Distributed Tertiary Replica for Rapid Volume Backup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cloud computing systems face challenges in efficiently managing and replicating data volumes due to bandwidth limitations and latency issues, particularly when creating frequent backups or large numbers of copies, which can strain communication bandwidth and result in high latencies for users.
Innovation Solution
The implementation of a highly distributed tertiary replica system, where data is split into a large number of partitions across multiple computing devices, allowing for asynchronous updating and rapid creation of clones and backups, while maintaining low-latency user experiences through the use of primary and secondary replicas for real-time operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is replicated frequently to create backups and copies, then data redundancy and reliability are improved, but communication bandwidth is strained and data transfer time increases
Solution Approach 1:
The patent divides a volume into multiple partitions and distributes them across multiple computing devices to form a tertiary replica. This segmentation enables parallel data transfer operations, where multiple partitions can be copied simultaneously to different destinations, thereby reducing overall data transfer time while maintaining data redundancy through distributed replication.
Solution Approach 2:
The system pre-creates a distributed tertiary replica of the volume by partitioning and distributing data across multiple computing devices before backup operations are needed. This preliminary distribution establishes multiple ready-to-use data copies, enabling rapid backup generation and reducing data transfer time when backups are actually required.
2Productivity
If data is split into many partitions across multiple devices, then replication speed and backup creation efficiency are improved, but system complexity increases
Solution Approach 1:
The volume is divided into multiple partitions that are distributed across different computing devices. Each partition can be independently managed and replicated, enabling parallel processing and faster replication speeds. The segmentation allows the system to leverage multiple devices simultaneously, improving overall productivity without requiring complex coordination between all devices.
Solution Approach 2:
The patent introduces a distributed file system layer that acts as an intermediary between the primary/secondary replicas and the underlying storage devices. This intermediary manages the partitioning, distribution, and coordination of data across multiple computing devices, simplifying the system architecture by providing a unified interface while enabling complex parallel replication operations underneath.
3Loss of time
If a distributed tertiary replica is used for rapid backup generation, then backup creation time is reduced, but user access latency may increase due to data distribution
Solution Approach 1:
By dividing the volume into partitions distributed across multiple devices, the system enables parallel backup operations where each partition can be copied simultaneously, dramatically reducing backup creation time. The segmented structure allows independent processing of multiple data segments without requiring sequential operations.
Solution Approach 2:
The system maintains different replica types with different characteristics: primary and secondary replicas provide low-latency user access, while the distributed tertiary replica optimized for rapid backup generation. Each replica type has localized quality optimized for its specific purpose, allowing the system to achieve both fast backups and fast user access through appropriate replica selection.
Data Source
AI summary
Generally described, one or more aspects of the present application correspond to a highly distributed replica of a volume stored in a networked elastic computing environment. First and second replicas of the volume can be synchronously replicated, and some implementations of the tertiary replica can be asynchronously replicated. The highly distributed nature of the tertiary replica supports parallel data transfer of the data of the volume, resulting in faster creation of backups and new copies of the volume.