Application heartbeats: a generic interface for specifying program performance and goals in autonomous computing environments

  • Authors:

  • Henry Hoffmann;Jonathan Eastep;Marco D. Santambrogio;Jason E. Miller;Anant Agarwal

  • Affiliations:

  • MIT, Cambridge, MA, USA;MIT, Cambridge, MA, USA;MIT, Cambridge, MA, USA;MIT, Cambridge, MA, USA;MIT, Cambridge, MA, USA

  • Venue:
  • Proceedings of the 7th international conference on Autonomic computing
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The rise of multicore computing has greatly increased system complexity and created an additional burden for software developers. This burden is especially troublesome when it comes to optimizing software on modern computing systems. Autonomic or adaptive computing has been proposed as one method to help application programmers handle this complexity. In an autonomic computing environment, system services monitor applications and automatically adapt their behavior to increase the performance of the applications they support. Unfortunately, applications often run as performance black-boxes and adaptive services must infer application performance from low-level information or rely on system-specific ad hoc methods. This paper proposes a standard framework, Application Heartbeats, which applications can use to communicate both their current and target performance and which autonomic services can use to query these values. The Application Heartbeats framework is designed around the well-known idea of a heartbeat. At important points in the program, the application registers a heartbeat. In addition, the interface allows applications to express their performance in terms of a desired heart rate and/or a desired latency between specially tagged heartbeats. Thus, the interface provides a standard method for an application to directly communicate its performance and goals while allowing autonomic services access to this information. Thus, Heartbeat-enabled applications are no longer performance black-boxes. This paper presents the Applications Heartbeats interface, characterizes two reference implementations (one suitable for clusters and one for multicore), and illustrates the use of Heartbeats with several examples of systems adapting behavior based on feedback from heartbeats.