Parallel Tape File Copying Method
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage systems face inefficiencies in tape storage due to sequential writing, leading to wasted space and prolonged tape drive occupation during migration commands, which hinders the reuse of tapes and increases resource consumption.
Innovation Solution
A method is introduced to generate file lists of source tapes, determine parallel copy processes, and copy files in parallel using multiple tape drives, allowing for efficient redistribution of valid files to other tapes, thereby reducing the time required for tape copying and reclaiming unused space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If sequential writing is used for tape storage, then data is written in order, but tape drive occupation time is prolonged and tape reuse is hindered
Solution Approach 1:
The patent segments the file copying process into multiple parallel operations. Instead of copying files sequentially from source tape to destination tape, the system divides files into subsets and copies them simultaneously across multiple tape drives, breaking the monolithic sequential process into concurrent segments that improve throughput
Solution Approach 2:
The patent introduces parallelism as a new dimension to the traditionally sequential tape copying process. By utilizing multiple tape drives operating simultaneously, the system transforms the single-threaded sequential operation into a multi-threaded parallel operation, effectively adding a temporal dimension to the copying process
2Stability of the object's composition
If sequential copying is performed, then files are copied in order, but the time required for tape copying is prolonged
Solution Approach 1:
The patent segments the file list into multiple subsets and distributes these subsets across multiple tape drives for parallel copying. Each tape drive handles a specific subset of files simultaneously, dividing the total copying time by the number of parallel drives while maintaining data integrity
Solution Approach 2:
The patent performs preliminary actions by generating file lists, determining parallel copy capabilities, and preparing multiple tape drives before initiating the actual copying process. This pre-planning enables efficient parallel execution without compromising the orderly transfer of data
3Reliability
If tape drives are occupied for prolonged periods, then copying is thorough, but resource consumption increases and tape availability decreases
Solution Approach 1:
The patent segments the copying workload across multiple tape drives, allowing each drive to handle a portion of the files simultaneously. This distribution reduces the occupation time for each individual drive while maintaining complete copying through coordinated parallel operations
Solution Approach 2:
The patent ensures continuous useful action by keeping multiple tape drives occupied simultaneously with parallel copying operations. Instead of one drive working sequentially while others remain idle, all available drives perform useful copying work at the same time, maximizing resource utilization and reducing overall completion time
Data Source
AI summary
Embodiments are disclosed for a method. The method includes generating a file list of an original source tape. The file list identifies files that are stored on the original source tape. The method further includes determining a number of possible parallel copies for a data storage system having multiple tape drives. The method additionally includes generating multiple tape file lists. Each of the tape file lists identify copies of the files stored on one of multiple source tapes. Further, the method includes generating multiple new copies of the files by copying, in parallel, a subset of the files, and a subset of the copies, based on the tape files lists, and using a first of the tape drives, and a second of the tape drives.