Backup System Sorting Data Sets by Size to Reduce Window

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current backup systems using multiple streams often result in a larger backup window due to the specific order of data sets, which can be determined by trial and error, and do not efficiently manage different-sized data sets.

Innovation Solution

The backup system sorts data sets in descending order of their sizes and performs backups in this sorted order, contrary to the specified order, ensuring that larger data sets are backed up before smaller ones, thereby reducing the backup window.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If data sets are backed up in the specified order received from the user, then the backup process follows user-defined sequence, but the backup window becomes larger due to inefficient ordering

Engineering Contradiction:

Improveuser-defined backup sequenceVSAvoidbackup window duration

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system inverts the traditional backup approach by sorting data sets in descending order of size rather than following the user-specified order. This inversion allows the backup process to prioritize larger data sets, thereby reducing the overall backup window while still respecting user-defined constraints through the sorting mechanism

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The system changes the ordering parameter from user-specified sequence to size-based descending sequence. By transforming the sorting criterion from arbitrary user order to a systematic size-based order, the backup process optimizes the backup window duration without compromising data integrity

Inventive Principle:

Principle #35Parameter changes

2Productivity

If multiple streams are used for concurrent backups, then backup throughput increases, but the backup window is not optimized due to poor data set ordering

Engineering Contradiction:

Improvebackup throughputVSAvoidbackup window

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary sorting of data sets by size in descending order before initiating the backup process. This preliminary action ensures that when multiple streams perform concurrent backups, the larger data sets are processed first, optimizing the overall backup window while maintaining high throughput

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically assigns data sets to multiple streams based on the sorted order, allowing flexible and efficient distribution of backup tasks. This dynamic assignment ensures that larger data sets are handled by available streams first, maximizing parallel processing efficiency and reducing total backup time

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS8560788B1Method of performing backups using multiple streams

Publication Date: 2013.10.15 EMC IP HLDG CO LLC

AI summary

A method, system, and a computer program product for performing backups using multiple streams. An aspect of the present invention performs the backups based on the size of the data sets sought to be backed up. In particular, the backups of bigger data sets (in terms of size) are performed before the backups of smaller data sets. It is accordingly observed that the backup window is reduced (without increasing the number of streams).