TY - JOUR AB - Virtualization technology makes data centers more dynamic and easier to administrate. Today, cloud providers offer customers access to complex applications running on virtualized hardware. Nevertheless, big virtualized data centers become stochastic environments and the simplification on the user side leads to many challenges for the provider. He has to find cost-efficient configurations and has to deal with dynamic environments to ensure service level objectives (SLOs). We introduce a software solution that reduces the degree of human intervention to manage clouds. It is designed as a multi-agent system (MAS) and placed on top of the Infrastructure as a Service (IaaS) layer. Worker agents allocate resources, configure applications, check the feasibility of requests, and generate cost estimates. They are equipped with application specific knowledge allowing it to estimate the type and number of necessary resources. During runtime, a worker agent monitors the job and adapts its resources to ensure the specified quality of service—even in noisy clouds where the job instances are influenced by other jobs. They interact with a scheduler agent, which takes care of limited resources and does a cost-aware scheduling by assigning jobs to times with low costs. The whole architecture is self-optimizing and able to use public or private clouds. Building a private cloud needs to face the challenge to find a mapping of virtual machines (VMs) to hosts. We present a rule-based mapping algorithm for VMs. It offers an interface where policies can be defined and combined in a generic way. The algorithm performs the initial mapping at request time as well as a remapping during runtime. It deals with policy and infrastructure changes. An energy-aware scheduler and the availability of cheap resources provided by a spot market are analyzed. We evaluated our approach by building up an SaaS stack, which assigns resources in consideration of an energy function and that ensures SLOs of two different applications, a brokerage system and a high-performance computing software. Experiments were done on a real cloud system and by simulations. AU - Niehörster, Oliver AU - Simon, Jens AU - Brinkmann, André AU - Keller, Axel AU - Krüger, Jens ID - 1965 IS - 3 JF - Journal of Grid Computing TI - Cost-aware and SLO Fulfilling Software as a Service VL - 10 ER - TY - JOUR AB - System virtualization has become the enabling technology to manage the increasing number of different applications inside data centers. The abstraction from the underlying hardware and the provision of multiple virtual machines (VM) on a single physical server have led to a consolidation and more efficient usage of physical servers. The abstraction from the hardware also eases the provision of applications on different data centers, as applied in several cloud computing environments. In this case, the application need not adapt to the environment of the cloud computing provider, but can travel around with its own VM image, including its own operating system and libraries. System virtualization and cloud computing could also be very attractive in the context of high‐performance computing (HPC). Today, HPC centers have to cope with both, the management of the infrastructure and also the applications. Virtualization technology would enable these centers to focus on the infrastructure, while the users, collaborating inside their virtual organizations (VOs), would be able to provide the software. Nevertheless, there seems to be a contradiction between HPC and cloud computing, as there are very few successful approaches to virtualize HPC centers. This work discusses the underlying reasons, including the management and performance, and presents solutions to overcome the contradiction, including a set of new libraries. The viability of the presented approach is shown based on evaluating a selected parallel, scientific application in a virtualized HPC environment. AU - Birkenheuer, Georg AU - Brinkmann, André AU - Kaiser, Jürgen AU - Keller, Axel AU - Keller, Matthias AU - Kleineweber, Christoph AU - Konersmann, Christoph AU - Niehörster, Oliver AU - Schäfer, Thorsten AU - Simon, Jens AU - Wilhelm, Maximilan ID - 1971 JF - Software: Practice and Experience TI - Virtualized HPC: a contradiction in terms? ER - TY - CONF AU - Niehörster, Oliver AU - Simon, Jens AU - Brinkmann, André AU - Krieger, Alexaner ID - 2203 SN - 978-0-7695-4572-1 T2 - Proc. IEEE/ACM Int. Conf. on Grid Computing (GRID) TI - Autonomic Resource Management with Support Vector Machines ER - TY - CONF AU - Niehörster, Oliver AU - Brinkmann, André AU - Fels, Gregor AU - Krüger, Jens AU - Simon, Jens ID - 2237 SN - 1552-5244 T2 - Proc. Int. Conf. on Cluster Computing (CLUSTER) TI - Enforcing SLAs in Scientific Clouds ER - TY - CONF AU - Birkenheuer, Georg AU - Brinkmann, André AU - Dömer, Hubert AU - Effert, Sascha AU - Konersmann, Christoph AU - Niehörster, Oliver AU - Simon, Jens ID - 2357 T2 - Proc. Gemeinsamer Workshop der GI/ITG Fachgruppen "Betriebssysteme" und "KuVS": Virtualized IT infrastructures and their management TI - Virtual Supercomputer for HPC and HTC ER - TY - CONF AU - P. Miller, Barton AU - Labarta, Jesús AU - Schintke, Florian AU - Simon, Jens ID - 2426 SN - 978-3-540-45706-0 T2 - Proc. European Conf. on Parallel Processing (Euro-Par) TI - Performance Evaluation, Analysis and Optimization VL - 2400 ER - TY - CONF AU - Schintke, Florian AU - Simon, Jens AU - Reinefeld, Alexander ID - 2431 T2 - Proc. Int. Conf. on Computational Science (ICCS) TI - A Cache Simulator for Shared Memory Systems VL - 2074 ER - TY - THES AU - Simon, Jens ID - 2434 SN - 3-934445-03-9 TI - Werkzeugunterstützte effiziente Nutzung von Hochleistungsrechnern ER - TY - CHAP AU - Simon, Jens AU - Reinefeld, Alexander AU - Heinz, Oliver ED - Hellwagner, Hermann ED - Reinefeld, Alexander ID - 2435 SN - 0302-9743 T2 - SCI: Scalable Coherent Interface. Architecture and Software for High-Performance Compute Clusters TI - Large-Scale SCI Clusters in Practice: Architecture and Performance in SCI VL - 1734 ER - TY - JOUR AU - Simon, Jens AU - Wierum, Jens-Michael ID - 2437 IS - 5 JF - Information Processing Letters - Special Issue on Models of Computation SN - 0020-0190 TI - The Latency-of-Data-Access model for Analyzing Parallel Computation VL - 66 ER - TY - CONF AU - Simon, Jens AU - Weicker, Reinhold AU - Vieth, Marco ID - 2438 SN - 978-3-540-69549-3 T2 - Proc. European Conf. on Parallel Processing (Euro-Par) TI - Workload Analysis of Computation Intensive Tasks: Case Study on SPEC CPU95 Benchmarks VL - 1300 ER - TY - CONF AU - Heinz, Oliver AU - Simon, Jens ID - 2439 T2 - Proc. Int. Conf. on Architecture of Computing Systems (ARCS) TI - Experiences with a SCI Multiprocessor Workstation Cluster ER - TY - CONF AU - Simon, Jens AU - Heinz, Oliver ID - 2440 T2 - Proc. Workshops im Rahmen der 14. ITG/GI-Fachtagung Architektur von Rechensystemen TI - SCI multiprocessor PC cluster in a WindowsNT environment ER - TY - CONF AU - Fischer, Markus AU - Simon, Jens ID - 2441 T2 - Proc. European Parallel Virtual Machine / Message Passing Interface Users’ Group Meeting (EuroPVM/MPI) TI - Embedding SCI into PVM VL - 1332 ER - TY - CONF AU - Reinefeld, Alexander AU - Baraglia, Ranieri AU - Decker, Thomas AU - Gehring, Jörn AU - Laforenza, Domenico AU - Ramme, Friedhelm AU - Römke, Thomas AU - Simon, Jens ID - 2442 T2 - Proc. Heterogenous Computing Workshop (HCW) TI - The MOL Project: An Open, Extensible Metacomputer ER - TY - CONF AU - Simon, Jens AU - Wierum, Jens-Michael ID - 2443 SN - 978-3-540-61142-4 T2 - Proc. Int. Conf. on High-Performance Computing and Networking (HPCN-Europe) TI - Sequential Performance versus Scalability: Optimizing Parallel LU-Decomposition VL - 1067 ER - TY - CONF AU - Simon, Jens AU - Wierum, Jens-Michael ID - 2444 T2 - Proc. Annual Int. Conf. on High-Performance Computers (HPCS) TI - Performance Prediction of Benchmark Programs for Massively Parallel Architectures ER - TY - CONF AU - Simon, Jens AU - Wierum, Jens-Michael ID - 2445 T2 - Proc. European Conf. on Parallel Processing (Euro-Par) TI - Accurate Performance Prediction for Massively Parallel Systems and its Applications VL - 1124 ER - TY - GEN AU - Simon, Jens AU - Wierum, Jens-Michael ID - 2446 TI - On Accurate Performance Prediction for Massively Parallel Systems and its Applications ER - TY - CONF AU - Röttger, Markus AU - Schroeder, Ulf-Peter AU - Simon, Jens ID - 2447 T2 - Proc. Int. Conf. on High-Performance Computing and Networking TI - Implementation of a Parallel and Distributed Mapping Kernel for PARIX VL - 919 ER -