Cross-zone replicated block storage resilience
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network-based block storage devices are susceptible to wide-scale failures such as power outages or natural disasters due to lack of off-site replication, which can result in data loss and service interruptions, as traditional off-site backups are not immediately usable and may take hours or days to restore.
Innovation Solution
Implementing cross-zone replication across isolated availability zones, where data is synchronously replicated across multiple zones, allowing each volume to be independently functional and up-to-date, reducing the risk of data loss and performance impact, and enabling seamless failover in case of failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is replicated across multiple availability zones, then reliability is improved, but device complexity increases
Solution Approach 1:
The storage system is segmented into multiple independent availability zones, each containing local storage devices. Data is divided and replicated across these zones, allowing the system to maintain reliability while managing complexity through modular organization. Each zone operates semi-independently, reducing the propagation of failures and simplifying the management of replication logic within each segment.
Solution Approach 2:
The patent implements synchronous copying of data blocks across multiple availability zones. Each write operation is replicated to corresponding storage devices in different zones simultaneously, ensuring data consistency and reliability. This copying mechanism is managed through a coordination layer that tracks replication status without requiring complex asynchronous synchronization logic.
2Manufacturing precision
If synchronous replication is implemented across zones, then data consistency is improved, but speed of write operations deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-establishing replication connections and allocating storage resources across availability zones before actual data writes occur. This preparation allows synchronous replication to proceed more efficiently during write operations, as the infrastructure is already in place and configured, reducing the overhead impact on write speed while maintaining data consistency.
3Loss of information
If off-site backups are used, then loss of information is reduced, but loss of time increases
Solution Approach 1:
The system performs preliminary replication of data to multiple availability zones in real-time, so that restored data is immediately available from replicated copies. This eliminates the time-consuming process of recreating backups and enables instant restoration, as the data is already prepared and positioned in advance across multiple locations.
Solution Approach 2:
Instead of creating periodic backup copies, the system continuously copies data to replicated storage devices in other availability zones. These copies are kept synchronized and ready for immediate use, transforming the restore process from a time-intensive reconstruction operation to a simple data retrieval operation from existing replicas.
Data Source
AI summary
The present disclosure generally relates to creating virtualized block storage devices whose data is replicated across isolated computing systems to lower risk of data loss even in wide-scale events, such as natural disasters. The virtualized device can include at least two volumes, each of which is implemented in a distinct computing system. Each volume can be implemented by at least two computing devices, a first of which is configured as a primary device to which reads from and writes to the volume are directed. Of the two volumes, one can be indicated as primary, indicating authority to accept reads to and writes from the virtualized device. A primary device of the primary volume, on obtaining a write to the volume, can replicate the write to both a secondary device of a primary volume and to the secondary volume.