Description

Data center is a pool of resources (computational, storage, network) interconnected using a communication network as it interconnects all of the data center resources together. Inter-connecting number of servers in a data center is becoming a major concern to meet the need of high capacity architecture. The processors are deployed in racks. Each rack can have a top-of-rack (ToR) Ethernet switch that is used to connect to an aggregation layer that consists of large Ethernet switches. Then, the aggregation layer is connected to a set of routers which provide connection to the public Internet. The advent and continued growth of large data centers has led to much interest in switch architectures that can economically meet the high capacities needed for interconnecting the thousands of servers in these data centers. Various multilayer architectures employing thousands of switches have been pro-posed in the literature. The system make use of the observation that the traffic in a data center is a mixture of relatively static and rapidly fluctuating components, and develop a combined scheduler for both these components using a generalization of the load-balanced scheduler. The system proposed a new load-balanced scheduler combining these two components and incorporate an opportunistic scheduler that sends traffic on a direct path. The result show that the proposed scheduling process enhance the overall throughput and reduce the average delay and also works very well despite avoiding the use of a central scheduler for making packet-by-packet scheduling decisions.