Grid Computing Implemented Computer Science

In the Grid environment every service or group of services that the grid runs uses resources of the grid nodes. Every service or a group of services has its own process assigned to it which is perforrmed by them when any failure occurs it is shared with the other grid nodes. it has its own IP Address and it has its own Network name. All of the resources that a grided service uses are called a Resource Group. The Resource group contains the basic resources that every service needs, Disk Drive, IP Address, Network Name, and the service itself. The basic grid nodes dependence on a specific server. The user can access the resources effectively via server.

The grid aims to provide improved load sharing since it process based on parallel computing handel symmetric tasks so the load balancing remains bottleneck. The load balancing is sharing the memory and othe I/O Resources among the clinets to share the load accross the network which could imrpove the Qos

The following factors are considered for improving QoS in Grid computing, we focus on Scalability and load balancing to improve the Quality of Service in grid computing.

The grid environment can be created with high degree of scalability by reducing the work load of the server by scheduling the tasks of the client request to the server using efficient scheduling algorithms. To improve the efficiency of the GRID nodes by scheduling the Client-Request .

Load Balancing:

Load Balancing (LB), one of the griding technologies offered as a part of grid group. The Load Balancing enhances the scalability and availability of server applications. Many applications can take advantage of Load Balancing such as information retrieval services and other multiple processing nodes,etc Load Balancing can also help you scale your server's performance to keep up with the increasing demands of clients in grid environment

Advantages of Grid Computing:

There are several strong benefits for building Grid Computing; they provide

• A uniform corporate computing environment that is efficient to users,

• Secure communications,

• The cost effective

Objective

The main objective of this project is to

1. The main objective is to minimize the waiting and execution time.

2. We here implement a scheduling algorithm to distribute the process among the client in peer to peer environment

3. Thus an efficient load balancing with improved efficiency and increased scalability in the grid nodes can be achieved

LOAD BALANCING AND SCALABILITY IN GRIDS

We present and evaluate an implementation of a scalable load-balancing scheme that collectively accept and service the client nodes. The node addresses using Priority technique, and memory management allowing any node to participate effectively. Once a client is active in the network the system information's are retrieved to balance the load among the grid.. We use the low-overhead based technique to improve the communications of the node in the grid. In our prototype, each host keeps information about the remaining hosts in the system. Load information is maintained using periodic multicast amongst the grid hosts. Performance measurements suggest that our prototype provides a base solution for improving the functionality

In the grid environment the other factor that is a frequently claimed attribute of multiprocessor systems. The ability to maintain cost effectiveness as the workload grows is the scalability constraint. This in turn improves the working of the luster nodes and the workload is distributed based on the scheduling scheme proposed.

IMPORTANCE OF LOAD BALANCING AND SCALABILITY

Ø There is no single-point of failure (when one element fails, another fills its void);

Ø Your sites will be quicker because these servers balance the workload between them which predict their performance and improve.

Ø True reliability at 99.99% uptime

Ø High degree of Flexibility at any modeling.

EXISTING SCHEME

As the previous work many design issues remained with the grid environment

1. The load increases with the increase in number/size of grid nodes.

2. FCFS and SJF are basically used for process scheduling in Grid computing

3. The shorter jobs completes immediately while the longer jobs waits for a long time.

4. The scalability and availability of the complex grids

Advantages:

1. Dynamic allocation of CPU to running process

2. The system can provide and they handle process fragmentation problem

3. Adaptive for local jobs and remote jobs without any loss of performance and highly adaptive for grid environment

4. Job allocation based on Priority with FCFS,SJF as sub-routines

Disadvantages:

1. The load increases with the increase in number/size of grid nodes.

2. FCFS and SJF are basically used for process scheduling in Grid computing which remained complex over time.

3. The shorter jobs completes immediately while the longer jobs waits for a long time.

NEED FOR NEW SCHEDULING ALGORITHM

The assignment of physical processors to processes allows processors to accomplish work. The problem of determining when processors should be assigned and to which processes is called processor scheduling or CPU scheduling. When more than one process is run able, the operating system must decide which one first. The part of the operating system concerned with this decision is called the scheduler, and algorithm it uses is called the scheduling algorithm. Many objectives must be considered in the design of a scheduling discipline. In particular, a scheduler should consider fairness, efficiency, response time, turnaround time, throughput, etc., Some of these goals depends on the system one is using for example batch system, interactive system or real-time system, etc. but there are also some goals that are desirable in all systems.

The proposed scheduling scheme Process Scheduling improves the performance. We proposed a new scheduling scheme called process scheduling. its based on the information's retrieved the process are scheduled effectively. Get the jobs from the job pool and arrange in the order using Priority Scheduling. Ordered jobs are scheduled by using Round-robin scheduling

In the process scheduling, processes are dispatched in a priority manner and are given a limited amount of CPU time called a time-slice or a quantum. Here used common quantum time for all the processor.

If a process does not complete before its CPU-time expires, the CPU is preempted and given to the next process waiting in a queue. The preempted process is then placed at the back of the ready list.

Process Scheduling is preemptive (at the end of time-slice) therefore it is effective in time-sharing environments in which the system needs to guarantee reasonable response times for interactive users. In any event, the average waiting time under process scheduling is often quite long

The only interesting issue with this scheduling scheme is the length of the quantum. Setting the quantum too short causes too many context switches and lower the CPU efficiency. On the other hand, setting the quantum too long may cause poor response time and approximates FCFS.

Advantages:

Ø To minimize the waiting and processing time of the given jobs

Ø Improves QoS

Ø We can increase the number of nodes and given jobs by using the proposed scheduling

PROBLEM FORMULATION

Problem statement

1. To create a Group of grid computing

2. To increase the performance of Scheduling

Generating graphs to fond a optimal solution for Scheduling and job allocation

Ø In the grid group choose the grid nodes under a server

Ø Retrieve the system information such as processor speed, RAM utilized and other.

Ø Order the system utilization and assign the jobs based on it.

Ø Given jobs are scheduled by Processing Scheduling

Ø Compare the scheduling outcome with the proven results

CONCLUSION AND FUTURE ENHANCEMENT

In this project we have connected around 20 clients to a single server, this is our Grid environment .The system information which includes the Capacity of RAM, processor speed and memory are retrieved dynamically from the Grid nodes. The retrieved information is sequenced by using priority scheduling, allotted the jobs based on the priority of the processor .The jobs are then processed by the processor based on process scheduling algorithm.

The proposed method will calculate the both capability of jobs and processor. It will reduce the waiting time of jobs in queue and turn around time also, thus overall Grid Performance has increased. We implement the Process scheduling to provide a best effort scheduling to improve the load balancing and scalability.