Active Monitoring in GRID environments using Mobile Agent technology Orazio Tomarchio Andrea Calvagna Dipartimento di Ingegneria Informatica e delle Telecomunicazioni.

Slides:



Advertisements
Similar presentations
Understanding Code Mobility
Advertisements

Database System Concepts and Architecture
Distributed Systems 1 Topics  What is a Distributed System?  Why Distributed Systems?  Examples of Distributed Systems  Distributed System Requirements.
Network Management Overview IACT 918 July 2004 Gene Awyzio SITACS University of Wollongong.
Workload Management Workpackage Massimo Sgaravatto INFN Padova.
Mobile Agents: A Key for Effective Pervasive Computing Roberto Speicys Cardoso & Fabio Kon University of São Paulo - Brazil.
1 Introduction to Load Balancing: l Definition of Distributed systems. Collection of independent loosely coupled computing resources. l Load Balancing.
Grids and Grid Technologies for Wide-Area Distributed Computing Mark Baker, Rajkumar Buyya and Domenico Laforenza.
Managing Agent Platforms with the Simple Network Management Protocol Brian Remick Thesis Defense June 26, 2015.
Chapter 1: Overview of Workflow Management Dr. Shiyong Lu Department of Computer Science Wayne State University.
McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 17 Client-Server Processing, Parallel Database Processing,
Workload Management Massimo Sgaravatto INFN Padova.
SensIT PI Meeting, April 17-20, Distributed Services for Self-Organizing Sensor Networks Alvin S. Lim Computer Science and Software Engineering.
GLOMAR  Aims - Provides adaptive consistency control for mobile enabled file systems  Abstracting consistency control into a component architecture 
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Overview of Database Languages and Architectures.
DISTRIBUTED PROCESS IMPLEMENTAION BHAVIN KANSARA.
Architectural Design Establishing the overall structure of a software system Objectives To introduce architectural design and to discuss its importance.
Web-based Portal for Discovery, Retrieval and Visualization of Earth Science Datasets in Grid Environment Zhenping (Jane) Liu.
WORKFLOWS IN CLOUD COMPUTING. CLOUD COMPUTING  Delivering applications or services in on-demand environment  Hundreds of thousands of users / applications.
Understanding and Managing WebSphere V5
Database System Concepts and Architecture Lecture # 3 22 June 2012 National University of Computer and Emerging Sciences.
MobSched: An Optimizable Scheduler for Mobile Cloud Computing S. SindiaS. GaoB. Black A.LimV. D. AgrawalP. Agrawal Auburn University, Auburn, AL 45 th.
SensIT PI Meeting, January 15-17, Self-Organizing Sensor Networks: Efficient Distributed Mechanisms Alvin S. Lim Computer Science and Software Engineering.
Cloud Computing 1. Outline  Introduction  Evolution  Cloud architecture  Map reduce operation  Platform 2.
Mobile Agent Technology for the Management of Distributed Systems - a Case Study Claudia Raibulet& Claudio Demartini Politecnico di Torino, Dipartimento.
The Data Grid: Towards an Architecture for the Distributed Management and Analysis of Large Scientific Dataset Caitlin Minteer & Kelly Clynes.
Chapter 1: Overview of Workflow Management Dr. Shiyong Lu Department of Computer Science Wayne State University.
1 Introduction to Middleware. 2 Outline What is middleware? Purpose and origin Why use it? What Middleware does? Technical details Middleware services.
The Grid System Design Liu Xiangrui Beijing Institute of Technology.
Advanced Computer Networks Topic 2: Characterization of Distributed Systems.
MOBILE AGENTS What is a software agent ? Definition of an Agent (End-User point of view): An agent is a program that assists people and acts on their behalf.
Tool Integration with Data and Computation Grid GWE - “Grid Wizard Enterprise”
Service - Oriented Middleware for Distributed Data Mining on the Grid ,劉妘鑏 Antonio C., Domenico T., and Paolo T. Journal of Parallel and Distributed.
DISTRIBUTED SYSTEMS Principles and Paradigms Second Edition ANDREW S
Introduction Infrastructure for pervasive computing has many challenges: 1)pervasive computing is a large aspect which includes hardware side (mobile phones,portable.
Issues Autonomic operation (fault tolerance) Minimize interference to applications Hardware support for new operating systems Resource management (global.
Using SaaS and Cloud computing For “On Demand” E Learning Services Application to Navigation and Fishing Simulator Author Maha KHEMAJA, Nouha AMMARI, Fayssal.
Understanding Code Mobility A Fuggetta, G P Picco and G Vigna Presenter Samip Bararia.
NA-MIC National Alliance for Medical Image Computing UCSD: Engineering Core 2 Portal and Grid Infrastructure.
ABone Architecture and Operation ABCd — ABone Control Daemon Server for remote EE management On-demand EE initiation and termination Automatic EE restart.
GSAF: A Grid-based Services Transfer Framework Chunyan Miao, Wang Wei, Zhiqi Shen, Tan Tin Wee.
Globus and PlanetLab Resource Management Solutions Compared M. Ripeanu, M. Bowman, J. Chase, I. Foster, M. Milenkovic Presented by Dionysis Logothetis.
Development of e-Science Application Portal on GAP WeiLong Ueng Academia Sinica Grid Computing
Tool Integration with Data and Computation Grid “Grid Wizard 2”
Chapter 2 Database Environment.
Problem On a regular basis we use: –Java applets –JavaScript –ActiveX –Shockwave Notion of ubiquitous computing.
Control-Theoretic Approaches for Dynamic Information Assurance George Vachtsevanos Georgia Tech Working Meeting U. C. Berkeley February 5, 2003.
Mobile Analyzer A Distributed Computing Platform Juho Karppinen Helsinki Institute of Physics Technology Program May 23th, 2002 Mobile.
IT 5433 LM1. Learning Objectives Understand key terms in database Explain file processing systems List parts of a database environment Explain types of.
INTRODUCTION TO GRID & CLOUD COMPUTING U. Jhashuva 1 Asst. Professor Dept. of CSE.
DGAS Distributed Grid Accounting System INFN Workshop /05/1009, Palau Giuseppe Patania Andrea Guarise 6/18/20161.
The EPIKH Project (Exchange Programme to advance e-Infrastructure Know-How) gLite Grid Introduction Salma Saber Electronic.
Service Oriented Architecture (SOA) Prof. Wenwen Li School of Geographical Sciences and Urban Planning 5644 Coor Hall
Workload Management Workpackage
Introduction to Load Balancing:
Self Healing and Dynamic Construction Framework:
Walter Binder Giovanna Di Marzo Serugendo Jarle Hulaas
Gestione di Service Level Agreements (SLA) in sistemi Grid
Distributed System Concepts and Architectures
Copyright © 2011 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 2 Database System Concepts and Architecture.
Chapter 2 Database Environment Pearson Education © 2009.
AGENT OS.
Mobile Agents.
The Globus Toolkit™: Information Services
Assoc. Prof. Dr. Syed Abdul-Rahman Al-Haddad
Unit V Mobile Middleware.
Wide Area Workload Management Work Package DATAGRID project
In Distributed Systems
L. Glimcher, R. Jin, G. Agrawal Presented by: Leo Glimcher
Presentation transcript:

Active Monitoring in GRID environments using Mobile Agent technology Orazio Tomarchio Andrea Calvagna Dipartimento di Ingegneria Informatica e delle Telecomunicazioni Università di Catania (ITALY)

Outline § Monitoring Grid systems § Mobile agents paradigms § Mobile agents and monitoring § MAP: a mobile agents platform § Architecture description § Conclusions

Grid Monitoring §The capability of monitoring distributed computational resources effectively is a crucial factor for high-performance distributed computation §As distributed systems become bigger, and more widely distributed, automating the operations of monitoring becomes very important.

Grid Monitoring Why is monitoring important? §to find the cause of performance problems §for tuning systems parameters in order to optimize resource usage §fault detection §to build prediction models of performance (used by sophisticated scheduling algorithms) §for billing and accounting

Grid Monitoring What are the problems to deal with? §Wasting of resources dedicated to monitoring purposes §Scalability §Possibility to start monitoring application on- demand §Possibility to customize monitoring strategies §Different metrics of measurement data

Grid Monitoring with Agents § Mobile code and agents: l basic assumptions and characteristics § Key issues for using mobile agents technology in the monitoring context

Mobile Code §The basic idea is allowing to move code to remote sites and execute transferred code there §problems arising from mobility, e.g. l heterogeneity of systems l security (as more parties are involved) §Programming paradigms based on mobile code can be divided according to initiator of code transfer

Programming paradigms based on code mobility ClientServer Client/server local resources Client Server Code on DemandMobile Agents local resources Client Server Remote evaluation local resources

Mobile Agents §Mobile Agents are program instances that are able move within a network under their own control §mobile agents consist of: l code l data state (i.e. variables) l execution state (i.e. stack) §Some basic capabilities: l able to autonomously migrate between places l able to communicate to each other l some agents offer services or interfaces to legacy applications

Application Areas for Mobile Agents §Distributed Information Retrieval §Mobile computing §Distributed Network Management §Collaborative and workflow applications §Active networks §Electronic commerce Grid monitoring (?)

Grid Monitoring with agents: key issues §Customizable algorithms of data analysis dinamically executed on-demand by the user §Reduction of network load §Filtering of monitoring data at several abstraction level without high overheads for the system §Asynchronous and indipendent execution of task §Integration of heterogeneous resource monitoring tools §On-demand enabling of necessary services

MAP: a Mobile Agent Platform MAP is a software platform for the development and the management of mobile agents. Its main characteristics are: §It provides an environment in which agents can execute, stop and resume their execution, communicate among them, move on other nodes on the network §It is entirely developed using the Java language, which provides total architecture independence §The platform also provides different programming paradigms for distributed systems, such as remote evaluation and code on demand §In the latest version it has been made MASIF compliant

MAP architecture MAP Server MAP Server Region Registrator Region MAP Server MAP Server Region Registrator Region Dynamic Network Class Loading Communication Interface Context Agents

Graphic interface for agents’ control and management

Main features of MAP §Key features of MAP relevant for Grid systems are: l security l interoperability with different agents’ systems

Monitoring with agents: System Architecture Directory Service Agent Cache Repository Performance Data Repository Other Agents Monitoring Application Resource Local Monitoring Application High-Level Monitoring Agents HLMAgents Sensor Agents Low-Level Sensors LLSensors LLSManager

Monitoring with agents: Basic components §Low-Level sensors (LLSensors) §SensorAgents §High-Level Monitoring Agents (HLMAgents) §Low-Level Sensor Manager (LLSManager) §Directory Service §Performance Data Repository §Agent Cache Repository

Monitoring with agents: Basic components Low-Level sensors (LLSensors) §they are not agents (in general) §specific for each resource §directly interfaced with resources §The Low-Level Sensor Manager deals with their registration in the Directory Service

Monitoring with agents: Basic components Sensor Agents §They use the data supplied by the LLSensors for providing uniform informations about the state of a resource §Resources taken into account include: l hosts l network l storage l process/applications

Monitoring with agents: Basic components High-Level Monitoring Agents (HLMAgents) §Their task is gathering significant information relying on all the agents present in the system l user or application initiated (e.g. CollectSensorAgent, AggregateAgent) l event-initiated (e.g. TrapAgent)

Monitoring with agents: Basic components Directory Service §Basically the Directory Service maintains informations on what kind of Sensors are available for the different resources.

Monitoring with agents: Basic components Performance Data Repository §to store the events and data recorded by LLSensors and SensorAgents Agent Cache Repository §a repository of agents that have been executed within the region

Piano temporale attività §People l 2 persone al 30% Orazio Tomarchio Andrea Calvagna

Piano temporale attività §Tasks l task 1 M0-M1 Evaluation of mobile agent technology for Grid network monitoring l task 2 M0-M2 Use and testing of MAP (Mobile Agent Platform) in a Grid environment (eventually adapt it to new requirements imposed by geographically dispersed environment) l task 3M1-M4 Definition of a base architecture for monitoring networks using mobile agents

Piano temporale attività §Tasks l task 4 M2-M3 Evaluation of this approach against more traditional approach l task 5 M4-M9 Integration/Interfacing the agent platform with existing low-level tools for gathering network informations. l task 6M4-M12 Implementation of the proposed approach and experimental measurements and validations.