Personal Miscellaneous TCP/IP GRID Quality of Service Multi-Cast


lan wan



Bandwidth and recording




A tool to measure link utilisation between endnodes.

IperfER is a suite of perl scripts with the aim to automate the collation of iperf data and anaylsis of such data. It is based heavily on the PingER suite.
It is currently implemented on the UCL HEP Network Monitoring machine located at here.


Pipechar is a program that probes the network to find out a bottleneck link across a network. It can also supply information regarding RTT and jitter times. It does, however, require superuser privileges in order to run, you can change this by following hte instructions here. As the tool throttles the network to each hop in the connection, it can be a very intrusive application to use on a network.

Pipechar is a 'Sender only' network probing program that can be used to diagnose potential problems in a network link by displaying. Information about the bandwidth at each hop of an internet connection is displayed along with information regarding the ping times. However, in order to do this pipechar has to send a large burst of data through the link which may cause further problems on the network if already problematic.
Pipechar only accurately reports up to the slowest hop in the link. Hence measurements past this slowest hop should not be assumed accurate. The benefit of this is that pipechar runs a lot faster than similar tools like pchar\footnote{pchar also is also not very reliable above OC-3 connections} that do attempt to record everything - completing in minutes rather than tens of minutes.


Similar to pipechar but actually works for high capacity links


PingER can be used to measure the RTT, packet loss percentages and the variability in response time between a pair of end-nodes. Being well established in the HEP community, it currently has hundreds of sites in many countries. As such, it is favoured above other tools such as Surveyor [SURVEYOR], RIPE NCC [RIPE_NCC] and MRTG [MRTG].


Netperf provides a general measure of performance of a network. It can give a measure of latency between request and response of generic transactions across a TCP/IP network by conducting unidirectional throughput.

Packet Tracing

For a more information, see here.

Tool Description


http://www-didc.lbl.gov/NetLogger/NetLogger.Tutorial.pdf - NetLogger Tutorial
http://www-didc.lbl.gov/papers/chep.2K.Netlogger.pdf - NetLogger Application and Usage


Traceroute is a program that analyses the path of an end-to-end connection. It can supply information regarding the ping times to the intermediate routers and the names (IP/DNS) of the routers. As such it can give information about the route that an end-to-end connection establishes.
- a frontend for the traceroute program which gives a graphical rep of hops.
VisualRoute - a java applet which shows the hops of an internet connection.


TCPDump is a tool for network monitoring and data acquisition. It requires the libcap library. You can visualise tcpdump info using tcptrace. More information here.
tbit Is a tool to identify the use of TCP on various servers over the internet. One site information here.


Tool Description


Network Weather Service (NWS) is a distributed system that periodically monitors and dynamically forecasts the performance of various network and computational resources over given time interval. It can also measure metrics such as TCP bandwidth. It utilises a central reserve from which data is collated and used for network forecasting.




Thu, 3 October, 2002 17:31 Previous PageNext Page
    email me!
2001-2003, Yee-Ting Li, email: ytl@hep.ucl.ac.uk, Tel: +44 (0) 20 7679 1376, Fax: +44 (0) 20 7679 7145
Room D14, High Energy Particle Physics, Dept. of Physics & Astronomy, UCL, Gower St, London, WC1E 6BT