<abstract xml:lang="en" xmlns="http://www.w3.org/1999/xhtml"><p>Introspection is the prerequisite of autonomic behavior, the first step towards performance improvement and resource usage optimization for large-scale distributed systems. In grid environments, the task of observing the application behavior is assigned to monitoring systems. However, most of them are designed to provide general resource information and do not consider specific information for higher-level services. More precisely, in the context of data-intensive applications, a specific introspection layer is required to collect data about the usage of storage resources, data access patterns, etc. This paper discusses the requirements for an introspection layer in a data management system for large-scale distributed infrastructures. We focus on the case of BlobSeer, a large-scale distributed system for storing massive data. The paper explains why and how to enhance BlobSeer with introspective capabilities and proposes a three-layered architecture relying on the MonALISA monitoring framework. We illustrate the autonomic behavior of BlobSeer with a self-configuration component aiming to provide storage elasticity by dynamically scaling the number of data providers. Then we propose a preliminary approach for enabling self-protection for the BlobSeer system, through a malicious client detection component. The introspective architecture has been evaluated on the Grid'5000 testbed, with experiments that prove the feasibility of generating relevant information related to the state and behavior of the system.</p></abstract>

Introspection is the prerequisite of autonomic behavior, the first step towards performance improvement and resource usage optimization for large-scale distributed systems. In grid environments, the task of observing the application behavior is assigned to monitoring systems. However, most of them are designed to provide general resource information and do not consider specific information for higher-level services. More precisely, in the context of data-intensive applications, a specific introspection layer is required to collect data about the usage of storage resources, data access patterns, etc. This paper discusses the requirements for an introspection layer in a data management system for large-scale distributed infrastructures. We focus on the case of BlobSeer, a large-scale distributed system for storing massive data. The paper explains why and how to enhance BlobSeer with introspective capabilities and proposes a three-layered architecture relying on the MonALISA monitoring framework. We illustrate the autonomic behavior of BlobSeer with a self-configuration component aiming to provide storage elasticity by dynamically scaling the number of data providers. Then we propose a preliminary approach for enabling self-protection for the BlobSeer system, through a malicious client detection component. The introspective architecture has been evaluated on the Grid'5000 testbed, with experiments that prove the feasibility of generating relevant information related to the state and behavior of the system.

Bringing introspection into BlobSeer: Towards a self-adaptive distributed data management system

INRIA Rennes-Bretagne Atlantique/IRISA, Campus Universitaire de Beaulieu, 35042 Rennes, France

Department of Computer Science, Polytechnic University of Bucharest, 313 Spl. Independentei, 060042 Bucharest, Romania

Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China

Ecole Normale Supérieure de Cachan Antenne de Bretagne/IRISA, Campus Universitaire de Beaulieu, 35042 Rennes, France

International Journal of Applied Mathematics and Computer Science

Introspection is the prerequisite of autonomic behavior, the first step towards performance improvement and resource usage optimization for large-scale...

Bringing introspection into BlobSeer: Towards a self-adaptive distributed data management system

Published Online: Jun 22, 2011

Page range: 229 - 242

DOI: https://doi.org/10.2478/v10006-011-0017-y

Keywords
distributed system, storage management, large-scale system, monitoring, introspection

This content is open access.

Bringing introspection into BlobSeer: Towards a self-adaptive distributed data management system

Published Online: Jun 22, 2011

Page range: 229 - 242

DOI: https://doi.org/10.2478/v10006-011-0017-y

Keywordsdistributed system, storage management, large-scale system, monitoring, introspection

This content is open access.

Keywords
distributed system, storage management, large-scale system, monitoring, introspection