Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Author: search.filters.author.Santhi Thilagam, P.S.Subject: search.filters.subject.Distributed computer systems

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    An efficient search to improve neighbour selection mechanism in P2P network
    (2009) Totekar, C.R.; Santhi Thilagam, P.S.
    One of the key challenging aspects of peer-to-peer systems has been efficient search for objects. For this, we need to minimize the number of nodes that have to be searched, by using minimum number of messages during the search process. This can be done by selectively sending requests to nodes having higher probability of a hit for queried object. In this paper, we present an enhanced selective walk searching algorithm along with low cost replication schemes. Our algorithm is based on the fact that most users in peer-to-peer network share various types of data in different proportions. This knowledge of amount of different kinds of data shared by each node is used to selectively forward the query to a node having higher hit-ratio for the data of requested type, based on history of recently succeeded queries. Replication scheme replicates frequently accessed data objects on the nodes which get high number of similar queries or closer to the peers from where most of the queries are being issued. Two simple replication schemes have been discussed and their performances are compared. Experimental results prove that our searching algorithm performs better than the selective walk searching algorithm. © 2009 Springer Berlin Heidelberg.
  • No Thumbnail Available
    Item
    Live migration of virtual machines with their local persistent storage in a data intensive cloud
    (Inderscience Enterprises Ltd. editor@inderscience.com, 2017) Modi, A.; Achar, R.; Santhi Thilagam, P.S.
    Processing large volumes of data to drive their core business has been the primary objective of many firms and scientific applications in these days. Cloud computing being a large-scale distributed computing paradigm can be used to cater for the needs of data intensive applications. There are various approaches for managing the workload on a data intensive cloud. Live migration of a virtual machine is the most prominent paradigm. Existing approaches to live migration use network attached storage where just the run time state needs to be transferred. Live migration of virtual machines with local persistent storage has been shown to have performance advantages like security, availability and privacy. This paper presents an optimised approach for migration of a virtual machine along with its local storage by considering the locality of storage access. Count map combined with a restricted block transfer mechanism is used to minimise the downtime and overhead. The solution proposed is tested by various parameters like bandwidth, write access patterns and threshold. Results show the improvement in downtime and reduction in overhead. © © 2017 Inderscience Enterprises Ltd.