Friedrich-Alexander-Universität UnivisDeutsch FAU-Logo
Techn. Fakultät Willkommen am Department Informatik FAU-Logo
Department of Computer Science 4
Dept. of Computer Science  >  CS 4  >  Research  >  PowerManagement  >  Projects  >  CoolIX
CoolIX Project
Event-Driven Temperature Estimation
With increasing clock speed and level of integration in today's processors, memories, and I/O-controllers, power dissipation is becoming a definitive concern of system design. Control-theoretic techniques have proven to manage the heat dissipation and temperature starting from the level of functional blocks within the processor up to the level of complete systems, so that a thermal emergency will never be reached. However application-, user- or service-specific requirements had to be neglected.
In this work we investigate dynamic thermal management with respect to the demands of individual applications, users or services. We present an event-driven approach to determine on-the-fly the energy consumption on a fine grained level and describe a model to estimate the temperature without the need for measurement. With this power and thermal model - combined with the well-known facility of resource containers - it is possible to throttle the execution of individual tasks according to their energy-specific characteristics and the thermal requirements of the system. In addition to throttling we investigate a modified process scheduler which allots CPU time according to the power contribution of each task to the current temperature level of the processor.
Experiments using a Pentium 4 architecture running a modified Linux show that a given temperature limit for the CPU will not be exceeded while tasks are scheduled according to their energy consumption.

Distributed Thermal Management
In modern data centers, the impact on the thermal properties by increased scale and power densities is enormous and poses new challenges on the designers of both computing as well as cooling systems. Control-theoretic techniques have proven to manage the heat dissipation and the temperature to avoid thermal emergencies, but are not aware of the task currently executing or its specific service requirements.
We developed a new operating system abstraction to transparently account and control the energy usage of individual tasks in a distributed system. Event-monitoring counters embedded in modern processors are used to determine on-the-fly the power consumption and who has used the power in the system. With the specification of the cooling system (thermal resistance and capacitance), the temperature can be estimated without the need for measurement and used to trigger task-specific throttling. This is achieved by extending the well-known concept of resource containers to a distributed system, similar to Cluster Reserves. Our energy containers are globally identifiable and represent activities or tasks composed of several processes communicating over the network, e.g. in a client/server relationship. Forwarding the identifiers does not require extra messages as they are sent piggyback with the network traffic via IPv6 connections.
The processing of a request can be throttled to meet the thermal requirements of the system, even if machine boundaries are crossed, e.g. by remote procedure calls in a client/server relationship.
The concept is transparent to the applications running on the modified operating system as well as to other (unmodified) operating systems. Our approach allows individual temperature limits to be set for each server based on its location in the cluster and the position of the air-conditioning units.

Dynamic Thermal Management for Distributed Systems
Andreas Weissel, Frank Bellosa
Proceedings of the First Workshop on Temperature-Aware Computer Systems (TACS-1), München, Germany,
June 2004
[Abstract] [Full Paper (pdf), 200 kB]

Event-Driven Energy Accounting for Dynamic Thermal Management
Frank Bellosa, Simon Kellner, Martin Waitz, Andreas Weissel
Proceedings of the Workshop on Compilers and Operating Systems for Low Power (COLP'03), New Orleans, Louisiana, USA,
September 2003
[Abstract] [Full Paper (pdf), 596 kB]

The Case for Event-Driven Energy Accounting
Frank Bellosa
June 2001
Technical Report TR-I4-01-07, Department of Computer Science, University of Erlangen
[Abstract] [Full Paper (ps,http), 907 kB] [Full Paper (pdf), 753 kB]

The Benefits of Event-Driven Energy Accounting in Power-Sensitive Systems
Frank Bellosa
Proceedings of 9th ACM SIGOPS European Workshop, Kolding, Denmark
September 2000
[Abstract] [Full Paper (pdf), 60 kB]
  Imprint   Privacy Last modified: 2004-06-28 11:33   AW