traffic engineering methods

(redirected from Fair queuing)
Also found in: Wikipedia.

traffic engineering methods

There are a variety of traffic engineering methods that are used to regulate network traffic. Mostly dealing with queuing, they ensure that transmitted data are received in a timely manner. Following are the common methods. See traffic engineering, traffic shaping and traffic policing.

First-In, First-Out (FIFO) Queuing
First-Come, First-Served (FCFS) Queuing
The simplest queuing method. Packets are placed into a single queue and serviced in the order they were received.

Priority Queuing (PQ)
Each packet is assigned a priority and placed into a hierarchy of queues based on priority. When there are no more packets in the highest queue, the next-lower queue is serviced. The problem with this method is that lower-priority packets may get little attention.

Fair Queuing (FQ)
Each packet is assigned a type (flow) and placed into the queue for that type. All queues are serviced round-robin: a packet from one queue, a packet from the next and so on. FQ provides a more uniform service to all packet types than priority queuing (PQ).

Weighted Fair Queuing (WFQ)
Similar to fair queuing (FQ), except that queues are given priorities and can support variable-length packets.

Hierarchical Weighted Fair Queuing (HWFQ)
Similar to WFQ, but monitors traffic and evaluates current conditions to adjust queues. Uses worst-case packet delay as its evaluation metric.

Weighted Round Robin (WRR)
Class-Based Queuing (CBQ)
Custom Queuing (CQ)
Similar to fair queuing, packets are assigned a class (real time, file transfer, etc.) and placed into the queue for that class of service. Packets are accessed round-robin style, but classes can be given priorities. For example, four packets from a high-priority class might be serviced, followed by two from a middle-priority class and then one from a low-priority class.

Deficit Weighted Round Robin (DWRR)
A weighted round-robin (WRR) method that uses a deficit counter. A maximum packet size number is subtracted from the packet length, and packets that exceed that number are held back until the next visit of the scheduler.

TCP Rate Shaping (TRS)
This non-queuing method dynamically adjusts the TCP window size based on real-time evaluation of the traffic flows.
References in periodicals archive ?
Other router-based schemes such as Fair Queuing (FQ), Stochastic Fair Queuing (SFQ) and Deficit Round Robin (DRR), were developed to ensure fair access to network resources and to prevent a bursty flow from consuming more than its fair share.
LLQ was developed by Cisco to bring strict priority queuing (PQ) to class-based weighted fair queuing (CBWFQ).
Traditionally, FIFO (First in First out) was used for scheduling and RED (Random early detection) was used for packet dropping and to control the overall traffic flow.WFQ (Weighted Fair Queuing) scheduler was used to prioritize different flows to provide service guaranty.
Table 1 is shown various fair queuing algorithms, we can use these algorithms to offer the same opportunity to use common resources for users.
Our proposed class-based weighted fair queuing algorithm shows performance improvements in comparison with the other traditional approach.
LLQ scheduling is an enhancement of Class Based Weighted Fair Queuing CBWFQ in which one or more strict priority queues are integrated to solve latency issues in multimedia applications that makes it ideal for jitter and delay sensitive applications.
In [10] authors, designed an efficient fair queuing algorithm that was based on to overcome the issues of previous WRR and RR algorithms.
A fair queuing algorithm determines which flow to serve next so as to satisfy a certain fairness criterion [3].
Few of them are as following: Class Based Queue (CBQ), Faire Queue (FQ), Weight Faire Queue (WFQ), Generalized Processor Sharing (GPS), Worst-case Fair Weighted Fair Queuing (WF2Q), Deficit Round Robin (DRR), Deficit Transmission Time (DTT), Low Latency and Efficient Packet Scheduling (LLEPS), Credit Based SCFQ (CBSCFQ), Controlled Access Phase Scheduling (CAPS), Queue size Prediction-Computation of Additional Transmission (QP-CAT), Temporally-Weight Fair Queue (TWFQ), Contention-Aware Temporally fair Scheduling (CATS), and Decentralized-CATS (DCATS).
According to the company, the SMC8024L2 model comes in a 1u high chassis and is designed to handle high-bandwidth applications at speeds reaching up to 48Gb/s with a non-blocking single chip switching architecture providing Gigabit Ethernet switching.In addition, the SMC8024L2 features ACLs and 802.1x for secure network access, IP filtering, Quality of Service (QoS) with four levels of priority and weighted fair queuing. The unit is equipped with four combo ports that accept optional SX, LX or ZX SFP transceivers to provide the option for fiber connectivity, the company claims.