Ethernet Network Domination

Venerable Ethernet provides the backbone of the internet. Ethernet has risen to complete dominance for local area networks over its forty years of existence. The first Ethernet experimentals versions started in 1972 (patented 1978). The commercialization of Ethernet started in 1980′s.

At first Ethernet technology remained primarily focused on connecting up systems within a single facility, rather than being called upon for the links between facilities, or the wider Internet. Ethernet at short distances has primarily used copper wiring. Fiber optic connections have also been available for the transmission of Ethernet over considerable distances for nearly two decades.

Today, Ethernet is everywhere. It’s evolved from a 2.93-Mb/s and then 10-Mb/s coax-based technology to one that offers multiple standards using unshielded twisted pair (UTP) and fiber-optic cable with speeds over 100 Gb/s. Ethernet, standardized by the IEEE as “802.3,” now dominates the networking world. And the quest for more variations continues onward.

Ethernet has always had the ability to communicate over reasonably large lengths of wiring, with even the very first prototype using 1km of copper cabling. Although Gigabit Ethernet over copper twisted pair cabling is only specified for 100m between links, fiber optic versions have allowed Ethernet to run over single connections up to 70km each.

Ethernet is on the Way to Total Networking Domination. Ethernet is all over the place. Most of us use it day by day. The first coax-primarily based Ethernet LAN conceived in 1973 by Bob Metcalfe and David Boggs. Since then Ethernet has grown to the stage of pretty much entire local area networking goes through it (even most WiFi hot spots are wired with Ethernet). It’s hard to overestimate the importance of Ethernet to networking over the past 25 years, during which we have seen seen Ethernet come to dominate the Networking industry. Ethernet’s future could be even more golden than its past.

Ethernet has pretty much covered office networking and backbones industrial networks. In industrial applications there applications where Ethernet is still coming. Ethernet is on the Way to Total Networking Domination article says that single-pair Ethernet makes possible cloud-to-sensor connections that enable full TCP/IP, and it’s revolutionizing factory automation. This technology will expand the use of Ethernet on the industrial applications. Several different single-pair Ethernet (SPE) standards seeks to wrap up full networking coverage by addressing the Internet of Things (IoT), and specifically the industrial Internet of Things (IIoT) and Industry 4.0 application space.

Traditional copper Ethernet

Started with 50 ohms coax in 1973. In the 1990′s the twisted pair Ethernet with RJ-45 connectors and fiber became the dominant media choices. Modern Ethernet versions use a variety of cable types.

Twisted pair Ethernet mainstream use stared with CAT 5 cable that has been long time used for 100 Mbps or slower plans, while CAT 5a cables and newer are ideal for faster speeds. Both CAT5e and CAT6 can handle speeds of up to 1000 Mbps, or a Gigabit per second.

Today, the most common copper cables are Cat5e, Cat6, and Cat6a. Now twisted pair the main media (CAT 6A, CAT7, CAT8 etc.) can handle speeds from 10M to 10G with mainstream devices, typically up to 100 meters. All those physical layers require a balanced twisted pair with an impedance of 100 Ω. Standard CAT cable has four wire pairs, and different Ethernet standards use two of them (10BASE-T, 100BASE-TX) or all four pairs (1000BASE-T and faster).

Many different modes of operations (10BASE-T half-duplex, 10BASE-T full-duplex, 100BASE-TX half-duplex, etc.) exist for Ethernet over twisted pair, and most network adapters are capable of different modes of operation. Autonegotiation is required in order to make a working 1000BASE-T connection. Ethernet over twisted-pair standards up through Gigabit Ethernet define both full-duplex and half-duplex communication. However, half-duplex operation for gigabit speed is not supported by any existing hardware.

In the past, enterprise networks used 1000BASE-T Ethernet at the access layer for 1 Gb/s connectivity over typically Cat5e or Cat6 cables. But the advent of Wi-Fi 6 (IEEE 802.11ax) wireless access points has triggered a dire need for faster uplink rates between those access points and wiring closet switches preferably using existing Cat5e or Cat6 cables. As a result, the IEEE specified a new transceiver technology under the auspices of the 802.3bz standard, which addresses these needs. The industry adopted the nickname “mGig,” or multi-Gigabit, to designate those physical-layer (PHY) devices that conform to 802.3bz (capable of 2.5 Gb/s and 5 Gb/s) and 802.3an (10 Gb/s). mGig transceivers fill a growing requirement for higher-speed networking using incumbent unshielded twisted-pair copper cabling. The proliferation of mGig transceivers, which provide Ethernet connectivity with data rates beyond 1 Gb/s over unshielded copper wires, has brought with it a new danger: interference from radio-frequency emitters that can distort and degrade data-transmission fidelity.

10GBASE-T is the standard technology that enables 10 Gigabit Ethernet operations over balanced twisted-pair copper cabling system, including Category 6A unshielded and shielded cabling.

CAT8 can go even higher speeds up to 40G up to 30 meters. Category 8, or just Cat8, is the latest IEEE standard in copper Ethernet cable. Cat8 is the fastest Ethernet cable yet. Cat8 support of bandwidth up to 2 GHz (four times more than standard Cat6a bandwidth) and data transfer speed of up to 40 Gbps. Cat 8 cable is built using a shielded or shielded twisted pair (STP) construction where each of the wire pairs is separately shielded. Shielded foil twisted pair (S/FTP) construction includes shielding around each pair of wires within the cable to reduce near-end crosstalk (NEXT) and braiding around the group of pairs to minimize EMI/RFI line noise in crowded network installations. Cat 8 Ethernet cable is ideal for switch to switch communications in data centers and server rooms, where 25GBase‑T and 40GBase‑T networks are common. Its RJ45 ends will connect standard network equipment like switches and routers. Cat8 cable supports Power over Ethernet (PoE) technology. Cat8 is designed for a maximum range of 98 ft (30 m). If you want fater speeds and/or long distance there are various fiber interfaces.

Power over Ethernet

Power over Ethernet (PoE) offers convenience, flexibility, and enhanced management capabilities by enabling power to be delivered over the same CAT5 or higher capacity cabling as data. PoE technology is especially useful for powering IP telephones, wireless LAN access points, cameras with pan tilt and zoom (PTZ), remote Ethernet switches, embedded computers, thin clients and LCDs.

The original IEEE 802.3af-2003 PoE standard provides up to 15.4 W of DC power (minimum 44 V DC and 350 mA) supplied to each device. The IEEE standard for PoE requires Category 5 cable or higher (can operate with category 3 cable for low power levels). The updated IEEE 802.3at-2009 PoE standard also known as PoE+ or PoE plus, provides up to 25.5 W (30W) of power.

IEEE 802.3bt is the 100W Power over Ethernet (PoE) standard. IEEE 802.3bt calls for two power variants: Type 3 (60W) and Type 4 (100W). This means that you can now carry close to 100W of electricity over a single cable to power devices. IEEE 802.3bt takes advantage of all four pairs in a 4-pair cable, spreading current flow out among them. Power is transmitted along with data, and is compatible with data rates of up to 10GBASE-T.

Advocates of PoE expect PoE to become a global long term DC power cabling standard and replace a multiplicity of individual AC adapters, which cannot be easily centrally managed. Critics of this approach argue that PoE is inherently less efficient than AC power due to the lower voltage, and this is made worse by the thin conductors of Ethernet.

Cat5e cables usually run between 24 and 26 AWG, while Cat6, and Cat6A usually run between 22 and 26 AWG. When shopping for Cat5e, Cat6, or Cat6a network cables, you might notice an AWG description printed on the cable jacket such as: 28AWG, 26 AWG, or 24AWG. AWG stands for American wire gauge, a system for defining the diameter of the conductors of a wire which makes up a cable. The larger the wire gauge number, the thinner the wire and the smaller the diameter.

One of the newest types of Ethernet cables on the market, Slim Run Patch Cables, actually have a 28 AWG wire. This allows these patch cords to be at least 25% smaller in diameter, than standard Cat5e, Cat6, and Cat6a Ethernet. Smaller cable diameter is beneficial for high-density networks and data centers.

The downside of 28 AWG cable is higher resistance and power loss in PoE applications. Before February 2019, the short answer to “Can 28 AWG patch cords be used in PoE applications?” was “no.” Today, however, the answer is “yes”! 28 AWG patch cords can now be used to support power delivery.

It has been approved that 28 AWG cables can support power delivery and higher PoE levels with enough airflow around the cable. According to TSB-184-A-1, an addendum to TSB-184-A: 28 AWG patch cabling can support today’s higher PoE levels, up to 60W.

To maintain recommendations for temperature rise, 28 AWG cables must be grouped into small bundles. By keeping 28 AWG PoE patch cords in bundles of 12 or less, the impacts of cable temperature rise are diminished thus allowing you to stay within the suggested maximum temperature rise of 15 degrees Celsius. Per TSB-184-A-1, an addendum to TSB-184-A: 28 AWG in bundles of up to 12 can be used for PoE applications up to 30W.In PoE applications using between 30W and 60W of power, spacing of 1.5 inches between bundles of 12 cables is recommended. Anything above 60W with 28 AWG cable requires authorization from the authority in USA.

There is no installation location or bundle size limitations for 28 AWG cord cables when power is not being distributed over the data network. The limitations only apply when PoE comes into play. Another thing you should bear in mind is that 28 AWG wires should never be used as horizontal, or “backbone” cabling as their maximum distance according to the standards is 10 meters.

Single pair Ethernet

Several different single-pair Ethernet (SPE) standards seeks to wrap up full networking coverage by addressing the Internet of Things (IoT), and specifically the industrial Internet of Things (IIoT) and Industry 4.0 application space.

Single Pair Ethernet, or SPE, is the use of two copper wires that can transmit data at speeds of up to 1 Gb/s over short distances. In addition to data transfer, SPE has option to simultaneously delivering Power over Dataline (PoDl). This could be a major step forward in factory automation, building automation, the rise of smart cars, and railways. Single-pair Ethernet (SPE) allows legacy industrial networks to migrate to Ethernet network technology whilst delivering power and data to and from edge devices.

Traditional computer-oriented Ethernet comes normally in two and four-pair variants. Different variants of Ethernet are the most common industrial link protocols. Until now, they have required 4 or 8 wires, but the SPE link is allows using only two wire pairs. Using only two wire pairs can simplify the wiring and can allow reusing some old industrial wiring for Ethernet application. SPE offers additional benefits such as lighter and more flexible cables. Their space requirements and assembly costs are lower than with traditional Ethernet wiring. Those are the reasons why the technology is of interest to many.

The 10BASE-T1, 100BASE-T1 and 1000BASE-T1 single-pair Ethernet physical layers are intended for industrial and automotive applications or as optional data channels in other interconnect applications.
Automotive Ethernet, called 802.3bw or 100BASE-T1, that adapts Ethernet to the hostile automotive environment with a single pair.

Also 2.5 Gb/s, 5 Gb/s, and 10 Gb/s over a 15 m single pair is standardized in 802.3ch-2020. As of 2021, the P802.3cy Task Force is examining having 25, 50, 100 Gb/s speeds at lengths up to 11 m.

The single pair operates at full duplex and has a maximum reach of 15 m or 49 ft (100BASE-T1, 1000BASE-T1 link segment type A) or up to 40 m or 130 ft (1000BASE-T1 link segment type B) with up to four in-line connectors.

There is also a long distance 10BASE-T1L standard that can support distance up to one one kilometer at 10-Mb/s speed. In building automation, long reach is often needed for HVAC, fire safety, and equipment like elevators. The 10BASE-T1 standard has two parts. The main offering is 10BASE-T1L, or long reach to 1 km. The connection is point-to-point (p2p) with full-duplex capability. The other is 10BASE-T1S, or short-reach option that provides p2p half-duplex coverage to 25 meters and includes multidrop possibilities.

All those physical layers require a balanced twisted pair with an impedance of 100 Ω. The cable must be capable of transmitting 600 MHz for 1000BASE-T1 and 66 MHz for 100BASE-T1.

Single-pair Ethernet defines its own connectors:

  • IEC 63171-1 “LC”: This is a 2-pin connector with a similar locking tab to the modular connector, if thicker.
  • IEC 63171-6 “industrial”: This standard defines 5 2-pin connectors that differ in their locking mechanisms and one 4-pin connector with dedicated pins for power. The locking mechanisms range from a metal locking tab to M8 and M12 connectors with screw or push-pull locking. The 4-pin connector is only defined with M8 screw locking.

Fiber Ethernet

When most people think of an Ethernet cable, they probably imagine a copper cable, and that’s because they’ve been around the longest. A more modern take on the Ethernet cable is fiber optic. Instead of depending on electrical currents, fiber optic cables send signals using beams of light, which is much faster. In fact, fiber optic cables can support modern 10Gbps networks with ease. Fiber optic has been option on Ethernet for a long time. Ethernet has been using optical fiber for decades. The first standard was 10 Mbit/s FOIRL in 1987. The currently fastest PHYs run 400 Gbit/s. 800 Gbit/s and 1.6 Tbit/s started development in 2021.

The advantage most often cited for fiber optic cabling – and for very good reason – is bandwidth. Fiber optic Ethernets can easily handle the demands of today’s advanced 10 Gbps networks or 100Gbps, and have the capability of doing much more. Fiber optic cables can run without significant signal loss for distances, from kilometers up to tens of kilometers depending on the fiber type and equipment used.

The cost of fiber has come down drastically in recent years. Fiber optic cable is usually still a little more expensive than copper, but when you factor in everything else involved in installing a network the prices are roughly comparable.

Fiber optics is immune to the electrical interference problems because fiber optic cable doesn’t carry electricity, it carries light. Because fiber optic cables don’t depend on electricity, they’re less susceptible to interference from other devices.

Fiber optic cables are sometimes advertised to be more secure than copper cables because light signals are more difficult to hack. It is true that light signals are slightly more difficult to hack than copper cable signals, but actually they are nowadays well hackable with right tools.

Fiber has won the battle in the backbone networks on long connections, but there is still place for copper on shorter distances Nearly every computer and laptop sold today has a NIC card with a built-in port ready to accept a UTP copper cable, while a potentially expensive converter or fiber card is required to make a fiber optic cable connection.

Standard fiber-optic cables have a glass quartz core and cladding. Nowadays, there are two fiber optic cable types widely adopted in the field of data transfer—single mode fiber optic cable and multimode fiber optic cable.

A single-mode optical fiber is a fiber that has a small core, and only allows one mode of light to propagate at a time. So it is generally adapted to high speed, long-distance applications. The core size of single mode fiber has a core diameter between 8 and 10.5 micrometers with and a cladding diameter of 125 micrometers. OS1 and OS2 are standard single-mode optical fiber used with wavelengths 1310 nm and 1550 nm (size 9/125 µm) with a maximum attenuation of 1 dB/km (OS1) and 0.4 dB/km (OS2). SMF is used in long-haul applications with transmission distances of up to 100 km without need a repeater. Typical transmission distances are up 10-40 kilometers. Single mode capable hardware used to be very expensive years ago, but prices for then have came down quicly. Nowadays single mode is very commonly uses.

Multimode optical fiber is a type of optical fiber with a larger core diameter larger (65 or 50 micrometer core) designed to carry multiple light rays, or modes at the same time. It is mostly used for communication over short distances. Multimode Fiber (MMF) uses a core/cladding diameter of typically 50 micrometer/125 mictometer, providing less reach, up to approximately 2 km or less, due to increased dispersion as a result of the larger diameter core.

Image fromhttps://www.cables-solutions.com/whats-difference-fiber-optic-cable-twisted-pair-cable-coaxial-cable.html:

Fiber has become common in datacenters due to the frequency and reach limitations of twisted-pair copper – currently and probably permanently limited to 40 Gbit/s over only 30 m of category-8 twisted pair or just 10 Gbit/s over the full 100 m (of category 6A).

Fiber optic cables are commonly used for core network lines and connections that must span long distances, such as those used by Internet service providers.

Depending on your requirements, when going to use fiber, you’re probably first looking for one of these commonly used interfaces: 1000BASE-SX (1 Gbit/s over up to 550 m of OM2 multi-mode fiber), 1000BASE-LX (1 Gbit/s over up to 10 km of single-mode fiber), 10GBASE-SR (10 Gbit/s over up to 400 m of OM4 MMF), 10GBASE-LR (10 Gbit/s over up to 10 km of SMF).

There are many other PHY standards for various data rates and distances, also many common non-standards for even longer distance. The required optical transceivers are usually SFP (1G) or SFP+ modules (10G) plugged into your network hardware. Switches and network adapters with SFP modules allow you to create custom fiber optic high-speed Ethernet networks by plugging in suitable type SFP module. External media converters for devices without SFP slot are also available. A fiber media converter, also known as a fiber to Ethernet converter, allows you to convert typical copper Ethernet cable (e.g., Cat 6a) to fiber and back again.

100G (100 Gb/s) Ethernet has had a good run as the backbone technology behind the cloud, but the industry is moving on. There is expected to be exploding demand for bandwidth in the 5G/mmWave era that’s now upon us. Modern
400G and 800G test platforms validate the cloud’s Ethernet backbone, ensuring support for the massive capacity demands of today and tomorrow.
Many service providers and data centers, for various reasons, skipped over 400G Ethernet implementations and are looking toward 800G Ethernet for their next network transport overhaul. Adoption of 400G is still happening, but the growth of 800G will eclipse it before long.

In the future, the speeds of Ethernet networks will increase. Even after the 25, 40, 50 and 100 gigabit versions, more momentum is needed. For example, growing traffic in data centers would require 100G or even faster connections over long distances. Regardless of future speed needs, 200G or 400G speeds are best suited for short-term needs. The large cloud data centers on the Internet have moved to 100GbE, 200GbE and 400G solutions for trunk connections. They also require strong encryption and, in addition, accurate time synchronization of the backbone networks of 5G networks. Media Access Control security (MACsec) provides point-to-point security on Ethernet links. MACsec is defined by IEEE standard 802.1AE. IEEE 802.1X is an IEEE Standard for port-based Network Access Control (PNAC).

High-speed terabit rates do not yet make sense to implement now. The standardization organization OIF (Optical Interworking Forum) has worked up to 800 gigabit connection speeds. The Ethernet Technology Consortium proposed an 800 Gbit/s Ethernet PCS variant based on tightly bundled 400GBASE-R in April 2020. In December 2021, IEEE started the P802.3df Task Force to define variants for 800 and 1600 Gbit/s over twinaxial copper, electrical backplanes, single-mode and multi-mode optical fiber along with new 200 and 400 Gbit/s variants using 100 and 200 Gbit/s lanes. Lightwave magazine expects that 800G Ethernet transceivers become most popular module in mega data centers by 2025. There are already test instruments designed to validate 1.6T designs.

There is also one fiber tpye I have not mentioned yet. Plastic optical fiber (POF) has emerged as a low cost alternative to twisted pair copper cabling and coaxial cables in office, home and automotive networks. POF technology offers an attractive alternative to traditional glass optical fiber as well as copper for industrial, office, home and automotive networks. POF typically utilizes a polymethylmethacrylate (PMMA) core and a fluoropolymer cladding. Glass fiber-optic cable offers lower attenuation than its plastic counterpart, but POF provides a more rugged cable, capable of withstanding a tighter bend radius.

POF has generally been utilized in more niche applications where its advantages outweigh the need for high bandwidth and relatively short maximum distance (only tens of meters). Currently in the market, several manufacturers have developed fiber optic transceivers for 100Mbps Ethernet over plastic optical fiber and there exist also 1Gbit/s versions. Advances in LED technology and Vertical Cavity Surface Emitting Laser (VCSEL) technology are enabling POF to support data rates of 3Gbps and above

POF offers many benefits to the user: it is lightweight, robust, cheap and easy to install; the use of 650nm red LED light makes it completely safe and easier to diagnose as red light can be seen by the human eye. There are several different connectors used for PoF. There is also connector-less option called Optolock, where you can simply slice the plastic fiber with a knife, separate the fibers, insert the fiber into the housing and then lock it in place.

Industrial networks special demands for Ethernet

Industrial networks need to be durable. Industrial applications on the field needs often more durable connectors than the traditional RJ-45 connector of office networks.

Here is a list of some commonly used industrial Ethernet connector types:

  • 8P8C modular connector: For stationary uses in controlled environments, from homes to datacenters, this is the dominant connector. Its fragile locking tab otherwise limits its suitability and durability. Bandwidths supporting up to Cat 8 cabling are defined for this connector format.
  • M12X: This is the M12 connector designated for Ethernet, standardized as IEC 61076-2-109. It is a 12mm metal screw that houses 4 shielded pairs of pins. Nominal bandwidth is 500MHz (Cat 6A). The connector family is used in chemically and mechanically harsh environments such as factory automation and transportation. Its size is similar to the modular connector.
  • ix Industrial: This connector is designed to be small yet strong. It has 10 pins and a different locking mechanism than the modular connector. Standardized as IEC 61076-3-124, its nominal bandwidth is 500MHz (Cat 6A).

In addition to those there are applications that use other versions of M12 and smaller M8 connectors.

Current industrial trends like Industrie 4.0 and the Industrial Internet of Things lead to an increase in network traffic in ever-growing converged networks. Many industrial applications need reliable and low latency communications. Many industries require deterministic Ethernet, and Industrial Automation is one of them. The automation industry has continuously sought solutions to achieve fast, deterministic, and robust communication. Currently, several specialized solutions are available for this purpose, such as PROFINET IRT, Sercos III, and Varan. TSN can help standardize real-time Ethernet across the industry.

TSN refers to a set of IEEE 802 standards that make Ethernet deterministic by default. TSN is an upcoming new technology that sits on Layer 2 of the ISO/OSI Model. It adds definitions to guarantee determinism and throughput in Ethernet networks. It will provide standardized mechanisms for the concurrent use of deterministic and non-deterministic communication. AVB/TSN can handle rate-constrained traffic, where each stream has a bandwidth limit defined by minimum inter-frame intervals and maximal frame size, and time-trigger traffic with an exact accurate time to be sent. Low-priority traffic is passed on best-effort base, with no timing and delivery guarantees. Time-sensitive traffic has several priority classes.


Time-Sensitive Networking (TSN) is a set of standards under development by the Time-Sensitive Networking task group of the IEEE 802.1 working group
. The majority of projects define extensions to the IEEE 802.1Q – Bridges and Bridged Networks, which describes Virtual LANs and network switches. These extensions in particular address the transmission of very low transmission latency and high availability. Applications include converged networks with real-time Audio/Video Streaming and real-time control streams which are used in automotive or industrial control facilities.

In contrast to standard Ethernet according to IEEE 802.3 and Ethernet bridging according to IEEE 802.1Q, time is very important in TSN networks. For real-time communication with hard, non-negotiable time boundaries for end-to-end transmission latencies, all devices in this network need to have a common time reference and therefore, need to synchronize their clocks among each other. This is not only true for the end devices of a communication stream, such as an industrial controller and a manufacturing robot, but also true for network components, such as Ethernet switches. Only through synchronized clocks, it is possible for all network devices to operate in unison and execute the required operation at exactly the required point in time. Scheduling and traffic shaping allows for the coexistence of different traffic classes with different priorities on the same network.

The following are some of the IEEE standards that make up TSN:

Enhanced synchronization behavior (IEEE 802.1AS)
Suspending (preemption) of long frames (IEEE 802.1-2018)
Enhancements for scheduled traffic (IEEE 802.1Q-2018)
Path control and bandwidth reservation (IEEE 802.1Q-2018)
Seamless redundancy (IEEE 802.1CB)
Stream reservation (IEEE 802.1Q-2018)

Synchronization of clocks across the network is standardized in Time-Sensitive Networking (TSN). Time in TSN networks is usually distributed from one central time source directly through the network itself using the IEEE 1588 Precision Time Protocol, which utilizes Ethernet frames to distribute time synchronization information.

262 Comments

  1. Tomi Engdahl says:

    This NAS motherboard has more 2.5G Ethernet ports than USB ports — Topton N9 comes with eight 2.5G Ethernet ports

    This NAS motherboard has more 2.5G Ethernet ports than USB ports — Topton N9 comes with eight 2.5G Ethernet ports
    News
    By Zhiye Liu published 12 hours ago
    The Topton N9 motherboard targets NAS users.
    https://www.tomshardware.com/pc-components/motherboards/this-nas-motherboard-has-more-25g-ethernet-ports-than-usb-ports-topton-n9-comes-with-eight-25g-ethernet-ports?fbclid=IwAR0iYbipGJ7ylZmSVAT3kvjnmBpoiEFJTOifMAA4U3asxzPJbL7XrzczZL8

    The Topton N9 conforms to the standard mini-ITX form factor but doesn’t have an Intel or AMD socket. Instead, the motherboard leverages Intel’s Core i7-8705G (Kaby Lake G) processor, soldered to the PCB. It doesn’t come with a heatsink, but you can add one for around $20.

    The base Topton N9 sells for $269.57 on AliExpress. Adding the processor heatsink will set you back $288.17. The other customization options range from 8GB of DDR4 with a 128GB NVMe SSD to 64GB of DDR4 and a 2TB NVMe SSD, with pricing varying from $324.95 to $622.80.

    Reply
  2. Tomi Engdahl says:

    How DEC’s LANBridge 100 Gave Ethernet A Fighting Chance
    https://hackaday.com/2024/04/09/how-decs-lanbridge-100-gave-ethernet-a-fighting-chance/

    When Ethernet was originally envisioned, it would use a common, shared medium (the ‘Ether’ part), with transmitting and collision resolution handled by the carrier sense multiple access with collision detection (CSMA/CD) method. While effective and cheap, this limited Ethernet to a 1.5 km cable run and 10 Mb/s transfer rate. As [Alan Kirby] worked at Digital Equipment Corp. (DEC) in the 1980s and 1990s, he saw how competing network technologies including Fiber Distributed Data Interface (FDDI) – that DEC also worked on – threatened to extinguish Ethernet despite these alternatives being more expensive. The solution here would be store-and-forward switching, [Alan] figured.

    After teaming up with Mark Kempf, both engineers managed to convince DEC management to give them a chance to develop such a switch for Ethernet, which turned into the LANBridge 100. As a so-called ‘learning bridge’, it operated on Layer 2 of the network stack, learning the MAC addresses of the connected systems and forwarding only those packets that were relevant for the other network. This instantly prevented collisions between thus connected networks, allowed for long (fiber) runs between bridges and would be the beginning of the transformation of Ethernet as a shared medium (like WiFi today) into a star topology network, with each connected system getting its very own Ethernet cable to a dedicated switch port.

    How Engineers at Digital Equipment Corp. Saved Ethernet
    Their groundbreaking learning bridge technology increased LAN performance
    https://spectrum.ieee.org/how-dec-engineers-saved-ethernet

    Reply
  3. Tomi Engdahl says:

    Microsoft does not want you to use iPerf3 to measure network performance on Windows
    https://www.xda-developers.com/microsoft-iperf3-network-performance-windows/?fbclid=IwZXh0bgNhZW0CMTEAAR3e_GKkchOcra4uvXBX2us9mY0f4pw9-iw5M59frtbv91w2wD1V2GVMGYE_aem_AegisqfsprFkv4p19bbKdUBMHZ7VxgsTq-TIW1hKbiA4Kv8M_xqH3cfO3kU30e9_oA21JbKdijruwbgUhHNPfifh

    Microsoft has asked customers to ditch iPerf3 on Windows, recommending other tools instead.

    iPerf3 is not supported on Windows, with performance issues due to the Cygwin emulation layer.
    Microsoft recommends ntttp and ctsTraffic over iPerf3 for network performance testing on Windows.
    Using older iPerf3 versions on Windows may limit network benchmarking capabilities.

    iPerf is a fairly popular cross-platform tool that is used by many to measure network performance and diagnose any potential issues in this area. The open-source utility is maintained by an organization called Energy Sciences Network (ESnet) and officially supports Linux, Unix, and Windows. However, Microsoft has now published a detailed blog post explaining why you should not use the latest version, iPerf3, on Windows installations.

    Reply
  4. Tomi Engdahl says:

    Jim Keller suggests Nvidia should have used Ethernet to stitch together Blackwell GPUs, saving billions
    News
    By Anton Shilov published April 13, 2024
    Suitable for programmability and for porting to other platforms.
    https://www.tomshardware.com/tech-industry/artificial-intelligence/jim-keller-suggests-nvidia-should-have-used-ethernet-to-stitch-together-blackwell-gpus

    Reply
  5. Tomi Engdahl says:

    ROBERT KAHN: THE GREAT INTERCONNECTOR
    The 2024 IEEE Medal of Honor recipient envisioned the network of networks that became the Internet
    https://spectrum.ieee.org/bob-kahn-2667754905

    Reply

Leave a Comment

Your email address will not be published. Required fields are marked *

*

*