Free packet loss software for linux

NetMate comes from Network Measurement and Accounting System and is a flexible and extensible network measurement tool (meter).
It can be used for accounting, delay/loss measurement, packet capturing and much more. The main advantage over other existing tools is that it can be easily extended due to its modular (class-based) structure and dynamic loadable packet processing and information export modules.
A GUI for controlling multiple meters and displaying measurement results is currently under development.
NMRSH is the NetMate Remote Shell which allows to remote control NetMate meters.
Main features:
- Flexibility and Extensibility
- Runtime loadable metric and export modules
- Modular architecture (C++ classes)
- Extensible Ruleset Format (XML-based)
- Portable Implementation
- GNU autotools
- OS tested: Linux (SuSE, Debian, Redhat), FreeBSD, Solaris
- Open Source (GPL)
- Configurable Multithreading
- IPv4 and IPv6 Support
- Multiple Classification Algorithms
- Automatic flow generation based on arbitrary packet attribute combinations
- Packet Sampling Support
- Secure Control Interface
- SSL Encryption
- Host-based Authentication (DNS, IP address)
- User-based Authentication (HTTP)
- Packet capturing using libpcap
- Support simultaneous measurement on multiple interfaces
- Currently only Ethernet, IPv4/IPv6, ICMP, TCP, UDP, data layer support
- Extensible to everything libpcap can capture
- Metric Modules
- Counter, bandwidth, jitter, port usage, packet length, RTP packet loss, packet ID generation (crc32 and md5), capture (tcpdump file), RTT (ICMP echo), text output (similar to tcpdump output), DNS latency, HTTP performance, TCP connection setup latency
- Export Modules
- Text file, binary file, SQL (under development), IPFIX (under development)
- Remote Control via Shell Tool or Standard Web Browser
- Interactive or batch processing of meter commands
Enhancements:
- Minor changes and bugfixes were made.

mrtg-ping-probe project monitors round trip time and packet loss to another host. Still on my TODO list: add own min/max/avg rtt calculation, add perl ping module, add rping and rsh support...
mrtg-ping-probe is a ping probe for MRTG 2.x. It is used to monitor the round trip time and packet loss to networked devices. MRTG uses its output to generate graphs visualizing minimum and maximum round trip times or packet loss.
mrtg-ping-probe depends on the following software being installed on your system: perl (at least version 5.6.1), mrtg (I use version 2.8.8, though any mrtg 2.x version should work), and a ping program that displays a summary of the round trip times upon termination or timeout.
mrtg-ping-probe runs on AIX, BSD/OS 2.1, FreeBSD/2.2.x, IRIX/6.2, Linux, Mac OS X (Darwin 5.4), NetBSD, OpenBSD, OS/2, OSF1 V3.2, Solaris 1.1.2 (SunOS 4.1.4), Solaris 2.5.1 (SunOS 5.5.1), Solaris 7 (SunOS 5.7), Solaris 8 (SunOS 5.8), Solaris 9 (SunOS 5.9), HP-UX 9, Windows 98, and Windows 2000 (english, french, portugesee, and spanish locales).
If you install the Windows ping program that comes with Windows 98, Windows 2000, or WinSock 2.x, mrtg-ping-probe will also run on Windows 95 and Windows 4.0.
Support for additional systems is usually easy to add, as described in the file INSTALL.
Act responsible: do not use mrtg-ping-probe to ping devices without the owners permission. Just imagine 10,000 people would decide to ping your hosts ... mrtg-ping-probe is meant to be used within your network to get round trip time performance figures for your network.
Usage: mrtg-ping-probe [-hsvV] [-d deadtime] [-k count] [-l length] [-o ping_options] [-p [factor*]{min|max|avg|loss|integer}/[factor*]{min|max|avg|loss|integer}] [-r [rsh:][user@]host[:osname]] [-t timeout] host
Enhancements:
- new platforms supported: italian Windows 2000 locale.
- bugfixes: on Windows actually return deadtime when we lost all packets, not 0. the ping child process should actually be killed now on Unix platforms.
- changes: ***** Possible Incompatability ***** raised minimum required perl version to 5.6.1. lots of typos fixed.

Packet Debugger presents a debugger-like UI for pcap packet capture files.

The Packet Debugger (pdb) allows users to work with packet streams as if they were working with a source code debugger.

Users can list, inspect, modify, and retransmit any packet from captured files, as well as work with live packet captures.

WANem is a WAN Emulator, meant to provide real experience of Internet, during development and test on a LAN environment. Typically application developers develop applications on a LAN while the intended purpose for the same could be the client is accessing the application by WAN or even the internet.

WANem allows for the application development team to setup a transparent application gateway which can be made use to simulate WAN characteristics like Network delay, Packet loss, Packet corruption, Disconnections, Packet re-ordering, Jitter, etc.

WANem allows for WAN network characteristic emulation and thus allowing for applications to be tested in a realistic WAN environment before they are moved into production.

WANem is a combined development strategy where it hooks into the Linux kernel for performing network emulations and provides GUI to make it simple to use. Remastering of Knoppix Live CD makes it even more effective as it becomes platform independant.

DNS Blacklist Packet Filter project is a Linux netfilter client that decides whether to accept or drop packets based on the results of a DNS blacklist query (such as MAPS, SORBS, or SPEWS, to name a few).

One use is to filter all incoming SMTP SYN packets for spam filtering.

The Torque Network Library project is a robust, secure, and easy-to-use cross-platform C++ networking API designed for high performance simulations and games.
It features a UDP- based connection architecture with DoS prevention functionality, different types of data guarantee, bit stream compression, server object replication and updating, and a simple, highly space efficient RPC mechanism.
It includes a deterministic application journaling replay function for eliminating hard to find networking bugs.
Main features:
- Portable
- Powerful RPC Support
- Lightweight and efficient - not intended to be a replacement for CORBA.
- Extremely easy to use - two simple macro definitions and youre done.
- No complex wrapper classes to work with - write and call your functions as you normally would, and TNL will take care of the rest.
- Robust UDP-based notification protocol
- Supports fixed or adaptive rate data transfer.
- Arbitrary sized packet window.
- Robust connection handshaking.
- Handles packet loss/out of order delivery.
- Networked Objects
- Instantiation of objects by name or ID.
- IDs are assigned to NetGroups, so that only objects relevant to a connection can be references.
- Event Support
- Unguaranteed, guaranteed unordered, or guaranteed ordered event delivery.
- Notification to the event when it has been received or dropped by a client.
- Ghost Support
- Most-recent state information is transmitted to clienst.
- Scoping of objects to only those clients for which they are relevant - this helps prevent cheating or data sniffing and makes dramatically more effective use of available bandwidth.
- Prioritization of state updates by arbitrary criteria, such as relative velocity, team, ownership, etc.
- Extensible Protocol Architecture
- Easy to extend the protocol, for instance, to transmit player move information with every packet, or add voice support.
- See Torque for examples of additional capabilities that could be added to the protocol.

Yavipind is a secure tunnel aka 2 peers securely forwarding packets toward each other. It forwards any kind of packet (IPv4, IPv6 or other) sent over the virtual point-to-point device (e.g. tun0). It fully runs in linux userspace.

yavipin has been written because i wasnt satisfied by the existing alternatives. i published some security holes i know in alternatives to bring awareness to users and help them to do a knowledgeable choise:

Security analysis of VTun: This text is a security analysis of VTun. It includes a description of the security based on the source and lists the possible attacks. An attacker can modify packets, replay them, learn pattern of the plain text or easily guess low-entropy password.
Security flaws in tinc: This text describes security flaws in Tinc. It includes a description of the security and lists the possible attacks. An attacker can modify packets, replay them and learn pattern of the plain text.

When designing the protocol and writting the software, the author used the following criteria: the security MUST as strong as reasonably possible, yavipin SHOULD be network efficient, easy to use and install.

Network efficiency:

small packet overhead: 26bytes (e.g. ESP with DES+MD5 is 32byte)
Packet compression: Forwarded packets may be compressed using deflate (gzip). (WORK: add stat about efficiency)
NAT compatible: yavipins tunnel may be establish over NAT as all packets of a tunnel are sent over a single UDP/IPv4 connection. Moreover the peer unreachability detection periodically send packets which prevent the NAT engine from timing out the connection state.
Peer unreachabilty detection: If the other peer becomes unreachable, it will be detected. It is done ala IPv6 neighbours discovery (rfc2461.7).
Gracefull shutdown: If a peer purposely stops, it will notify the other which is immediatly aware of it.

Usages simplicity:

it works in userspace and you dont need to recompile the kernel
reuse existing tools: As yavipin use a virtual device, it is possible to apply to the tunnel any tool designed for network device. For example, it is possible to set up a firewall using ipchains/netfilter or to do traffic shapping using the kernels traffic control (see tc).

Securitys strength:

packet security: each packet exchanged during the connection is encrypted using blowfish CFB and authenticated with HMAC-MD5 96bits.
protection against packet replay: It uses strict anti-replay and no packet can be accepted twice. A eavedropper cant take a packet, keep it for a while and make it accept a second time by the destination.
Efficient session key renewal: It uses hash chains for efficiency. It allows smooth key transition not to cause any packet loss during the renewal. It provides forward secrecy inside the connection.
Protect DoS ala TCP syn : It uses cookie exchange (rfc2522.3) during the connection establishement.
Forward secrecy : Even if the attacker cracks the box, he wont be able to decrypt network traffic older than a given delay (default 10min). The diffie-hellman private key and the session key are periodically renewed and securely erased from memory.

SmokePing is a delux latency measurement tool. SmokePing project can measure, store and display latency, latency distribution and packet loss. SmokePing uses RRDtool to maintain a longterm datastore and to draw pretty graphs, giving up to the minute information on the state of each network connection.
SmokePing uses latency measurement plugins for seamless extendability.
SmokePing comes with a smart alarm system. Apart from simple threshold alarms, you have the option of defining latency or loss patterns and use them to trigger alarms.
This allows you to define a pattern which would generate a single alarm when the loss goes from below 1% to over 20% and stays over 20% for more than 10 minutes. The advantage of this approach is the virtual elimination of duplicate alarms which you would get with a simple threshold based system.
Alarms can be sent to a mail address or a pager and if you want you can also start an external script to handle the alarms.
Complex Alarms can be written as plug-ins.
SmokePing can also deal with machines who frequently change their IP address by allowing the remote host to call SmokePings attention to its new IP address. In such a setup SmokePing monitors also for how long the remote system could keep its IP address.
To ensure that it is not suddenly monitoring the wrong host, SmokePing further tries to fingerprint each of its Dynamic IP targets via SNMP.
SmokePing is written in Perl. It consists of a daemon process responsible for data collection and a CGI script presenting the data on the web.
The CGI script uses SpeedyCGI to achieve mod_perl like performance without the need to deploy mod_perl on your web server. SmokePing sports a plug-in architecture to easily add new latency measurement capabilities to SmokePing. SmokePing works happily on all Unix platforms.
Enhancements:
- The scoreboard has a list of hottest targets.
- Echoping V6 compatibility.
- Mail templates.
- A failover server for alert email messages.
- Many new plugins.
- Several bugfixes.