Peloton: a relational database management system that is designed for autonomous operation.

Peloton is a relational database management system that is designed for autonomous operation. The system’s integrated planning component not only optimizes the system for the current workload, but also predicts future workload trends before they occur so that the system can prepare itself accordingly. It also enables new optimizations that are not possible today because the complexity of managing these systems has surpassed the abilities of human experts.

In-Memory

Fast execution using an architecture designed for DRAM/NVM data storage.

Hybrid

Execute OLAP workloads while simultaneously executing OLTP transactions that update the database.

 Autonomous

Automatically optimize and tune the database without any human intervention.

 Open Source

Apache Software Licensed. All code is available on Github.

Link to Wiki Documentation

Link to Publications

Notice

Peloton is still in its early development, and thus it is not ready for production environments. Furthermore, all the of the self-driving components are currently disabled by default in the latest release. Please contact us if you are interested in trying this out in your application: info@pelotondb.io

DOWNLOAD

Designed and developed at Carnegie Mellon University in Pittsburgh, PA.

You may also like...