Speeding DBLP querying using hadoop and spark

Aegean International Textile and Advanced Engineering Conference 2018

Alsmirat, M.^1 ; Jararweh, Y.^1 ; Al-Ayyoub, M.^1

Jordan University of Science and Technology, Computer and Information Technology, Computer Science Department, Jordan^1

关键词: Conventional database;    Execution time;    Library projects;    Query execution time;    Querying process;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/459/1/012003/pdf
DOI  :  10.1088/1757-899X/459/1/012003

来源: IOP

【 摘 要 】

Big data is becoming bigger every day. Even for simple applications such as the Digital Bibliography & Library Project (DBLP) database, the data is becoming unmanageable using the conventional databases because of its size. Applying big data processing methods such as Hadoop and Spark is becoming more popular because of that. In this work, we investigate the use of Hadoop and Spark in the querying process of big data and we compare the performance of them in terms of their execution time. We use the DBLP database as a case study. Results show that Hadoop and Spark enhances the query execution time significantly when compared with conventional database management systems. We also found that Spark enhances the execution time over Hadoop.