Haren

Abstract

In modern Stream Processing Engines (SPEs), numerous diverse applications, which can differ in aspects such as cost, criticality or latency sensitivity, can co-exist in the same computational node. When these differences need to be considered to control the performance of each application, custom scheduling of operators to threads is of key importance. Many solutions have been proposed regarding schedulers that allocate threads to operators to optimize specific metrics (e.g., latency) but there is still lack of a middleware that allows arbitrarily complex scheduling strategies to be seamlessly plugged on top of an SPE. We demonstrate Haren, a general scheduling middleware that fills this gap. Haren can be integrated into SPEs through a compact interface and efficiently enforce user-defined scheduling rules. This demo shows how Haren makes it is possible to adapt the use of computational resources over time to meet the goals of a variety of user-defined scheduling policies.