Tape Drive Data Reclamation Using Disk Cache Mediator

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The prolonged occupation time of two tape drives during data reclamation processing in hierarchical storage management systems, particularly due to increased magnetic tape capacity, leads to inefficiencies and prolonged processing times.

Innovation Solution

A method that identifies pre-migrated and migrated data, allowing data to be reclaimed from primary and secondary storage tiers using a single drive, thereby reducing the simultaneous occupation time of tape drives by switching between source tape media and disk cache for data reading and writing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If reclamation processing is performed using two tape drives simultaneously accessing source and target tapes, then data reclamation can be completed, but the occupation time of the two tape drives is prolonged (up to eight hours for 10 TB data)

Engineering Contradiction:
Improvedata reclamation throughputVSAvoidtape drive occupation time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent introduces a disk cache as an intermediary storage medium between the source tape and target tape. Data is first read from the source tape to the disk cache, then from the disk cache to the target tape. This mediator allows the tape drives to operate sequentially rather than simultaneously, reducing the occupation time of each tape drive while maintaining the data reclamation function.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The reclamation process is divided into two separate phases: first reading data from source tape to disk cache, then writing data from disk cache to target tape. This segmentation allows each tape drive to complete its operation independently without waiting for the other, significantly reducing the total occupation time of the tape drives.

Inventive Principle:
Principle #1Segmentation

2Quantity of substance

If magnetic tape capacity is increased to store more data, then storage capacity is improved, but the time required for reclamation processing is prolonged

Engineering Contradiction:
Improvemagnetic tape capacityVSAvoidreclamation processing time
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The disk cache serves as a high-speed intermediary that buffers large volumes of data during reclamation. When dealing with large-capacity tapes (e.g., 10 TB), the disk cache allows data to be staged at high speed before being written to the target tape, reducing the overall reclamation time despite the increased data volume.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the operational parameters of the reclamation process by introducing a disk cache with different access characteristics than magnetic tape. This parameter change (from sequential tape access to faster disk access for intermediate storage) accelerates the reclamation process even when handling larger tape capacities.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS10732843B2Tape drive data reclamation
Publication Date: 2020.08.04 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US10732843B2 patent drawing
  • US10732843B2 patent drawing
  • US10732843B2 patent drawing

AI summary

The method, computer program product, and computer system may include a computing device which may generate a list of data to be copied from a plurality of source media to a target medium. The computing device may identify a first type of data in the generated list of data with the first type of data being pre-migrated data. The computing device may reclaim the first type of data from a primary storage tier to the target medium with the target medium being associated with the first drive. The computing device may identify a second type of data in the generated list of data, the second type of data being migrated data, and reclaim the second type of data from at least one secondary source medium to the target medium using the first drive and a second drive. The secondary source medium may be associated with the second drive.