Autobuf / FTP Autotuning FTP client and server. Iperf Iperf is a TCP and UDP bandwidth testing tool, similar in function to the traditional ttcp tool but nicer.
Multicast Beacon Beacon is a multicast diagnostic tool, showing packet loss, delay, jitter, out-of-order packets, and duplicate packets for a given multicast group.
Netlog Netlog is a C library that can be linked into an existing network application to provide instrumentation of network performance.
Network Tools from CAIDA A family of modules intended for pipeline use
Squid Squid is a high-performance proxy caching server for web clients, supporting FTP, gopher, and HTTP data objects. Unlike traditional caching software, Squid handles all requests in a single, non-blocking, I/O-driven process.
Viznet Java application to visualize network bandwidth performance over time.
Non-Commercial Tools Globus The Globus project is developing basic software infrastructure for computations that integrate geographically distributed computational and information resources.
Bandwidth/Throughput Measurement AMP The NLANR active measurement project is undertaking site to site measurement across the HPC networks. This work is intended to compliment the measurements taken by MCI and Abilene within the networks' infrastructure. Currently round trip times, topology and loss are being measured. On demand throughput tests will be added in the future.
Bing Bing is a point-to-point bandwidth measurement tool (hence the 'b'), based on ping. Bing determines the real (raw, as opposed to available or average) throughput on a link by measuring ICMP echo requests roundtrip times for different packet sizes for each end of the link.
bprobe/cprobe bprobe estimates the maximum possible bandwidth along a given path. cprobe estimates the current congestion along a path. Currently these tools rely on two features of the IRIX operating system for SGI hardware.
Netperf Netperf is a benchmark that can be used to measure the performance of many different types of networking. It provides tests for both unidirecitonal throughput, and end-to-end latency. The environments currently measureable by netperf include:
TCP and UDP via BSD Sockets
DLPI
Unix Domain Sockets
Fore ATM API
HP HiPPI Link Level Access
nettimer nettimer is useful for measuring end-to-end network performance. It can simulate or passively collect network traffic, and can also actively probe the network using a packet-pair 'tailgating' technique. There is no requirement for any special information from the network and no limitation to a particular transport protocol. Currently implemented metrics include bottleneck bandwidth and link bandwidth. Collected data is output using 'ns' database format.
pathchar pathchar estimates performance characteristics of each node along a path from a source to destination. Pathchar leverages the ICMP protocol's Time Exceeded response to packets whose TTL has expired. Sending a series of UDP packets of various sizes to each hop, pathchar uses knowledge about earlier hops and the round trip time distribution to this hop to assess incremental bandwidth, latency, loss, and queue characteristics across this link.
pchar Similar to pathchar, pchar attempts to characterize the bandwidth, latency, and loss of links along an end-to-end path through the Internet. pchar works on both IPv4 and IPv6 networks. It has been tested on various versions of FreeBSD, NetBSD, OpenBSD, Linux, Solaris, OSF/1, and IRIX, with primary development on FreeBSD and Solaris. Written in C++, recent additions to pchar include an SNMP query feature and better IPv6 detection at configure-time.
Surveyor The Surveyor project has deployed a number of machines at participating sites around the world. Currently, end-to-end one-way delay and packet loss is measured along the paths among them. The project started with the deployment of three machines in June 1997.
TReno TReno is a TCP internet throughput measurement tool based on a user-level implementation of a TCP-like protocol. This allows it to measure throughput independently of the TCP implemention of end hosts and to serve as a useful platform for prototyping TCP changes. TReno is associated with the IPPM formal metrics effort (see http://www.psc.edu/~mathis/ippm/).
ttcp and nttcp Originally written to move files around, became the classic throughput benchmark or load generator, with the addition of support for sourcing to/from /dev/null. Has spawned many variants, recent ones include support for UDP, data pattern generation, page alignment, and even alignment offset control. nttcp allows mcast UDP transfers.
vBNS Operated by MCI, vBNS publishes extensive backbone status information on the web. Four categories of information are available: performance measurements, router and switch statistics, short term and long term reports, and statistical analysis of data flows.
GTrace Combines traceroute with NetGeo server queries to plot hops at latitude and longitude on a map. Users can add their own maps as part of or independent of the existing world map hierarchy. Heuristics are used to determine router location. Color on the display distinguishes between authoritative and guessed locations: Green = both endpoints are authoritative. Yellow = one endpoint is authoritative; other is a guess. Blue = both endpoints are guesses. Red = one endpoint is a location that is a country center, state center, or obtained from a whois record.
Optional ttl reporting, o Support LSRR option, to show the route between arbitrary destinations.
Improved timeout handling during icmp packet catching.
Option to probe all addresses of multi-homed destinations.
Option to disable fragmentation and perform MTU discovery.
Recognize various new icmp packet types.
Round-trip time reporting in fractional milliseconds.
Configurable default options via environment variables.
Optional setting of initial ttl to skip first hops.
Optional min/avg/max rtt statistics summary for each hop.
Include standard deviation in rtt statistics summary.
Cache nameserver lookups to minimize DNS queries.
pingplotter Ping Plotter is a fast, small, and visual Ping/Trace Route utility that uses multiple threads to trace all hops at once for SUBSTANTIAL performance improvements over standard trace routes. Delivers visual graphs of performance to pinpoint problems and see ranges of responses and trends. Will trace continuously with any interval and can alert via e-mail if desired. Can display data over a period of time for trending information. Support includes on-line FAQ and support forums.
traceroute Directs a packet to each router along a path without actually knowing the path, by setting the IP TTL field from 1 to n until the ultimate destination is reached. Upon receiving a packet with an expired (0) TTL, the hop generates an ICMP Time Exceeded response back to the source, thus identifying the hop and its round trip delay. Each UDP packet is sent to a probably-unused port, so when the destination receives the packet it responds with ICMP Port Unreachable.
WhatRoute A traceroute variant for the Macintosh. Traces Internet paths, pings remote hosts, uses either Open Transport or DNS Query to resolve names, can monitor activity on an Ethernet LAN, includes finger and whois clients, and a built-in Telnet server. Can plot routes on a world map.
Xtraceroute Graphical traceroute that shows a path as a series of lines
between 'sites' (shown as small balls of different colors) on a rotating globe.
IPTraf IPTraf is a console-based network statistics utility for Linux. It gathers a variety of figures such as TCP connection packet and byte counts, interface statistics and activity indicators, TCP/UDP traffic breakdowns, and LAN station packet and byte counts.
An IP traffic monitor that shows information on the IP traffic passing over your network. Includes TCP flag information, packet and byte counts, ICMP details, OSPF packet types.
General and detailed interface statistics showing IP, TCP, UDP, ICMP, non-IP and other IP packet counts, IP checksum errors, interface activity, packet size counts.
A TCP and UDP service monitor showing counts of incoming and outgoing packets for common TCP and UDP application ports.
A LAN statistics module that discovers active hosts and shows statistics showing the data activity on them
TCP, UDP, and other protocol display filters, allowing you to view only traffic you're interested in.
Logging
Supports Ethernet, FDDI, ISDN, SLIP, PPP, and loopback interface types.
Utilizes the built-in raw socket interface of the Linux kernel, allowing it to be used over a wide range of supported network cards.
Full-screen, menu-driven operation.
libpcap Portable Unix library for dumping packets. Serves as a machine-independent layer packet collection mechanism. Tcpdpriv Tcpdpriv removes sensitive information from a packet trace, replacing it with contrived information from which the sensitive information cannot be reconstructed. By removing the sensitive information, the output of tcpdpriv may be shared with others (for debugging or network analysis, say). tcpdpriv requires libpcap. It works on SunOS, Solaris, and FreeBSD. Link-level headers are passed through unchanged. tcpdump Stable, mature, canonical portable packet collector, built using libpcap. Network researchers frequently use tcpdump in lieu of bundled packet collectors; some vendors even ship it as bundled packet dumper. Requires reasonable understanding of networking to interpret collected packets. Output format can be easily and portably analyzed using awk, sed, and perl scripts.
Network Weather
Abilene An animated "weather map" for aggregate traffic between Abilene core nodes is available on the home page and shows a rough idea of how congested the backbone links are. Andover Internet Traffic Report ping is used to measure round-trip travel time along major paths on the Internet. We have several servers in different areas of the globe perform the same ping at the same time. Each test server then compares the current response to past responses from the same test to determine if the response was bad or good on a scale of 0 to 100. The scores from all test servers are averaged together into a single index. Network Weather Service The Network Weather Service is a distributed system that periodically monitors and dynamically forecasts the performance various network and computational resources can deliver over a given time interval. The service operates a distributed set of performance sensors (network monitors, CPU monitors, etc.) from which it gathers readings of the instantaneous conditions. It then uses numerical models to generate forecasts of what the conditions will be for a given time frame. We think of this functionality as being analogous to weather forecasting, and as such, the system inherits its name.
One-way Availability/Latency Tests
echoping Echoping is a utility for measuring TCP/UDP latency by sending to an arbitrary (default 'echo') port. It includes support for testing HTTP query latency. fping A ping variant suitable for use in scripts. fping will issue ICMP echo requests to a list of hosts in round-robin fashion. fping output is meant to be parsed by scripts. See the fping man page for more information. gnuplotping Pings multiple hosts in parallel, with graphical display (gnuplot) of delay distribution. Imeter Imeter is a series of scripts that supports collection, analysis, and web-displayed graphs of long-term ping data. It was originally written to measure ISP service. A paper describing its use can be found at ftp://ftp.intel.com/pub/papers/lachesis.ps. Nikhef ping A 'ping' variant with the following differences from classic 'ping':
Redesign for proper flood and Cisco style ping handling
Packet loss now properly reported in all modes
Support for LSRR in addition to RR option
Quick ping without normal output, quits when target is alive.
Option to probe all addresses of multi-homed destinations
Supports pinging to broadcast address
Portability hooks for easy installation on various platforms
Recognizes various new ICMP packet types and subcodes
Recognizes bounce messages in response to sent ping requests
RTT reporting in fractional milliseconds
RTT standard deviation displayed in statistics summary
Minimizes DNS queries by caching DNS lookups
Auto-adjusts timeout period to cope with slow links
ping Classic tool for reachability/latency assessment. Measures hop-to-hop latency and packet loss.
sting sting is a TCP-based network measurement tool that measures end-to-end network path characteristics. characteristics. sting is unique because it can estimate one-way properties, such as loss rate, through careful manipulation and observation of TCP behavior. In addition, using TCP allows sting to leverage the existing Internet infrastructure - any TCP server can be used as a de facto measurement service - and it avoids increasing problems with ICMP-based network measurement (blocking, spoofing, rate limiting, etc.). The README file includes instructions for compilation and usage. Traceping Traceping uses ping and traceroute to track packet loss rates to a variety of destinations. It is currently used to track performance between various mostly-international, mostly physics-related sites. Runs on VMS.
Network Performance and Measurement Tools
Linear Mode
