Project: Operating In-Memory Databases in the Cloud

Team: Dr. Jan Schaffner, Benjamin Frank

Research institution: SAP AG

Abstract: More and more data-intensive enterprise applications are deployed in shared environments, such as the data centers of large enterprises or public cloud infrastructures. One example are Software-as-a-Service (SaaS) offerings, where a service provider operates a cluster of servers to host an enterprise application for many customers. A large fraction of such applications exert a so-called mixed workload of transactional and analytical queries on the backend database systems. Because of their read-mostly characteristics, such workloads benefit notably from the performance characteristics of in-memory column databases, making them the database of choice for enterprise SaaS.

To reduce total cost of ownership, SaaS providers try to consolidate multiple customers into each database instance, a technique referred to as multi tenancy. In this project, we develop techniques that elastically contract and expand a cluster of in-memory databases depending on tenants behavior over time while maintaining response time guarantees.

Over the course of a typical working day, dramatic variations in tenant load can be observed for the different tenants. The figureshows a load trace taken from a productive SAP on-demand application cluster in the last week of 2010, and clearly features workdays (with a drop at lunch time), working weeks and annual calendar events. This project seeks to exploit these load variations to achieve good utilization of the database cluster.

Last modified 8 years ago Last modified on Jan 10, 2014 11:01:46 AM

Attachments (1)

Download all attachments as: .zip