Virtual Volume Replication Across Storage Systems for VM Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems face inefficiencies in data management and reliability due to redundant write operations and lack of centralized control over storage processes, particularly in flash storage systems, leading to increased wear and reduced performance.
Innovation Solution
Implementing a direct-mapped flash storage system where the operating system directly addresses data blocks without translation by lower-level controllers, offloading device management responsibilities, and utilizing non-volatile RAM for quick data buffering and proactive data replication across storage nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional storage controllers manage data blocks with translation layers, then device management is centralized, but redundant write operations increase and device wear accelerates
Solution Approach 1:
The patent extracts the translation layer functionality from the storage controller and implements it directly in the operating system kernel. This eliminates the redundant translation operations performed by traditional controllers, reducing unnecessary write amplification while maintaining data integrity through direct OS-managed mapping of logical to physical blocks.
Solution Approach 2:
The storage system implements self-service by enabling the operating system to directly manage data block mapping and replication without intermediary controllers. The OS kernel handles translation and replication tasks natively, allowing the storage devices to operate more efficiently with reduced redundant writes and extended device lifespan.
2Reliability
If storage systems implement comprehensive data replication, then reliability improves, but storage resource utilization decreases
Solution Approach 1:
The patent implements selective replication where only critical data blocks are replicated across multiple storage devices, while less critical data uses single-copy storage. This local quality approach ensures system reliability for important data while optimizing overall storage resource utilization by avoiding unnecessary duplication of all data blocks.
Solution Approach 2:
The system performs partial replication by replicating data blocks based on priority levels and failure domain requirements rather than universally replicating all blocks. This partial action approach maintains adequate reliability through strategic replication while preserving storage capacity for additional useful data.
3Speed
If flash storage devices are used for fast data access, then speed improves, but device wear increases due to write limitations
Solution Approach 1:
The patent implements preliminary action by proactively replicating data blocks to alternative storage locations before the original flash device reaches its write limit. The system monitors device wear and pre-coordinates replication operations, ensuring data redundancy is established before failure occurs, thereby extending effective device lifespan while maintaining fast access speeds through intelligent wear distribution.
Data Source
AI summary
Synchronous replication between storage systems with virtualized storage includes: assigning a virtual volume datastore to a pod, the pod including a management object, the virtual volume datastore including virtual machine data; stretching the pod from a first storage system to a second storage system, including copying the virtual machine data from the first storage system to the second storage system; and synchronously replicating access operations of the virtual machine data of the pod between the first and second storage systems.