Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Programmed Algorithm for Arraysites, Arrays and Ranks Selection for Automated Extent Pool Creation

IP.com Disclosure Number: IPCOM000124383D
Original Publication Date: 2005-Apr-18
Included in the Prior Art Database: 2005-Apr-18
Document File: 2 page(s) / 21K

Publishing Venue

IBM

Abstract

This invention describes a programmed algorithm that selects and creates the arraysites, arrays and ranks for automated extent pool creation. This algorithm selects and creates the optimal arraysites, arrays and ranks for the extent pool creation appropriate for the current existing storage configuration, extent pool storage requirement and data access performance requirements with minimal user involvement.

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

Page 1 of 2

Programmed Algorithm for Arraysites, Arrays and Ranks Selection for Automated Extent Pool Creation

This invention describes an expert algorithm implemented by the Configuration Advisor. It selects and creates the optimal arraysites, arrays and ranks for the automated extent pool creation. The algorithm evaluates the current storage configuration, the extent pool storage requirement and data access performance requirements. The configuration factors used by this algorithm that concerns the extent pool storage requirement include but not limited to RAID type, needed capacity, arraysite status, array status, rank configuration status, arraysite capacity and array capacity. These configuration factors may be manually input via the ICAT-GUI, the Command Line Interface (CLI) or any software application that uses the Configuration Advisor.

The purpose for providing an automated process of selecting and creating the best arraysites, arrays and ranks for the automated extent pool creation is to assist user in the complex and lengthy process of the storage configuration. With this algorithm, users can create extent pool without any prior knowledge of the internal storage architecture or expert understanding of the configuration planner worksheets.

The lengthy and complex process has cost IBM a lot of money and has affected customer satisfaction.

The expert algorithm executes several steps to process the selection and creation of the best arraysites, arrays and ranks for the automated extent pool creation.

Step 1 evaluates the existing ranks that are not yet part of an extent pool by grouping all these ranks based on the disk adapter pair that they belong to.

Step 2 uses the configuration factor that determines whether a specific existingrank is compatible with the extent pool and able to support the storage requirement.

Step 3 allows spreading of the ranks which means that ranks from different disk adapters are used. Using the ranks that are created from arraysites with the fewest connection drops between the disk adapter and the DDM first. This is good for high transaction and random application, and it will yield the highest performance since we are distributing the workload across multiple DA paths. Step 3 returns the selected existingranks to use for the new extent pool.

Step 4 evaluates the existing arrays, if there are not enough existing ranks to...