Fault Distribution Tables for Data Storage Redundancy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing distributed systems face challenges in maintaining efficiency and fault tolerance when handling large numbers of data comparisons across multiple nodes, as the likelihood of node failures increases with the number of comparisons and nodes, leading to potential downtime and increased execution time.

Innovation Solution

The implementation of fault-tolerant methods and architectures that generate fault distribution tables to uniformly distribute data records among nodes, ensuring that each node has multiple copies of data records stored in a tree structure, allowing for seamless re-distribution and access in case of node failures, thereby maintaining system continuity and reducing downtime.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the number of cluster nodes is increased to handle more comparisons, then productivity is improved, but the likelihood of node failures increases, worsening reliability

Engineering Contradiction:
Improvematching task execution speedVSAvoidsystem availability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent creates multiple copies of data records and distributes them across the cluster using fault distribution tables. Each data record is replicated and assigned to multiple nodes, ensuring that if a node fails, its data copies are still accessible from other nodes. This copying strategy maintains system availability while enabling parallel processing across multiple nodes.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent pre-generates fault distribution tables that anticipate potential node failures before they occur. These tables are created in advance and stored locally at each node, containing pre-computed redistribution information. When a node fails, the system can immediately use the pre-computed tables to redistribute work without calculation delays, thus maintaining productivity while handling failures.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If fault tolerance mechanisms are implemented, then reliability is improved, but device complexity increases due to additional distribution tables and data copying

Engineering Contradiction:
Improvefault toleranceVSAvoiddata distribution management
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements self-service mechanisms where each node maintains its own local copy of the fault distribution table and autonomously determines how to redistribute data when failures occur. Nodes independently query their local tables to identify which data copies to retrieve from which peers, eliminating the need for complex centralized coordination and reducing overall system complexity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent stores fault distribution tables locally at each node rather than maintaining a single centralized table. Each node has tailored local information about which data records it should have as backups and from which nodes. This localization reduces network traffic and simplifies the complexity by distributing the management burden across all nodes rather than concentrating it.

Inventive Principle:
Principle #3Local quality

3Reliability

If data is re-distributed after node failures, then reliability is maintained, but loss of time occurs during the re-balancing process

Engineering Contradiction:
Improvesystem continuityVSAvoiddowntime during re-balancing
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent pre-computes and stores fault distribution tables locally at each node before any failures occur. These tables contain all the information needed for redistribution, including which data records should be copied to which nodes under various failure scenarios. When a node fails, the system immediately queries the pre-computed local table and executes redistribution without any computation delays, minimizing downtime.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent enables the system to skip the time-consuming steps of failure analysis and redistribution planning by having all this information pre-computed and stored locally. The system rushes through the redistribution process by directly executing pre-determined actions from the local fault distribution tables, significantly reducing the time lost during failure recovery.

Inventive Principle:
Principle #21Skipping (Rushing through)

Data Source

PatentEP3353657B1Fault-tolerant methods, systems and architectures for data storage, retrieval and distribution
Publication Date: 2023.11.29 TIGERIT AMERICAS LLC
  • EP3353657B1 patent drawingFigure 1
  • EP3353657B1 patent drawingFigure 2
  • EP3353657B1 patent drawingFigure 3

AI summary

The disclosure is directed towards fault-tolerant methods, systems and architectures for data distribution. One method includes generating fault distribution tables. The table entries correspond to a copy of data records. The entry and copy are associated with a fault status, a node, and a group that are based on a position of the entry within the distribution table. The method also includes storing the copy of the data record that corresponds to the entry in a database that is included in a plurality of databases. In response to determining an unavailable node included in the plurality of nodes, the method determines a fault status, a node, and a group. The method provides an available node sequential access to data records that are stored in a particular database that is stored locally on the available node in a tree structure.