Contiguous Data Streaming for Tape Backup Systems

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing content addressed storage systems face inefficiencies and data loss during restoration due to fragmentation of large data objects across multiple locations in secondary storage devices, leading to delayed and often failed recovery operations.

Innovation Solution

A process and system for contiguously streaming and recording data objects to secondary storage media without fragmentation, using a data block buffer and a tape block buffer to ensure data objects are written sequentially, compatible with existing NDMP-compatible content addressed storage systems.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data objects are packaged according to byte size and divided into multiple locations on secondary storage device, then storage capacity utilization is improved, but data object integrity and recovery reliability deteriorate

Engineering Contradiction:

Improvestorage capacity utilizationVSAvoiddata object recovery reliability

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The patent segments data objects into multiple data streams and distributes them across multiple tape drives simultaneously, rather than dividing a single data object into fragments across different locations. This segmentation approach maintains the integrity of each data object while improving storage capacity utilization and recovery reliability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a backup software module as an intermediary that manages the streaming and distribution of data objects across multiple tape drives. This intermediary coordinates the backup process to ensure that data objects are properly distributed and can be reliably recovered, resolving the contradiction between storage efficiency and recovery reliability.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If large data objects are divided and placed across multiple sections of tape, then storage efficiency is improved, but restoration speed and complexity deteriorate

Engineering Contradiction:

Improvebackup efficiencyVSAvoidrestoration time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent segments data objects into multiple data streams that are distributed across multiple tape drives during backup. During restoration, these segmented streams can be simultaneously retrieved from different tape drives and reassembled, significantly reducing restoration time compared to sequentially accessing fragmented data objects.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from a single-tape sequential backup approach to a multi-tape parallel backup approach, adding the dimension of parallelism. This allows both backup and restoration operations to occur simultaneously across multiple storage devices, improving productivity without increasing restoration time.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Reliability

If data objects are streamed in single stream format one at a time, then data object integrity is improved, but backup productivity deteriorates

Engineering Contradiction:

Improvedata object integrityVSAvoidbackup productivity

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent segments data objects into multiple data streams that can be simultaneously transmitted across multiple tape drives. Each data stream maintains the integrity of its portion of the data object, while the parallel transmission across multiple streams significantly improves backup productivity compared to single-stream sequential backup.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent combines multiple data streams from the same data object across multiple tape drives, allowing parallel backup operations. This merging of multiple streaming operations maintains data integrity through coordinated transmission while dramatically improving backup productivity through concurrent operations.

Inventive Principle:

Principle #5Merging (Combining)

4Quantity of substance

If data objects are fragmented across multiple locations, then storage capacity utilization is improved, but recovery complexity and data loss risk increase

Engineering Contradiction:

Improvestorage capacity utilizationVSAvoidrecovery operation complexity

Core Design Contradiction:

Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent segments data objects into organized data streams that are distributed across multiple tape drives according to a systematic pattern. This segmentation with systematic distribution allows recovery operations to follow a predictable sequence, reducing complexity compared to random fragmentation while maintaining high storage capacity utilization.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS8190834B2Process for contiguously streaming data from a content addressed storage system

Publication Date: 2012.05.29 EMC IP HLDG CO LLC

AI summary

What is disclosed is process for backing data objects from a content addressed storage system to a tape storage device such that the data objects are written in a contiguous sequential fashion. Data objects are kept together on the storage medium, rather than fragmented. An embodiment of the present invention describes the software modules and memory buffers required to implement this process. Additionally, what is disclosed is a process that restores data objects that have been contiguously written to tape. According to one embodiment of the present invention, recovery of non-fragmented data objects is made more efficient and less prone to failure.