Joint Computing and Network Resource Scheduling in a Lambda Grid Network

Data-intensive Grid applications require huge data transfers between grid computing nodes. These computing nodes, where computing jobs are executed, are usually geographically separated. A grid network that employs optical wavelength division multiplexing (WDM) technology and optical switches to interconnect computing resources with dynamically provisioned multi-gigabit rate bandwidth lightpath is called a Lambda Grid network. A computing task may be executed on any one of several computing nodes which possesses the necessary resources. In order to reflect the reality in job scheduling, allocation of network resources for data transfer should be taken into consideration. However, few scheduling methods consider the communication contention on Lambda Grids. In this paper, we investigate the joint scheduling problem while considering both optical network and computing resources in a Lambda Grid network. The objective of our work is to maximize the total number of jobs that can be scheduled in a Lambda Grid network. An adaptive routing algorithm is proposed and implemented for accomplishing the communication tasks for every job submitted in the network. Four heuristics (FIFO, ESTF, LJF, RS) are implemented for job scheduling of the computational tasks. Simulation results prove the feasibility and efficiency of the proposed solution.

Joint Computing and Network Resource Scheduling in a Lambda Grid Network

Data-intensive Grid applications require huge data transfers between grid computing nodes. These computing nodes, where computing jobs are executed, are usually geographically separated. A grid network that employs optical wavelength division multiplexing (WDM) technology and optical switches to interconnect computing resources with dynamically provisioned multi-gigabit rate bandwidth lightpath is called a Lambda Grid network. A computing task may be executed on any one of several computing nodes which possesses the necessary resources. In order to reflect the reality in job scheduling, allocation of network resources for data transfer should be taken into consideration. However, few scheduling methods consider the communication contention on Lambda Grids. In this paper, we investigate the joint scheduling problem while considering both optical network and computing resources in a Lambda Grid network. The objective of our work is to maximize the total number of jobs that can be scheduled in a Lambda Grid network. An adaptive routing algorithm is proposed and implemented for accomplishing the communication tasks for every job submitted in the network. Four heuristics (FIFO, ESTF, LJF, RS) are implemented for job scheduling of the computational tasks. Simulation results prove the feasibility and efficiency of the proposed solution.

Wh plus missing-E-T signature from gaugino pair production at the LHC

In SUSY models with heavy squarks and gaugino mass unification, the gaugino pair production reaction pp -> (W) over tilde (+/-)(1)(Z) over tilde (2) dominates gluino pair production for m (g) over tilde less than or similar to 1 TeV at LHC with root s = 14 TeV (LHC14). For this mass range, the two-body decays (W) over tilde (1) -> W (Z) over tilde (1) and (Z) over tilde (2) -> h (Z) over tilde (1) are expected to dominate the chargino and neutralino branching fractions. By searching for lb (b) over tilde + is not an element of(T) events from (W) over tilde (+/-)(1)Z(2) production, we show that LHC14 with 100 fb(-1) of integrated luminosity becomes sensitive to chargino masses in the range m((W) over tilde1) similar to 450-550 GeV corresponding to m (g) over tilde similar to 1.5-2 TeV in models with gaugino mass unification. For 10(3) fb(-1), LHC14 is sensitive to the Wh channel for m((W) over tilde1) similar to 300-800 GeV, corresponding to m (g) over tilde similar to 1-2.8 TeV, which is comparable to the reach for gluino pair production followed by cascade decays. The Wh + is not an element of(T) search channel opens up a new complementary avenue for SUSY searches at LHC, and serves to point to SUSYas the origin of any new physics discovered via multijet and multilepton + is not an element of(T) channels.

Realisierung der IceCube MonteCarlo-Produktion im WLCG und Untersuchung von Auswirkungen meteorologischer Parameter auf die Erzeugung atmosphärischer Myonen

Das am Südpol gelegene Neutrinoteleskop IceCube detektiert hochenergetische Neutrinos über die schwache Wechselwirkung geladener und neutraler Ströme. Die Analyse basiert auf einem Vergleich mit Monte-Carlo-Simulationen, deren Produktion global koordiniert wird. In Mainz ist es erstmalig gelungen, Simulationen innerhalb der Architektur des Worldwide LHC Computing Grid (WLCG) zu realisieren, was die Möglichkeit eröffnet, Monte-Carlo-Berechnungen auch auf andere deutsche Rechnerfarmen (CEs) mit IceCube-Berechtigung zu verteilen. Atmosphärische Myonen werden mit einer Rate von über 1000 Ereignissen pro Sekunde aufgezeichnet. Eine korrekte Interpretation dieses dominanten Signals, welches um einen Faktor von 10^6 reduziert werden muss um das eigentliche Neutrinosignal zu extrahieren, ist deswegen von großer Bedeutung. Eigene Simulationen mit der Software-Umgebung CORSIKA wurden durchgeführt um die von Energie und Einfallswinkel abhängige Entstehungshöhe atmosphärischer Myonen zu bestimmen. IceCube Myonraten wurden mit Wetterdaten des European Centre for Medium-Range Weather Forcasts (ECMWF) verglichen und Korrelationen zwischen jahreszeitlichen sowie kurzzeitigen Schwankungen der Atmosphärentemperatur und Myonraten konnten nachgewiesen werden. Zudem wurde eine Suche nach periodischen Effekten in der Atmosphäre, verursacht durch z.B. meteorologische Schwerewellen, mit Hilfe einer Fourieranalyse anhand der IceCube-Daten durchgeführt. Bislang konnte kein signifikanter Nachweis zur Existenz von Schwerewellen am Südpol erbracht werden.

Misura della sezione d'urto di produzione tt-barra nel canale adronico in collisioni pp con radice di s = 8tev a cms

La sezione d'urto di produzione per coppie tt-barra viene misurata utilizzando dati raccolti dall'esperimento CMS in collisioni protone-protone ad LHC, con energia nel sistema del centro di massa radice di s = 8 TeV. Il campione raccolto corrisponde ad una luminosità integrata di 19.5 fb^-1. La misura viene effettuata su eventi che contano un numero di jet pari o superiore a 6, almeno due dei quali identificati come prodotto dell'adronizzazione di quark bottom. Il valore di sezione d'urto ottenuto è (260 pm 10 (stat)) pb, in accordo con le previsioni teoriche del Modello Standard.

Implementazione di una infrastruttura basata su Kafka e Storm per il Mobile Cloud computing

Lo scopo dell'elaborato di tesi è l'analisi, progettazione e sviluppo di un prototipo di una infrastruttura cloud in grado di gestire un grande flusso di eventi generati da dispositivi mobili. Questi utilizzano informazioni come la posizione assunta e il valore dei sensori locali di cui possono essere equipaggiati al fine di realizzare il proprio funzionamento. Le informazioni così ottenute vengono trasmesse in modo da ottenere una rete di device in grado di acquisire autonomamente informazioni sull'ambiente ed auto-organizzarsi. La costruzione di tale struttura si colloca in un più ampio ambito di ricerca che punta a integrare metodi per la comunicazione ravvicinata con il cloud al fine di permettere la comunicazione tra dispositivi vicini in qualsiasi situazione che si potrebbe presentare in una situazione reale. A definire le specifiche della infrastruttura e quindi a impersonare il ruolo di committente è stato il relatore, Prof. Mirko Viroli, mentre lo sviluppo è stato portato avanti da me e dal correlatore, Ing. Pietro Brunetti. Visti gli studi precedenti riguardanti il cloud computing nell'area dei sistemi complessi distribuiti, Brunetti ha dato il maggiore contributo nella fase di analisi del problema e di progettazione mentre la parte riguardante la effettiva gestione degli eventi, le computazioni in cloud e lo storage dei dati è stata maggiormente affrontata da me. In particolare mi sono occupato dello studio e della implementazione del backend computazionale, basato sulla tecnologia Apache Storm, della componente di storage dei dati, basata su Neo4j, e della costruzione di un pannello di visualizzazione basato su AJAX e Linkurious. A questo va aggiunto lo studio su Apache Kafka, utilizzato come tecnologia per realizzare la comunicazione asincrona ad alte performance tra le componenti. Si è reso necessario costruire un simulatore al fine di condurre i test per verificare il funzionamento della infrastruttura prototipale e per saggiarne l'effettiva scalabilità, considerato il potenziale numero di dispositivi da sostenere che può andare dalle decine alle migliaia. La sfida più importante riguarda la gestione della vicinanza tra dispositivi e la possibilità di scalare la computazione su più macchine. Per questo motivo è stato necessario far uso di tecnologie per l'esecuzione delle operazioni di memorizzazione, calcolo e trasmissione dei dati in grado di essere eseguite su un cluster e garantire una accettabile fault-tolerancy. Da questo punto di vista i lavori che hanno portato alla costruzione della infrastruttura sono risultati essere un'ottima occasione per prendere familiarità con tecnologie prima sconosciute. Quasi tutte le tecnologie utilizzate fanno parte dell'ecosistema Apache e, come esposto all'interno della tesi, stanno ricevendo una grande attenzione da importanti realtà proprio in questo periodo, specialmente Apache Storm e Kafka. Il software prodotto per la costruzione della infrastruttura è completamente sviluppato in Java a cui si aggiunge la componente web di visualizzazione sviluppata in Javascript.

Grid Global Behavior Prediction

Complexity has always been one of the most important issues in distributed computing. From the first clusters to grid and now cloud computing, dealing correctly and efficiently with system complexity is the key to taking technology a step further. In this sense, global behavior modeling is an innovative methodology aimed at understanding the grid behavior. The main objective of this methodology is to synthesize the grid's vast, heterogeneous nature into a simple but powerful behavior model, represented in the form of a single, abstract entity, with a global state. Global behavior modeling has proved to be very useful in effectively managing grid complexity but, in many cases, deeper knowledge is needed. It generates a descriptive model that could be greatly improved if extended not only to explain behavior, but also to predict it. In this paper we present a prediction methodology whose objective is to define the techniques needed to create global behavior prediction models for grid systems. This global behavior prediction can benefit grid management, specially in areas such as fault tolerance or job scheduling. The paper presents experimental results obtained in real scenarios in order to validate this approach.

Extending Science Gateway Frameworks to Support Big Data Applications in the Cloud

Cloud computing offers massive scalability and elasticity required by many scien-tific and commercial applications. Combining the computational and data handling capabilities of clouds with parallel processing also has the potential to tackle Big Data problems efficiently. Science gateway frameworks and workflow systems enable application developers to implement complex applications and make these available for end-users via simple graphical user interfaces. The integration of such frameworks with Big Data processing tools on the cloud opens new oppor-tunities for application developers. This paper investigates how workflow sys-tems and science gateways can be extended with Big Data processing capabilities. A generic approach based on infrastructure aware workflows is suggested and a proof of concept is implemented based on the WS-PGRADE/gUSE science gateway framework and its integration with the Hadoop parallel data processing solution based on the MapReduce paradigm in the cloud. The provided analysis demonstrates that the methods described to integrate Big Data processing with workflows and science gateways work well in different cloud infrastructures and application scenarios, and can be used to create massively parallel applications for scientific analysis of Big Data.

Cloud Benchmarking For Maximising Performance of Scientific Applications

How can applications be deployed on the cloud to achieve maximum performance? This question is challenging to address with the availability of a wide variety of cloud Virtual Machines (VMs) with different performance capabilities. The research reported in this paper addresses the above question by proposing a six step benchmarking methodology in which a user provides a set of weights that indicate how important memory, local communication, computation and storage related operations are to an application. The user can either provide a set of four abstract weights or eight fine grain weights based on the knowledge of the application. The weights along with benchmarking data collected from the cloud are used to generate a set of two rankings - one based only on the performance of the VMs and the other takes both performance and costs into account. The rankings are validated on three case study applications using two validation techniques. The case studies on a set of experimental VMs highlight that maximum performance can be achieved by the three top ranked VMs and maximum performance in a cost-effective manner is achieved by at least one of the top three ranked VMs produced by the methodology.

HPC management and engineering in the hybrid cloud

The evolution and maturation of Cloud Computing created an opportunity for the emergence of new Cloud applications. High-performance Computing, a complex problem solving class, arises as a new business consumer by taking advantage of the Cloud premises and leaving the expensive datacenter management and difficult grid development. Standing on an advanced maturing phase, today’s Cloud discarded many of its drawbacks, becoming more and more efficient and widespread. Performance enhancements, prices drops due to massification and customizable services on demand triggered an emphasized attention from other markets. HPC, regardless of being a very well established field, traditionally has a narrow frontier concerning its deployment and runs on dedicated datacenters or large grid computing. The problem with common placement is mainly the initial cost and the inability to fully use resources which not all research labs can afford. The main objective of this work was to investigate new technical solutions to allow the deployment of HPC applications on the Cloud, with particular emphasis on the private on-premise resources – the lower end of the chain which reduces costs. The work includes many experiments and analysis to identify obstacles and technology limitations. The feasibility of the objective was tested with new modeling, architecture and several applications migration. The final application integrates a simplified incorporation of both public and private Cloud resources, as well as HPC applications scheduling, deployment and management. It uses a well-defined user role strategy, based on federated authentication and a seamless procedure to daily usage with balanced low cost and performance.

Deployment of a data analysis workflow of the ATLAS experiment on HPC systems

LHC experiments produce an enormous amount of data, estimated of the order of a few PetaBytes per year. Data management takes place using the Worldwide LHC Computing Grid (WLCG) grid infrastructure, both for storage and processing operations. However, in recent years, many more resources are available on High Performance Computing (HPC) farms, which generally have many computing nodes with a high number of processors. Large collaborations are working to use these resources in the most efficient way, compatibly with the constraints imposed by computing models (data distributed on the Grid, authentication, software dependencies, etc.). The aim of this thesis project is to develop a software framework that allows users to process a typical data analysis workflow of the ATLAS experiment on HPC systems. The developed analysis framework shall be deployed on the computing resources of the Open Physics Hub project and on the CINECA Marconi100 cluster, in view of the switch-on of the Leonardo supercomputer, foreseen in 2023.

Construction and test of a cosmic ray telescope based on CMS Drift Tube chambers and data acquisition prototypes of the Phase-2 upgrade

In this thesis work, a cosmic-ray telescope was set up in the INFN laboratories in Bologna using smaller size replicas of CMS Drift Tubes chambers, called MiniDTs, to test and develop new electronics for the CMS Phase-2 upgrade. The MiniDTs were assembled in INFN National Laboratory in Legnaro, Italy. Scintillator tiles complete the telescope, providing a signal independent of the MiniDTs for offline analysis. The telescope readout is a test system for the CMS Phase-2 upgrade data acquisition design. The readout is based on the early prototype of a radiation-hard FPGA-based board developed for the High Luminosity LHC CMS upgrade, called On Board electronics for Drift Tubes. Once the set-up was operational, we developed an online monitor to display in real-time the most important observables to check the quality of the data acquisition. We performed an offline analysis of the collected data using a custom version of CMS software tools, which allowed us to estimate the time pedestal and drift velocity in each chamber, evaluate the efficiency of the different DT cells, and measure the space and time resolution of the telescope system.

Applying semantics to grid middleware

Scheduling parallel and distributed applications efficiently onto grid environments is a difficult task and a great variety of scheduling heuristics has been developed aiming to address this issue. A successful grid resource allocation depends, among other things, on the quality of the available information about software artifacts and grid resources. In this article, we propose a semantic approach to integrate selection of equivalent resources and selection of equivalent software artifacts to improve the scheduling of resources suitable for a given set of application execution requirements. We also describe a prototype implementation of our approach based on the Integrade grid middleware and experimental results that illustrate its benefits. Copyright (C) 2009 John Wiley & Sons, Ltd.

Are there hidden scalars in LHC Higgs results?

The Higgs boson recently discovered at the Large Hadron Collider has shown to have couplings to the remaining particles well within what is predicted by the Standard Model. The search for other new heavy scalar states has so far revealed to be fruitless, imposing constraints on the existence of new scalar particles. However, it is still possible that any existing heavy scalars would preferentially decay to final states involving the light Higgs boson thus evading the current LHC bounds on heavy scalar states. Moreover, decays of the heavy scalars could increase the number of light Higgs bosons being produced. Since the number of light Higgs bosons decaying to Standard Model particles is within the predicted range, this could mean that part of the light Higgs bosons could have their origin in heavy scalar decays. This situation would occur if the light Higgs couplings to Standard Model particles were reduced by a concomitant amount. Using a very simple extension of the SM - the two-Higgs doublet model we show that in fact we could already be observing the effect of the heavy scalar states even if all results related to the Higgs are in excellent agreement with the Standard Model predictions.

Exploring distributed computing tools through data mining tasks

Harnessing idle PCs CPU cycles, storage space and other resources of networked computers to collaborative are mainly fixated on for all major grid computing research projects. Most of the university computers labs are occupied with the high puissant desktop PC nowadays. It is plausible to notice that most of the time machines are lying idle or wasting their computing power without utilizing in felicitous ways. However, for intricate quandaries and for analyzing astronomically immense amounts of data, sizably voluminous computational resources are required. For such quandaries, one may run the analysis algorithms in very puissant and expensive computers, which reduces the number of users that can afford such data analysis tasks. Instead of utilizing single expensive machines, distributed computing systems, offers the possibility of utilizing a set of much less expensive machines to do the same task. BOINC and Condor projects have been prosperously utilized for solving authentic scientific research works around the world at a low cost. In this work the main goal is to explore both distributed computing to implement, Condor and BOINC, and utilize their potency to harness the ideal PCs resources for the academic researchers to utilize in their research work. In this thesis, Data mining tasks have been performed in implementation of several machine learning algorithms on the distributed computing environment.