Abstract-Peer-peer networking has recently emerged as a new paradigm for building distributed networked applications. In this paper we develop simple mathematical models to explore and illustrate fundamental performance issues of peer-peer file sharing systems. The modeling framework introduced and the corresponding solution method are flexible enough to accommodate different characteristics of such systems. Through the specification of model parameters, we apply our framework to three different peer-peer architectures: centralized indexing, distributed indexing with flooded queries, and distributed indexing with hashing directed queries. Using our model, we investigate the effects of system scaling, freeloaders, file popularity and availability on system performance. In particular, we observe that a system with distributed indexing and flooded queries cannot exploit the full capacity of peer-peer systems. We further show that peer-peer file sharing systems can tolerate a significant number of freeloaders without suffering much performance degradation. In many cases, freeloaders can benefit from the available spare capacity of peer-peer systems and increase overall system throughput. Our work shows that simple models coupled with efficient solution methods can be used to understand and answer questions related to the performance of peer-peer file sharing systems.

No abstract

Traffic application classification is an essential step in the network management process to provide high availability of network services. However, network management has seen limited use of traffic classification because of the significant overheads of existing techniques. In this context we explore the feasibility and performance of lightweight traffic classification based on NetFlow records. In our experiments, the NetFlow records are created from packettrace data and pre-tagged based upon packet content. This provides us with NetFlow records that are tagged with a high accuracy for ground-truth. Our experiments show that NetFlow records can be usefully employed for application classification. We demonstrate that our machine learning technique is able to provide an identification accuracy (≈ 91%) that, while a little lower than that based upon previous packet-based machine learning work (> 95%), is significantly higher than the commonly used port-based approach (50 − 70%). Trade-offs such as the complexity of feature selection and packet sampling are also studied. We conclude that a lightweight mechanism of classification can provide application information with a considerably high accuracy, and can be a useful practice towards more effective network management.

No abstract

No abstract

The user experience for networked applications is becoming a key benchmark for customers and network providers. Perceived user experience is largely determined by the frequency, duration and severity of network events that impact a service. While today's networks implement sophisticated infrastructure that issues alarms for most failures, there remains a class of silent outages (e.g., caused by configuration errors) that are not detected. Further, existing alarms provide little information to help operators understand the impact of network events on services. Attempts to address this through infrastructure that monitors end-to-end performance for customers have been hampered by the cost of deployment and by the volume of data generated by these solutions.We present an alternative approach that pushes monitoring to applications on end systems and uses their collective view to detect network events and their impact on services -an approach we call Crowdsourcing Event Monitoring (CEM). This paper presents a general framework for CEM systems and demonstrates its effectiveness for a P2P application using a large dataset gathered from BitTorrent users and confirmed network events from two ISPs. We discuss how we designed and deployed a prototype CEM implementation as an extension to BitTorrent. This system performs online service-level network event detection through passive monitoring and correlation of performance in end-users' applications.

One of the key infrastructure components in all telecommunication networks, ranging from the telephone network, to VC-oriented data networks, to the Internet, is its signaling system. Two broad approaches towards signaling can be identified: so-called hard-state and soft-state approaches. Despite the fundamental importance of signaling, our understanding of these approaches-their pros and cons and the circumstances in which they might best be employed-is mostly anecdotal (and occasionally religious). In this paper, we compare and contrast a variety of signaling approaches ranging from a "pure" soft state, to soft-state approaches augmented with explicit state removal and/or reliable signaling, to a "pure" hard state approach. We develop an analytic model that allows us to quantify state inconsistency in single-and multiple-hop signaling scenarios, and the "cost" (both in terms of signaling overhead, and application-specific costs resulting from state inconsistency) associated with a given signaling approach and its parameters (e.g., state refresh and removal timers). Among the class of soft-state approaches, we find that a soft-state approach coupled with explicit removal substantially improves the degree of state consistency while introducing little additional signaling message overhead. The addition of reliable explicit setup/update/removal allows the soft-state approach to achieve comparable (and sometimes better) consistency than that of the hard-state approach.

IPTV is increasingly being deployed and offered as a commercial service to residential broadband customers. Compared with traditional ISP networks, an IPTV distribution network (i) typically adopts a hierarchical instead of mesh-like structure, (ii) imposes more stringent requirements on both reliability and performance, (iii) has different distribution protocols (which make heavy use of IP multicast) and traffic patterns, and (iv) faces more serious scalability challenges in managing millions of network elements. These unique characteristics impose tremendous challenges in the effective management of IPTV network and service.In this paper, we focus on characterizing and troubleshooting performance issues in one of the largest IPTV networks in North America. We collect a large amount of measurement data from a wide range of sources, including device usage and error logs, user activity logs, video quality alarms, and customer trouble tickets. We develop a novel diagnosis tool called Giza that is specifically tailored to the enormous scale and hierarchical structure of the IPTV network. Giza applies multi-resolution data analysis to quickly detect and localize regions in the IPTV distribution hierarchy that are experiencing serious performance problems. Giza then uses several statistical data mining techniques to troubleshoot the identified problems and diagnose their root causes. Validation against operational experiences demonstrates the effectiveness of Giza in detecting important performance issues and identifying interesting dependencies. The methodology and algorithms in Giza promise to be of great use in IPTV network operations.