Tape Media Multi-Source Write Order

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In magnetic storage systems, writing data from multiple sources to a single tape medium results in a significantly reduced data transfer rate during read operations due to fragmented file storage, requiring additional storage capacity and time for re-writing data in contiguous locations, and large buffer areas for temporary storage are not cost-effective.

Innovation Solution

A method where data from multiple sources is stored in a buffer and written to tape in alternating predetermined orders on successive wraps, allowing for faster access to contiguous data in adjacent wraps, thereby increasing read transfer rates without the need for additional storage or re-writing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If data from multiple cameras is concurrently written to a tape medium, then the tape medium can store data from all sources, but the read transfer rate decreases to 1/N the maximum transfer rate due to fragmented file storage

Engineering Contradiction:
Improvestorage capacityVSAvoidread transfer rate
Core Design Contradiction:
Quantity of substanceVSProductivity

Solution Approach 1:

The tape medium is divided into multiple wraps, with each wrap dedicated to storing data from a specific camera source. This segmentation allows data from different sources to be stored in separate, non-overlapping regions, enabling sequential reading without fragmentation while maintaining the ability to store data from multiple cameras simultaneously.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new organizational dimension by using multiple wraps instead of a single linear tape structure. Each wrap represents a new spatial dimension for data storage, allowing N camera feeds to be stored in parallel across N wraps. This dimensional approach enables the read head to access data from different cameras sequentially without fragmentation, achieving high read transfer rates while maintaining full storage capacity for multiple sources.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If data is re-written to the same tape medium to create contiguous locations, then the read transfer rate increases to maximum, but the available space on the tape medium decreases by half and extra time is required

Engineering Contradiction:
Improveread transfer rateVSAvoidavailable space
Core Design Contradiction:
ProductivityVSQuantity of substance

Solution Approach 1:

Instead of re-writing data to create contiguous locations, the patent segments the tape into multiple wraps, with each wrap dedicated to a specific camera source. This allows all data to be stored in contiguous locations within their respective wraps without requiring re-writing operations, maintaining full storage capacity while enabling fast sequential reading.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary organization of data during the writing process by automatically placing data from each camera into its designated wrap. This preliminary segmentation eliminates the need for subsequent re-writing operations to create contiguous locations, saving both time and storage capacity while ensuring fast read access.

Inventive Principle:
Principle #10Preliminary action

3Ease of operation

If data is temporarily stored in a buffer before writing, then data can be written file by file, but a considerably large buffer area is required which is not cost-effective

Engineering Contradiction:
Improvefile-by-file writing capabilityVSAvoidbuffer area
Core Design Contradiction:
Ease of operationVSArea of stationary object

Solution Approach 1:

The patent segments the writing process by organizing data from multiple cameras into separate wraps during the writing operation. This allows file-by-file writing capability without requiring a large buffer, as data is written directly to its designated wrap location rather than being accumulated in a large buffer first.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent uses multiple wraps as an additional dimension for data organization, allowing data to be written directly to its final destination in the appropriate wrap without needing to wait for buffer accumulation. This dimensional approach enables efficient file-by-file writing with minimal buffer requirements.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances data reading speed and transfer rates by ensuring data from each source is placed in allocated regions on the tape, reducing the time required to read data and eliminating the need for extra storage capacity or re-writing, while maintaining efficient buffer usage.

Implementation Method 1

The magnetic recording transducer then generates a magnetic field, which encodes the data into the magnetic media

Methodology Applied
Scientific EffectMagnetic field generation: Electromagnet

Implementation Method 2

Data is read from the media by similarly positioning the magnetic read transducer and then sensing the magnetic field of the magnetic media

Methodology Applied
Scientific EffectMagnetic field sensing: Magnetic Field

Data Source

PatentUS9128617B2Writing multiple files simultaneously to a tape media
Publication Date: 2015.09.08 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US9128617B2 patent drawing
  • US9128617B2 patent drawing
  • US9128617B2 patent drawing

AI summary

In one embodiment, a method includes storing data received from at least two data sources in a buffer, writing the data from the at least two data sources to regions in a first wrap of a tape on a data-source basis in a first predetermined order, and writing the data from the at least two data sources to regions in the second wrap in a second predetermined order, the second predetermined order being a reverse order relative to the first predetermined order.