Khondaker M. Salehin

Combined methodology for measurement of available bandwidth and link capacity in wired packet networks

Accurate measurement of network parameters such as available bandwidth (ABW), link capacity, delay, packet loss and jitter are used to support and monitor several network functions, for example traffic engineering, quality-of-service (QoS) routing, end-to-end transport performance optimisation and link capacity planning. However, proactive network measurement schemes can impact both the data traffic and the measurement process itself, affecting the accuracy of the estimation if a significant amount of probe traffic is injected into the network. In this work, the authors propose two measurement schemes, one for measuring ABW and the other for measuring link capacity, both of them use a combination of data probe packets and Internet control messaging protocol (ICMP) packets. Our schemes perform ABW and link-capacity measurements in a short time and with a small amount of probe traffic. The authors show a performance study of our measurement schemes and compare their accuracy to those of other existing measurement schemes and also show that the proposed schemes achieve shorter convergence time than other existing schemes and high accuracy.

Active Scheme to Measure Throughput of Wireless Access Link in Hybrid Wired-Wireless Network

In this letter, we propose an active scheme to measure the download throughput of an IEEE 802.11 wireless access link in a hybrid wired-wireless network. The proposed scheme is based on sending pairs of probing packets to a wireless end host to determine the smallest and average intra-packet gaps of the probing packets that are used for the estimation of the constant dispersion gap that wireless access creates. We present experimental evaluations of the proposed scheme, and the obtained results show that the proposed scheme achieves high measurement accuracy. Furthermore, we show that the proposed scheme is able to work under the presence of cross traffic along the path.

Scheme to Measure Packet Processing Time of a Remote Host through Estimation of End-Link Capacity

As transmission speeds increase faster than processing speeds, the packet processing time (PPT) of a host is becoming more significant in the measurement of different network parameters in which packet processing by the host is involved. The PPT of a host is the time elapsed between the arrival of a packet at the data-link layer and the time the packet is processed at the application layer (RFCs 2679 and 2681). To measure the PPT of a host, stamping the times when these two events occur is needed. However, time stamping at the data-link layer may require placing a specialized packet-capture card and the host under test in the same local network. This makes it complex to measure the PPT of remote end hosts. In this paper, we propose a scheme to measure the PPT of an end host connected over a single- or multiple-hop path and without requiring time stamping at the data-link layer. The proposed scheme is based on measuring the capacity of the link connected to the host under test. The scheme was tested on an experimental testbed and in the Internet, over a U.S. inter-state path and an international path between Taiwan and the U.S. We show that the proposed scheme consistently measures PPT of a host.

Packet-pair sizing for controlling packet dispersion on wired heterogeneous networks

The packet-pair structure is a widely used probing technique for measuring link capacity over network paths. In packet-pair probing, the probe-gap value at the link of interest (e.g., the link with the smallest capacity or any link along a path) is determined for link-capacity measurement, which can be affected if dispersion (i.e., separation) of the packet pair is created by the heterogeneous link capacities and cross traffic over an end-to-end path. In this paper, we present an analytical model concerning the effect of heterogeneous link capacities and cross traffic on the packet-pair structure over a multiple-hop path, and define the constraints on the packet sizing for accurate end-link (i.e., the link connected to the destination node of an end-to-end path) capacity measurement. We test the model through numerical evaluations and experimentally, on end-to-end paths with heterogeneous links and different cross traffic loads. The experiments are performed on a testbed and in the Internet.

A Method to Measure Packet Processing Time of Hosts Using High-Speed Transmission Lines

In this paper, we propose a scheme to measure the packet processing time of a host using Internet Control Message Protocol packets and a packet-capture line card in the same network segment. The proposed scheme is not affected by clock synchronization, the packet generation time, and the transmission speeds of the host under measurement. We show the experimental results of the proposed scheme tested on different hosts and under different transmission speeds, including 1000 Mb/s.

Measurement of packet processing time of an Internet host using asynchronous packet capture at the data-link layer

As transmission speeds increase faster than processing speeds, the packet processing time (PPT) of a host (i.e., workstation) is becoming more significant in the measurement of different network parameters, in which packet processing by the host is involved. The PPT of a host is the time elapsed between the arrival of a packet at the data-link layer and the time the packet is processed at the application layer of the TCP/IP protocol stack (RFCs 2679 and 2681). In this paper, we propose a methodology to measure the PPT of a host using Internet Control Message Protocol (ICMP) packet and a specialized packet-capture card that does not require synchronization between the host under test and the packet-capture card. We tested the proposed methodology on two hosts with different specifications. The experimental results show that the proposed methodology consistently measures PPT.

Ternary-Search-Based Scheme to Measure Link Available-Bandwidth in Wired Networks

Accurate measurement of available bandwidth (ABW) is an important parameter to analyze network performance. Active measurement is an attractive approach as it has the advantage of controllability and flexibility for performing network measurement. However, it can affect both the data traffic and the measurement process itself if a significant amount of probe traffic is injected into the network. Furthermore, measurement must be completed in short time to effectively monitor the network state. In this paper, we propose a fast ABW measurement scheme that generates a small amount of probe traffic to achieve an acceptable measurement accuracy. The proposed scheme achieves an accuracy comparable to that of popular existing schemes. We present a performance study of the proposed scheme through ns2 simulation under different traffic conditions.

Evaluation of switching performance of a virtual software router

Software routers are an alternative low-cost and moderate-performance router solutions implemented with general-purpose workstations able to host two or more network interface cards (NICs). Workstations can be programmed to forward packets between different NICs and to participate in routing functions. The value of software routers lies on their low cost and on the flexibility to modifying routing and switching functions. Machine virtualization can be used to model novel protocols or hardware systems, however, implemented in software and without modifications to the hosts kernel. This virtualization allows the implementation of not only one but also multiple (and independent) virtual systems. Virtualization of software routers, called virtual software routers, is then a possible application of this technology. However, because of the software platforms, virtualized machines are expected to suffer from performance degradation. In this paper, we investigate the switching performance of a virtual software router and compare it to that of a software router. We present the performance of virtual software routers hosted by different workstations, with single and multiple processing cores.

Experimental performance evaluation of a virtual software router

Software routers (SRs) are an alternative low-cost and moderate-performance router solutions implemented with general-purpose workstations able to host multiple network interface cards (NICs). Workstations can be programmed to forward packets between different NICs and to participate in routing functions. Virtualization can be used to model new protocols or hardware systems in software and without modifying the hosts kernel. However virtualized routers are expected to suffer from performance degradation because of software execution overhead. In this paper, we investigate the performance impact of a virtual software router (VSR) in comparison to that of a SR. We present the performance of VSRs hosted by different workstations — with different number of processing cores.

Schemes to measure available bandwidth and link capacity with ternary search and compound probe for packet networks

Accurate measurement of network parameters such as available bandwidth (ABW) and link capacity are needed for analyzing network performance. Active measurement is an attractive approach as it has the advantage of controllability and flexibility for performing network measurement. However, it can affect both the data traffic and the measurement process itself, affecting the accuracy of the measurement if significant amount of probe traffic is injected into the network. Furthermore, measurement must be completed in short time to effectively monitor the network state. In this paper, we present two new measurement schemes: one for measuring ABW, and the other for measuring per-hop link capacities of an end-to-end path. The ABW measurement scheme performs measurement in short period of time and with small amount of probe traffic, and it achieves accuracy comparable to that of IGI and Pathload. The link-capacity measurement scheme provides immunity to cross traffic. We present ns-2 simulation results of the ABW and link-capacity measurement schemes to show their performance.