Synthetic Baseline Snapshots to Prevent Stable Data Eviction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data management systems incur time penalties during snapshot restoration due to the eviction of stable data blocks, which are not efficiently managed, leading to increased download times from cloud storage.

Innovation Solution

Implementing a storage appliance that maintains snapshot metadata and data in a key-value store layout, using synthetic baseline snapshots and refreshing eviction states to prevent stable data block eviction, thereby ensuring efficient snapshot restoration without relying on cloud downloads.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If stable data blocks are evicted from local storage to make room for new data, then storage capacity is improved, but snapshot restoration time increases due to required cloud downloads

Engineering Contradiction:

Improvestorage capacityVSAvoidsnapshot restoration time

Core Design Contradiction:

Quantity of substanceVSLoss of time

Solution Approach 1:

The system performs preliminary actions by creating synthetic baseline snapshots that proactively refresh eviction states of stable data blocks before they are evicted. This preliminary refresh ensures that frequently accessed stable data remains in local storage, preventing eviction and avoiding subsequent cloud downloads during snapshot restoration, thus resolving the contradiction between storage capacity and restoration time.

Inventive Principle:

Principle #10Preliminary action

2Loss of energy

If cloud storage is used to store snapshot data, then storage cost is reduced, but data retrieval speed decreases due to network dependency

Engineering Contradiction:

Improvestorage costVSAvoiddata retrieval speed

Core Design Contradiction:

Loss of energyVSSpeed

Solution Approach 1:

The system applies local quality by differentiating the storage location of different data blocks based on their access patterns. Stable data blocks that are frequently needed for snapshot restoration are kept in local storage (higher quality/faster access), while less frequently accessed data is stored in cloud storage (lower quality/slower access but lower cost). This selective local retention resolves the contradiction between storage cost and data retrieval speed.

Inventive Principle:

Principle #3Local quality

3Ease of operation

If incremental snapshots are created without refreshing eviction states, then data management simplicity is improved, but stable data block eviction increases

Engineering Contradiction:

Improvedata management simplicityVSAvoidstable data retention

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system implements feedback by monitoring the eviction states of data blocks and using this information to guide synthetic baseline snapshot creation. When stable data blocks are at risk of eviction, the system triggers a synthetic baseline snapshot to refresh their eviction states, ensuring they remain in local storage. This feedback mechanism maintains stable data retention while keeping the overall data management process relatively simple, resolving the contradiction between operational simplicity and data retention reliability.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12561281B2Reducing stable data eviction with synthetic baseline snapshot and eviction state refresh

Publication Date: 2026.02.24 NETAPP INC

AI summary

With a forever incremental snapshot configuration and a typical caching policy (e.g., least recently used), a storage appliance may evict stable data blocks of an older snapshot, perhaps unchanged data blocks of the snapshot baseline. If stable data blocks have been evicted, restore of a recent snapshot will suffer the time penalty of downloading the stable blocks for restoring the recent snapshot. Creating synthetic baseline snapshots and refreshing eviction data of stable data blocks can avoid eviction of stable data blocks and reduce the risk of violating a recovery time objective.