Virtual Volume Datastore Replication for Reliable VM Data Sync
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems face inefficiencies in data management and reliability, particularly in flash storage systems, due to unnecessary write operations and lack of centralized control over storage processes, leading to reduced reliability and increased wear on storage devices.
Innovation Solution
Implementing a direct-mapped flash storage system where the operating system directly addresses data blocks without translation by storage controllers, offloading device management tasks, and utilizing non-volatile RAM for quick data buffering and proactive data replication across storage nodes to ensure data integrity and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If storage controllers translate and manage data blocks, then data management control is improved, but device complexity and write operations increase
Solution Approach 1:
The patent extracts the data translation and management functions from the storage controller to the host system. The host OS directly addresses flash memory data blocks without controller translation, eliminating redundant write operations and reducing controller complexity while maintaining centralized control over storage processes.
Solution Approach 2:
The patent introduces a virtual volume datastore as an intermediary layer between the host OS and physical storage devices. This virtual layer enables direct host addressing of data blocks while providing centralized control for replication and wear leveling, resolving the contradiction between simplified device management and reliable data control.
2Reliability
If data is replicated across storage nodes, then reliability is improved, but write operations and storage overhead increase
Solution Approach 1:
The patent implements proactive data replication where the host OS pre-replicates data blocks across multiple storage nodes before failures occur. This preliminary action ensures data integrity without requiring additional write operations during normal operations, as replication happens in advance during idle periods.
Solution Approach 2:
The patent creates virtual copies of data blocks in a virtual volume datastore across multiple storage nodes. These copies serve as redundancy for reliability but are managed efficiently through host-controlled replication strategies that minimize redundant write operations and optimize storage utilization.
3Speed
If flash memory is used for high-speed storage, then speed is improved, but device lifespan is reduced due to wear
Solution Approach 1:
The patent implements host-controlled wear leveling where the host OS directly manages flash memory block addressing and distributes write operations across multiple physical blocks. This self-service approach prevents any single block from excessive wear while maintaining flash memory's high-speed characteristics, extending device lifespan without sacrificing performance.
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.