Showing papers in "Journal of Network and Systems Management in 2003"

The WSLA Framework: Specifying and Monitoring Service Level Agreements for Web Services

Abstract: We describe a novel framework for specifying and monitoring Service Level Agreements (SLA) for Web Services. SLA monitoring and enforcement become increasingly important in a Web Service environment where enterprise applications and services rely on services that may be subscribed dynamically and on-demand. For economic and practical reasons, we want an automated provisioning process for both the service itself as well as the SLA managment system that measures and monitors the QoS parameters, checks the agreed-upon service levels, and reports violations to the authorized parties involved in the SLA management process. Our approach to these issues is presented in this paper. The Web Service Level Agreement (WSLA) framework is targeted at defining and monitoring SLAs for Web Services. Although WSLA has been designed for a Web Services environment, it is applicable as well to any inter-domain management scenario, such as business process and service management, or the management of networks, systems and applications in general. The WSLA framework consists of a flexible and extensible language based on XML Schema and a runtime architecture comprising several SLA monitoring services, which may be outsourced to third parties to ensure a maximum of objectivity. WSLA enables service customers and providers to unambiguously define a wide variety of SLAs, specify the SLA parameters and the way they are measured, and relate them to managed resource instrumentations. Upon receipt of an SLA specification, the WSLA monitoring services are automatically configured to enforce the SLA. An implementation of the WSLA framework, termed SLA Compliance Monitor, is publicly available as part of the IBM Web Services Toolkit.

An Adaptive Policy-Based Framework for Network Services Management

Abstract: This paper presents a framework for specifying policies for the management of network services. Although policy-based management has been the subject of considerable research, proposed solutions are often restricted to condition-action rules, where conditions are matched against incoming traffic flows. This results in static policy configurations where manual intervention is required to cater for configuration changes and to enable policy deployment. The framework presented in this paper supports automated policy deployment and flexible event triggers to permit dynamic policy configuration. While current research focuses mostly on rules for low-level device configuration, significant challenges remain to be addressed in order to:a) provide policy specification and adaptation across different abstraction layers; and, b) provide tools and services for the engineering of policy-driven systems. In particular, this paper focuses on solutions for dynamic adaptation of policies in response to changes within the managed environment. Policy adaptation includes both dynamically changing policy parameters and reconfiguring the policy objects. Access control for network services is also discussed.

Provisions and Obligations in Policy Rule Management

Abstract: Policies in modern systems and applications play an essential role. We argue that decisions based on policy rules should take into account the possibility for the users to enable specific policy rules, by performing actions at the time when decisions are being rendered, and/or by promising to perform other actions in the future. Decisions should also consider preferences among different sets of actions enabling different rules. We adopt a formalism and mechanism devised for policy rule management in this context, and investigate in detail the notion of obligations, which are those actions users promise to perform in the future upon firing of a specific policy rule. We also investigate how obligations can be monitored and how the policy rules should be affected when obligations are either fulfilled or defaulted.

Report: The TeleManagement Forum's Enhanced Telecom Operations Map (eTOM)

Abstract: The telecom industry is facing unprecedented churn in a market where the only constant seems to be change. Information and communications service providers worldwide all face similar challenges, risks, and struggles to remain profitable in the face of more competition, higher customer expectations, falling market share and growing price pressures. The industry has a clear need to define and understand its business processes to tackle these issues. It also needs to reach a consensus on the common process view for equipment suppliers, applications builders and integrators so they can build management systems that combine third-party and in-house developments. The enhanced Telecom Operations Map  (eTOM) initiative is an ongoing TeleManagement Forum (TM Forum) project to deliver a business process model or framework for use by service providers and others within the telecommunications industry. The TM Forum’s eTOM [1] describes all the enterprise processes required by a service provider. It provides a business framework with hierarchy, relationships, and individual process decompositions, as well as linking process flows that allow the business to be modeled in detail and end-to-end. This can be used by service providers themselves, and by other companies, such as their suppliers, to ensure that activities dovetail effectively and support products that mesh with enterprise needs. The eTOM is being evaluated and applied widely within the telecommunications industry, and is even attracting interest outside of this area. It is also a key part of the wider TM Forum initiative on NGOSS (New Generation Operations Systems and Software) which addresses the whole OSS/BSS (Operations Support

Building Quality-of-Service Monitoring Systems for Traffic Engineering and Service Management

Abstract: Deployment of quality-of-service (QoS) based value-added services in IP networks necessitates the use of traffic engineering. Traffic engineering allows service providers to use the network resources efficiently, according to the different quality levels associated with the range of services they offer. Traffic engineering relies typically on monitoring data for both “offline proactive” and “dynamic reactive” approaches. Monitoring data may be used for network provisioning, dynamic resource allocation, route management, and in-service performance verification for value-added IP services. A monitoring system should scale with the network size, the network speed, and the number of customers subscribed to use value-added IP services. This paper investigates the requirements of scalable monitoring system architectures, proposes principles for designing such systems and validates these principles through the design and implementation of a scalable monitoring system for traffic engineering and QoS delivery in IP Differentiated Services networks. Methods for assessing the relative merits of such monitoring systems are proposed. Experimental assessment results prove the scalability, accuracy, and also demonstrate the benefits of the proposed monitoring system.

Guest Editorial: Policy-Based Management of Networks and Services

Abstract: Policies are rules governing the choices in behavior of a system . The original focus for their application was the management of Quality-of-Service within communications networks, and many of the concepts employed in the formulation and use of policies have been around for more than ten years. Over that period of time, these have been extended and applied to other domains. Policies can be used for provisioning of virtual private networks, for deployment of distributed applications, and for management of all aspects of computing systems, including: configuration, storage services, security, and support for user mobility in a pervasive computing environment. This has led to the evolution of a software paradigm denoted aspolicy-based computing . In policy-based computing a set of explicit decision making technologies are incorporated into the management components of computing systems. The primary advantage of such an approach is that it simplifies the complex task of administering large, distributed systems by allowing administrators and operators to specify management operations in terms of the objectives or goals that need to be met, rather than the detailed instructions that need to be executed. It also supports separation of concerns, in that decision points are called out explicitly and considerations that would lead to various alternatives are captured in the policies. The incorporation of policy-based technologies augments the capabilities of computing environments by making them more customizable, and more responsive to the overall objectives of the organizations that they support. Policy-based systems have thus become a promising solution for implementing many forms of large-scale, adaptive systems that dynamically change their behavior in response to changes in the environment or to changing application requirements. This can be achieved by modifying the policy rules interpreted by

Active Robust Resource Management in Cluster Computing Using Policies

Abstract: We present an implementation of a policy-based management architecture for emerging communications and computing paradigms such as Active Networks and the Grid. To manage such open, highly distributed and decentralized environments, an approach based on policy concepts is adopted, allowing support for active, dynamic adaptability in network elements, services and end-user applications, as well as achieving decentralization and distribution. We present our flexible, extensible policy and event specifications in XML, and describe our management architecture. One key feature of our approach is the distributed infrastructure: the Directory and the Management Information Distribution system. The second feature is the Resource and Security Management elements residing on the multi-node managed systems. These combine to provide a light-weight, self-organizing management architecture. As an applications example, we describe the implementation of our management system applied to the Application Level Active Networking (ALAN) environment, implemented in the European Commission Information Society Technologies (IST) project ANDROID.

Managing QoS for Multimedia Applications in the Differentiated Services Environment

Abstract: The overall quality of network connections has a significant impact on the performance of networked applications. As a result, Quality-of-Service (QoS) management for networked multimedia applications over IP is a significant and immediate challenge. While differentiated services (DiffServ) provide a sense of resource allocation and QoS, they do not guarantee QoS. This paper presents the design, implementation and evaluation of a content-aware bandwidth broker (CABB) that manages QoS for multimedia applications in a DiffServ environment. CABB allocates network resources to multimedia flows based on client requirements, the adaptability of the application, and its tolerance to network level parameters such as bandwidth, delay, and latency. It has been implemented and evaluated using the NS-2 simulator toolkit. Evaluations show that CABB improves network resource allocations and increases overall throughput. Furthermore multimedia application flows are better managed and controlled, improving perceived QoS and avoiding possible congestion at core routers.

Semantic Analysis of E-Business Operations

Abstract: An e-business infrastructure is comprised of a large number of business processes that are exposed through web services. To manage such an infrastructure, it is necessary for business managers to be able to observe their e-business operations in greater detail. In particular, a framework and a tool is required that allows business users to define qualitative and quantitative metrics, depending on their own (business or IT) goals. Once metrics have been defined, the tool should be able to measure them and support users in semantic analysis of the results, allowing them to quickly identify quality degradations as well as their causes.

Realizing Network Control Policies Using Distributed Action Plans

Abstract: The increasing complexity in size and heterogeneity of networks requires the development of network management tools that are less dependent on human intervention Many tasks in network management consist of the coordination and execution of multiple activities across different network platforms In the first part of this paper we introduce a language to write Distributed Action Plans (DAPs) A DAP is meant to specify one of these distributed network management tasks To run these plans we use policy agents These are agents that can be specified in \cal{PDL}, an event-driven programming language developed at Bell Labs to perform policy-based network management The second half of the paper shows how DAPs are translated into \cal{PDL} and describes the policy agent system that executes these DAPs

Inter-Area Traffic Engineering in a Differentiated Services Network

Abstract: In this paper, an off-line traffic engineering algorithm is presented that optimizes the single-path routing of Label Switched Paths in a Differentiated Services IP domain by means of explicit, Multi-Protocol Label Switching controlled nonshortest paths. This algorithm allows traffic engineering up to 2500 traffic trunks in flat networks with sizes up to 150 nodes while supporting protection, pre-emption, quality-of-service, oversubscription, and resource class affinity. The algorithm with proper extensions can be applied to hierarchical networks, thus increasing the scalability properties for network size with a factor of about 50. First the single-area algorithm is detailed, then the concept and implementation of hierarchy is introduced for inter-area traffic engineering. These topics are illustrated with simulation results.

GAP: A General Approach to Quantitative Diagnosis of Performance Problems

Abstract: Quantitative performance diagnosis (QPD) provides explanations that quantify the impact of problem causes. An example of such an explanation is it Increased web server traffic accounts for 90% of the increase in LAN utilization, which in turn accounts for 20% of the increase in web response times. This paper describes GAP, a general approach to quantitative performance diagnosis. GAP has two parts: (1) an algorithm for computing quantitative performance diagnosess and (2) a framework for constructing diagnostic techniques that provides the basis for quantifications produced by the algorithm. The GAP algorithm makes use of a measurement navigation graph, a directed acyclic graph whose nodes are measurement variables and whose arcs have weights that quantify the effect of child variables (e.g., LAN utilization) on parent variables (e.g., response time). The framework for developing diagnostic techniques consists of (a) the choice of statistic (e.g., mean, variance) to aggregate problem values, and (b) the estimator of the statistic.

Managing Pervasive Computing and Ubiquitous Communications: A Report on APNOMS 2003

Abstract: The 7th Asia-Pacific Network Operations and Management Symposium (APNOMS 2003) was held during October 1–3, 2003 in Fukuoka, Japan. APNOMS 2003, which was organized by IEICE TM (The Institute of Electronics Information and Communication Engineers, Telecommunication Management Committee) and KICS KNOM (The Korean Institute of Communication Science, Korean Network Operations and Management Committee) with support from IEEE CNOM (Committee on Network Operations and Management), IEEE APB (Asia Pacific Board), IEEE ComSoc Japan Chapter and TMF (TeleManagement Forum), has continued to play an important role in exchanging and discussing all aspects of telecommunications management among academics and telecommunication industry at large in the Asia-Pacific region. As in the previous symposia [1–5], APNOMS 2003 was a great success, attracting about 250 researchers, practitioners, operators, and vendors from 10 countries. Its program included keynote speeches, tutorials, special sessions, technical sessions, poster sessions, a distinguished experts panel, and exhibitions. The theme of this symposium was “Managing Pervasive Computing and Ubiquitous Communications.” The concept of “ubiquitous society” frequently appears in mass media, and it spreads a roseate dream and image to the future human life. Application examples include, inventory management, product tracking and tracing, home automation, home and community security management, and environment protection. Governments are trying to push research and development in ubiquitous-related areas. Industries are seeking business opportunities in the near future. In the coming ubiquitous society, it will be hard, or in some cases

A Multi-Agent Architecture for QoS Management in Multimedia Networks

Abstract: Increasing interest in the transmission of audiovisual applications over best-effort networks (i.e., IP and ATM ABR, and UBR services) and efficient video-aware congestion control techniques have to be designed in order to improve the video quality in the presence of cell loss. This paper presents a new slice-based discard scheme to be used with Guaranteed Frame Rate service (formerly UBR+). The scheme adaptively and selectively adjusts discard levels to the switch's buffer occupancy, video cell payload types, and Forward Error Correction Drop Tolerance. To improve its performance, we introduce a distributed multiagent system that provides a self-regulating network control management by means of automatic adjustment of congestion control parameters. The control agents are distributed in the network and operate on a local scope referred to as a “domain” consisting of two adjacent ATM switches. The aim of the overall Intelligent Quality-of-Service (QoS) control framework is twofold. First, to ensure graceful picture quality degradation by minimizing the cell loss probability for critical video data while guaranteeing a bounded cell transfer delay. Second, to optimize the network effective throughput by reducing the transmission of “nonuseful” data. Performance evaluations show significant improvement over traditional approaches.

Mobile Agent-Based Performance Management for the Virtual Home Environment

Abstract: Virtual Home Environment (VHE) encompasses the deployment and management of adaptable services that retain any personalized service aspects, irrespective of terminal, network' and geographic location. We assert that the dynamic nature of the VHE requires management capabilities that can be suitably provided through the use of mobile agent technology. We examine four different engineering solutions for the realization of a VHE performance management component that allows service adaptation in relation to the available network Quality-of-Service (QoS). The mobile agent approach is compared with competing technologies in order to identify the benefits of this novel application of mobile agents, discuss its drawbacks' and finally focus on the lessons learned from our prototype system. Although mobile agents are typically associated with increased performance costs, it is through agent migration that we were able to address the VHE requirements of universality, dynamic programmability, and network technology independence.

Towards the Technology Neutral Modeling of Management Components

Abstract: This paper outlines an Architectural Model and accompanying modeling notation that addresses on the need to model management component interfaces and their business contexts in a technology neutral manner in order to promote convergence on stable, reusable solutions. The approach combines existing modeling concepts related to component-based and model-driven software development from TINA-C, OMG, DMTF and TM Forum in order to provide guidance on the development of models that need to be exchanged between organizations involved in the development of software components and the management systems in which they are used. The Architectural Model is assessed through application to the management a specific set of e-business support services.

Auto-Discovering Configurations for Service Management

Abstract: Determining service configurations is essential for effective service management. In this paper we describe a model-driven approach for service configuration auto-discovery. We develop metrics for performance and scalability analysis of such auto-discovery mechanisms. Our approach addresses several problems in auto-discovery: specification of what services to discover, how to efficiently distribute service discovery, and how to match instances of services into related groups. We use object-oriented models for discovery specifications, a flexible bus-based architecture for distribution and communication, and a novel multi-phased, instance matching approach. We have applied our approach to typical e-commerce services, Enterprise Resource Planning applications, like SAP, and Microsoft Exchange services running on a mixture of Windows and Unix platforms. The main contribution of this work is the flexibility of our models, architecture and algorithms to address discovery of a multitude of services.

Rule-Based Building-Block Architectures for Policy-Based Networking

Abstract: We developed two rule-based building-block architectures, i.e., pipe-connection and label-connection architectures, for describing complex and structured policies, especially network QoS policies. This study focuses on the latter. The relationships or connections between building blocks are specified by the data flow and control flow between them. The data flow is specified by tags, including virtual flow labels (VFLs), which are data attached to “outside packets.” The control flow can be classified and specified by four control structures: concatenation, parallel application, selection, and repetition. We have designed fine-grained and coarse-grained building blocks and methods for specifying data flow and control flow in differentiated services (Diffserv), and implemented the coarse-grained ones in a policy server. Two cases of building-block use are described, and we concluded that there are five advantages of building-block-based policies, i.e., expressibility, uniform semantics, simplicity, flexibility, and management-task-oriented design. We also developed techniques for transforming building-block policies into executable ones, which are called policy division and fusion.

Future Trends in Network Management: A Report on LANOMS 2003

Abstract: The Third Latin American Network Operations and Management Symposium (LANOMS 2003) was held in Iguassu Falls, Brazil, during September 4–6, 2003. This was the third edition of a now established symposium series, the first of which was held in Rio de Janeiro, Brazil, in 1999 [1], and the second in Belo Horizonte, Brazil, in 2001 [2]. The symposium was an initiative of Federal University of Paraná, Brazil, technically co-sponsored by IEEE Communications Society, and supported by IEEE Technical Committee on Network Operations and Management (CNOM). The main goal of LANOMS 2003 was to create a forum more specific to the necessities of Latin America in the area of network management, involving networking and telecommunication companies, academic institutions, and equipment vendors. LANOMS 2003 attracted 100 participants from all around the globe who were interested in having, or already have, research or commercial liaisons in Latin America, one of the fastest growing regions in the world in networking. This year, the symposium presented a technical program with contributions from South and North America, Europe, and Asia. The theme for LANOMS 2003 was “Future Trends in Network Management.” We currently see the convergence of several networks, like data and telephone networks, into a multi-service network, taking advantage of the ubiquity of the Internet. Particularly in Latin America, optic fiber backbones are being installed to interconnect cities and countries; and these backbones will support gigabit networks for research and education. Connections of these networks to United States and Europe are being established.

Ticket Servers for Network Traffic Prioritization

Abstract: For broadband packet networks to be widely useful to society, they must dynamically recognize some network flows, like those that deal with disaster response, military operations, or emergencies as having greater importance than others. This paper proposes an architecture of geographically distributed ticket servers that issue importance tickets that indicate the priority that a flow should be given in the current dynamic network context. Any type of user or flow can be given priority, depending on the user needs and the context. User agents contact ticket servers using an agent communication languages then a ticket server intelligent agent determines how valuable of a ticket to issue. Use of ticket servers and agent communication enables quick adaptation to dynamic context changes and provides user feedback so that high priority communication activities can be conducted effectively.

Thresholds: Understanding Active Service Level Management

Abstract: From the Thresholds Editor This approach is not as innovative as it seems since the congestion management system of yesteryear and toady do manage service. The contribution here is the attempt to map the servers and application into the service. This requires the integration of the in band SNMP and the out-of-band network management controls. It seems to me a ‘shadow’ service pinged periodically and monitored for traffic by header snooping would be a more effective, if more difficult, approach. I always observed real network managers and system administrators first looking at traffic patterns and then looking for alarms as they troubleshoot and react to service problems, but I could be wrong. Let the debate begin. We welcome all views on this critical vision for our industry.

Policy 2003: Workshop on Policies for Distributed Systems and Networks

Abstract: Policy-based systems are the subject of a wide range of activities in universities, standardization bodies and within industry [1]. They have a wide spectrum of applications ranging from quality-of-service management within networks to security and enterprise modeling. Within the Internet community there is considerable interest in Policy Based Networking. A number of companies have announced tools to support the specification and deployment of policies. Much of this work is focused on policies for quality-of-service management within networks and the Internet Engineering and Distributed Management Task Forces (IETF/DMTF) are actively working on standards [2] related to this area. The Security community has focused on the specification and analysis of access control policy, which has evolved into the work on Role-Based Access Control (RBAC) [3]. There had been work over a number of years in the academic community on specification and analysis of policies for Distributed Systems [4], mostly concentrating on authorization polices. Although there are strong similarities in the concepts and techniques used by the different communities there is no commonly accepted terminology or notation for specifying policy. Several research groups are looking at high-level aspects of policy related to Enterprise Modelling. An ISO Open Distributed Processing (ODP) working group is defining Policy and Role concepts within the Enterprise Viewpoint [5]. Enterprise goals or Service Level Agreements can be considered as high-level abstract policies, which must be progressively refined into implementable policies. The work on the specification and analysis of Business Rule is also relevant.

Guest Editorial: E-Business Management

Abstract: Electronic commerce has become important for businesses that perform commercial activities over the Internet, including information catalogs, buying and selling products and services, online delivery, collaborative work, and information transfer among partners. A related concept is an e-business, or virtual organization, covering areas such as manufacturing, healthcare, and government. E-business is the term used to cover the models, processes, techniques, and tools to support the complete cycle of business activities over the Internet. It covers market research, market segmentation, product development targeted at well-defined market segments, and sales and support of various types of businesses. The management of such e-businesses has become a major issue. The management of e-business services is concerned with the development, deployment and support of e-business applications and processes over the Internet. Although there have been several efforts towards the development of frameworks and standards for e-business application interoperability, the field of e-business management is new. This issue of theJNSMis devoted to a discussion of models, frameworks, and methodologies for the development of management solutions for e-businesses. In the Call-for-Papers, we encouraged contributions in the form of case studies and implementation experiences on management solutions in real e-businesses. The list of topics included the following: r Models for e-business management r Integration of e-business management with service-level management r Integration of e-business management with systems and network management r Patterns and architectures for e-business management r Relationship with standards such as CIM, XML, and DEN, and telecommunication management standards (TMN, TINA, and TMF)

Path and Oracle Discovery Protocol for Centralized Bandwidth Reservation Mechanisms

Abstract: The introduction of Differential Service architecture has initiated interests in centralized bandwidth reservation via an oracle with each network domain defining its own oracle. The centralized bandwidth reservation mechanism requires knowledge of network topology and reservation paths in the domain to control access to premium services as well as log usage. We propose a new reactive protocol, Path and Oracle Discovery Protocol (PODP), to facilitate the management of networks with centralized bandwidth reservations. This protocol discovers the routers traversed by the network connection request and the respective domain oracle. PODP is able to respond to network path changes at minimum network overhead and storage requirements compared to other methods. A prototype router and oracle supporting the PODP has been successfully developed and tested across multiple domains.

Applying and Evaluating Active Technologies in Distributed Management

Abstract: The idea of Distributed Management has been around for quite some time. In recent years, several different technologies have been developed to implement this paradigm. However, until today a practical comparison of these technologies with the implementation of various management applications has—to the authors knowledge—not been made. Therefore, this paper discusses and compares the application of different active technologies to distributed Internet management. Three management application areas that profit from the Distributed Management paradigm are investigated: scalable monitoring, explicit placement of management tasks, and remote systems management of network nodes. The specific requirements of these application areas are analyzed and compared to the capabilities of three different active Distributed Management technologies: the Internet Engineering Task Force (IETF) Script MIB, the active network backbone (ABone), and the mobile agent platform Voyager. For all combinations of technologies and application areas, prototype implementations have been made, that demonstrate strengths and weaknesses of current Distributed Management technologies. The paper evaluates the tested technologies and concludes with suggestions for improvements.

Extending TINA with Secure On-Line Accounting Services

Abstract: Concepts and principles of TINA (Telecommunications Information Networking Architecture) are introduced with the objective of correcting problems of the current centralized service control and service data model in an IN (Intelligent Network). It is becoming increasingly clear that the future sophisticated telecommunication services, e.g., multimedia, and multi-party conferencing, breaking away from the traditional telephony call model will need the solutions for rapid and efficient introduction, deployment, operations, and management. In this paper, we discuss accounting features and requirements, as well as security services in the TINA management context. We will introduce and present an implementation of a model for a security management, based on secure objects, cryptography and certificate distribution. In order to provide secure services, secure objects that have security functionality, such as authentication and access control, have been defined. Secure objects in our model are CORBA objects. The security domain is also called SBS (Security Base Server), provides security services and has an SMIB (Security Management Information Base) that contains security policies, cryptographic algorithms, and other relevant information. A prototype has been implemented and some experimental results are presented.

Managing It All—A Report on IM 2003

Abstract: The 2003 IFIP/IEEE International Symposium on Integrated Network Management (IM 2003,http://www.im2003.org/ ) was held in Colorado Springs, Colorado, March 24–28, 2003. This is the most important international technical symposium in the field of network and distributed systems management. IM is a flagship conference for both IFIP Working Group 6.6 on Network and Distributed Systems Management and the IEEE Communications Society Technical Committee on Network Operations and Management (CNOM). This eighth edition of the symposium continued the established tradition of IM as the premier technical network management symposium (see Ref. 1 for a report on the previous IM symposium). The theme for IM 2003 was “Managing it all” to reflect the topical coverage of the research community and to represent the excitement and diversity present in this field. In accordance with this challenging theme, the IM 2003 Technical Program Committee (TPC) established the scope for the symposium covering the management of the plethora of network devices and systems, multiple inter-connected networking technologies, and the complexity of distributed applications. The scope highlighted the many management issues related to next generation networks including the ubiquitous explosion of the Internet, the fast proliferation of networked devices and applications, and the convergence of data and telecommunications networks, from narrowband to broadband, terrestrial to satellite, fixed to mobile and uni-media to multi-media. IM 2003 attracted 149 paper submissions from all over the world, representing research contributions in a wide variety of topics related to network and systems

Thresholds: Policies to Optimize BGP Routing Tables

Abstract: From the Thresholds Editor Forwarding table size limits the size of subnets in the Internet. As they grow, table look-up gets longer, queues overflow, and latency increases. Steps have been taken by Network Managers to reduce the size of forwarding tables. Network Managers have purchased routers for Multiprotocol Label Switching, Metarouters, and the Luela algorithm. Now, Border Gateway Protocol (BGP) routers are becoming the bottleneck. This insightful paper points to ways to deal with the BGP Routing Table size. Of course, the routing tables soon are transferred to become forwarding tables. Real Network Managers face size problems every day. If you know of better solutions let us know.