine and discard incorrect packets, thereby preventing their propagation to normal partitions through simple control actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If error notification mechanisms are implemented to stop operations in faulty partitions, then failure propagation is prevented, but system cost and complexity increase significantly

Engineering Contradiction:

Improvefailure propagation preventionVSAvoiderror notification mechanism complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system divides the computer system into multiple independent partitions, each with its own identifier. This segmentation allows failures to be isolated to specific partitions without affecting others, eliminating the need for complex error notification mechanisms while maintaining reliability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Partition identifiers are pre-assigned to each partition before failures occur. This preliminary action enables immediate identification and isolation of faulty partitions without requiring complex real-time error notification systems, thus reducing system complexity while maintaining reliability.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If management tables are used to monitor packets and prevent incorrect packet flow, then failure propagation is prevented, but system cost increases with system size

Engineering Contradiction:

Improveincorrect packet flow preventionVSAvoidmanagement table size and cost

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

Instead of using a single large management table for the entire system, the invention assigns simple partition identifiers to each partition. This segmentation approach replaces complex centralized management with decentralized, lightweight identification, reducing system cost while maintaining the ability to prevent incorrect packet flow.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes from managing detailed packet information in large tables to using simple partition identifier parameters. This parameter change simplifies the data structure from complex management tables to lightweight identifiers, reducing memory requirements and system cost as the system scales.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If management tables are configured for partition resource monitoring, then packet flow control is achieved, but setting complexity and error likelihood increase

Engineering Contradiction:

Improvepacket flow control capabilityVSAvoidmanagement table setting complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The invention segments the complex management table configuration into simple partition identifier assignments. Each partition receives a unique identifier without requiring complex setting procedures, thereby maintaining packet flow control capability while dramatically reducing configuration complexity and error likelihood.

Inventive Principle:

Principle #1Segmentation

4Adaptability or versatility

If dynamic partition border changes are implemented, then system flexibility is improved, but management table updates become extremely cumbersome

Engineering Contradiction:

Improvepartition configuration flexibilityVSAvoidmanagement table update complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system segments partition identification into independent, assignable identifiers rather than relying on fixed management table structures. This allows partition borders to be changed dynamically by simply reassigning identifiers, maintaining system flexibility while eliminating the complexity of updating large management tables.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS8108736B2Multi-partition computer system, failure handling method and program therefor

Publication Date: 2012.01.31 NEC PLATFROMS LTD

AI summary

The present invention determines an incorrect packet from a faulty partition quickly and reliably and prevents the packet from flowing into normal partitions through simple control actions. The multi-partition computer system is a multi-partitioned computer system in which a plurality of nodes are logically divided into a plurality of partition, and each node contained in the partitions includes a packet identification unit which, upon receiving a packet, compares the partition identification information uniquely assigned to own partition against the partition identification information contained in the receive packet, and if these pieces of information do not match each other, judges and discards the receive packet as an incorrect packet.