76

The terms are usually used in the context of data centers. Generally speaking, "east-west" traffic refers to traffic within a data center -- i.e. server to server traffic. "North-south" traffic is client to server traffic, between the data center and the rest of the network (anything outside the data center). I believe the terms have come into use from ...


22

The accurate answer is that they are not Ethernet cables. The cables themselves are not limited to transmitting Ethernet, nor is Ethernet restricted to using just UTP cables. In the first case, they are often used with many different types of signaling, including as examples voice and serial. In the second case, you can run Ethernet over coax, fiber, or ...


12

Background An Erlang measures load on a Circuit-Switched link. Quoting Russ Rowlett's page: The erlang is a dimensionless "unit" representing a traffic density of one call-second per second (or one call-hour per hour, etc.). The classical definition of an Erlang was developed in the early 1900s by Professor A.K. Erlang. Erlang's definition does not ...


12

BASE indicates baseband signaling - there is no modulated carrier, the frequency starts near zero and extends to a certain cut-off frequency. BROAD indicates broadband modulation - there is a wide frequency band with a number of carriers modulated with the data (similar to xDSL). The X in -TX, -SX, ... stands for 4b/5b (100 Mbit/s) or (improved) 8b/10b line ...


10

The first number represents the speed. If the next part is "BASE", then it is baseband. If it is "BROAD", then it is broadband. This is the original meaning of baseband/broadband, not the government idea (any speed at or above an arbitrary speed) of broadband. The last part is tricky. "2" means about (185) 200 meters. "5" means 500 meters. "36" means 3600 ...


9

I found the definitions from Microsoft Technet very useful: East-West – East-West refers to traffic flows that occur between devices within a datacenter. During convergence for example, routers exchange table information to ensure they have the same information about the internetwork in which they operate. Another example are switches, which can exchange ...


9

It has also been, in my years of understanding, general network traffic descriptors: North/South - Meaning traffic coming into and out of the network into Internet space, i.e in and out of edge firewalls and/routers. East/West - Traffic internal to the network that doesn't leave, i.e. LAN client to server and server to server communications.


9

Latency is the amount of time it takes a packet of data to leave your computer and receive a response back from the end point. That is why this is measure in time. This is key for time sensitive applications like VoIP and video conferencing. Bandwidth/data rate is the amount of data (bits) you can upload or download in a given time (seconds). This is key ...


8

(Nodal) Processing Delay The (nodal) processing delay is every device along the communication path that actually processes/examines the packets; these include routers, switches, and statistical multiplexers. The receiver doesn’t count towards this delay because the receiver is the receiver and has received the packet at that point, it doesn’t matter what ...


8

Source: Ethernet_Nomenclature_GA-TB-357.pdf 100BASE-FX Optical link that uses short wavelength (850 nm) lasers over two FDDI grade multimode optical Fibers, with eXternal sourced coding. Supports up to at least 2 km. So, F=fiber, X=external sourced coding


8

RFC 5952 gives you the canonical IPv6 format. That is explained in the RFC itself: This document defines a canonical textual representation format. and 4. A Recommendation for IPv6 Text Representation A recommendation for a canonical text representation format of IPv6 addresses is presented in this section. There are people who incorrectly call a fully ...


8

Short answer: no, an ONT is no modem. Modem is short for MOdulator/DEModulator and the term is only used for three device classes: telephone modems, DSL modems, and cable modems (thx Cody). These modulate digital data on to voice-grade phone lines or (possibly former) television cable. DSL and cable "modems" often include a router, but technically ...


7

First, an IP address is specified in bits, not bytes. Since humans tend to have a difficult time with binary, it is often converted into dotted decimal or bytes. This is an important distinction. For example, two hosts share the same network of 10.10.10.0/23, they could have IP addresses of 10.10.10.3 and 10.10.11.3. They share the same 23 bits, but they ...


7

A very good question coming at it from a networking viewpoint. Your question is based on the networking models that were developed long after packet switching was proposed as a concept. However networks across any distance were interconnected over the existing telecommunications "networks" and while many network and telecommunications terms are the same, ...


7

This terminology comes from network programming: A computer typically has one IP address for each network card. A computer may have multiple IP addresses for a network card (this is even the normal case when using IPv6). And a computer has the "localhost" address (127.0.0.1 when using IPv4). This means that a computer has multiple IP addresses. By "...


6

Some distinctions and history: Ethernet and other networking systems can use a variety of physical media, including fiber optic and metallic wires. Since the wires are almost always made of copper, people usually speak of fiber vs. copper. The original 3 MBps Ethernet developed by Xerox in the 1970s used 50-Ohm RG-8/U coax cable. Later a version using the ...


6

Click here to view Ron's comment. Here is what he said: Signaling is the method by which you define what a one or zero is. Encoding is how you use the 1s and 0s to represent information. Just posting it as an answer since Ron didn't.


6

From the diffs of draft-ietf-ippm-tcp-throughput-tm: This diff seems to show all the RWIN abberviations being replaced with RWND, below is an example. It is important to clarify the interaction between the sender's Send - Socket Buffer and the receiver's advertised TCP RWIN Size. TCP test - programs such as iperf, ttcp, etc. allow the sender to ...


6

The first IP address in a prefix is usually called the network address. In most setups, the first assignable address is the gateway, though any IP address within a prefix could be configured as gateway. So assuming 8.8.8.8 is in a /24 network, 8.8.8.0 would be the network address and 8.8.8.1 the gateway. Also, is there something I need to know about 8.8.8....


5

Signaling defines method (voltage, current, RF, light) will be used to represent a 1 or 0. For example; if I say a 1 is 5 volts and a 0 is 0 volts, this is signaling. Encoding is how the 1s and 0s will be used. For example; if I say a 1 means "On" and a 0 means "Off", this is encoding.


5

The term LAN is rather amorphous. It can mean a single broadcast domain, a network on a single cable plant, a network in a building or small group of close buildings, etc. As far as the broadcast domain definition, a data center could have multiple LANs, separated by routers. It really depends on the definition of LAN which you are using. A data center ...


5

A Frame is a combination of the L2 header and the Data being carried A Packet is a combination of the L3 header and the Data being carried. In either case, the Data being carried is the payload of the Frame/Packet. This animation will help illustrate the differences: source At any point in the animation, the DATA is the Payload for the respective layer (...


5

I believe that CS stands for Computer Science, and EE stands for Electrical Engineering. What it means is that electrical engineering looks at the physical circuit properties, while computer science looks at the practical application of moving bits. The number of bits can be more, less, or the same as the frequency in Hz, depending on several things, e.g. ...


5

I simply call this link speed or L1 throughput; with Ethernet, this is the nominal speed. You can directly calculate the maximum, effective L4 throughput for TCP over IPv4 over standard Ethernet (without any options) with (1460/1538) * link speed. For completeness, the nominal speed doesn't include all Ethernet overhead. The physical layer encodes bits ...


5

The guys who defined it called it Transmission Control Protocol only. The others seem to have it mixed up.


4

Think of Morse Code. The signal is the sound, pulse, or light. The message is encoded using the "dits" and "dahs", for example.


4

"Hostname" is used specifically in the context of the TCP/IP suite. Other protocols or operating systems (MS Windows) often use the term "server name." So for example, a device could be referred to by its Server Name in Windows, but by its Hostname using DNS. The names can be different. Often the two terms are used interchangeably.


4

It's not really all that difficult. When you bisect a network, such as a data center, the bisection bandwidth is the bandwidth usable to get from one side of the bisection to the other, possibly asymmetric values, depending on the topology. There may be links between the two sides which are unavailable for use due to things like STP blocking, and they don't ...


4

In the context of RFC 6177, "IPv6 Address Assignment to End Sites", an end site would be a single location with its own dedicated IP service provision. That definition might encompass multiple buildings if they're all on one site and sharing the same upstream IP service, and interconnected via an inter-building LAN. For a multi-location SME who ...


4

In most respects, yes. A bridge may be just a switch, but it may also be more: there are (were) bridges that could connect different MAC-oriented layer 2 protocols like Ethernet, Wi-Fi, Token Ring, ARCNET, ... These you wouldn't call switches since switches only support a single layer 2 protocol (but may support several layer 1 media like 1000BASE-T, ...


Only top voted, non community-wiki answers of a minimum length are eligible