Virtual Disk Grafting for Disaster Recovery Data Seeding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data failover methods in distributed computing systems are costly and inefficient due to the need for constant data replication across geographically separated datacenters, often resulting in bandwidth overutilization and failure to meet recovery point objectives.
Innovation Solution
The technique employs grafting and differential-based data pulling, where a special virtual disk is grafted onto an existing snapshot chain, with data changes retrieved on-demand from an external repository, using Changed Region Tracking API to identify and fetch only changed regions, reducing data transfer and leveraging CRI metadata for efficient data seeding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If constant data replication is performed across geographically separated datacenters, then data availability and continuity are improved, but network bandwidth consumption increases and costs rise
Solution Approach 1:
The patent extracts only the changed data blocks from the source snapshot and transfers them to the target datacenter, rather than replicating entire datasets. This selective extraction of modified portions dramatically reduces network bandwidth consumption while maintaining data availability through incremental updates.
Solution Approach 2:
The patent segments data into individual blocks and identifies only those blocks that have changed between snapshots. By processing data at the block level rather than as monolithic datasets, the system transfers only necessary portions, reducing overall network traffic while ensuring data continuity.
2Reliability
If full data replication is performed to meet recovery point objectives, then data recovery capability is improved, but data transfer time increases
Solution Approach 1:
The patent performs preliminary actions by maintaining local snapshots at the source datacenter and pre-identifying changed blocks before failover is needed. This allows the target datacenter to have ready-to-use data blocks, significantly reducing recovery time while meeting recovery point objectives.
Solution Approach 2:
The system extracts only the specific changed data blocks that are necessary for recovery, rather than transferring complete datasets. This selective extraction minimizes data transfer time while ensuring all required data for meeting recovery point objectives is available at the target.
3Reliability
If all data is transferred to external repository, then data security and backup completeness are improved, but storage costs and data retrieval complexity increase
Solution Approach 1:
The patent segments backup data into individual blocks and stores only changed blocks in the external repository. This segmentation allows for simpler retrieval operations where only specific changed blocks need to be fetched rather than managing complete dataset replicas, reducing retrieval complexity while maintaining backup completeness.
Data Source
AI summary
A technique utilizes grafting and differential based (diff-based) data seeding to hydrate a special virtual disk (vdisk) on a multi-node cluster with data changes (differences) between a reference vdisk stored on the cluster and a snapshot stored in an external repository to enable failover (including failback) recovery of an application workload in a disaster recovery environment. The application workload is stored as a workload vdisk on local storage of the cluster and snapshots of the workload vdisk are generated and organized as a vdisk chain on the cluster. One or more snapshots of the vdisk chain may be replicated to the external repository using a long-term snapshot service. Each replicated snapshot may be backed up from the cluster to the external repository at the granularity of a vdisk, referred to herein as an external datasource disk. The special vdisk is a thinly provisioned, datasource-backed vdisk that is grafted onto the vdisk chain, e.g., as a child vdisk of the reference vdisk. The differences between the reference vdisk and datasource disk are seeded from the datasource disk to hydrate the datasource-backed vdisk.