Browse Prior Art Database

Optimized Movement of Collocated Data

IP.com Disclosure Number: IPCOM000031508D
Original Publication Date: 2004-Sep-27
Included in the Prior Art Database: 2004-Sep-27
Document File: 2 page(s) / 36K

Publishing Venue

IBM

Abstract

Improved efficiency of collocation processing by moving data belonging to the same collocation set in the same pass of the input volume. Also, data copy or data movement from sequential type storage pools to collocated storage pools is prioritized according to the collocation set with the largest number of files occupying the input volume.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 1 of 2

Optimized Movement of Collocated Data

Background

This disclosure pertains to a storage-management software application, such as IBM Tivoli Storage Manager (TSM), which provides a repository for computer information that is backed up, archived, or migrated (also called space-managed) from client nodes in a computer network. The storage-management server stores data objects (often referred to as files) in one or more storage pools and uses its own database for tracking information about the stored files.

TSM provides a mechanism called collocation that controls how data is stored to a storage pool. Collocation can be set for each sequential-access storage pool (that is, a storage pool containing sequential media such as tape). The collocation setting on the destination storage pool determines whether files will be collocated together with files that belong to the same group of nodes, file spaces for a single node, or a single filespace. These sets of files that are collocated together will be referred to as collocation sets. With collocation enabled, the server attempts to keep files that belong to the same collocation set on as few sequential-access storage volumes as possible. By enabling collocation, an administrator can reduce the number of volume mount operations required when users restore, retrieve, or recall many files from the storage pool. Collocation thus improves access time for these operations.

Problem Description

Collocation reduces the number of sequential-access media mounts for restore, retrieve, and recall operations. However, there are some inefficiencies in the transfer of data in a collocated configuration:

Data copy or movement to collocated storage pools is inefficient because multiple output volumes may need to be mounted for each input volume. This occurs if data from different collocation sets is st...