A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments

ABSTRACT:
We address the problem of dynamic resource management for a large-scale cloud environment. Our contribution includes outlining a distributed middleware architecture and presenting one of its key elements: a gossip protocol that (1) ensures fair resource allocation among sites/applications, (2) dynamically adapts the allocation to load changes and (3) scales both in the number of physical machines and sites/applications. We formalize the resource allocation problem as that of dynamically maximizing the cloud utility under CPU and memory constraints. We first present a protocol that computes an optimal solution without considering memory constraints and prove correctness and convergence properties. Then, we extend that protocol to provide an efficient heuristic solution for the complete problem, which includes minimizing the cost for adapting an allocation. The protocol continuously executes on dynamic, local input and does not require global synchronization, as other proposed gossip protocols do. We evaluate the heuristic protocol through simulation and find its performance to be well-aligned with our design goals.




EXISTING SYSTEM:
}  Gossip protocols are used in an existing system for resource allocation in cloud environment.
}  Gossip protocols used in an existing system assume static input and produce a single output value.
}  Whenever the input changes, they are restarted and produce a new output value.
}  The above process requires global synchronization.

DISADVANTAGES OF EXISTING SYSTEM:
}  Drawbacks of the existing system :
}  Gossip protocol in the existing system assumes static input and produces a single output value.
}  Whenever the input changes, they restarted and produce a new output value which leads to time consumption and requires global synchronization.
}  It’s hard to adapt to changes as the input is static.

PROPOSED SYSTEM:
}  Gossip protocol used in the proposed system executes in a middleware platform.
}  The protocol ensures three design goals namely fairness, adaptability and scalability.
}  The protocol continuously executes while its input and consequently its output dynamically changes.
}  We evaluate the heuristic protocol through simulation and find its performance to be well-aligned with our design goals.
}  We treat all machines as equivalent in the sense they do not belong to specific racks or clusters.

ADVANTAGES OF PROPOSED SYSTEM:
}  Advantages of the proposed system are as follows:
}  Global synchronization can be avoided, as there is a single continuous execution instead of a sequence of executions with restarts.
}  The system can continuously adapt to changes in local input.
}  The gossip protocol continuously executes and dynamically solves the problem of optimally placing applications in a cloud, achieving fair resource allocation.

DATA FLOW DIAGRAM:


 
MODULES:
}  VM Evaluation
}  Resource Allocation
}  Adaptation
}  Demand Sharing
}  Evaluation

MODULES DESCRIPTION
VM Evaluation
}  VM Evaluation is the evaluation of virtual machines in the cloud.
}  The evaluation is based on the physical memory usage of the virtual machines in the cloud.
}  Load of each virtual machine in the cloud is computed and sent to the client for further process.
}  The virtual machine which has most free memory will be ready to receive and process the module/process selected by the client.
}  The evaluation has made for the maximum utility of all virtual machines in the cloud.


Resource Allocation
}  Resource allocation refers to the allocation of cloud resources to the process sent by the client.
}  The most free memory virtual machine in the cloud will receive the process.
}  The resource of the virtual machine is allocated to the process.
}  The resources are allocated without memory constraints.
Adaptation
}  Adaptation is the process of resource allocation for modified process.
}  The client appending something to the process which is already allocated in the cloud for reallocation.
}  The resource is allocated with memory constraints using heuristic algorithm.
}  The memory load of the virtual machines in the cloud is computed and also the memory demand of the modified process is computed.
}  Depend upon the memory usage of VM and demand of process, the resources are allocated to the process.
Demand Sharing
}  Demand Sharing is based on heuristic algorithm and it refers to sharing of memory demand of the process while demand exceeds the capacity of virtual machine.
}  The virtual machines in the cloud are evaluated and memory demand of the process is calculated. If the demand exceeds the capacity of VM, the process is split (divided).
}  Memory demand is computed for the split process.
}  The process of high memory demand is allocated in high free memory VM and other process is allocated in another VM.
Evaluation
}  The overall dynamic resource allocation in large cloud environment is evaluated and displayed as pie graph.
}  The graph shows the overall usage of the virtual machines in the cloud.
}  The graph shows the maximum utility of the Virtual machine under memory constraints.
}  Equal usage of all virtual machines in the cloud is shown in the graph.

HARDWARE REQUIREMENTS:
}  System                 :         Pentium IV 2.4 GHZ
}  Hard Disk            :         160 GB
}  Monitor                :         15 VGA color
}  Mouse                  :         Logitech
}  RAM                    :         2 GB

SOFTWARE REQUIREMENTS:
}  Operating System          :         Windows XP
}  Language                       :         Java
}  IDE                                :         Net beans
}  Tool                               :         VM ware Workstation 2.1

REFERENCE:

Fetahi Wuhib, Rolf Stadler, and Mike Spreitzer, “A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments”, IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, VOL. 9, NO. 2, JUNE 2012.





**********************************

A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments 2012 ieee, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments abstract, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments base paper, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments ppt, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments review documents, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments document, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments details, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments source code,A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments video file, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments project, A Gossip Protocol for Dynamic Resource Management in Large Cloud Environments in java