Information Technology Reference
In-Depth Information
When the bioinformatics grid server receives the computational requests
from the client, it locates a suitable node in the grid to perform the
mathematical computation according to the users' requirement and task
allocation rule, or integrates a virtual supercomputer to perform the larger
computational requests from users. There are three key modules in
bioinformatics grid. They are as given below.
4.4.1.1
Management of Heterogeneous Resources
In the bioinformatics grid, resource management consists of both
resource abstraction and resource organization. In order to integrate
the diverse resources in a uniform and seamless way, all hardware and
software resources are packaged into certain services. A set of attributes is
abstracted to describe the services (such as OS information, computation
power, software category, software name). Objectives of OMR (organiza-
tion and management of resources) are as follows:
•
Integrated heterogeneous computer
•
Make bioinformatics computing tools grid-enabled
•
Basic communication mechanisms: These mechanisms must
permit the efi cient implementation of a wide range of communi-
cation methods, including message passing, remote procedure
call, and multicasting
Process creation: This component is used to initiate computation
•
on a computing grid node once it has been located and allocated.
This task includes setting up executables, creating an execution
environment, starting an executable, passing arguments, integrat-
ing the new process into the rest of the computation, and manag-
ing termination and process shutdown
4.4.1.2
Monitoring
The bioinformatics grid provides uniform protocol and interface specii -
cat ion for g r id re sou rce s mon itor i ng. Mon itor i ng i s u s ed to ident i f y system
bottlenecks. The system can be adjusted and optimized by using the infor-
mation gathered by monitoring. Objectives of grid resources monitoring
(GRM) in the bioinformatics grid are as follows:
•
Maintaining the latest copy of crucial data in the root node
•
Task sc hedu l i ng
•
Monitoring bioinformatics grid
•
Keeping log of operations, errors, and statistics
Search WWH ::
Custom Search