SLSM - A Scalable Log Structured Merge Tree with Bloom Filters for Low Latency Analytics. (2016)

• Record Type: Journal Article
• Authors: Riyaz, P.A.; Varghese, Surekha Mariam
• Is Part Of: Procedia technology. Volume 24(2016)
• Page Start: 1491
• Page End: 1498
• Publication Date: 2016
• Subjects: Bigdata -- HBase -- Log Structured Merge tree -- bloom-filter -- next generation databases -- SLSM ;; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.05.075
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: In the era of Bigdata, millions of searches, queries etc. happens in a second. There is a need for next generation databases which can store and process bigdata more effectively. NoSQL databases are created to solve the problems of scalability issues related with traditional databases. Year by year the bigdata is getting new dimensions. HBase is a NoSQL database suitable for random, real-time read/write access to Big Data. LSM tree used in HBase helps to achieve this high performance. Commodity hardware have moderate RAM size. SLSM, an optimized Log Structured Merge Tree which dramatically reduces the read amplification and write amplification is proposed in this paper for commodity hardware. Incorporation of variant of bloom filters increases the read performance.