pranjul mishra

Galgotias University,Greater Noida, Computer Science and Engineering, Post-Doc

Followers

Following

Public Views

Interests

Uploads

Papers by pranjul mishra

Massively Distributed Systems: Design Issues and Challenges

The forty year trend in the computing industry is away from centralized, high unit cost, low unit... more The forty year trend in the computing industry is away from centralized, high unit cost, low unit volume products toward distributed, low unit cost, high unit volume products. The next step in this process is the emergence of massively distributed systems. These systems will penetrate even more deeply into the fabric of society and become the information power grids of the 21st century. They will be ubiquitous. Most will operate outside the normal cognizance of the people they serve and most will be based on embedded systems that present nontraditional computing interfaces to their users. They will be engineered to operate as distributed utilities, much like the energy, water, transportation and media broadcast businesses do today. The first deployment of massively distributed systems is likely to occur as support structures for these industries.

Download

Use of efficient broadcast protocols in asynchronous distributed systems. Doctoral thesis

Reliable broadcast protocols are important tools in distributed and fault-tolerant programming. T... more Reliable broadcast protocols are important tools in distributed and fault-tolerant programming. They are useful for sharing information and for maintaining replicated data in a distributed system. However, a wide range of such protocols has been proposed. These protocols differ in their fault tolerance and delivery-ordering characteristics. There is a tradeoff between the cost of a broadcast protocol and how much ordering it provides. It is, therefore, desirable to employ protocols that support only a low degree of ordering whenever possible. This dissertation presents techniques for deciding how strongly ordered a protocol is necessary to solve a given application problem. It is shown that there are two distinct classes of application problems: problems that can be solved with efficient, asynchronous protocols, and problems that require global ordering. The concept of a linearization function is introduced that maps partially ordered sets of event to totally ordered histories. The author show how to construct an asynchronous implementation that solves a given problem if a linearization function for it can be found. He proves that, in general, the question of whether a problem has an asynchronous solution is undecidable; hence, there exists no general algorithm that would automatically construct a suitable linearization function for a given problem. Therefore, he considers an important subclass of problems that have certain commutativity properties. He presents techniques for constructing asynchronous implementations for this class.

An ordered and reliable broadcast protocol for distributed systems

Computer Communications, 1997

The purpose of a reliable broadcast protocol is to allow groups of nodes on unreliable broadcast ... more The purpose of a reliable broadcast protocol is to allow groups of nodes on unreliable broadcast networks to reliably broadcast messages. A reliable broadcast protocol must guarantee two properties: (1) all of the receivers in a group receive the broadcast messages, and (2) each of the receivers orders the messages in the same sequence. In an optimistic approach to reliable broadcast protocol, a batch acknowledgement is employed for a sequence of broadcast messages, instead of one or more acknowledgements per broadcast message used in the pessimistic approach. In this paper, based on the optimistic approach, we have proposed a counter-based reliable broadcast protocol. In this protocol, the unique token ownership is circulated among all the nodes in an order specified by a token-passing-list. The system state which records related information about messages broadcast by each node is included in the token message. By appropriately updating the counter information recorded in the system state included in the token message, instead of using explicit acknowledgement messages, the proposed protocol needs fewer control messages to commit a broadcast message than other protocols, no matter whether the rate of transmission errors is high or low. Moreover, we show how to handle the flow control problem and describe the token update technique.

Download

Broadcast Protocols for Distributed Systems

IEEE Transactions on Parallel and Distributed Systems, 1990

... Based on this strategy, it is possible to design simple and networks, total order. efficient ... more

pranjul mishra

Uploads

Papers by pranjul mishra

Log In