No abstract

We propose a push-based approach to network monitoring that allows the detection, within the dataplane, of traffic aggregates. Notifications from the switch to the controller are sent only if required, avoiding the transmission or processing of unnecessary data. Furthermore, the dataplane iteratively refines the responsible IP prefixes, allowing the controller to receive information with a flexible granularity. We implemented our solution, Elastic Trie, in P4 and for two different FPGA devices. We evaluated it with packet traces from an ISP backbone. Our approach can spot changes in the traffic patterns and detect (with 95% of accuracy) either hierarchical heavy hitters with less than 8KB or superspreaders with less than 300KB of memory, respectively. Additionally, it reduces controller-dataplane communication overheads by up to two orders of magnitude with respect to state-of-the-art solutions. CCS CONCEPTS• Networks → Network monitoring; Network measurement; Programmable networks; In-network processing.

Measuring and monitoring network traffic is a fundamental aspect in network management. This poster is a first step towards an SDN solution using an event triggered approach to support advanced monitoring dataplane capabilities. Leveraging P4 programmability, we built a solution to inform a remote controller about the detected hierarchical heavy hitters, thus minimizing control plane overheads.

Many data center applications are latency-sensitive. Monitoring continuously the network latency and reacting to congestion on a network path is important to ensure that the applications performance does not suffer penalties. We show how to use the Precision Time Protocol (PTP) to infer network latency and packet loss in data centers, and we conduct network latency and packet loss measurements in data centers from different cloud providers, using PTPd, an open-source software implementation of PTP.

Increased network latency and packets losses can affect substantially application performance. Due to the scale of data centers, custom network monitoring tools have been developed to measure network latency and packet loss. In our previous work, we used the Precision Time Protocol (PTP) to measure one-way delay and to quantify packet loss ratios, and we proposed PTPmesh as a cloud network monitoring tool. In this work, we provide a better understanding on how to exploit the measurement data offered by PTPmesh and present a detailed analysis of PTPmesh measurements collected in ten data centers from three cloud providers. Our findings reveal different latency, latency variance and packet loss characteristics across data centers. Through our analysis, we showcase the strengths and limitations of PTPmesh as a cloud network monitoring tool. To foster further research in this area, we make our dataset available.