Zone-Redundant Computing Services via Multi-Zone Data Stitching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing cloud storage systems face risks of data unavailability or loss when an entire availability zone becomes unavailable due to events like datacenter blackouts or regional electricity failures, as they rely on zone-dependent storage schemes that lack redundancy across multiple zones.

Innovation Solution

Implementing availability zone-redundant computing services by deploying multiple local computing services across multiple zones, which are then 'stitched' together to form a virtual computing service, allowing data storage and computing services to be provided from other zones in case of failures, using a deployment description file and software load balancer to route user requests and manage data operations across zones.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is replicated within a single availability zone to provide redundancy, then data resiliency against node failures is improved, but data unavailability risk increases when the entire availability zone becomes unavailable

Engineering Contradiction:

Improvedata resiliencyVSAvoiddata unavailability risk

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system segments data storage across multiple availability zones rather than concentrating all replicated data within a single zone. Each availability zone maintains a portion of the replicated data, ensuring that if one zone fails, data remains accessible from other zones. This spatial segmentation of data redundancy resolves the contradiction by providing both node-level and zone-level fault tolerance.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of redundancy by replicating data not only across multiple nodes within a zone but also across multiple availability zones. This multi-dimensional replication strategy (within-zone + between-zone) transforms single-zone redundancy into multi-zone redundancy, eliminating the harmful effect of zone-wide failures while maintaining data resiliency.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Object-affected harmful factors

If multiple availability zones are deployed to provide zone-redundant computing services, then data unavailability risk is reduced, but system complexity increases

Engineering Contradiction:

Improvedata unavailability riskVSAvoidsystem complexity

Core Design Contradiction:

Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The system employs universal service instances that can operate across multiple availability zones with identical functionality. These universal services are designed to be zone-independent and can be deployed, migrated, or failovered between zones without requiring zone-specific customization. This universality simplifies the management of multi-zone redundancy while maintaining data unavailability protection.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces availability zone-redundant service instances as intermediary components that coordinate data operations across multiple zones. These intermediary services manage the complexity of multi-zone data replication, routing, and failover automatically, shielding the user from the underlying system complexity while providing robust data availability protection.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If computing services are deployed in multiple availability zones to ensure continuous operation during zone failures, then service continuity is improved, but deployment and management difficulty increases

Engineering Contradiction:

Improveservice continuityVSAvoiddeployment difficulty

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The system performs preliminary actions by pre-configuring service instances in multiple availability zones before failures occur. Universal service instances are deployed across zones in advance with proper data replication and routing configurations, so that when a zone failure occurs, services can continue operating without requiring complex real-time deployment decisions or manual intervention during the crisis.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent utilizes parameter changes to manage multi-zone service deployment. Service instances are configured with flexible parameters that allow automatic adaptation to different availability zones, such as zone-specific routing rules, data replication ratios, and failover thresholds. These parameter-based configurations simplify deployment by allowing a single service definition to be automatically adapted across multiple zones without manual reconfiguration.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP3811597B1Zone redundant computing services using multiple local services in distributed computing systems

Publication Date: 2023.10.04 MICROSOFT TECHNOLOGY LICENSING LLC

Figure 1
Figure 2
Figure 3A

AI summary

Techniques for implementing zone redundant computing services in distributed computing systems are described herein. In one embodiment, a computing device is configured to query a database in a first availability zone for a list of computing services corresponding to a user account and provided by servers in a second availability zone different than the first availability zone. The computing device can then select one or more computing services provided by the servers in the second availability zone from the queried list of computing services and transmit an instruction to the servers in the second availability zone for performing the requested data operation.