The computer network is experiencing a rapid change. The widespread use of optical fiber to transmit data has made tremendous increse in network bandwidth possible. Furthermore, greater CPU power, increasing disk capacity and support for digital audio and video are creating demand for a new class of network service. The result of these trends is ‘gigabit environment’ – the latest version of ethernet that offers 1000 Mbps raw bandwidth. Gigabit ethernet is compatible with existing ethernet while using the same protocols, but when it will be launched in the market, it will compete with some existing technology like ATM. This paper introduces the gigabit ethernet, its features, future and comparison with ATM.

1. Introduction
2 History of Networking
3. Gigabit Migration
    3.1. Upgrading Switch-to-Switch Links
    3.2. Upgrading Switch-to-Server Links
    3.3. Upgrading a Switched Fast Ethernet Backbone
    3.4. Upgrading a Shared FDDI Backbone
    3.5. Upgrading High Performance Desktops
4. Technology
5. Goals of gigabit ethernet
6. ATM vs.Gigabit Ethernet
7. Conclusion

List of references
Further information
 

1. Introduction

Technology advancement in the fields of fiber optics, computing systems, computer applications, data communications and internetworking has been linked closely to the development of networks that have the capability of operating at gigabit speeds. The capability of today's fiber optic signaling equipment to transmit several gigabits per second over long distances with very low error rates through optical fiber has convinced the researchers that gigabit networks are technologically feasible.Further, technology has realized a tremendous increase in the power and bandwidth of many parts of computing systems today at an affordable price. It is also predicted that computing power in 1997 is 2 GIPS (Gillion Instruction Per Second). High-bandwidth storage systems have also been improved in performance. It is now possible to have gigabit-bandwidth file systems with a technology known as RAID.

As computing power and storage systems become increasingly powerful, it is easier now to support new and existing network and computer applications with high-bandwidth data, high-resolution graphics, and other complex and rich multimedia data. Real-time video conferencing, 3D animation modeling, Internet telephony, medical imaging, CAD/CAM applications, and Mbone transmissions.Further, the explosive growth of the Internet, the WWW (World Wide Web) and enterprise intranets is radically changing the pattern of network traffic by introducing more and more different subnets. As a result, the traditional "80/20" rule is no longer true. where network traffic was 80% locally based in the subnet and 20% leaving the subnet, or running over the corporate backbone and across WAN (wide area network).  Today's network must be able to handle anywhere-to-anywhere traffic with 80% of the traffic crossing subnet boundaries.

With today's data-intensive applications, increasing number of network users, enterprise intranets, LANs (Local Area Networks), and new methods of information delivery, pressure for higher bandwidth is growing rapidly at desktops, servers, hubs, and switches. The concern is how to achieve a high-performance network with a bandwidth that matches the capabilities of its processing power and memory capacity. Therefore, the primary goal of data communications today is not only to facilitate data exchange between computing systems, but to do it fast as well. This drives a widespread interest in the technologies for gigabit networking.

Further, achieving true gigabit networks is not only the matter of raw bandwidth increases. Other aspects of networking should be considered. Such aspects are the existing “legacy” infrastructure networks in the existing switches, the software and network interface cards (NICs), and the ability of the protocol stacks to move data in and out of the computer, fast routing and switching. Other issues are increasing traffic demands, unpredictable traffic flows, and the priority of critical applications. Therefore, all of these aspects of the networking system should be taken into account in order to achieve true high-bandwidth networking.

2.History of networking

Today, Ethernet is synonymous with the IEEE 802.3 standard for a "1-persistent CSMA/CD LAN".  In the beginning of 802.3 standard , is generally considered to be the University of Hawaii ALOHA network. This system is the ancestor of all shared media networks. The original Ethernet, developed by Xerox was based on the ALOHA system. It was a 2.94 Mbps CSMA/CD system and was used to connect over 100 personal workstations on a 1 Km cable. It was so successful, that Xerox, DEC and Intel came up with a 10 Mbps standard. The IEEE 802.3 standard was based on the 10 Mbps Ethernet. CSMA/CD refers to the protocol used by stations sharing the medium, to arbitrate use of the medium. A sender has to "listen" to the medium. If no one else is transmitting, then the sender may transmit. If two senders start transmitting at the same time, then a collision is said to have occurred. Transmitting stations, therefore, have to listen to the medium for collisions while transmitting, and retransmit a packet after some time, if a collision occurs. The original 802.3 standard was published in 1985. Originally two types of coaxial cables were used called Thick Ethernet and Thin Ethernet. Later unshielded copper twisted pair (UTP) , used for telephones, was added. In 1980, when Xerox, DEC and Intel published the DIX Ethernet standard, 10 Mbps was a lot of bandwidth. Since then, as computing technology improved, network bandwidth requirements also increased. In 1995, IEEE adopted the 802.3u Fast Ethernet standard. Fast Ethernet is a 100 Mbps Ethernet standard. Fast Ethernet established Ethernet scalability. With Fast Ethernet came full-duplex Ethernet. Until, now, all Ethernets worked in half-duplex mode, that is, if there were only two station on a segment, both could not transmit simultaneously. With full-duplex operation, this was now possible. Today's advanced technology in fiber optics, computing systems and networking has made the development of gigabit networks possible. With the bandwidth more than 1 Gbps, gigabit networks can support the demand of increasing network traffic, and many sophisticated computer applications. To achieve true gigabit networks, other aspects of networking, such as routing, switching, protocols should also be considered[6].

3.Gigabit Migration

Network administrator should plan migration based onthe following features: -
1. Current environment and analyzing network patterns as[5]:

     Congestion points
     New advanced applications upcoming
     Type traffic patterns
     Suitable backbone and horizontal wiring
     Minimal network disruption

2. Financial Investment - Quick (ROI)
3. Simple upgrading - Network management and tool deployment remain the same
4. Overall cost - “single technology base”, Minimal training costs, simple network maintenance & provisioning[1].
5. Backwards compatible to 10 & 100Mb/s[1].

The initial applications for Gigabit Ethernet will be for campuses or buildings requiring greater bandwidth between routers, switches, hubs, repeaters, and servers. Examples include switch-to-router, switch-to-switch, switch-to-server and repeater-to-switch connections. In its early phase, Gigabit Ethernet is not expected to be deployed widely to the desktop. The five most likely upgrade scenarios are outlined below.[4]

3.1 Upgrading Switch-to-Switch Links  A very straightforward upgrade scenario is upgrading 100-Mbps links between Fast Ethernet switches or repeaters to 1000-Mbps links between 100/1000 switches. Such high-bandwidth, switch-to-switch links would enable the 100/1000 switches to support a greater number of both switched and shared Fast Ethernet segments.

3.2 Upgrading Switch-to-Server Links  The simplest upgrade scenario is upgrading a Fast Ethernet switch to a Gigabit Ethernet switch to obtain high-speed, 1000-Mbps interconnection to a server farm of high-performance super servers with Gigabit Ethernet NICs installed.

3.3 Upgrading a Switched Fast Ethernet Backbone  A Fast Ethernet backbone switch that aggregates multiple 10/100 switches can be upgraded to a Gigabit Ethernet switch supporting multiple 100/1000 switches as well as other devices such as routers and hubs with Gigabit Ethernet interfaces and uplinks. Gigabit repeaters can also be installed as needed. Once the backbone is upgraded to a Gigabit Ethernet switch, high-performance server farms can be connected directly to the backbone with Gigabit Ethernet network interface cards, increasing throughput to the severs for users with high-bandwidth applications. Also, the network can now support a greater number of segments, more bandwidth per segment, and hence a greater number of nodes per segment.

3.4 Upgrading a Shared FDDI Backbone  An FDDI campus or building backbone can be upgraded by replacing the FDDI concentrator or hub or Ethernet-to-FDDI router with a Gigabit Ethernet switch or repeater. (As an intermediate step, some users might migrate to an FDDI switch before installing a Gigabit Ethernet Switch.) The only upgrade required is the installation of new Gigabit Ethernet interfaces in the routers, switches or repeaters. All the investment in fiber-optic cabling is retained, and the aggregate bandwidth is increased at least tenfold for each segment.

3.5 Upgrading High Performance Desktops  In the later phases of Gigabit Ethernet adoption, as Fast Ethernet or FDDI connected desktops run out of bandwidth, Gigabit Ethernet NICs will be used to upgrade high-performance desktop computers with Gigabit Ethernet connectivity. The high-performance desktop computers are then connected to Gigabit Ethernet switches or repeaters [4]

5.Technology

There are four technologies competing each other in production or development today to provide gigabit networks. They are ATM, Fiber Channel, Gigabit Ethernet, and Serial HIPPI.

Asynchronous Transfer Mode (ATM)

Originally, the goal of ATM design was to simplify and standardize international telecommunications. Today, it has become standard for WANs. ATM provides a high-speed transmission for all types of communications, from voice to video to data, over one network with small, fixed-size cells. It also provides unparalleled scalability and Quality of Service. Currently, ATM technology is used in network backbones or specific workgroup applications with heavy traffic load with the mix traffics of voice, video, and data into a single network. To achieve gigabit speeds, ATM is being developed to operate on 622 Mbps (OC-12) and 1.244 Gbps (OC-24).[2]

The future of ATM is still unknown. It depends heavily on its ability to integrate with existing LAN and WAN network technologies. Most observers feel ATM technology will not become a major force in future networks since the other networking technologies can easily achieve the advantages of ATM. Other observers believe that ATM seems to meet the future needs of WAN and a few highly specialized LAN environments.

Fiber Channel

The standards and architectures of Fiber Channel are still under development although some vendors have settled on a standard known as Arbitrated Loop, which is basically a ring topology. It is very sensitive to adding new users, which can cause increased congestion and reduced bandwidth to each user. At present, Fiber Channel is used to attach storage devices to computers.

Arbitrated Loop Fiber Channel runs at a gigabit per second and supports the SCSI protocol. This design seems to be a good choice for peripheral-attachment operations. However, many experts agree that Fiber Channel is not a good choice to replace IP technology and to provide future gigabit networks.

Gigabit Ethernet

Many network experts agree that Gigabit Ethernet will become the gigabit technology for the LAN environments. It is a good choice for providing a higher capacity enterprise backbone throughout an organization and high-performance workstations with a cost-effective gigabit networking connection. Nevertheless, Gigabit Ethernet is not a good solution for moving applications with huge data rapidly due to the issues of the Ethernet-based CSMA/CD support, host-bust connection issues, and relatively small packet size.

Serial HIPPI (High Performance Parallel Interface)

Serial HIPPI is the fiber-optic version of the HIPPI, which was originally developed in the late 1980s to serve the connectivity and high-bandwidth needs of super computers and high-end workstations. It provides a simple, fast point-to-point unidirectional connection. Recently, this technology shows its establishment as the gigabit technology for big data applications, clustering and a broad of server-connectivity environments, providing a speed of 1.2 Gbps over distances up to 10 kilometers. Serial HIPPI implements non-blocking switching technology and packet sizing up to 64 KB in size. It also provides reliable ANSI (ANSI X3T9.3)- and ISO-standardized Gbps connectivity with the packet loss rate approaching zero percent.

Serial HIPPI operates within the physical- and data-link layers in the ISO seven-layer model. At higher layers, Serial HIPPI supports IPI-3 for storage connection and TCP/IP for networking which makes it compatible with Ethernet, Token Ring, FDDI, and the wide-area protocols used on the Internet. It also supports ARP (Address Resolution Protocol) to automatically specify how to find IP addresses on its network. At physical layer, Serial HIPPI provides flow control to eliminate errors and data loss due to congestion, guaranteed end-to-end, in-order packet delivery, and error reporting.  Other protocols have to rely on TCP/IP for data lost detection, which is not efficient.

At present, Serial HIPPI seems to be the only available technology that offers gigabit performance with 100% reliability. However, this does not eliminate the possibility of other technologies, such as ATM and Gigabit Ethernet to be a significant factor in the implementation of gigabit networking.

5 Goals of gigabit ethernet

Very common method in networking computers in LAN’s and can handle about 10,000,000 bits per second and compatible with almost any kind of computers[5]. Ethernet operates at 10, 100, 1000 Mb/s using CSMA/CD (shared Bus with multiple stations) to target the followings:

• Achieve 1000Mb/s
• Use 802.3 Ethernet frame format
• Meet 802 functionality
• Provide forwarding between 10mb, 100Mb and 1000Mb
• Preserve min/max frame size of current standard
• Provide Full and Half Duplex operation
• Support star-wired topologies
• Utilize CSMA/CD w/support for at least one repeater per collision domain
• Support ANSI Fibre Channel FC-1 and   FC-0, fiber media and copper media, if possible
• Family of layer specifications
• 500m on MM fiber
• 25m on Copper (100m pref.)
• 3km on single mode
• Support media selected by ISO/IEC 11801
• Accommodate flow control

Specify Gigabit Ethernet media independent interface (GMII)

When ATM (Asynchronous Transfer Mode) was introduced, it offered 155 Mbps bandwidth, which was 1.5 times faster than Fast Ethernet. ATM was ideal for new applications demanding a lot of bandwidth, especially multimedia. Demand for ATM continues to grow for LAN's as well as WAN's.

On the one hand , proponents of ATM try to emulate Ethernet networks via LANE ( LAN Emulation) and IPOA ( IP over ATM). On the other, proponents of Ethernet/IP try to provide ATM functionality with RSVP( Resource Reservation Protocol ) and RTSP ( Real-time Streaming Transport Protocol ). Evidently, both technologies have their desirable features, and advantages over the other. It appears that these seemingly divergent technologies are actually converging.

Scalability

ATM was once thought to be the scalable technology for supporting faster desktops and servers. But Ethernet's proven to be just as scalable in terms of interface speeds. Ethernet switching is now in its third wave, having moved from 10- to 100- to 1,000-Mbit/s speeds. The migration has been smooth and graceful. Each step can be taken one at a time as the network grows along an evolutionary path, without learning a whole new way of configuring, managing, and troubleshooting the LAN.[8]

LAN Backbone

Gigabit Ethernet will own the LAN backbone for many of the same reasons people thought ATM would thrive there. The difference is that migration to a backbone based on gigabit Ethernet is more natural, painless, and cost-effective than migration to ATM. When building networks, business reasons matter most-the technical considerations are secondary. Gigabit vendors always seem to gloss over that point.  Demand for ATM continues to grow in the LAN as well as the WAN, and the reason is simple: Most of today's business objectives depend on networked applications. ATM has been installed in some LAN pockets, but the growth and installation of ATM is only a fraction of that of Ethernet. There are more than 100 million Ethernet nodes in the world, and fewer than 100,000 ATM adapters installed. Businesses do depend on networked applications--and they've been depending on Ethernet for more than 20 years! As today's networks can't supply adequate performance in terms of consistent throughput and  redictable response time, several performance hungry applications have been stalled. The promise of free, unlimited network capacity has caused business managers to roll out new, demanding applications in the belief that all roadblocks have been removed. It is considered that gigabit Ethernet means networking nirvana has been attained. The ethernet evolves and scales to meet the needs of the new applications. Even though the ATM is in use today, but it's expensive compared with Ethernet switches. It also requires a complete revolutionary shift in LAN infrastructure, as opposed to the evolution of Ethernet switches.

Interoperability

RSVP is a proposed standard for QOS  signaling in a router-based IP environment.  It's focused on reserving bandwidth for a  small number of few-to-many sessions. It was never intended to--nor will it--support  thousands of point-to-point connections from clients to servers across a backbone. Inoperability was a problem for 100Base-T a year after adoption of the standard. And a gigabit Ethernet standard  isn't the whole story. ATM-like services, switched gigabit Ethernet must also support RSVP , RTP , and RTSP --not to mention 802.1p , 802.1q, and 802.3x . Of course, how well this yet-to-be finished  Ethernet alphabet soup will work, and how well it will approximate ATM, is far from clear.[10]

ATM interoperability is still an issue. Even where ATM standards are  firm, few vendors have implemented all the ones necessary to deliver true QOS. In order for QOS to work, ATM end-stations must  support ABR [available bit rate]. Without  that, end-to-end QOS doesn't exist. If and  when ABR is supported, it will require new  hardware at every end-station.  The right mix of RSVP and other  higher-level prioritization services on  Ethernet will bring QOS to the installed base  of Ethernet without the need for an   infrastructure change--or new adapters in each end-station. Since ATM network interface cards  have hardware support for allocating and  scheduling QOS on a per-application basis,  622-Mbit/s ATM will provide server links for interactive and timing-sensitive applications  like IP telephony and streaming video.

Performance and Load balancing

With ATM, multiple NICs in a server increase performance by load balancing. They also insulate sessions from a failed NIC by automatically switching to alternates. This built-in reliability will drive the use of ATM in connecting mission-critical application servers.IP telephony applications are intended to work on the Internet and on Ethernet. If anything should be at the edge of the network, it's ATM, with WAN interfaces. The core is frame-based, and it will stay that way.

The core is ATM-and net managers already have installed thousands of ATM backbone networks. And the dependency of wide-area carriers on ATM has driven the development of test and modeling tools for ATM networks. Gigabit Ethernet will do very well in applications that take advantage of its  strengths. It will be an excellent "feeder" into ATM backbones. It will provide  cost-effective server connections, both at the departmental and enterprise level, for  applications that don't demand rigorous QOS capabilities. But it's ATM that will continue to be the only fully standardized backbone that provides the critical mix of bandwidth, predictability,  manageability, fault tolerance, and investment protection. Backbone switches in the 2.5- to 10-Gbit/s range are available, as are trunk speeds of 155 and 622 Mbit/s. And ATM's inherent load-balancing provides parallel links with additional bandwidth as needed. Within a year, 40- to 50-Gbit/s switches and 2.5-Gbit/s links wi ll be available. ATM prices have been declining by more than 40 percent per year. So deployment doesn't have to be delayed by budget limitations anymore.

Bandwidth and Budget

Gigabit Ethernet switches with 8.5- and 17.5-Gbit/s capacities, full-duplex support, and nonblocking switching fabrics are becoming available. The price of a 10/100Base-T adapter is still less than half that of a 25-Mbit/s ATM adapter and one-fourth the cost of a 155-Mbit/s ATM adapter.

An ATM switch from Fore, configured for eight 622-Mbit/s ports, costs $13,738 per port at published list prices. An eight-port gigabit Ethernet switch, with eight ports running at 1 Gbit/s each, costs $3,125 per port; it's one-fourth the price and delivers nearly twice the bandwidth. So even if 622-Mbit/s port costs come down by 50 percent this year, they'll still be twice the cost of those for gigabit Ethernet in an equivalent configuration.

Ethernet has a role to play--as a switched edge technology around an ATM core that spans LAN and  WAN--which is something gigabit Ethernet doesn't do. The switched edge is a combination of full-duplex Ethernet--now running at 10 or 100 Mbit/s, with the addition of gigabit Ethernet in 1998 and beyond--and ATM running at 25 or 155 Mbit/s.  The desktop connection choice is based on  application requirements. For most  applications, the Ethernet alphabet soup will suffice for connections   to the wiring closet. There, a well-designed Ethernet-to-ATM switch maps the  best-effort QOS of RSVP to guaranteed  ATM QOS for transport across the  backbone to the server. But until that soup is done, another solution is needed.

ATM was touted to be the seamless and scaleable networking solution - to be used in LANs, backbones and WANs alike. However, that did not happen. And Ethernet, which was for a long time restricted to LANs alone, evolved into a scalable technology. As Gigabit Ethernet products enter the market, both sides are gearing up for the battle. Currently, most installed workstations and personal computers do not have the capacity to use these high bandwidth networks. So, the imminent battle is for the backbones, the network connections between switches and servers in a large network.

In a Nutshell

ATM still has some advantages over Gigabit Ethernet :

• ATM is already there. So it has a head start over Gigabit Ethernet. Current products may not support gigabit speeds,but faster versions are in the pipeline.
• ATM is better suited than Ethernet for applications such as video, because ATM has QOS ( Quality of Service) and different services available such asCBR (constant bit rate) which are better for such applications. Though the IETF (Internet Engineering Task Force, the standards body for internet protocols) is working on RSVP which aims to provide QOS on Ethernet, RSVP has it's limitations. It is a "best effort" protocol, that is , the network may acknowledge a QOS request but not deliver it. In ATM it is possible to guarantee QOS parameters such as maximum delay in delivery.

The greatest strength is that it is Ethernet. Upgrading to Gigabit Ethernet is expected to be painless. All applications that work on Ethernet will work on Gigabit Ethernet. This is not the case with ATM. Running current applications on ATM requires some amount of translation between the application and the ATM layer, which means more overhead. Currently, the fastest ATM products available run at 622 Mbps. At 1000 Mbps, Gigabit Ethernet is almost twice as fast. It is not clear whether any one technology will succeed over the other. It appears that sooner or later, ATM and Ethernet will complement each other and not
compete[2].

7. Conclusion

Gigabit Ethernet seems to be ready to succeed. It is backed by the industry in the form of the Gigabit Ethernet Alliance. The standardization is currently on schedule. Pre-standard products with claims of inter-operability with standardized products have already hit the market. Many Fast Ethernet pre-standard products were inter-operable with the standard. So it is expected that most pre-standard Gigabit Ethernet products will also be compatible with the standard. This is possible because many of the companies that have come out with products are also actively participating in the standardization process.
 

List of references
 

 [1]  Billings Roger E. , Gigabit Networking, 30.10.1998 [referred 1.11.1999]
       <http://www.bicsi.org/BICSIreb/index.htm>

 [2]  Djumin Sadikin, Gigabit Networking: High-Speed Routing and Switching ,  12.08.1997 [referred 1.11.1999]
       <http://www.cis.ohio-state.edu/~jain/cis788-97/gigabit_nets/index.htm#2>

 [3] Gigabit Ethernet Alliance,The Alliance,12.07,1999 [referred 1.11.1999]
       < http://www.gigabit-ethernet.org/alliance/ >

 [4] Gigabit Ethernet Alliance, Gigabit ethernet migration [referred 1.11.1999]
       <http://www.gigabit-ethernet.org/technology/whitepapers/gige/migration.html>

 [5] Gigabit Ethernet Migration Path , 29.07.1998 [referred 1.11.1999]
        <http://www.bicsi.org/Path/index.htm>

 [6] Gigabit Ethernet Alliance, Gigabit ethernet technology [referred 1.11.1999]
       <http://www.gigabit-ethernet.org/technology/whitepapers/gige/technology.html>

 [7] Gigabit Ethernet,15.05.1998 [referred 1.11.1999]
       <http://webopedia.internet.com/TERM/G/Gigabit_Ethernet.html>

 [8] Gigabit Ethernet Alliance, Ethernet:The dominant network technology [referred 1.11.1999]
       <http://www.gigabit-ethernet.org/technology/whitepapers/gige/dominant.html>

 [9] McLean Michelle Rae , Gigabit Speeds Mandate Fix , Move to 1Gbps Ethernet keeps some network structure but
 requires key adaptations  [referred 1.11.1999]
       < http://www.wcmh.com/96sep/609c029a.html>

[10] Skorupa Joe & Prodan Georg, Battle of the Backbones: ATM vs. Gigabit Ethernet , April 1997
[referred 1.11.1999]
        <http://www.data.com/tutorials/backbones.html>
 

Further information:

 [1] NORDX/CDT, Gigabit Ethernet Copper or Fiber ,17.06.1998 [referred 1.11.1999]
       <http://www.bicsi.org/Paul/index.htm>

[2] Patridge Craig, Gigabit Networking, Addision-Wesley publishing company, 1993, 396 p, [referred 1.11.1999]

[3] Sauders Stephen , Data communications Gigabit ethernet handbook, McGraw-Hill, New York, 1998, p12, p84-87,
 p193, p286,  [referred 1.11.1999]

[4] Spurgeon Charles, Quick Reference Guides to 100 Mbps Fast Ethernet [referred 1.11.1999]
        < http://www.ots.utexas.edu/ethernet/descript-100quickref.html>

[5] Whitepapers, Gigabit Ethernet [referred 1.11.1999]
        <http://www.wirescope.com/whitepap/whitegig.htm>