19-12-2012, 01:17 PM
Parallel Data Processing In Cloud computing
1Parallel Data.pptx (Size: 187.26 KB / Downloads: 34)
Introduction
What does cloud computing mean?
Cloud computing is the use of computing resources (hardware and software) that are delivered as a service over a network (typically the Internet).
Parallel data processing
In parallel data processing users can access information simultaneously
Read and write operations can performed simultaneously.
In recent years a variety of systems have developed MTC . Although these systems typically share common goals (e.g. to hide issues of parallelism or fault tolerance), they aim at different fields of application.
Map Reduce is designed to run data analysis jobs on a large amount of data.
Once a user has fit his program into the required map and reduce pattern, the execution framework takes care of splitting the job into subtasks, distributing and executing them.
Scope
A growing number of companies have to process huge amounts of data in a cost-efficient manner
The vast amount of data they have to deal with every day has made traditional database solutions prohibitively expensive.
so the huge amount of data can be processed by using parallel data processing which helps these companies.
Objective
In our project we are going do parallel data processing by using the Nephele framework.
Rapid accessing of data.
We are going to reduce the load by disturbing
its tasks. Eg
PACT
PACT it is a Parallelization Contracts.
The PACT programming model is a generalization of the well-known map/reduce programming model.
We describe methods to transform a PACT program into a data flow for Nephele, which executes its sequential building blocks in parallel and deals with communication, synchronization and fault tolerance.
Nephele
At the Nephele layer, programs are defined as directed acyclic graphs (DAGs). Each vertex of the DAG represents a particular task of the overall processing job. Three types of vertices exist:
Input Vertices
Task Vertices
Output Vertices
PARALLEL EXECUTION
First, the compiler transforms the PACT program into a Nephele DAG. The Nephele DAG is a compact representation of a parallel data flow. It consists of vertices and edges.
Second, the Nephele system spans the compact Nephele DAG and obtains a parallel data flow by creating multiple instances of each vertex