Testing Very Large Database Management Systems: The Case of SAP HANA

Bach, Thomas; Andrzejak, Artur; Seo, Changyun; Bierstedt, Christian; Lemke, Christian; Ritter, Daniel; Hwang, Dong Won; Sheshi, Erda; Schabernack, Felix; Renkes, Frank; Gaumnitz, Gordon; Martens, Jakob; Hoemke, Lars; Felderer, Michael; Rudolf, Michael; Jambigi, Neetha; May, Norman; Joy, Robin; Scheja, Ruben; Schwedes, Sascha; Seibel, Sebastian; Seifert, Sebastian; Haas, S.; Kraft, Stephan; Kröll, Thomas; Scheuer, Tobias; Lehner, Wolfgang

doi:10.1007/s13222-022-00426-x

Cited by 12 publications

(1 citation statement)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies on in-memory computing have demonstrated its efficacy in various applications. For instance, SAP HANA, one of the leading in-memory computing platforms (Bach et al, 2022), has been shown to accelerate database processing times by orders of magnitude compared to disk-based systems. Researchers have also explored the scalability aspects of in-memory computing, focusing on how distributed architectures can be leveraged to handle growing data loads without compromising performance.…”

Section: Background and Related Workmentioning

confidence: 99%

Unleashing real-time analytics: A comparative study of in-memory computing vs. traditional disk-based systems

Levin

2024

Braz. J. of Sci.

View full text Add to dashboard Cite

The article presents a comprehensive study evaluating the performance differences between in-memory computing (IMC) and traditional disk-based database systems, specifically focusing on Redis and PostgreSQL. Given the escalating demands for real-time data analytics across various sectors, the research delves into the comparative efficiency of these two data management paradigms in processing large datasets. Utilizing a synthetic dataset of 23.6 million records, we orchestrated a series of data manipulation tasks, including aggregation, table joins, and filtering operations, to simulate real-world data analytics scenarios. The experiment, conducted on a high-performance computing setup, revealed that Redis significantly outperformed PostgreSQL in all tested operations, showcasing the inherent advantages of IMC in terms of speed and efficiency. Data aggregation tasks saw Redis completing the process up to ten times faster than PostgreSQL. Similarly, table joining, and data filtering tasks were executed more swiftly on Redis, emphasizing IMC's potential to facilitate instantaneous data analytics. These findings underscore the pivotal role of IMC technologies like Redis in empowering organizations to harness real-time insights from big data, a critical capability in today's fast-paced business environment. The study further discusses the implications of adopting IMC over traditional systems, considering aspects such as cost, integration challenges, and the importance of skill development for IT teams. Concluding with strategic recommendations, the article advocates for a nuanced approach to incorporating IMC technologies, highlighting their transformative potential while acknowledging the need for balanced investment and operational planning.

show abstract

Section: Background and Related Workmentioning

confidence: 99%