 |
|
|
|
|
|
|
Department of Computer Science 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
 |
|
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]
|
|
|
|
