Bandwidth and Throuhgput

Bandwidth and Throuhgput

A major disadvantage of Ethernet 802.3 networks is collisions. Collisions occur when two hosts transmit frames simultaneously. When a collision occurs, the transmitted frames are corrupted or destroyed. The sending hosts stop sending further transmissions for a random period, based on the Ethernet 802.3 rules of CSMA/CD.
Because Ethernet has no way of controlling which node will be transmitting at any time, we know that collisions will occur when more than one node attempts to gain access to the network. Ethernet's resolution for collisions does not occur instantaneously. Also, a node involved in a collision cannot start transmitting until the matter is resolved. As more devices are added to the shared media the likelihood of collisions increases. Because of this, it is important to understand that when stating the bandwidth of the Ethernet network is 10 Mb/s, full bandwidth for transmission is available only after any collisions have been resolved. The net throughput of the port (the average data that is effectively transmitted) will be considerably reduced as a function of how many other nodes want to use the network. A hub offers no mechanisms to either eliminate or reduce these collisions and the available bandwidth that any one node has to transmit is correspondingly reduced. As a result, the number of nodes sharing the Ethernet network will have effect on the throughput or productivity of the network.

Collision Domains

When expanding an Ethernet LAN to accommodate more users with more bandwidth requirements, the potential for collisions increases. To reduce the number of nodes on a given network segment, you can create separate physical network segments, called collision domains.

The network area where frames originate and collide is called the collision domain. All shared media environments, such as those created by using hubs, are collision domains. When a host is connected to a switch port, the switch creates a dedicated connection. This connection is considered an individual collision domain, because traffic is kept separate from all other traffic, thereby eliminating the potential for a collision. The figure shows unique collision domains in a switched environment. For example, if a 12-port switch has a device connected to each port, 12 collision domains are created.
As you now know, a switch builds a MAC address table by learning the MAC addresses of the hosts that are connected to each switch port. When two connected hosts want to communicate with each other, the switch uses the switching table to establish a connection between the ports. The circuit is maintained until the session is terminated. In the figure, Host A and Host B want to communicate with each other. The switch creates the connection that is referred to as a microsegment. The microsegment behaves as if the network has only two hosts, one host sending and one receiving, providing maximum utilization of the available bandwidth.

Switches reduce collisions and improve bandwidth use on network segments because they provide dedicated bandwidth to each network segment.

Network Latency

Latency is the time a frame or a packet takes to travel from the source station to the final destination. Users of network-based applications experience latency when they have to wait many minutes to access data stored in a data center or when a website takes many minutes to load in a browser. Latency has at least three sources.

First, there is the time it takes the source NIC to place voltage pulses on the wire, and the time it takes the destination NIC to interpret these pulses. This is sometimes called NIC delay, typically around 1 microsecond for a 10BASE-T NIC.

Second, there is the actual propagation delay as the signal takes time to travel through the cable. Typically, this is about 0.556 microseconds per 100 m for Cat 5 UTP. Longer cable and slower nominal velocity of propagation (NVP) result in more propagation delay.

Third, latency is added based on network devices that are in the path between two devices. These are either Layer 1, Layer 2, or Layer 3 devices. These three contributors to latency can be discerned from the animation as the frame traverses the network.
Latency does not depend solely on distance and number of devices. For example, if three properly configured switches separate two computers, the computers may experience less latency than if two properly configured routers separated them. This is because routers conduct more complex and time-intensive functions. For example, a router must analyze Layer 3 data, while switches just analyze the Layer 2 data. Since Layer 2 data is present earlier in the frame structure than the Layer 3 data, switches can process the frame more quickly. Switches also support the high transmission rates of voice, video, and data networks by employing application-specific integrated circuits (ASIC) to provide hardware support for many networking tasks. Additional switch features such as port-based memory buffering, port level QoS, and congestion management, also help to reduce network latency.

Switch-based latency may also be due to oversubscribed switch fabric. Many entry-level switches do not have enough internal throughput to manage full bandwidth capabilities on all ports simultaneously. The switch needs to be able to manage the amount of peak data expected on the network. As the switching technology improves, the latency through the switch is no longer the issue. The predominant cause of network latency in a switched LAN is more a function of the media being transmitted, routing protocols used, and types of applications running on the network.