Senior Researcher
Operating Systems and Middleware Group
Hasso-Plattner-Institute for Software Engineering at University Potsdam
Prof.-Dr.-Helmert-Str. 2-3
14482 Potsdam, Germany
@book{ citemaster_1315, author = {Peter Tr\"oger }, isbn = {{9783867276221}}, address = {{G\"ottingen}}, publisher = {{Cuvillier Verlag}}, title = {{Dynamische Ressourcenverwaltung f\"ur dienstbasierte Software-Systeme}}, year = {2008}, }
Kuropka, D., Tröger, P., Staab, S., and Weske, M., eds., Semantic Service Provisioning, Springer Verlag, 2008.
[BibTex]
@book{ citemaster_8367, author = {Dominik Kuropka and Peter Tr\"oger and Steffen Staab and Mathias Weske }, isbn = {{978-3-540-78616-0}}, publisher = {{Springer Verlag}}, title = {{Semantic Service Provisioning}}, year = {2008}, }
Book Section
Tröger, P., “.NET Technology,” Handbook on Industrial Information Technology, Zurawski, R., ed., CRC Press LLC, 2004.
[BibTex]
@inbook{ citemaster_1330, author = {Peter Tr\"oger and Richard Zurawski }, booktitle = {{Handbook on Industrial Information Technology}}, edition = {1}, publisher = {{CRC Press LLC}}, title = {{.NET Technology}}, year = {2004}, month = nov, }
Tröger, P., “Cloud Computing,” Service-orientierte Architekturen mit Web Services. Konzepte - Standards - Praxis., Melzer, I., ed., Spektrum Akademischer Verlag, 2010.
[BibTex]
@inbook{ citemaster_8312, author = {Peter Tr\"oger and Ingo Melzer }, booktitle = {{Service-orientierte Architekturen mit Web Services. Konzepte - Standards - Praxis.}}, edition = {4}, isbn = {{978-3827425492}}, publisher = {{Spektrum Akademischer Verlag}}, title = {{Cloud Computing}}, year = {2010}, month = apr, }
Tröger, P., “Grid Computing,” Service-orientierte Architekturen mit Web Services. Konzepte - Standards - Praxis., Melzer, I., ed., Spektrum Akademischer Verlag, 2008.
[BibTex]
@inbook{ citemaster_1331, author = {Peter Tr\"oger and Ingo Melzer }, booktitle = {{Service-orientierte Architekturen mit Web Services. Konzepte - Standards - Praxis.}}, edition = {3}, isbn = {{978-3827418852}}, publisher = {{Spektrum Akademischer Verlag}}, title = {{Grid Computing}}, year = {2008}, month = may, }
Thesis
Tröger, P., “Aspect-oriented object and component migration,” 2002.
[BibTex]
@mastersthesis{ citemaster_1314, author = {Peter Tr\"oger }, howpublished = {{Humboldt-Universit\"at zu Berlin}}, address = {{Berlin}}, title = {{Aspect-oriented object and component migration}}, year = {2002}, month = sep, }
Journal Article
Polze, A. and Tröger, P., “Trends and Challenges in Operating Systems - from Parallel Computing to Cloud Computing,” Concurrency and Computation: Practice & Experience, vol. 24, 2012, pp. 676-686.
[BibTex]
@article{ citemaster_8873, author = {Andreas Polze and Peter Tr\"oger }, doi = {{10.1002/cpe.1903}}, isbn = {{1532-0634}}, issue = {7}, journal = {{Concurrency and Computation: Practice \& Experience}}, publisher = {{John Wiley \& Sons, Ltd}}, title = {{Trends and Challenges in Operating Systems - from Parallel Computing to Cloud Computing}}, howpublished = {\url{http://dx.doi.org/10.1002/cpe.1903}}, volume = {24}, year = {2012}, pages = {{676-686}}, }
Burkhard, H.-D., Ritzschke, M., Werner, M., Myritz, H., Düffert, U., Winkler, F., Kock, A., Nagel, A., and Tröger, P., “The Humboldt Heroes: Controlling Sony Legged Robots using BDI,” RoboCup-99 Team Descriptions, 1999.
[BibTex]
@article{ citemaster_1265, author = {Hans-Dieter Burkhard and Michael Ritzschke and Matthias Werner and Helmut Myritz and Uwe D\"uffert and Frank Winkler and Andreas Kock and Andreas Nagel and Peter Tr\"oger }, doi = {{10.1.1.86.6136}}, journal = {{RoboCup-99 Team Descriptions}}, title = {{The Humboldt Heroes: Controlling Sony Legged Robots using BDI}}, year = {1999}, }
[Abstract]
The paper describes the architecture and the scientific goals of the Sony Legged Robots team “Humboldt Heroes”. Scientific goals are the study of techniques for autonomous agents under real life conditions.
Tröger, P. and Saar, A., “Web-Services für zustandsbehaftete Ressourcen,” JavaSPEKTRUM, Jan. 2006.
[BibTex]
@article{ citemaster_8358, author = {Peter Tr\"oger and Alexander Saar }, isbn = {{1431-4436}}, journal = {{JavaSPEKTRUM}}, title = {{Web-Services f\"ur zustandsbehaftete Ressourcen}}, year = {2006}, month = jan, }
Tröger, P., “The Multi-Core Era - Trends and Challenges,” Oct. 2008.
[BibTex]
@article{ citemaster_973, author = {Peter Tr\"oger }, day = {{30}}, publisher = {{arXiv}}, title = {{The Multi-Core Era - Trends and Challenges}}, year = {2008}, month = oct, }
[Abstract]
Since the very beginning of hardware development, computer processors were invented with ever-increasing clock frequencies and sophisticated in-build optimization strategies. Due to physical limitations, this 'free lunch' of speedup has come to an end. The following article gives a summary and bibliography for recent trends and challenges in CMP architectures. It discusses how 40 years of parallel computing research need to be considered in the upcoming multi-core era. We argue that future research must be driven from two sides - a better expression of hardware structures, and a domain-specific understanding of software parallelism.
Tröger, P., Rajic, H., Haas, A., and Domagalski, P., “Standardised job submission and control in cluster and grid environments,” International Journal of Grid and Utility Computing, vol. 1, Dec. 2009, pp. 134-145.
[BibTex]
@article{ citemaster_8319, author = {Peter Tr\"oger and Hrabri Rajic and Andreas Haas and Piotr Domagalski }, doi = {{http://dx.doi.org/10.1504/IJGUC.2009.022029}}, isbn = {{1741-847X}}, issue = {2}, journal = {{International Journal of Grid and Utility Computing}}, address = {{Geneva, Switzerland}}, publisher = {{Inderscience Publishers}}, title = {{Standardised job submission and control in cluster and grid environments}}, volume = {1}, year = {2009}, pages = {{134-145}}, month = dec, }
[Abstract]
Cluster and Grid environments mostly require the use of product-specific Application Programming Interface (APIs) to submit, control and monitor computational jobs. The Open Grid Forum standardisation body therefore has developed several specifications to fill the gap and enable developers to code to few standardised APIs. This paper discusses the details of one of these specifications, the Distributed Resource Management Application API. We compare the basic concepts of the finalised API to other specifications from the same area and explain issues and findings uncovered during the standardisation process.
Löwis, M. von and Tröger, P., “Flexibilität nachgerüstet – Cross-Plattform-Einsatz von Visual Studio,” iX, 2004, p. 136.
[BibTex]
@article{ citemaster_8359, author = {Martin L\"owis and Peter Tr\"oger }, issue = {4}, journal = {{iX}}, publisher = {{Heise Verlag}}, title = {{Flexibilit\"at nachger\"ustet \textendash Cross-Plattform-Einsatz von Visual Studio}}, year = {2004}, pages = {{136}}, }
Conference Paper
Tröger, P. and Polze, A., “Object and Process Migration in .NET,” Procceedings of IEEE Workshop on Object-Oriented Realtime Dependable Systems (WORDS), Jan. 2003, pp. 139-146.
[BibTex]
@conference{ citemaster_1316, author = {Peter Tr\"oger and Andreas Polze }, location = {{Guadalajara, Mexico}}, booktitle = {{Procceedings of IEEE Workshop on Object-Oriented Realtime Dependable Systems}}, isbn = {{0-7695-1929-6}}, publisher = {{IEEE Computer Society Press}}, booktitle = {{WORDS}}, title = {{Object and Process Migration in .NET}}, year = {2003}, pages = {{139-146}}, month = jan, citemaster_conference_year = {{2003}}, }
[Abstract]
Most of today’s distributed computing systems in the field do not support the migration of execution entities among computing nodes during runtime. The relatively static association between units of processing and computing nodes makes it difficult to implement fault-tolerant behavior or load-balancing schemes. The concept of code migration may provide a solution to the problems mentioned above. It can be defined as the movement of process, object or component instances from one computing node to another during system runtime in a distributed environment. Within our paper we describe the integration of a migration facility with the help of Aspect-Oriented Programming (AOP) into the.NET framework. AOP is interesting as it addresses non-functional system properties on the middleware level, without the need to manipulate lower system layers like the operating system itself. We have implemented two proof-of-concept applications, namely a migrating web server as well as a migrating file version checker application. The paper contains an experimental evaluation of the performance impact of object migration in context of those two applications.
Tröger, P., Polze, A., and Salfner, F., “On the Applicability of Virtual Machine Migration for Proactive Failover,” SDPS International Conference, Special Track on Virtualization, 2011.
To appear.
[BibTex]
@conference{ citemaster_8663, author = {Peter Tr\"oger and Andreas Polze and Felix Salfner }, booktitle = {{SDPS International Conference, Special Track on Virtualization}}, title = {{On the Applicability of Virtual Machine Migration for Proactive Failover}}, year = {2011}, citemaster_conference_year = {{2011}}, }
[Abstract]
Proactive failover is a resiliency strategy that replaces classical reactive recovery by a combination of failure prediction and preventive failover. The approach can be applied to different hardware and software layers that exist in modern evolving systems – but each layer has its own costs and failover capabilities.
This paper investigates the applicability of virtual machine live migration for proactive failover, based on a generic strategy for choosing a proactive failover system level. The experimental performance analysis shows that virtual machine live migration has product-specific performance behavior with product-independent upper bounds on the total migration time. One major influencing factor is the dirty page generation rate inside of the virtual machine.
Meyer, H., Kuropka, D., and Tröger, P., “ASG - Techniques of Adaptivity,” Dagstuhl Seminar on Autonomous and Adaptive Web Services, 2007.
[BibTex]
@conference{ citemaster_209, author = {Harald Meyer and Dominik Kuropka and Peter Tr\"oger }, booktitle = {{ Dagstuhl Seminar on Autonomous and Adaptive Web Services}}, publisher = {{Schloss Dagstuhl - Leibniz-Zentrum f\"ur Informatik}}, title = {{ASG - Techniques of Adaptivity}}, year = {2007}, }
[Abstract]
The introduction of service-orientation leads to significant improvements regarding flexibility in the choice of business partners and IT-systems. This requires an increased adaptability of enterprise software landscapes as the environment is more dynamic than the ones in traditional approaches. In this paper we present different types of adaptation scenarios for service compositions and their implementation in a service provision platform. Based on experiences from the Adaptive Services Grid (ASG) project, we show how dynamic adaptation strategies are able to support an automated selection, composition and binding of services during run-time.
Rasche, A., Tröger, P., Dirska, M., and Polze, A., “Foucault’s Pendulum in the Distributed Control Lab,” Procceedings of IEEE Workshop on Object-Oriented Realtime Dependable Systems, Oct. 2003, pp. 299-306.
[BibTex]
@conference{ citemaster_239, author = {Andreas Rasche and Peter Tr\"oger and Michael Dirska and Andreas Polze }, booktitle = {{Procceedings of IEEE Workshop on Object-Oriented Realtime Dependable Systems}}, title = {{Foucault's Pendulum in the Distributed Control Lab}}, year = {2003}, pages = {{299-306}}, month = oct, }
Tröger, P., Rajic, H., Haas, A., and Domagalski, P., “Standardization of an API for Distributed Resource Management Systems,” Seventh IEEE International Symposium on Cluster Computing and the Grid (CCGrid), May. 2007, pp. 619-626.
[BibTex]
@conference{ citemaster_243, author = {Peter Tr\"oger and Hrabri Rajic and Andreas Haas and Piotr Domagalski }, location = {{Rio de Janeiro}}, booktitle = {{ Seventh IEEE International Symposium on Cluster Computing and the Grid}}, doi = {{10.1109/CCGRID.2007.109}}, isbn = {{0-7695-2833-3}}, publisher = {{IEEE Computer Society}}, booktitle = {{CCGrid}}, title = {{Standardization of an API for Distributed Resource Management Systems}}, year = {2007}, pages = {{619-626}}, citemaster_conference_year = {{2007}}, month = may, }
Tröger, P. and Köhne, K., “Grid Programming for Heterogeneous Environments - The Grid-Occam Project,” Tagungsband des 2. Workshops zu Grid-Technologie für den Entwurf technischer System, Apr. 2006, pp. 39-46.
[BibTex]
@conference{ citemaster_244, author = {Peter Tr\"oger and Kai K\"ohne }, booktitle = {{Tagungsband des 2. Workshops zu Grid-Technologie f\"ur den Entwurf technischer System}}, title = {{Grid Programming for Heterogeneous Environments - The Grid-Occam Project}}, year = {2006}, pages = {{39-46}}, month = apr, }
Tröger, P., Löwis, M. von, and Polze, A., “The Grid-Occam Project,” Lecture Notes in Computer Science, vol. 3270, 2004, pp. 151-164.
[BibTex]
@conference{ citemaster_763, author = {Peter Tr\"oger and Martin L\"owis and Andreas Polze }, doi = {{10.1007/b100715}}, isbn = {{978-3-540-23301-5}}, publisher = {{Springer Berlin / Heidelberg}}, howpublished = {{Lecture Notes in Computer Science}}, title = {{The Grid-Occam Project}}, volume = {3270}, year = {2004}, pages = {{151-164}}, }
[Abstract]
We present a new implementation of the old Occam language, using Microsoft .NET as the target platform. We show how Occam can be used to develop cluster and grid applications, and how such applications can be deployed. In particular, we discuss automatic placement of Occam processes onto processing nodes.
Tröger, P. and Mengistu, D., “Performance Optimization for Multi-agent Based Simulation in Grid Environments,” 8th IEEE International Symposium on Cluster Computing and the Grid (CCGrid), 2008, pp. 560-565.
[BibTex]
@conference{ citemaster_953, author = {Dawit Mengistu and Peter Tr\"oger }, location = {{Lyon, France}}, booktitle = {{8th IEEE International Symposium on Cluster Computing and the Grid}}, publisher = {{IEEE Computer Society}}, booktitle = {{CCGrid}}, title = {{Performance Optimization for Multi-agent Based Simulation in Grid Environments}}, year = {2008}, pages = {{560-565}}, citemaster_conference_year = {{2008}}, }
Tröger, P., Rasche, A., Dirska, M., and Polze, A., “Foucault’s Pendulum in the Distributed Control Lab,” 9th IEEE International Workshop on Object-Oriented Real-Time Dependable Systems (WORDS), 2003, pp. 299-306.
[BibTex]
@conference{ citemaster_972, author = {Andreas Rasche and Peter Tr\"oger and Michael Dirska and Andreas Polze }, location = {{Anacapri, Italy}}, booktitle = {{9th IEEE International Workshop on Object-Oriented Real-Time Dependable Systems}}, isbn = {{0-7695-2054-5}}, publisher = {{IEEE Computer Society}}, booktitle = {{WORDS}}, title = {{Foucault's Pendulum in the Distributed Control Lab}}, year = {2003}, pages = {{299-306}}, citemaster_conference_year = {{2003}}, }
Mengistu, D., Tröger, P., Lundberg, L., and Davidsson, P., “Performance Optimization for Large-Scale Multi Agent Based Simulations,” First International Symposium on Grid and Distributed Computing (GDC).
To appear.
[BibTex]
@conference{ citemaster_984, author = {Dawit Mengistu and Peter Tr\"oger and Lars Lundberg and Paul Davidsson }, location = {{Sanya, China}}, booktitle = {{First International Symposium on Grid and Distributed Computing }}, booktitle = {{GDC}}, title = {{Performance Optimization for Large-Scale Multi Agent Based Simulations}}, citemaster_conference_year = {{2008}}, }
Tröger, P., Meyer, H., Melzer, I., and Flehmig, M., “Dynamic Provisioning and Monitoring of Stateful Services,” 3rd International Conference on Web Information Systems and Technologies (WEBIST 2007), Mar. 2007, pp. 434-438.
[BibTex]
@conference{ citemaster_994, author = {Peter Tr\"oger and Harald Meyer and Ingo Melzer and Marcus Flehmig }, booktitle = {{3rd International Conference on Web Information Systems and Technologies (WEBIST 2007)}}, isbn = {{978-972-8865-77-1}}, title = {{Dynamic Provisioning and Monitoring of Stateful Services}}, year = {2007}, pages = {{434-438}}, month = mar, }
[Abstract]
While tools for service-oriented architectures promise a seamless combination of stateless basic services to new applications, reality looks different. Real-world services are wrapping stateful behavior using application-specific concepts, the monitoring is only available through vendorspecific interfaces, and service installations are bound to particular execution hosts. We present the ASG Services Infrastructure (SI) architecture as our practical solution to these real-world service integration issues. Our framework is based on established Web service standards and supports the dynamic hosting and monitoring of heterogeneous and stateful service implementations.
Schult, W. and Tröger, P., “Loom.NET - an Aspect Weaving Tool,” Workshop on Aspect-Oriented Programming (ECOOP), 2003.
[BibTex]
@conference{ citemaster_1223, author = {Wolfgang Schult and Peter Tr\"oger }, location = {{Darmstadt}}, booktitle = {{Workshop on Aspect-Oriented Programming}}, booktitle = {{ECOOP}}, title = {{Loom.NET - an Aspect Weaving Tool}}, year = {2003}, citemaster_conference_year = {{2003}}, }
Rasche, A., Tröger, P., Dirska, M., and Polze, A., “Foucault’s Pendulum in the Distributed Control Lab,” IEEE International Workshop on Object-Oriented Real-Time Dependable Systems, vol. 0, 2003.
[BibTex]
@conference{ citemaster_1307, author = {Andreas Rasche and Peter Tr\"oger and Michael Dirska and Andreas Polze }, booktitle = {{IEEE International Workshop on Object-Oriented Real-Time Dependable Systems}}, doi = {{http://doi.ieeecomputersociety.org/10.1109/WORDS.2003.1267543}}, isbn = {{0-1795-2054-5}}, address = {{Los Alamitos, CA, USA}}, publisher = {{IEEE Computer Society}}, title = {{Foucault's Pendulum in the Distributed Control Lab}}, volume = {0}, year = {2003}, }
Salfner, F., Tröger, P., and Tschirpke, S., “Cross-Core Event Monitoring For Processor Failure Prediction,” The International Conference on High Performance Computing & Simulation, Workshop on Dependable Multi-Core Computing (DMCC), Jun. 2009, pp. 67-73.
[BibTex]
@conference{ citemaster_6770, author = {Felix Salfner and Peter Tr\"oger and Steffen Tschirpke }, location = {{Leipzig}}, booktitle = {{The International Conference on High Performance Computing \& Simulation, Workshop on Dependable Multi-Core Computing}}, doi = {{10.1109/HPCSIM.2009.5191988}}, publisher = {{IEEE}}, booktitle = {{DMCC}}, title = {{Cross-Core Event Monitoring For Processor Failure Prediction}}, year = {2009}, pages = {{67-73}}, month = jun, citemaster_conference_year = {{2009}}, }
[Abstract]
A recent trend in the design of commodity processors is the combination of multiple independent execution units on one
chip. With the resulting increase of complexity and transistor count, it becomes more and more likely that a single execution unit on
a processor gets faulty. In order to tackle this situation, we propose an architecture for dependable process management in chip-
multiprocessing machines. In our approach, execution units sur veil each other to anticipate future hardware failures. The prediction
relies on the analysis of processor hardware performance counters by a statistical rank-sum test. Initial experiments with the Intel Core
processor platform proved the feasibility of the approach, but also showed the need for fur ther investigation due to a high prediction
quality variation in most of the cases.
Polze, A., Tröger, P., Hentschel, U., and Heinze, T., “A scalable, self-adaptive architecture for remote patient monitoring,” First IEEE International Workshop on Object/component/service-oriented Real-time Networked Ultra-dependable Systems (WORNUS), 2010.
To appear.
[BibTex]
@conference{ citemaster_7587, author = {Andreas Polze and Peter Tr\"oger and Uwe Hentschel and Theodor Heinze }, location = {{Carmona, Spain}}, booktitle = {{First IEEE International Workshop on Object/component/service-oriented Real-time Networked Ultra-dependable Systems}}, booktitle = {{WORNUS}}, title = {{A scalable, self-adaptive architecture for remote patient monitoring}}, year = {2010}, citemaster_conference_year = {{2010}}, }
Tröger, P., “System Dependability in the Many-Core Era,” Intel European Research and Innovation Conference (ERIC), 2010.
[BibTex]
@conference{ citemaster_7918, author = {Peter Tr\"oger }, location = {{Braunschweig}}, booktitle = {{Intel European Research and Innovation Conference}}, booktitle = {{ERIC}}, title = {{System Dependability in the Many-Core Era}}, year = {2010}, citemaster_conference_year = {{2010}}, }
Rasche, A., Rabe, B., Tröger, P., and Polze, A., “Distributed Control Lab,” 1st International Workshop on e-learning and Virtual and Remote Laboratories (VIRTUAL-LAB’2004), Aug. 2004, pp. 150-160.
[BibTex]
@conference{ citemaster_8369, author = {Andreas Rasche and Bernhard Rabe and Peter Tr\"oger and Andreas Polze }, booktitle = {{ 1st International Workshop on e-learning and Virtual and Remote Laboratories (VIRTUAL-LAB'2004)}}, isbn = {{972-8865-14-7}}, address = {{Set\'ubal, Portugal}}, publisher = {{INSTICC Press}}, title = {{Distributed Control Lab}}, year = {2004}, pages = {{150-160}}, month = aug, }
[Abstract]
The Distributed Control Lab (DCL)[10] provides an open infrastructure for conducting robotics and control experiments from the Internet. It is based on web service technologies and offers a wide range of frontend applications. Within the DCL environment we focus on safety mechanisms in order to prevent malicious code from damaging experimental equipment. This includes source code analysis, runtime observation and the dynamic replacement of faulty control algorithms. Within the paper we present an overview of our architecture and explain the implemented frontends in detail. We introduce the installed experiments and report our experiences from operation in the last years. In addition we will describe our latest integration of grid computing technologies, which allows the outsourcing of computing-intensive simulation tasks.
Tröger, P., Salfner, F., and Tschirpke, S., “Software-Implemented Fault Injection at Firmware Level,” The Third International Conference on Dependability (DEPEND), 2010, pp. 13-16.
[BibTex]
@conference{ citemaster_8221, author = {Peter Tr\"oger and Felix Salfner and Steffen Tschirpke }, location = {{Venice/Mestre, Italy}}, booktitle = {{The Third International Conference on Dependability }}, doi = {{10.1109/DEPEND.2010.10}}, isbn = {{978-0-7695-4090-0}}, booktitle = {{DEPEND}}, title = {{Software-Implemented Fault Injection at Firmware Level}}, year = {2010}, pages = {{13-16}}, citemaster_conference_year = {{2010}}, }
[Abstract]
Software-implemented fault injection is an established method to emulate hardware faults in computer systems. Existing approaches typically extend the operating system by special drivers or change the application under test. We propose a novel approach where fault injection capabilities are added to the computer firmware. This approach can work without any modification to operating system and / or applications, and can support a larger variety of fault locations. We discuss four different strategies in X86/X64 and Itanium systems. Our analysis shows that such an approach can increase portability, the non-intrusiveness of the injector implementation, and the number of supported fault locations. Firmware-level fault injection paves the way for new research directions, such as virtual machine monitor fault injection or the investigation of certified operating systems.
Sobania, J.-A., Tröger, P., and Polze, A., “Linux Operating System Support for the SCC Platform - An Analysis,” 3rd Many-core Applications Research Community (MARC) Symposium (MARC), 2011.
[BibTex]
@conference{ citemaster_9060, author = {Jan-Arne Sobania and Peter Tr\"oger and Andreas Polze }, location = {{Ettlingen, Germany}}, booktitle = {{3rd Many-core Applications Research Community (MARC) Symposium}}, isbn = {{978-3-86644-717-2 }}, publisher = {{KIT Scientific Publishing, Karlsruhe }}, booktitle = {{MARC}}, title = {{Linux Operating System Support for the SCC Platform - An Analysis}}, year = {2011}, citemaster_conference_year = {{2011}}, }
Salfner, F., Tröger, P., and Polze, A., “Downtime Analysis of Virtual Machine Live Migration,” The Fourth International Conference on Dependability (DEPEND), 2011, pp. 100-105.
[BibTex]
@conference{ citemaster_8655, author = {Felix Salfner and Peter Tr\"oger and Andreas Polze }, location = {{Nice}}, booktitle = {{The Fourth International Conference on Dependability}}, organization = {{IARIA}}, isbn = {{978-1-61208-149-6}}, publisher = {{IARIA}}, booktitle = {{DEPEND}}, title = {{Downtime Analysis of Virtual Machine Live Migration}}, year = {2011}, citemaster_conference_day = {{23}}, citemaster_conference_end_month = {{8}}, citemaster_conference_end_day = {{24}}, citemaster_conference_month = {{8}}, citemaster_conference_end_year = {{2011}}, pages = {{100-105}}, citemaster_conference_year = {{2011}}, }
[Abstract]
Virtual machine environments like VMware, XEN, KVM, and Hyper-V support live migration of guest operating systems, which is used in data centers to provide uninterrupted service during maintenance or to move computation away from failure-prone hosts. The duration of migration, as well as the virtual machine downtime during this process are essential when assessing if service availability agreements might be violated.
We present the result of an experimental study that analyzed virtual machine live migration downtime and duration. We show that total migration time as well as downtime are dominated by specific memory utilization patterns inside the virtualized guest. We experienced that downtime involved by live migration can vary by a factor of more than 23, which can have significant impact on service availability
Tröger, P., Richly, M., and Salfner, F., “Pro-Active Virtual Machine Migration in the HPI FutureSOC Lab,” Fall 2010 Future SOC Lab Day, vol. 42, 2011, pp. 53-58.
[BibTex]
@conference{ citemaster_9064, author = {Peter Tr\"oger and Matthias Richly and Felix Salfner and Christoph Meinel and Andreas Polze and Alexander Zeier and Gerhard Oswald and Dieter Herzog and Volker Smid and Doc D'Errico and Zahid Hussain }, booktitle = {{Proceedings of the Fall 2010 Future SOC Lab Day}}, booktitle = {{Fall 2010 Future SOC Lab Day}}, isbn = {{978-3-86956-114-1}}, address = {{Potsdam, Germany}}, publisher = {{Universit\"atsverlag Potsdam}}, title = {{Pro-Active Virtual Machine Migration in the HPI FutureSOC Lab}}, volume = {42}, year = {2011}, pages = {{53-58}}, citemaster_book_subtitle = {{Technische Berichte des Hasso-Plattner-Instituts für Softwaresystemtechnik an der Universität Potsdam}}, citemaster_conference_year = {{2010}}, }
[Abstract]
Next generation technologies such as multi-core
processors and large memory modules will result in
tremendously increased computing power. However,
this comes at a price: Due to the growing number of
transistors and increased complexity, overall system
reliability of future server systems is about to suffer
significantly.
The HPI FutureSOC Lab project „Towards an Archi-
tectural Pattern for Pro-Active Virtual Machine Mi-
gration“ 1 investigates an architectural blueprint for
managing system dependability in a pro-active fash-
ion. The approach is based on virtual machine live
migration technologies and new failure prediction
approaches.
Within this article, we present initial experimental
results of the project, with a focus on virtual machine
live migration capabilities.
Polze, A., Tröger, P., and Salfner, F., “Timely Virtual Machine Migration for Pro-Active Fault Tolerance,” 2nd International Workshop on Object/component/service-oriented Real-time Networked Ultra-dependable Systems (WORNUS), at 14th International Symposium on Object/Component/Service-oriented Real-time Distributed Computing (ISORC), Mar. 2011, pp. 234-243.
[BibTex]
@conference{ citemaster_8374, author = {Andreas Polze and Peter Tr\"oger and Felix Salfner }, booktitle = {{2nd International Workshop on Object/component/service-oriented Real-time Networked Ultra-dependable Systems (WORNUS), at 14th International Symposium on Object/Component/Service-oriented Real-time Distributed Computing (ISORC)}}, doi = {{10.1109/ISORCW.2011.42}}, publisher = {{IEEE}}, title = {{Timely Virtual Machine Migration for Pro-Active Fault Tolerance}}, year = {2011}, pages = {{234-243}}, month = mar, citemaster_conference_year = {{2011}}, }
[Abstract]
Next generation processor and memory technologies will provide tremendously increasing computing and memory capacities for application scaling. However, this comes at a price: Due to the growing number of transistors and shrinking structural sizes, overall system reliability of future server systems is about to suffer significantly. This makes reactive fault tolerance schemes less appropriate for server applications under reliability and timeliness constraints.
We propose an architectural blueprint for managing server system dependability in a pro-active fashion, in order to keep service-level promises for response times and availability even with increasing hardware failure rates. We introduce the concept of anticipatory virtual machine migration that proactively moves computation away from faulty or suspicious machines. The migration decision is based on health indicators at various system levels that are combined into a global probabilistic reliability measure. Based on this measure, live migration techniques can be triggered in order to move computation to healthy machines even before a failure brings the system down.
Bouche, P., Löwis, M. von, and Tröger, P., “Aggregated Accounting of Memory Usage in Java,” 4th International Conference on Software and Data Technologies (ICSOFT), vol. 1, 2009, pp. 177-185.
[BibTex]
@conference{ citemaster_204, author = {Paul Bouche and Martin L\"owis and Peter Tr\"oger }, location = {{Sofia, Bulgaria}}, booktitle = {{4th International Conference on Software and Data Technologies}}, isbn = {{978-989-674-009-2}}, publisher = {{INSTICC Press}}, booktitle = {{ICSOFT}}, title = {{Aggregated Accounting of Memory Usage in Java}}, volume = {1}, year = {2009}, pages = {{177-185}}, citemaster_conference_year = {{2009}}, }
Report
Böhme, H. and Tröger, P., “Prototypical tools for deployment, invocation, and monitoring of SLA-aware service implementations,” Adaptive Services Grid Project - Deliverable, May. 2006.
[BibTex]
@techreport{ citemaster_8371, author = {Harald B\"ohme and Peter Tr\"oger }, howpublished = {{Adaptive Services Grid Project - Deliverable}}, title = {{Prototypical tools for deployment, invocation, and monitoring of SLA-aware service implementations}}, year = {2006}, month = may, }
Lendholdt, M., “Ressourcenpartitionierung für Grid-Systeme,” Technischer Bericht des Hasso-Plattner-Instituts, 2005.
[BibTex]
@techreport{ citemaster_260, author = {Matthias Lendholdt and Peter Tr\"oger }, address = {{Potsdam}}, publisher = {{Hasso-Plattner-Institut f\"ur Softwaresystemtechnik}}, number = {8}, howpublished = {{Technischer Bericht des Hasso-Plattner-Instituts}}, title = {{Ressourcenpartitionierung f\"ur Grid-Systeme}}, year = {2005}, }
Tröger, P., Jorke, H., and Flehmig, M., “QoS criteria for the services within the Adaptive Services Grid,” Adaptive Services Grid Project - Deliverable, Jul. 2005.
[BibTex]
@techreport{ citemaster_263, author = {Peter Tr\"oger and Helmut Jorke and Marcus Flehmig }, howpublished = {{Adaptive Services Grid Project - Deliverable}}, title = {{QoS criteria for the services within the Adaptive Services Grid}}, year = {2005}, month = jul, }
Tröger, P., ed., “Grid Computing,” Technischer Bericht des Hasso-Plattner-Instituts, 2004.
[BibTex]
@techreport{ citemaster_261, author = {Peter Tr\"oger }, address = {{Potsdam}}, number = {3}, howpublished = {{Technischer Bericht des Hasso-Plattner-Instituts}}, title = {{Grid Computing}}, year = {2004}, }
Tröger, P. and Schult, W., “Research report about SLA fulfillment concepts and implementation,” Adaptive Services Grid Project - Deliverable, Feb. 2007.
[BibTex]
@techreport{ citemaster_262, author = {Peter Tr\"oger and Wolfgang Schult }, howpublished = {{Adaptive Services Grid Project - Deliverable}}, title = {{Research report about SLA fulfillment concepts and implementation}}, year = {2007}, month = feb, }
Flehmig, M., Tröger, P., and Saar, A., “Design and Integration of SLA Monitoring and Negotiation Capabilities,” Adaptive Services Grid Project - Deliverable, Aug. 2006.
[BibTex]
@techreport{ citemaster_8370, author = {Marcus Flehmig and Peter Tr\"oger and Alexander Saar }, howpublished = {{Adaptive Services Grid Project - Deliverable}}, title = {{Design and Integration of SLA Monitoring and Negotiation Capabilities}}, year = {2006}, month = aug, }
Tröger, P., Böhme, H., and Polze, A., “ASG Services Grid Infrastructure,” Adaptive Services Grid Project - Deliverable, Feb. 2005.
[BibTex]
@techreport{ citemaster_264, author = {Peter Tr\"oger and Harald B\"ohme and Andreas Polze }, howpublished = {{Adaptive Services Grid Project - Deliverable}}, title = {{ASG Services Grid Infrastructure}}, year = {2005}, month = feb, }
Generic
Tröger, P. and Gietzel, B., “Condor DRMAA 1.0 Implementation - Experience Report (GFD-E.103),” Feb. 2007.
Rajic, H., Brobst, R., Chan, W., Ferstl, F., Gardiner, J., Haas, A., Nitzberg, B., Templeton, D., Tollefsrud, J., and Tröger, P., “Distributed Resource Management Application API Specification 1.0 (GWD-R.133),” Jun. 2008.
[BibTex]
@misc{ citemaster_8372, author = {Hrabri Rajic and Roger Brobst and Waiman Chan and Fritz Ferstl and Jeff Gardiner and Andreas Haas and Bill Nitzberg and Daniel Templeton and John Tollefsrud and Peter Tr\"oger }, day = {{13}}, publisher = {{Open Grid Forum}}, title = {{Distributed Resource Management Application API Specification 1.0 (GWD-R.133)}}, year = {2008}, month = jun, }
Tröger, P., Templeton, D., Brobst, R., Haas, A., and Rajic, H., “Distributed Resource Management Application API 1.0 - IDL Specification (GFD-R-P.130),” Apr. 2008.
[BibTex]
@misc{ citemaster_265, author = {Peter Tr\"oger and Daniel Templeton and Roger Brobst and Andreas Haas and Hrabri Rajic }, publisher = {{Open Grid Forum}}, title = {{Distributed Resource Management Application API 1.0 - IDL Specification (GFD-R-P.130)}}, year = {2008}, month = apr, }
Tröger, P., “Distributed Resource Management Application API Specification 1.0 (GFD.22),” Aug. 2007.
[BibTex]
@misc{ citemaster_8373, author = {Peter Tr\"oger and Hrabri Rajic }, publisher = {{Open Grid Forum}}, title = {{Distributed Resource Management Application API Specification 1.0 (GFD.22)}}, year = {2007}, month = aug, }
Rajic, H., Brobst, R., Chan, W., Ferstl, F., Gardiner, J., Haas, A., Nitzberg, B., Templeton, D., Tollefsrud, J., and Tröger, P., “Distributed Resource Management Application API Specification 1.0 (GFD-R.022),” Aug. 2007.
[BibTex]
@misc{ citemaster_8385, author = {Hrabri Rajic and Roger Brobst and Waiman Chan and Fritz Ferstl and Jeff Gardiner and Andreas Haas and Bill Nitzberg and Daniel Templeton and John Tollefsrud and Peter Tr\"oger }, publisher = {{Open Grid Forum}}, title = {{Distributed Resource Management Application API Specification 1.0 (GFD-R.022)}}, year = {2007}, month = aug, }
Templeton, D., Tröger, P., Brobst, R., Haas, A., Rajic, H., and Tollefsrud, J., “Distributed Resource Management Application API Java(TM) Language Bindings 1.0,” Jan. 2006.
[BibTex]
@misc{ citemaster_240, author = {Daniel Templeton and Peter Tr\"oger and Roger Brobst and Andreas Haas and Hrabri Rajic and John Tollefsrud }, publisher = {{Open Grid Forum}}, title = {{Distributed Resource Management Application API Java(TM) Language Bindings 1.0}}, year = {2006}, month = jan, }
Standard
Tröger, P., Brobst, R., Gruber, D., Mamonski, M., and Templeton, D., “Distributed Resource Management Application API Version 2 (DRMAA),” Jan. 2012.
[BibTex]
@misc{ citemaster_9274, author = {Peter Tr\"oger and Roger Brobst and Daniel Gruber and Mariusz Mamonski and Daniel Templeton }, title = {{Distributed Resource Management Application API Version 2 (DRMAA)}}, howpublished = {\url{http://www.ogf.org/documents/GFD.194.pdf}}, year = {2012}, citemaster_section_number = {{GFD-R-P.194}}, citemaster_issuing_organization = {{Open Grid Forum}}, month = jan, }
[Abstract]
This document describes the Distributed Resource Management Application API Version 2 (DRMAA). It defines a generalized API to Distributed Resource Management (DRM) systems in order to facilitate the development of portable application programs and high-level libraries.
The intended audience for this specification are DRMAA language binding designers, DRM system vendors, high-level API designers and meta-scheduler architects. Application developers are expected to rely on product-specific documentation for the DRMAA API implementation in their particular DRM system.
Tröger, P. and Polze, A., eds., Proceedings of the 4th Many-core Applications Research Community (MARC) Symposium, 2012.
[BibTex]
@proceedings{ citemaster_9176, author = {Peter Tr\"oger and Andreas Polze }, isbn = {{978-3-86956-169-1}}, howpublished = {{Technische Berichte des Hasso-Plattner-Instituts f\"ur Softwaresystemtechnik an der Universit\"at Potsdam}}, title = {{Proceedings of the 4th Many-core Applications Research Community (MARC) Symposium}}, volume = {55}, year = {2012}, month = feb, citemaster_conference_year = {{2012}}, }
