# US 2018/0121105 A1 · Performance oriented data deduplication and duplication

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0121105 A1
- Document ID: US20180121105A1
- Status: Published application
- Kind: A1
- Application number: 15/663,940
- Filed: 2017-07-31
- Published: 2018-05-03
- Earliest claimed: 2016-10-31
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Joseph W. Dain; Itzhack Goldberg; Gregory T. Kishi; Daniel I. Tan
- Web page: https://patentgrep.com/patent/US20180121105A1

## CPC

- G06F 3/0611: {in relation to response time}
- G06F 3/0608: {Saving storage space on storage systems}
- G06F 3/0641: {De-duplication techniques}
- G06F 3/065: {Replication mechanisms}
- G06F 3/067: {Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]}
- G06F 3/0673: {Single storage device}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A system and method for data storage management is disclosed. The method includes determining, by an access tracking component, a quantity of access requests for at least one data block, and determining a quantity of current copies of the data block. The method also includes creating, by a duplication component, at least one additional copy of the data block when the quantity of the access requests exceeds an access request threshold. Additionally, a deduplication component removes at least one current copy of the data block when the quantity of the access requests falls below the access request threshold. The access request threshold can be a threshold number of access requests for the data block, the presence of an input/output bottleneck, or a given length of a read latency when accessing the data block. Further, data coloring techniques can be used to distribute current copies of the data block.

## Claims

### Claim 1

A method of data storage management, comprising:
determining a quantity of access requests for at least one data block;
creating at least one additional copy of the at least one data block when the quantity of the access requests for the at least one data block exceeds an access request threshold, wherein the access request threshold is a given quantity of access requests for the at least one data block within a given period of time;
determining a quantity of current copies of the at least one data block;
removing at least one current copy of the at least one data block when the quantity of the access requests for the at least one data block falls below the access request threshold;
removing the at least one current copy of the at least one data block when the quantity of current copies of the at least one data block exceeds a threshold number of data blocks;
determining whether there is an input/output bottleneck formed when at least one application requests access to the at least one data block;
removing, when the input/output bottle neck is formed, the at least one current copy of the at least one data block;
measuring a length of a read latency for accessing the at least one data block; and
removing, when the length of the read latency exceeds a threshold length, the at least one current copy of the at least one data block.
