Jianhua Yang

Handover Latency of MIPv6 Implementation in Linux

Mobile IPv6 (MIPv6) is proposed to enable network applications to continuously operate at the required quality of service in the wire or wireless IP network. Handover latency of MIPv6 is the main cause of packet loss and performance degradation and is too long for real-time and throughput-sensitive applications. Enhancement of basic MIPv6 with respect to handover latency has been studied widely. A L3 handover procedure can be divided into four phases: Movement Detection, CoA Configuration, Home agent Registration and Route Optimization. The latencies in different handover phases have been measured in an operated wireless LAN (WLAN) in order to determine the performance bottleneck of handover. The effect of handover latency on the sliding window of TCP and application layer protocol is also parsed with experiment. Further more, we modify the MIPv6 implementations of Linux on mobile node and home agent to verify the potential of performance improvement for MIPv6 protocol. The experiment result can help the enhancement of MIPv6 and application development.

Survey on traffic of metro area network with measurement on-line

Network traffic measurements can provide essential data for network research and operation. While Internet traffic has been heavily studied for several years, there are new characteristics of traffic having not been understood well brought by new applications for example P2P. It is difficult to get these traffic metrics due to the difficulty to measurement traffic on line for high speed link and to identify new applications using dynamic ports. In this paper, we present a broad overview of Internet traffic of an operated OC-48 export link of a metro area network from a carrier with the method of measurement on-line. The traffic behaves a daily characteristic well and the traffic data of whole day from data link layer to application layer is presented. We find the characteristics of traffic have changed greatly from previous measurements. Also, we explain the reasons bringing out these changes. Our goal is to provide the first hand of traffic data that is helpful for people to understand the change of traffic with new applications.

Characterization of HTTP behavior on access networks in Web 2.0

The traffic generated by the hypertext transfer protocol has a dominating position in current Internet traffic. The analyzing and characterizing of HTTP traffic is significant for understanding the nature of Internet traffic. Many studies on HTTP traffic were carried out when HTTP 1.1 appeared. Along with the prevailing of Web 2.0 the research on new features of HTTP traffic becomes a new issue in network measuring. In this paper comprehensive characterization of both the user behavior and the transportation feature on HTTP traffic are discussed. The characterization of HTTP behavior at HTTP conversation, TCP connection and Web flow level is parsed based on data collected on-line from access link of an institutepsilas LAN with more than 1500 users. The HTTP request and response length, temporal characteristics of HTTP message, and the interval of TCP connections as well as Web flows are discussed in detail. Some transformations of the investigated characterization caused by the influence of Web 2.0 are discovered in the experiment contrasting with previous result.

Self-Similar Characteristic of Traffic in Current Metro Area Network

Complexity and diversity of Internet traffic are constantly growing. Networking researchers become aware of the need to constantly monitor and reevaluate their assumptions in order to ensure that the conceptual models correctly represent reality. Using the dataset collected by NetTurbo from three different bidirectional OC-48 links in metro area networks at the two biggest ISPs of China, this paper carefully investigates the self-similar characteristics of traffic from different aspects. In contrast to the previous results which have been widely accepted, this paper shows that for the aggregated traffic and the TCP and UDP traffic whether the self-similarity exists is uncertain. Further, break down by the application category, only the traditional and uncategorized traffic are self-similar while the others are not. However, on the view of the individual application of each category, it seems that traffic of every application exhibits self-similarity. To the best of our knowledge, this paper firstly provides the experimental evidence showing that aggregating different groups of self-similar traffic series could generate a traffic series which is either self-similar or non-self-similar.

On-line estimating skew in one-way delay measurement

Delay metrics of Internet play an important role in evaluating the network performance. They are also the foundation for other metrics measuring, such as bandwidth, jitter and loss. One-way delay (OWD) measurement has been getting much attention in recent years. IP Performance Metrics Working Group of IETF has made great efforts on one-way related metrics measurement and brought several RFCs[G. Almes et al., (1999), R. Koodli et al., (2001)]. A key issue for one-way related metrics measurement is the clock skew, especially in the situation of without external clock synchronization mechanism. Many researches have been done on removing clock skew in OWD. A real time skew estimation algorithm named RTSE is proposed to estimate the online skew. We prove that it is not only as efficient as other static algorithms but also could provide an online insight view of the OWD dynamics of monitored networks with a month experiments on an operating network. RTSE has been integrated into our OWD measurement tool capOWD.

OSPFv3 protocol simulation with colored Petri nets

OSPF is the most popular interior gateway protocol proposed by IETF to distribute routing information among routers belonging to the same autonomous system. OSPF for IPv6, also referred to as OSPFv3, has been widely researched and implemented by many manufacturers in various devices such as routers and operation systems. Since IPv6 has been regarded as the kernel protocol of the next generation Internet, conformance of all OSPFv3 implementation with protocol specification is the premise to guarantee the interoperability between various routing devices. Protocol conformance test system (PCTS) is used for verifying whether the implementation under test (IUT) conforms to protocol specification. How to generate complete test cases is one of the most important issues in PCTS. In this paper, after analyzing the mechanism of OSPFv3, we use CPNs to model the main features of this complex protocol. The construction of this CPN model is presented, and the state space analysis is given based on the occurrence graph.

An Accurate and Efficient 3-Phase Measurement Method for IP Traffic Flow on High Speed Link

Flow metrics are critical for protocol research, anomaly detection, network operation and application deployment. There are great challenges to match every packet into millions of flows in high speed network link. A 3-phase measurement method for IP traffic flow is proposed in this paper. The packets are captured and classified into the flows through hash table, search tree and linear table with this approach. The traffic measurement systems in general purpose CPU platform and network processor platform with this method have been implemented and deployed in backbone links. The experiment on OC-48 backbone shows the average length search path for each packet is 7.7. Average process times of mapping successfully and unsuccessfully are about 1.3 mus and 1.8 mus respectively at the length of search path 350. Traffic matrix, host behavior and other metrics can been easily deduced with our approach.

Measuring one-way delay with multiple clock dynamics

A key issue in one-way metrics measurement is the removal of relative clock offset in the situation of without external clock synchronization mechanisms for the end-to-end hosts. The relative clock offset is resulted from clock dynamics including clock adjustment, frequency adjustment and clock drift. Many efforts have been done on the removal of clock skew (related to frequency) in OWD measurement. Most researches are based on the assumption that the clock skew retains constant and without clock adjustments and drifts during measurement. But this does not hold according to our practical measurements and other work. In fact, it is found that host clocks might be subject to gradual or instantaneous clock adjustments and frequency adjustments in operation. We discuss the detection of clock dynamics in OWD measurement, with the time series segmentation technology. An algorithm is proposed to estimate the relative clock offset with only unidirectional probe packets. Experiments results show that the algorithm can provide reasonable clock dynamics detection and informative OWD estimation.

A methodology of effective measurement for link traffic

Precise and real time measurement of link traffic is the fundamental procedure of traffic engineering, network behavior monitoring and capacity planning. The methodology of measuring links traffic by polling every device for large-scale network will impact performance of routers and bring up heavier traffic into the network. Further more, this methodology cannot meet the requirement of time scale since there are so many SNMP supported devices in network under management. How to decide the minimal set of devices to be interrogated with the premises of traffic of every link being confirmed is the key to resolve this problem. In the paper, traffic measurement mechanism is introduced and a sufficient condition is proposed for measuring each link on the network. The sufficient condition can include the condition of weak vertex cover proposed by Yuri Breitbart. A policy of traffic measurement is designed based on the sufficient condition. An example is used to explain the process of the policy. The methodology can decrease the number of nodes to be monitored and reduce the traffic caused by measurement. The policy has been used to network management system of long-distance education project supported by NEPC.

Efficient traffic flow measurement for ISP networks

Traffic flow measurement is of great importance to ISPs for various network engineering tasks. An interesting problem is that how to determine the minimum number of links by monitoring which one can obtain the traffic flows of the whole ISP network. Previous works view the problem as Vertex Cover problem. They suffer from high time complexity and redundant monitoring. Different from these works, we study the problem from the perspective of edges and propose two models. The first model, Extended Edge Cover model, can determine the minimum set of monitored links, which are 30% less than that of previous works. The second model, shared-path model, is more suitable when the monitoring resources are limited but one still wants to measure a large part of the networks. Using this method, one can measure 85% of the network by monitoring 5% of links. Finally, we evaluate the performance of the two models through extensive simulations. The experimental results show the effectiveness and robustness of the two models.