E-Locus - Institutional Repository of the University of Crete - Design and implementation of a system for evaluating distributed application deployments in multi-clouds

Home Design and implementation of a system for evaluating distributed application deployments in multi-clouds

Results - Details

[Add to Basket]

Identifier

000381372

Title

Design and implementation of a system for evaluating distributed application deployments in multi-clouds

Alternative Title

Σχεδίαση και υλοποίηση ενός συστήματος για την αξιολόγηση εφαρμογών σε πολλαπλά υπολογιστικά νέφη

Author

Παπαϊωάννου, Αντώνιος Α

Thesis advisor

Μαρκάτος, Ευάγγελος

Reviewer

Μαγκούτης, Κώστας
Πλεξουσάκης, Δημήτρης

Abstract

Cloud computing has recently become an important model of infrastructural services that complements, and in some cases replaces, traditional data centers in providing distributed applications with the resources they need to serve Internet-scale workloads. The multitude of Cloud providers offering infrastructural services today raise the challenge of heterogeneity in the resources available to applications. An application developer is thus faced with the problem of choosing an appropriate set of Cloud providers and resources to support their application. One way to address this problem is to establish a Cloud-independent classification of Cloud resources and to systematically explore a large collection of past execution histories of real deployments of applications. In this thesis we present an architecture for the modeling, collection, and evaluation of long-term histories of deployments of distributed multitier applications on federations of Clouds (Multi-Clouds). Our goal is to capture several aspects of application development and deployment lifecycle, including the evolving application structure, requirements, goals, and service-level objectives; application deployment descriptions; runtime monitoring, and quality control; Cloud provider characteristics; and to provide a Cloud-independent resource classification scheme that is a key to reasoning about Multi-Cloud deployments of complex large-scale applications. Since our target is to capture the continuous evolution of applications and their deployments over time, we ensure that our metadata model is designed to optimize space usage. Additionally, we demonstrate that using the model and data collections over varying deployments of an application (using the SPEC jEnterprise2010 distributed benchmark as a case study) one can answer important questions about which deployment options work best in terms of performance, reliability, cost, and combinations thereof. As an example, our analysis can pinpoint the most cost-effective among a dozen deployments of an application leading to savings of $2,100 per year without impacting its service-level objectives.

Language

English

Subject

Cloud computing

Distributed application management

Performance analysis

Ανάλυση απόδοσης

Διαχείριση κατανεμημένων εφαρμογών

Issue date

2013-11-15

Collection

School/Department--School of Sciences and Engineering--Department of Computer Science--Post-graduate theses