Autor: nagell

Ein Papier und ein Poster über das Simulationsframework "FederatedCloudSim" wird am 23.4.2017 auf dem CrossCloud-Workshop präsentiert werden. Der Workshop findet zusammen mit der EuroSys-Konferenz in Belgrad statt.

Titel: Financial Evaluation of SLA-based VM Scheduling Strategies for Cloud Federations

Autoren: Andreas Kohne, Marcel Krüger, Marco Pfahlberg, Olaf Spinczyk, Lars Nagel

Abstract: In recent years, cloud federations have gained popularity. Small as well as big cloud service providers (CSPs) join federations to reduce their costs, and also cloud management software like OpenStack offers support for federations. In a federation, individual CSPs cooperate such that they can move load to partner clouds at high peaks and possibly offer a wider range of services to their customers. Research in this area addresses the organization of such federations and strategies that CSPs can apply to increase their profit.

In this paper we present the latest extensions to the FederatedCloudSim framework that considerably improve the simulation and evaluation of cloud federations. These simulations include service-level agreements (SLAs), scheduling and brokering strategies on various levels, the use of real-world cloud workload traces and a fine-grained financial evaluation using the new CloudAccount module. We use FederatedCloudSim to compare scheduling and brokering strategies on the federation level. Among them are new strategies that conduct auctions or consult a reliance factor to select an appropriate federated partner for running outsourced virtual machines. Our results show that choosing the right strategy has a significant impact on SLA compliance and revenue.

Auf dem ACM Symposium on Principles of Distributed Computing (PODC) in Chicago wird am 26.7.2016 eine theoretische Arbeit über die Verteilung von Jobs auf Server präsentiert werden.

Titel: Self-stabilizing Balls & Bins in Batches

Autoren: Petra Berenbrink, Tom Friedetzky, Peter Kling, Frederik Mallmann-Trenn, Lars Nagel, Chris Wastell

Abstract: A fundamental problem in distributed computing is the distribution of requests to a set of uniform servers without a centralized controller. Classically, such problems are modelled as static balls into bins processes, where m balls (tasks) are to be distributed to n bins (servers). In a seminal work, Azar et al. proposed the sequential strategy Greedy[d] for n=m. When thrown, a ball queries the load of d random bins and is allocated to a least loaded of these. Azar et al. showed that d=2 yields an exponential improvement compared to d=1. Berenbrink et al. extended this to m >> n, showing that the maximal load difference is independent of m for d=2 (in contrast to d=1).

We propose a new variant of an infinite balls into bins process. In each round an expected number of c*n new balls arrive and are distributed (in parallel) to the bins and each non-empty bin deletes one of its balls. This setting models a set of servers processing incoming requests, where clients can query a server's current load but receive no information about parallel requests.
We study the Greedy[d] distribution scheme in this setting and show a strong self-stabilizing property: For any arrival rate c=c(n)<1, the system load is time-invariant. Moreover, for any (even super-exponential) round t, the maximum system load is (w.h.p.) O(1/(1-c) * log(n/(1-c))) for d=1 and O(log(n/(1-c)))$ for d=2. In particular, Greedy[2] has an exponentially smaller system load for high arrival rates.

FAST wird auf dem 11th Workshop on Virtualization in High-Performance Cloud Computing (VHPC) eine Arbeit vorstellen, die sich mit der Beschleunigung von Migrationen in virtuellen Umgebungen befasst. Der VHPC-Workshop wird am 23.6.2016 in Frankfurt stattfinden und zwar im Rahmen der International Supercomputing Conference - High Performance 2016 (ISC).

Titel: Accelerating Application Migration in HPC

Autoren: Ramy Gad, Simon Pickartz, Tim Süß, Lars Nagel, Stefan Lankes, André Brinkmann

Abstract: It is predicted that the number of cores per node will rapidly increase with the upcoming era of exascale supercomputers. As a result, multiple applications will have to share one node and compete for the (often scarce) resources available on this node. Furthermore, the growing number of hardware components causes a decrease in the mean time between failures. Application migration between nodes has been proposed as a tool to mitigate these two problems: Bottlenecks due to resource sharing can be addressed by load balancing schemes which migrate applications; and hardware errors can often be tolerated by the system if faulty nodes are detected and processes are migrated ahead of time.

VM migration currently seems to be the most promising technique for such approaches as it provides a strong level of isolation. However, the migration time of virtual machines is higher than the respective migration time on the process level. This can be explained by the additional virtualization layer in the memory hierarchy.

In this paper, we propose a technique for the acceleration of VM migration. We take advantage of the fact that freed memory regions within the guest system are not recognized by the hypervisor. Therefore, we fill them with zeros such that zero-page detection and compression can work more efficiently. We demonstrate that the approach reduces migration time by up to 8% with a negligible overhead for some applications.

Auf dem 11th Workshop on Virtualization in High-Performance Cloud Computing (VHPC) wird am 23.6.2016 die Publikation "Migrating LinuX Containers Using CRIU" vorgestellt werden. Der Workshop wird gemeinsam mit der International Supercomputing Conference (ISC) in Frankfurt ausgerichtet werden, einer wichtigen internationalen HPC-Konferenz.

Titel: Migrating LinuX Containers Using CRIU

Autoren: Simon Pickartz, Niklas Eiling, Stefan Lankes, Lukas Razik, Antonello Monti

Abstract: Process migration is one of the most important techniques in modern computing centers. It enables the implementation of load balancing strategies and eases the system administration. As supercomputers continue to grow in size, according mechanisms become interesting to High-Performance Computing (HPC) as well.

Usually, migration is accomplished by means of hypervisor-based virtualization. However, container-based approaches are an attractive alternative for HPC to minimize the performance penalties. In contrast to virtual machine migration, the migration of operating system containers is mostly unexplored in the context of HPC until today.

In this paper we present a prototype implementation of a libvirt driver enabling the migration of LinuX Containers. We evaluate the driver in terms of overhead added by the additional software layer and compare its migration performance with that of virtual machines based on KVM.

Der 1st COSH Workshop on Co-Scheduling of HPC Applications, organisiert vom FAST-Partner TU München, wird am 19. Januar zusammen mit der HiPEAC 2016 in Prag stattfinden. Die folgenden Arbeiten wurden akzeptiert und werden beim Workshop präsentiert werden:

"A Resource-centric Application Classification Approach"
Alexandros-Herodotos Haritatos, Konstantinos Nikas, Georgios Goumas und Nectarios Koziris
School of ECE, NTUA, Athen, Griechenland

"Dynamic Process Management with Allocation-internal Co-Scheduling Towards Interactive Supercomputing"
Carsten Clauss, Thomas Moschny und Norbert Eicker
ParTec GmbH und Forschungszentrum Jülich, Deutschland

"Detailed Characterization of HPC Applications for Co-Scheduling"
Josef Weidendorfer und Jens Breitbart
Technische Universität München, Deutschland

"Terrible Twins: A Simple Scheme to Avoid Bad Co-Schedules"
Andreas de Blanche und Thomas Lundqvist
Department of Engineering Science, University West, Schweden

"Implications of Process-Migration in Virtualized Environments"
Simon Pickartz, Jens Breitbart und Stefan Lankes
RWTH Aachen und Technische Universität München, Deutschland

"Impact of the Scheduling Strategy in Heterogeneous Systems That Provide Co-Scheduling"
Tim Süß, Nils Döring, Ramy Gad, Lars Nagel, André Brinkmann, Dustin Feld, Eric Schricker und Thomas Soddemann
Johannes Gutenberg-Universität Mainz und Fraunhofer SCAI, Deutschland

Der 1st COSH Workshop on Co-Scheduling of HPC Applications wird am 19. Januar 2016 in Prag stattfinden, gemeinsam mit der HiPEAC 2016. Organisiert wird der Workshop von Carsten Trinitis und Josef Weidendorfer von der Technischen Universität München.

Beschreibung

Die Aufgabe von Höchstleistungsrechnern ist die perfomante und energieeffiziente Durchführung von (meist wissenschaftlichen und rechenintensiven) Anwendungen. Bisher wird dieses Ziel in der Regel dadurch erreicht, dass Rechenkerne bzw. -knoten Anwendungen exklusiv zugewiesen werden. Aus diesem Grund müssen Anwendungen hochgradig optimiert werden, damit auch nur ein Teil der Rechenleistung des Supercomputers ausgenutzt werden kann. Das setzt erfahrene Programmierer voraus.

Es wird erwartet, dass dieses Problem auf zukünftigen Exascale-Umgebungen mit Tausenden von Kernen noch deutlich schwieriger wird. Viele der heutigen hochskalierbaren Anwendungen werden nicht in der Lage sein, extrem parallele Exascale-Systeme ausreichend auszunutzen, weil sie durch knotenspezifische Engpässe wie die I/O-Bandbreite ausgebremst werden. Deshalb wird es für die effiziente Nutzung zukünftiger Supercomputer notwendig sein, mehrere Anwendungen simultan auf einem Knoten auszuführen.

Um Co-Scheduling effizient zu machen, dürfen sich Anwendungen nicht gegenseitig ausbremsen; zum Beispiel könnten eine speicherbegrenzte und eine rechenbegrenzte Anwendung zusammen auf einem Knoten laufen. In diesem Kontext könnte es notwendig sein, Anwendungen dynamisch zwischen Knoten zu migrieren, zum Beispiel, wenn eine neue Anwendung im System platziert werden muss. Für die Überwachung von Performanz und Energie, könnten zusätzliche Sensoren nötig sein, die Werte für "Key Performance Indicators" (KPIs) liefern.

Themen

Exascale-Architekturen, Supercomputer, Scheduling, Leistungsüberwachung, Sensoren, Energieeffizienz, Job-Migration

Wichtige Termine

Einreichfrist: 22. November 2015
Benachrichtigung: 5. Dezember 2014
Finale Version: 5. Dezember 2015
Workshop: 19. Januar 2016

FAST wird auf der 10. "IEEE International Conference on Networking, Architecture, and Storage" (NAS 2015) ein Poster präsentieren. Die NAS wird im Boston Park Plaza Hotel am 6. und 7. August stattfinden.

Titel des Posters: "Evaluation of a Hash-Compress-Encryptfor Storage System Applications Pipeline"

Autoren: Matthias Grawinkel, Michael Mardaus, Tim Süß, André Brinkmann

Abstract: Great efforts are made to store data in a secure, reliable, and authentic way in large storage systems. Specialized, system specific clients help to achieve these goals. Nevertheless, often standard tools for hashing, compressing, and encrypting data are arranged in transparent pipelines.
We analyze the potential of Unix shell pipelines with several high-speed and high-compression algorithms that can be used to achieve data security, reduction, and authenticity. Furthermore, we compare the pipelines of standard tools against a house made pipeline implemented in C++ and show that there is great potential for performance improvement.