Storage System Snapshot Meta Information Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The Redirect on Write (RoW) method used in conventional storage systems for creating Snapshots results in inferior read performance and deepens the meta information tree as data is written, leading to asynchronous processing and I/O performance issues.
Innovation Solution
A storage system with multiple controllers that assigns logical volumes or snapshots to specific controllers, utilizing a log structured area for data and a meta information area for meta data, where meta information is structured into two tiers to manage data location information, allowing for efficient snapshot creation and data access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the Redirect on Write (RoW) method is used to create Snapshots, then the influence on I/O performance during Snapshot creation is minimized, but read performance becomes inferior and the meta information tree deepens
Solution Approach 1:
The patent segments the meta information into two distinct parts: meta information of a first tier (stored in a first meta information area) and meta information of a second tier (stored in a second meta information area). This segmentation allows the system to maintain a shallow meta information structure while preserving the RoW method's benefits for Snapshot creation, thereby resolving the contradiction between Snapshot creation performance and read performance.
2Quantity of substance
If data writing increases in the RoW method, then more data is appended to the log structured area, but the meta information tree becomes deeper and triggers asynchronous processing
Solution Approach 1:
By dividing meta information into two tiers stored in separate areas, the patent prevents the meta information tree from deepening as data is written. The first tier meta information maintains direct mapping relationships while the second tier handles detailed location information, thus avoiding the need for asynchronous processing even when data writing increases.
3Productivity
If load is concentrated on a specific volume or Snapshot, then the load concentrates on a specific controller, but multi-controller resources cannot be fully utilized
Solution Approach 1:
The patent enables any controller to access data from any volume or Snapshot by implementing a unified data access mechanism. Controllers can access the log structured area and meta information areas through a common interface, allowing load to be distributed across multiple controllers and fully utilizing multi-controller resources while maintaining high operational efficiency for any specific volume or Snapshot.
Data Source
AI summary
The operational performance and the I/O performance of Snapshots in a storage system are balanced. In a storage system, meta information of data appended to a log structured area is composed of meta information of a first tier and meta information of a second tier which correlate location information of data in a logical volume and location information of data in the log structured area. When creating a snapshot of the logical volume, a data management unit creates, in the same meta information area as a replication source, a replication of the meta information of the first tier stored in a plurality of meta information areas assigned to a plurality of controllers. A data control unit accesses the data of the log structured area from the logical volume, and accesses the data of the log structured area from the snapshot.