CBF: metadata management in cloud computing

Abstract

In cloud era as the data stored is enormous, the efficient retrieval of data with reduced latency plays a major role. This paper proposes the CBF: Cloud Bloom Filter - a novel mechanism for metadata management in the cloud computing database which improves the search efficiency of data. This paper proposes a three layered cloud metadata architecture which facilitates keyword based information retrieval that provides an efficient retrieval of exact data from cloud data server by reducing the search space. The attributes of metadata model is designed in such a way that the query is mapped to the exact location of the data in the data server, leads to the speedy retrieval of data from the data servers. CBF is used to reduce the disk lookups for non-existent files. Avoiding costly disk lookups considerably increases the performance of a database query operation. GBF, Global Bloom Filter provides the protocol for placing the metadata file in the metadata server and its replica location. LBF, Local Bloom Filter in the metadata server effectively reduces the time taken to update the respective file with limited updating overhead. CBF takes care of supply of the updated data instead of stale data to the user. The proposed scheme significantly reduces the time taken to retrieve the data from the data server.