Abstract
Current state-of-the-art parallel main memory DBMSs are designed according to the principles of a shared-nothing architecture driven by the intention of minimizing network traffic and thereby preserve the main memory performance advantage (as discussed in Chap. 2). The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage technology feasible. A modern storage system such as RAMCloud keeps all data resident in main memory, provides durability, high-availability and is elastic: exploiting these characteristics in the context of a database management system is desirable. Nowadays, provisioning of information technology infrastructure over the Internet—including in-memory computing—allows the service providers to leverage the economies of scale and offer their services at an unbeatable price point. Being able to utilize hosted main memory-based storage for operating a database system makes in-memory data management even more economically viable.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Tinnefeld, C. (2016). Conclusions. In: Building a Columnar Database on RAMCloud. In-Memory Data Management Research. Springer, Cham. https://doi.org/10.1007/978-3-319-20711-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-20711-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20710-0
Online ISBN: 978-3-319-20711-7
eBook Packages: Business and ManagementBusiness and Management (R0)