Shared Replica VMs for Cost-Optimized Zero RTO Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data protection systems face challenges in reducing the Recovery Time Objective (RTO) while managing costs, particularly in replicating and recovering multiple applications efficiently.
Innovation Solution
The implementation of a data protection system that replicates IO from production virtual machines to replica virtual machines, using strategies such as Quality of Service, Failure Domain Aware, and Related Application strategies to optimize replication and recovery operations, thereby reducing RTO and associated costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If data is replicated to dedicated replica virtual machines for each application, then recovery time is reduced, but cost increases
Solution Approach 1:
The patent combines multiple applications onto shared replica virtual machines instead of using dedicated replica VMs for each application. This merging approach reduces the total number of replica VMs required while maintaining efficient recovery capabilities through automated application assessment and selective recovery processes.
Solution Approach 2:
The shared replica virtual machines are designed to host multiple applications simultaneously, making them multi-functional resources. The system assesses application characteristics and dynamically determines which applications can share the same replica VM, optimizing resource utilization while meeting recovery objectives.
2Quantity of substance
If multiple applications are shared on the same replica virtual machine, then cost is reduced, but recovery time may increase
Solution Approach 1:
The system dynamically assesses application characteristics, dependencies, and recovery requirements to determine optimal placement on shared replica VMs. During recovery operations, the system dynamically evaluates which applications can be recovered simultaneously on the same replica VM versus which require separate resources, adapting to changing conditions to minimize RTO.
Solution Approach 2:
The system implements feedback mechanisms that continuously monitor application performance, resource utilization, and recovery status. This feedback informs the assessment engine to optimize the placement and recovery sequence of applications on shared replica VMs, ensuring that recovery time objectives are met while maximizing resource efficiency.
3Reliability
If full application recovery procedures are performed, then data integrity is ensured, but recovery time increases
Solution Approach 1:
The system performs partial recovery actions by assessing each application's specific requirements and executing only the necessary recovery steps for that application. Instead of applying a uniform full recovery procedure to all applications, the system selectively applies appropriate recovery actions based on application assessment, reducing overall recovery time while maintaining data integrity for each application.
Solution Approach 2:
The recovery process is segmented into distinct assessment and execution phases for each application. The system divides the recovery operation into independent application-specific tasks that can be executed in parallel when possible, allowing data integrity checks to be performed selectively on each application rather than as a monolithic process.
Data Source
AI summary
Data protection operations including replication operations are disclosed. Virtual machines, applications, and/or application data are replicated according to at least one strategy. The replication strategy can improve performance of the recovery operation.