FPGA-Based Network Microburst Analysis System with Flow Specification and Efficient Packet Capturing

Yoshida, Shuhei; Ukon, Yuta; Ohteru, Shoko; Uzawa, Hiroyuki; Ikeda, Namiko; Nitta, Koyo

doi:10.1109/asap49362.2020.00014

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 shows a block diagram of our system. The FPGA accelerator contains a packet receiver, packetheader analyzer, NTC, statistics aggregator, and microburst detector [11,12]. The packet receiver supports 10-Gigabit Ethernet.…”

Section: System Architecturementioning

confidence: 99%

Real-time Virtual-network-traffic-monitoring System with FPGA Accelerator

Ukon¹,

Yoshida

Ohteru

et al. 2021

NTT Technical Review

View full text Add to dashboard Cite

Real-time network-traffic monitoring is important for managing network services in a datacenter. Datacenter traffic has been diversifying as a result of advances in network virtualization technology such as software-defined networking [1] and network function virtualization [2]. Therefore, network operators require a real-time network-traffic-monitoring system to detect problems in the virtual network.A virtual-network-traffic-monitoring system constructed within a server enables the monitoring of communication with external machines and between virtual machines (VMs) in the server. However, inserver monitoring degrades the performance of VMs because the virtual-network-traffic-monitoring system uses the server's computing resources. To avoid this problem, such a system should be constructed on the virtual network. In this case, it must monitor virtual-network traffic to multiple servers. Traffic-monitoring software is not suitable for monitoring a high volume of virtual-network traffic because it cannot handle high-load processing such as analyzing encapsulated packets and classifying network traffic using many header fields at high speed. We propose a realtime virtual-network-traffic-monitoring system with

show abstract

Section: System Architecturementioning

confidence: 99%