Previous work on network measurements have explored several primitives of increasing complexity for measurement tasks at individual nodes, ranging from counters to hashing to arbitrary code fragments. In an SDN network, these primitives may require significant bandwidth, memory and processing resources, and the resources dedicated to these can affect the accuracy of the eventual measurement. In this paper, we first qualitatively discuss the tradeoff space of resource usage versus accuracy for these different primitives as a function of the spatial and temporal measurement granularity, then quantify these tradeoffs in the context of hierarchical heavy hitter detection.

No abstract

A Mobile Ad hoc Network (MANET) is a collection of wireless mobile nodes forming a self-configuring network without using any existing infrastructure. Since MANETs are not currently deployed on a large scale, research in this area is mostly simulation based. Among other simulation parameters, the mobility model plays a very important role in determining the protocol performance in MANET. Thus, it is essential to study and analyze various mobility models and their effect on MANET protocols. In this paper we introduce a new framework for simulation of mobility models in mobile Ad-Hoc networks. This simulator can generate mobility traces in various mobility models. The mobility traces can be customized for different network simulators using XML and text output formats. User friendly graphical interface and batch processing ability makes our simulator one of the most efficient and useful mobility simulators in this field of research. We also propose some new features and parameters in mobility models to make the behavior of our simulator supported mobility models more similar to real world mobile node motions and fix some problems in last proposed methods to generate mobility models.

With the advancement of multicore servers, there is a new trend of moving network functions to software servers. Measurement is critical to most network functions as it not only helps the operators understand the network usage and detect anomalies, but also produces feedback to the control loop in management tasks such as load balancing and traffic engineering. Traditional researches on measurement algorithms mainly focus on reducing the memory usage leveraging the fact that measurement can sustain bounded inaccuracy. In this study, we re-evaluate these algorithms on software servers in order to understand their tradeoffs of accuracy and performance. We observe that simple hash tables work better than more advanced measurement algorithms for a variety of measurement scenarios. This is because with better cache design in modern servers and the skewness in the access patterns of measurement tasks, the memory usage of measurement tasks is largely irrelevant to the packet processing performance.