Storage Controller Capacity Release Estimation via Signature Prefix Scanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for estimating storage capacity release in content addressable storage systems are computationally and memory-intensive, making it difficult to determine which snapshots to delete efficiently, thereby undermining system performance.
Innovation Solution
The use of designated content-based signature prefixes to scan logical address mapping information, identifying pages with specific signatures and determining compressibility measures to generate accurate capacity release estimates, reducing the need for extensive computational and memory resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques are used to generate capacity release estimates by scanning all pages, then measurement precision is improved, but use of energy and computational resources worsens
Solution Approach 1:
The patent segments the scanning process by using content-based signature prefixes to divide the address-to-hash mapping table into manageable sections. Instead of scanning all pages, the system scans only those pages whose content-based signatures match the designated prefix, effectively segmenting the search space and reducing computational overhead while maintaining estimation accuracy.
Solution Approach 2:
The patent applies local quality by focusing computational effort on specific regions of the data structure that are most relevant to capacity release estimation. By identifying pages with specific content-based signature prefixes, the system concentrates scanning resources on locally relevant data rather than uniformly processing the entire dataset, thereby improving resource efficiency.
2Reliability
If conventional techniques scan all pages to generate capacity release estimates, then reliability is improved, but productivity worsens
Solution Approach 1:
The patent implements preliminary action by pre-computing and storing content-based signatures for all pages in the address-to-hash mapping table. This preliminary organization of data by content-based signature prefixes enables subsequent capacity release estimation scans to quickly identify relevant pages without performing full dataset scans, thereby maintaining reliable deletion decisions while improving system productivity.
3Manufacturing precision
If full dataset scanning is performed to determine compressibility measures, then manufacturing precision is improved, but loss of time worsens
Solution Approach 1:
The patent extracts only the necessary information for compressibility measurement by focusing scans on pages with specific content-based signature prefixes. Instead of examining all pages in the dataset, the system extracts compressibility measures only from the subset of pages that are relevant to the capacity release estimate, thereby reducing scan time while maintaining the precision needed for accurate deletion decisions.
Data Source
AI summary
A storage system in one embodiment comprises a plurality of storage devices and an associated storage controller. The storage controller is configured to identify a dataset to be scanned to generate a capacity release estimate for prospective deletion of that dataset, to designate a content-based signature prefix to be utilized in the scan, and to scan logical address mapping information for the dataset to identify one or more pages of the dataset that have the designated content-based signature prefix. The scanning further comprises, for each such identified page, determining a reference count of the page, and responsive to the reference count of the page having a particular value, determining a compressibility measure for the page. The storage controller generates the capacity release estimate for prospective deletion of the dataset based at least in part on the one or more page compressibility measures determined as part of the scan.