SRLA: A Real Time Sliding Time Window Super Point Cardinality Estimation Algorithm for High Speed Network Based on GPU

Abstract

Super point is a special host in network which communicates with lots of other hosts in a certain time period. The number of hosts contacting with a super point is called as its cardinality. Cardinality estimating plays important roles in network management and security. All of existing works focus on how to estimate super point's cardinality under discrete time window. But discrete time window causes great delay and the accuracy of estimating result is subject to the starting of the window. sliding time window, moving forwarding a small slice every time, offers a more accuracy and timely scale to monitor super point's cardinality. On the other hand, super point's cardinality estimating under sliding time window is more difficult because it requires an algorithm can record the cardinality incrementally and report them immediately at the end of the sliding duration. This paper firstly solves this problem by devising a sliding time window available algorithm SRLA. SRLA consists of two cardinality estimating algorithms, sliding rough estimator SRE and sliding linear estimator SLE. SRE is used to detect super point while scanning packets and it generates a candidate super point list at the end of a sliding time window. With this candidate super point list, SLE estimates the cardinality of every candidate super point fast and accurately. SRLA's ability of working under sliding time window comes from a novel cardinality recorder, distance recorder DR. DR records the time a host appearing and helps SRE and SLE to judge if a host contacting with a super point is in a certain time period. SRLA could run parallel to deal with high speed network in line speed. This paper also gives the way to deploy SRLA on a common GPU. Experiments on real world traffics which have 40 GB/s bandwidth show that SRLA estimates super point's cardinality within 100 milliseconds under sliding time window when running on a Nvidia GPU GTX650 with 1 GB memory. The estimating time of SRLA is much smaller than that of other algorithms which consumes more than 2000 milliseconds under discrete time window.

Rough Estimator Based Asynchronous Distributed Super Points Detection on High Speed Network Edge

“…As a lightweight estimator, RE can quickly determine candidate super point, but it cannot accurately estimate the cardinality. Jie et al [21] used RE as a preliminary screening tool to reduce the range of candidate super points, and combined with LE to realize real-time detection of super points under a sliding time window. A detailed analysis of RE can be found in [22].…”

A Super Point Detection Algorithm Under Sliding Time Windows Based on Rough and Linear Estimators

“…This paper makes full use of the parallel computing ability of GPU to handle high-speed network traffic in real time. Some of the work in this paper has been published at the 20th International Conferences on High Performance Computing and Communications in 2018 [14].…”