Backup Image Duplication Scheduling via Duration Estimation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing backup image duplication systems face challenges in predicting the duration of duplication operations, leading to resource contention and inefficiencies due to unpredictable consumption of computing resources, especially when dealing with deduplicated data storage.

Innovation Solution

A system that includes a duplication module capable of estimating the duplication rate and scheduling operations within a specified time window by calculating the estimated duration based on deduplication density, deduplication schemes compatibility, and historical duplication data, allowing for more accurate resource allocation and minimizing resource contention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If duplication operations are performed to ensure data redundancy and storage reliability, then data security is improved, but computing resource consumption increases leading to resource contention

Engineering Contradiction:
Improvedata securityVSAvoidresource contention
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary actions by calculating the estimated duration of duplication operations before they start. This allows the system to proactively identify and schedule duplications during off-peak hours, preventing resource contention before it occurs while maintaining data security through guaranteed duplication completion

Inventive Principle:
Principle #10Preliminary action

2Productivity

If duplication operations are scheduled during off-peak hours to minimize resource contention, then resource usage is optimized, but the unpredictability of duplication duration makes accurate scheduling difficult

Engineering Contradiction:
Improveresource usage optimizationVSAvoidscheduling accuracy
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system uses feedback by analyzing historical duplication performance data and actual duration measurements to continuously refine its duration estimation algorithm. This feedback loop enables increasingly accurate predictions of duplication duration, allowing precise scheduling during off-peak hours while maintaining optimized resource usage

Inventive Principle:
Principle #23Feedback

3Reliability

If backup operations are scheduled during low-demand periods to reduce resource contention, then resource availability is improved, but the inability to predict duplication completion time reduces operational efficiency

Engineering Contradiction:
Improveresource availabilityVSAvoidoperational efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary calculation of estimated duplication duration using factors such as data size, network bandwidth, and storage device performance characteristics before scheduling the operation. This preliminary action enables accurate resource availability planning while maintaining operational efficiency through predictable scheduling

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system replaces manual trial-and-error scheduling approaches with an automated estimation and scheduling system that uses calculated duration predictions. This substitution of mechanical scheduling with intelligent automation improves both resource availability and operational efficiency simultaneously

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9798627B2Backup image duplication
Publication Date: 2017.10.24 COHESITY INC
  • US9798627B2 patent drawing
  • US9798627B2 patent drawing
  • US9798627B2 patent drawing

AI summary

Various systems and methods to display information regarding duplication operations and to configure duplication operations. For example, information regarding policies that can be included in a duplication operation is presented via a display. The display receives selection of one or more of the policies. In response to the selection, the display updates to reflect how much of a bucket has been allocated and how much is available, where the bucket specifies an amount of time and is calculated as a function of a duplication window duration.