Application Group Checkpointing for Multi-Service Recovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current enterprise and wireless systems lack mechanisms for protecting multi-application services, which are composed of individual applications from different vendors and loaded at different times, leading to challenges in maintaining high availability and data integrity across distributed storage systems.

Innovation Solution

A method and system for transparent checkpointing and migration of application groups, allowing individual applications to perform storage checkpoint restores without affecting other applications, using a coordinator to manage registration, fault detection, and recovery across nodes, and supporting both fork() and exec() processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If storage checkpointing is implemented at the block level of the storage subsystem, then storage recovery capability is improved, but all applications on the disk are affected including unrelated applications

Engineering Contradiction:
Improvestorage recovery capabilityVSAvoidapplication independence
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent segments the storage checkpointing mechanism from the storage subsystem level to the application level. Instead of checkpointing entire storage devices or partitions, the system creates application-specific checkpoints that only affect individual applications. This is achieved by implementing checkpointing at the file system or application data level, allowing selective recovery of specific applications without impacting other applications on the same storage device.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by making checkpointing effects localized to specific applications rather than globally affecting all applications on the storage device. Each application can have its own checkpoint markers and recovery processes, ensuring that storage recovery operations are confined to the local scope of the affected application only.

Inventive Principle:
Principle #3Local quality

2Adaptability or versatility

If multi-application services are composed of individual applications from different vendors loaded at different times, then system flexibility and vendor independence are improved, but mechanisms for protecting such services do not exist

Engineering Contradiction:
Improvesystem flexibilityVSAvoidservice protection capability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements a universal checkpointing mechanism that can protect multi-application services composed of applications from different vendors. The system provides a common framework that works across diverse applications, creating a unified protection layer that handles checkpointing, recovery, and coordination for multiple independent applications simultaneously, regardless of their vendor origins or loading times.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces an intermediary checkpointing management system that coordinates between multiple independent applications. This intermediary layer handles the complexity of protecting multi-application services by managing checkpoints, recovery sequences, and coordination without requiring modifications to the individual applications themselves, thus preserving vendor independence while providing comprehensive protection.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If traditional checkpointing mechanisms are used, then storage recovery is possible, but client connections and sessions cannot be transparently transferred during migration

Engineering Contradiction:
Improvestorage recoveryVSAvoidtransparent client connection transfer
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent applies preliminary action by establishing checkpoint mechanisms and migration frameworks in advance before actual failures or migrations occur. The system pre-configures checkpoint markers, recovery procedures, and client session transfer mechanisms so that when migration or failure occurs, the client connection transfer can proceed transparently without interrupting client awareness or requiring manual intervention.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10310754B1Method and system for providing storage checkpointing to a group of independent computer applications
Publication Date: 2019.06.04 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10310754B1 patent drawing
  • US10310754B1 patent drawing
  • US10310754B1 patent drawing

AI summary

A method and system for checkpointing at least one application in an application group. At least one full checkpoint and at least one incremental checkpoint are created for the application in the application group. The at least one incremental application checkpoint is merged against the at least one full application checkpoint, and checkpointing across all applications in the application group is synchronized. A storage checkpoint is taken for at least one of the full checkpoint and the incremental checkpoint, and memory and storage checkpoints are synchronized and consistent.