 | Level: Introductory David Kra (dakra@us.ibm.com), Executive IT Architect, IBM
20 Jul 2004 Welcome to the "Six strategies for grid application enablement" series here on developerWorks.The installments of this series are grouped from latest to first for your convenience.
Part 4 and last in the series, "Six strategies for grid application enablement, Part 4: Strategy 5: Parallel service," describes the fifth of six strategies for grid application enablement. At this level a program becomes multiple instances of a service subroutine callable in parallel by a client through some grid middleware. The article explains characteristics of applications at this level, as well as what the program developer must, should, and can optionally do to achieve and exploit this level. A major objective is to have the application as middleware agnostic as possible.
The third article, "Six strategies for grid application enablement, Part 3: Strategy 3: Parallel Batch and Strategy 4: Service," discusses grid enablement using these two mutually exclusive strategies. Strategy 3: Parallel Batch subdivides batch work into subjobs to be sent to grid nodes and afterwards aggregates the partial results. Strategy 4: Service is the transition step from batch to a service-oriented architecture.
The second article, "Six strategies for grid application enablement, Part 2: Strategy 1: Batch Anywhere and Strategy 2: Independent Concurrent Batch," shows how to enable applications for the grid using these two strategies. The first strategy enables the application to run as single job on any of many computers in a grid. The second strategy enables multiple independent instances of the application to run concurrently.
The first article in the series, "Six strategies for grid application enablement, Part 1: Overview," provides a series overview of the six strategies and summarizes the characteristics and benefits of each strategy.
About the author | 
| | David Kra is an Executive IT architect in IBM's Grid Computing organization. David has spent his 27 year IBM career guiding customers' distributed computing projects from the application layer down to cabling and from requirements through deployment. His scalable, high volume and high availability communicating solutions have involved several non-IBM platforms and almost every IBM platform since the 1970's. He is a member of the IBM Academy of Technology.
|
Rate this page
| |
