TD(07)037. The 10th COST 290 MC Meeting. Technische Universität Wien Wien, Austria October 1 2, 2007

Size: px
Start display at page:

Download "TD(07)037. The 10th COST 290 MC Meeting. Technische Universität Wien Wien, Austria October 1 2, 2007"

Transcription

1 TD(07)037 The 10th COST 290 MC Meeting Technische Universität Wien Wien, Austria October 1 2, 2007 Performance of Wireless IEEE e-Based Devices with Multiple Hardware Queues Gabriel Lazar, Virgil Dobrota, Tudor Blaga Technical University of Cluj-Napoca, Communications Department Baritiu Street, Cluj-Napoca, Romania Tel/Fax: virgil.dobrota@com.utcluj.ro Abstract The network subsystem of the Linux kernel connects to the underlying device drivers through a single entry point. With the advent of wireless adapters with multiple hardware queues, this method of communication poses difficulties in enabling efficient usage of the multiqueue features and assuring cross-layer QoS interoperation. The paper also describes some of the problems that can appear when Linux traffic control is employed for devices that operate over links with variable output rates. A popular device driver for wireless cards based on the Atheros chipsets is analyzed with respect to its support for multiqueue features, in conjunction with a recent version of the Linux kernel. Keywords Linux traffic control, cross-layer quality of service, IEEE e, multiple hardware queues COST 290 :: Wi-QoST :: Traffic and QoS Management in Wireless Multimedia Networks

2 Performance of Wireless IEEE e-Based Devices with Multiple Hardware Queues Gabriel Lazar, Virgil Dobrota, Tudor Blaga Abstract The network subsystem of the Linux kernel connects to the underlying device drivers through a single entry point. With the advent of wireless adapters with multiple hardware queues, this method of communication poses difficulties in enabling efficient usage of the multiqueue features and assuring cross-layer QoS interoperation. The paper also describes some of the problems that can appear when Linux traffic control is employed for devices that operate over links with variable output rates. A popular device driver for wireless cards based on the Atheros chipsets is analyzed with respect to its support for multiqueue features, in conjunction with a recent version of the Linux kernel. 1. LINUX NETWORK SUBSYSTEM One of the important reasons responsible for the efficiency and flexibility of the Linux network subsystem is the architecture of the data structures that manages network packets. When a packet is passed from the application layer into the kernel space using sockets, a socket kernel buffer is created (called skb for short). The socket buffer is passed through each layer of the network stack before reaching the device driver in order to be transmitted. This data structure (struct sk_buff) plays a central role in the network implementation of the Linux kernel, and it represents a packet during its entire processing lifetime inside the kernel space. A socket kernel buffer matches a sending or received packet, depending on traffic direction. In the network architecture of the Linux kernel, the interface between protocols implemented in software and the network adapters is accomplished by the concept of network devices. A network device provides an abstraction from the technical properties of the network adapter and also a uniform interface to be used by the protocols from the upper layers. The net_device structure represents each network device inside the Linux kernel. All network devices are connected into a doubly linked list. The entry point to the list of registered devices is obtained by accessing the list head, which is the kernel variable dev_base. Each element in the list is a net_device instance that contains all information and function pointers for that device. One of the pointers stored in this structure is the queuing discipline associated with the packets transmitted through this network adapter (the qdisc item). The process of transmitting a packet through the kernel can be handled in several ways. In the normal transmission process, the protocol instances of the higher network layers will use the function dev_queue_xmit(skb) to send a packet. The network device is specified in the socket buffer structure by the skb->dev parameter. If there is no queue management defined for that device (the.enqueue operation is NULL), the packet is put immediately into the hardware queue through a call to the dev->hard_xmit_method() method, if the driver s 1

3 hardware Tx queue is not full (Fig. 1). Otherwise, without any queues defined above the hardware layer, the packet is lost before the reaching the medium. Fig. 1. skb transmission using dev_queue_xmit It is the hard_start_xmit method s responsibility to check the hardware queues status. When the hardware queue is full, netif_stop_queue should be called, the skb has to be refused for transmission and the return code is NETDEV_TX_BUSY [2]. 2. LINUX TRAFFIC CONTROL In normal conditions, each network device has associated a queue management implementation, in order not to rely solely on the device hardware queues. This offers not only an additional buffer space in the form of software queues, but an entire QoS implementation inside the Linux kernel through the use of custom schedulers, configurable queues and detailed packet classification methods. This traffic control subsystem is placed between the upper network protocols and the net_device interface. When the higher protocols send a packet for transmission, by calling dev_queue_xmit(skb), the socket buffer is placed in one of the output queues of the network device. This is accomplished by use of the method.enqueue of the qdisc item associated with the device. This method is responsible with selecting the queue (if more than one) and the position of the packet inside the selected queue. Handling of packets inside queues is done by qdisc_run and depends on the type of the packet scheduler associated with the queue discipline. In the case of a work-conserving-scheduler, qdisc_run will call qdisc_restart until either there are no more packets in the queue(s), or the network packets does not accept any more packets (through a netif_stop_queue call). Unless the device is stopped, qdisc_restart will use the.dequeue operation to extract a packet from the traffic control queue discipline(s) and call hard_start_xmit for the device [1]. 2

4 If a non-work-conserving-scheduler is used (e.g. a traffic shaper), packets are serviced using a special Tx Soft IRQ triggered by a scheduling timer (Fig.2). Fig. 2. skb transmission with traffic control The basic building block of Linux traffic control is the queue discipline. While some queue disciplines are simple and consist of just one queue with a simple FIFO scheduling algorithm, other are much more complicated and of a different nature. A classful qdisc such as PRIO contains classes in which traffic is sent according to the priority encoded in the packet or using traffic control filters. Each class of such a queue discipline can contain another class or a qdisc. As these internal disciplines can be also classful, a powerful hierarchy of traffic queues, schedulers and classifiers can be built (Fig.3). Fig. 3. Traffic control hierarchy To configure traffic control elements from user space, the tc program is used. This command-line configuration application is part of the iproute2 package. The necessary information is passed to and from the kernel using the NETLINK sockets interface [3]. 3

5 3. LINK CHARACTERISTICS AND TRAFFIC CONTROL EFFICIENCY An important component of any QoS architecture is the resource reservation concept. In the core nodes of a DiffServ network for example, per-hop behaviors (PHBs) are implemented in order to decide the class of traffic to which a packet belongs and its corresponding treatment in that router. For some type of traffic such as voice or video data, the end-to-end delay must be kept to a minimum each node will try to reserve handling speed for these flows, usually by scheduling multimedia packets to high-priority, separate and short queues. In addition, a minimum, guaranteed rate has to be reserved in order to keep packet loss to an accepted level for certain data flows. In addition, when priorities are employed, important traffic has to be limited to a maximum service rate, or the lower priority packets have big chances to remain in their queues without being serviced for a long time. Minimum and maximum rate guarantees for different flows or flow aggregates form the basis of the link sharing concept. But in order to accomplish link sharing through resource reservation, the service rate of the outgoing link must be not only known, but of a relatively constant value. For example, consider a link being shared by traffic belonging to three different flows of different priorities. The QoS requirements state that each flow must have a guaranteed rate of one third of the link capacity. If the output rate is known and of constant value, a classful Hierarchical Token Bucket (HTB) queue discipline with 3 classes can be employed at a Linux router, with a total shaping rate slightly lower than the outgoing link rate. This limitation ensures that, when the arrival rate is bigger than the service rate, the queues of the HTB will fill up, and not the hardware queues (as device buffers cannot be configured). Each class of traffic has a different priority and a service rate (accomplished through usage of tokens) of one third of the total HTB service rate. This is the common usage in the case of wired links, for which the outgoing rate is of an approximate constant value. In the case of links with variable capacity, the situation is more complex. If the HTB total service rate is set to a value close to the maximum link capacity, when the link rate is lower, the packets from the high priority class can starve the lower priority flows, as they use a third of the maximum link capacity, and not one third of the actual value. In addition, there will be packets stationed into the hardware queue(s); depending on the hardware type, this may conflict with the QoS policy set in the traffic control subsystem. On the other hand, if the HTB total service rate is set to a smaller value, when the link rate goes higher than this value, some part of the link capacity is wasted as traffic is shaped to the HTB rate. This is often the case of wireless links where Linux traffic control is not so efficient, as it implements static QoS rules. Using fixed rate QoS rules for non-work-conserving schedulers in the presence of variable rate links is not an effective solution. A QoS mechanism that works well even when the quality of the outgoing link is variable is traffic prioritization. Employment of a classful queue discipline such as PRIO, without any traffic shaping, can ensure that important packets reach the hardware queue(s) before low priority packets leave the PRIO queues. In this case, there can not be no fixed service rate guarantees. 4

6 4. DEVICES WITH MULTIPLE HARDWARE QUEUES Traditionally, network adapters used only one Tx hardware queue, associated with a FIFO scheduling policy. In order to implement more grained QoS policies, a different set of queues and schedulers is created and managed above the device driver by means of traffic control mechanisms. The intention is to keep the hardware queue empty as much as possible and rely on the queue disciplines associated with the device by the router administrator. With the advent of network devices with multiple hardware queues, two interrelated problems arise. The first one is caused by a design limitation in the Linux network subsystem, while the second is more conceptual in nature and involves cross-layer QoS issues. A. Linux Network Design Limitation The general rules to be implemented by a normal network device driver in order to place packets on the hardware Tx queue are: When hardware queue is full, the network driver calls netif_stop_queue; The qdisc scheduler will stop sending packets to the network card; If dev->hard_start_xmit is called in these conditions, the dequeued packet is is not accepted, a NETDEV_TX_BUSY code is returned and packet must be requeued at the above layer; When actual transmission takes place and there is room for packets in the hardware queue, the driver calls netif_start_queue. If a driver does not call netif_stop_queue when the internal queue is full, CPU usage will rise drastically as the queue discipline set up for the device will dequeue and requeue packets continuously without any knowledge of the state of the hardware queue. A well-behaved device driver uses netif_stop_queue and netif_start_queue to provide feedback to the network scheduler. When the network adapter has multiple hardware queues, with QoS support at the hardware level, the method of providing feedback presented above is not sufficient. For example, consider a device with two Tx hardware queues, intended for packets with different priorities (Fig.4). In the situation when the low priority hardware queue is full, if the driver calls the netif_stop_queue method, the high priority packets will also be blocked, as the Tx queue is stopped. If the driver does not call netif_stop_queue, each time a low priority packet arrives, the driver has to refuse the packet, returning it to the qdisc where it will be requeued only to start over again and thus consuming CPU resources. 5

7 Fig. 4. Network adapter with two Tx hardware queues B. Cross-Layer QoS Issues If the network adapter implements any form of QoS at the hardware level, traditional traffic control disciplines must take this into account, or risk loosing some important benefits. For example, in the wireless case, the IEEE e offers higher chances of transmission for packets placed in the Voice Access Category hardware queue [4]. Lack of correlation between QoS policies implemented at different layers on the transmission path can nullify its effects. In the current Linux network subsystem implementation, the qdisc interface is not aware of multiple hardware queues. A.dequeue operation does not have enough information coming from the device driver, in order to know what skb to dequeue from the configured queue discipline. In [2], the authors propose a generic solution which involves adding support for multi-queue features to the Linux network schedulers implemented in various queue disciplines and also to the multiqueue devices drivers. One additional requirement is that the stack will have to handle traffic from multiqueue and non-multiqueue devices in a transparent manner, with little or no additional overhead. The first part of the implementation exposes the number of hardware queues present in the device to the net_device structure, and enables manipulation of each queue s state by using a new set of methods netif_{start stop wake}_subqueue. The crosslayer QoS coordination was implemented by the authors in the PRIO queue discipline, where the prio_dequeue operation checks that the hardware queue mapped to the skb priority is running or full, each time a packet has to be dequeued from the qdisc. Because this solution modifies core parts of the kernel network stack, it is still discussed on various kernel related mailing lists and it is not currently integrated into the standard kernel versions. In order to preserve the current network stack software unmodified, an alternative solution involves the creation of a new set of queue disciplines, specifically designed and tied to a particular multiqueue device driver. 6

8 5. IMPLEMENTATION AND PRELIMINARY RESULTS Based on the considerations presented in the previous sections, a testbed was set up in a Linux environment, in order to measure the performance of a multiqueue enabled wireless adapter with hardware QoS extensions. The network adapter tested was an SMC wireless card based on the Atheros chipset AR5212, with four internal hardware queues, one for each access class defined in the IEEE802.11e standard. This chipset is supported in Linux by the MadWifi WLAN driver [5]. The Linux distribution installed on the test client machine was Fedora Core 6, with a kernel based on version and the wireless card device driver (MadWifi version ) implemented as a kernel module. The client machine was configured as a WLAN station connected to a Linksys Access Point, at a statically configured rate of 1Mbps (Fig. 5). Fig. 5. Testbed Multiqueue Wireless Client sending traffic at 1Mbps As the network stack of standard kernels is not multi-queue aware, one of the first goals was to find out what is the device driver behavior when one of its queues is full. The first possibility was that the driver would call netif_stop_queue, although the other queues are still able to receive packets, while the other possibility was that the driver would not stop the device from receiving the packets, even if some (but not all) of its queues are full. The source code of the driver was modified in order to log its behavior at congestion. Traffic with different priorities was generated using an UPD command line application, in order to provoke link congestion. As a first result, to our surprise, the driver did not answer to congestion in a proper way: even if a queue was full, the returned status in its.hard_start_xmit method was NETDEV_TX_OK instead of NETDEV_TX_BUSY, and the packet was simply dropped without being returned to the qdisc buffers. This solution completely bypassed any level 3 nonshaping QoS schedulers, because packets were serviced to the hardware queues at a very high speed rate, not correlated with the actual transmission rate. For example, a FIFO or a PRIO queue discipline attached to the device would have a null effect in this conditions, as it will be always empty. This issue was addressed in the MadWifi 1428 Ticket [6], but was not included by default in our tested device driver. All the subsequent tests were done after applying this patch to the MadWifi kernel module. The UDP traffic generator was configured to send datagrams with two different priorities. In the first test, the queue discipline attached to the device was FIFO with a maximum queue length of 7

9 20 packets, while in the second test, the queue discipline was changed to PRIO with four classes of traffic, each class containing a FIFO queue with a maximum length of 10 packets. Preliminary test results show that in both cases the Madwifi device driver does not call netif_stop_queue when a queue is full. In these conditions the packet is refused and has to be returned at the configured queue discipline. Because the qdisc does not know some of the queues are full, it will try to dequeue the packet again, causing an excessive number of.requeue operations and thus consuming most of the CPU resources (Fig. 6, 7). As the UDP traffic generator uses the blocking sendto library function, even at congestion, only the low priority hardware queue was filled. Thus, the high priority packets were not requeued. Requeue Calls Per Packet Requeue Operations Time [ ms ] Fig. 6..requeue operations with FIFO qdisc, LOW priority traffic Requeue Calls Per Packet Requeue Operations Time [ ms ] Fig. 7..requeue operations with PRIO qdisc, LOW priority traffic 8

10 Mean Values Inter-Layer Delay [ms].requeue operations Queue occupation [skb] PFIFO PRIO qdisc qdisc LOW HIGH LOW HIGH Table 1. Mean values 6. CONCLUSIONS The paper described some of the shortcomings in the implementation of the network subsystem in the recent Linux kernels and device drivers, in conjunction with wireless network adapters with multiple hardware queues. Measurements performed showed that, although the high priority packets were delivered faster than the low priority packets, the number of.requeue operations is excessive. As a next step, subsequent tests will be performed with the driver modified to call netif_stop_queue when one of its queues is full. This would eliminate the.requeue problem, but will introduce head-of-line blocking for packets of different priorities than the priority mapped to the full hardware queue that is blocking communication. A further goal involves measuring rate, loss and delay performance of packets with different priorities, for a multiqueue-enabled kernel and driver, in order to enable cross-layer QoS interoperation. REFERENCES [1] K. Wehrle, F. Pählke, H. Ritter, D. Müller and M. Bechler, The Linux Networking Architecture: Design and Implementation of Network Protocols in the Linux Kernel, August [2] Z.Yi and P.P.Waskiewicz, Jr., Enabling Linux Network Support of Hardware Multiqueue Devices, Proceedings of the Linux Symposium, pp , June [3] A. Kuznetsov and S.Hemminger, Iproute 2: a collection of utilities for controlling TCP/IP networking and Traffic Control in Linux, [4] IEEE e, Wireless LAN Medium Access Control (MAC) Enhancements for Quality of Service (QoS), e Standard, 2005 [5] Multiband Atheros Driver for Wireless Fidelity, [6] MadWifi Ticket #1428, ath_hardstart returns 0 even if queue is full, [7] Linux kernel mailing list archive, [8] Linux NetDev, 9

Performance of Wireless IEEE e-Based Devices with Multiple Hardware Queues

Performance of Wireless IEEE e-Based Devices with Multiple Hardware Queues Performance of Wireless IEEE 802.11e-Based Devices with Multiple Hardware Queues Gabriel Lazăr, Virgil Dobrotă, Member, IEEE, Tudor Blaga, Member, IEEE 1 Agenda I. Linux Network Subsystem II. Linux Traffic

More information

Cross-Layer Architecture for H.264 Video Streaming in Heterogeneous DiffServ Networks

Cross-Layer Architecture for H.264 Video Streaming in Heterogeneous DiffServ Networks Cross-Layer Architecture for H.264 Video Streaming in Heterogeneous DiffServ Networks Gabriel Lazar, Virgil Dobrota, Member, IEEE, Tudor Blaga, Member, IEEE 1 Agenda I. Introduction II. Reliable Multimedia

More information

Quality of Service Mechanism for MANET using Linux Semra Gulder, Mathieu Déziel

Quality of Service Mechanism for MANET using Linux Semra Gulder, Mathieu Déziel Quality of Service Mechanism for MANET using Linux Semra Gulder, Mathieu Déziel Semra.gulder@crc.ca, mathieu.deziel@crc.ca Abstract: This paper describes a QoS mechanism suitable for Mobile Ad Hoc Networks

More information

DiffServ over MPLS: Tuning QOS parameters for Converged Traffic using Linux Traffic Control

DiffServ over MPLS: Tuning QOS parameters for Converged Traffic using Linux Traffic Control 1 DiffServ over MPLS: Tuning QOS parameters for Converged Traffic using Linux Traffic Control Sundeep.B.Singh, Girish.P.Saraph, Chetan.P.Bhadricha and Girish.K.Dadhich Indian Institute of Technology Bombay,

More information

DiffServ over MPLS: Tuning QOS parameters for Converged Traffic using Linux Traffic Control

DiffServ over MPLS: Tuning QOS parameters for Converged Traffic using Linux Traffic Control 1 DiffServ over MPLS: Tuning QOS parameters for Converged Traffic using Linux Traffic Control Sundeep.B.Singh and Girish.P.Saraph Indian Institute of Technology Bombay, Powai, Mumbai-400076, India Abstract

More information

Linux Traffic Control

Linux Traffic Control Linux Traffic Control Author: Ivan Delchev Course: Networks and Distributed Systems Seminar Instructor: Prof. Juergen Schoenwaelder International University Bremen, Spring 2006 Processing of Network Data

More information

Quality of Service in the Internet

Quality of Service in the Internet Quality of Service in the Internet Problem today: IP is packet switched, therefore no guarantees on a transmission is given (throughput, transmission delay, ): the Internet transmits data Best Effort But:

More information

Multimedia Communication. Project 6: Intelligent DiffServ

Multimedia Communication. Project 6: Intelligent DiffServ Multimedia Communication Project 6: Intelligent DiffServ Preliminary Design and interface definition (2003-07-08) Steffen Moser - 1 / 9 - Necessary tasks of a DiffServ aware router: Classifying Marking

More information

Quality of Service in the Internet

Quality of Service in the Internet Quality of Service in the Internet Problem today: IP is packet switched, therefore no guarantees on a transmission is given (throughput, transmission delay, ): the Internet transmits data Best Effort But:

More information

Kernel Korner. Analysis of the HTB Queuing Discipline. Yaron Benita. Abstract

Kernel Korner. Analysis of the HTB Queuing Discipline. Yaron Benita. Abstract 1 of 9 6/18/2006 7:41 PM Kernel Korner Analysis of the HTB Queuing Discipline Yaron Benita Abstract Can Linux do Quality of Service in a way that both offers high throughput and does not exceed the defined

More information

Grandstream Networks, Inc. GWN7000 QoS - VoIP Traffic Management

Grandstream Networks, Inc. GWN7000 QoS - VoIP Traffic Management Grandstream Networks, Inc. GWN7000 QoS - VoIP Traffic Management Table of Contents INTRODUCTION... 4 DSCP CLASSIFICATION... 5 QUALITY OF SERVICE ON GWN7000... 6 USING QOS TO PRIORITIZE VOIP TRAFFIC...

More information

TD(08)006. The 11th COST 290 MC Meeting. Tampere University of Technology (TUT), Finland, May 27 28, WAN Emulator Software Tool

TD(08)006. The 11th COST 290 MC Meeting. Tampere University of Technology (TUT), Finland, May 27 28, WAN Emulator Software Tool TD(08)006 The 11th COST 290 MC Meeting Tampere University of Technology (TUT), Finland, May 27 28, 2008 WAN Emulator Software Tool Andrei Bogdan Rus, Virgil Dobrota Technical University of Cluj-Napoca,

More information

VoIP over wireless networks: a packet scheduling approach to provide QoS using Linux

VoIP over wireless networks: a packet scheduling approach to provide QoS using Linux VoIP over 82.11 wireless networks: a packet scheduling approach to provide QoS using Linux Terrence van Valkenhoef and Mishar Mahboob December 13, 25 Abstract In this work, we propose a layer three scheduler

More information

Basics (cont.) Characteristics of data communication technologies OSI-Model

Basics (cont.) Characteristics of data communication technologies OSI-Model 48 Basics (cont.) Characteristics of data communication technologies OSI-Model Topologies Packet switching / Circuit switching Medium Access Control (MAC) mechanisms Coding Quality of Service (QoS) 49

More information

Quality of Service in the Internet. QoS Parameters. Keeping the QoS. Leaky Bucket Algorithm

Quality of Service in the Internet. QoS Parameters. Keeping the QoS. Leaky Bucket Algorithm Quality of Service in the Internet Problem today: IP is packet switched, therefore no guarantees on a transmission is given (throughput, transmission delay, ): the Internet transmits data Best Effort But:

More information

Operating Systems. 17. Sockets. Paul Krzyzanowski. Rutgers University. Spring /6/ Paul Krzyzanowski

Operating Systems. 17. Sockets. Paul Krzyzanowski. Rutgers University. Spring /6/ Paul Krzyzanowski Operating Systems 17. Sockets Paul Krzyzanowski Rutgers University Spring 2015 1 Sockets Dominant API for transport layer connectivity Created at UC Berkeley for 4.2BSD Unix (1983) Design goals Communication

More information

Implementation of Differentiated Services over ATM

Implementation of Differentiated Services over ATM Implementation of Differentiated s over ATM Torsten Braun, Arik Dasen, and Matthias Scheidegger; Institute of Computer Science and Applied Mathematics, University of Berne, Switzerland Karl Jonas and Heinrich

More information

UNIVERSITY OF OSLO Department of Informatics. Implementing Rate Control in NetEm. Untying the NetEm/tc tangle. Master thesis. Anders G.

UNIVERSITY OF OSLO Department of Informatics. Implementing Rate Control in NetEm. Untying the NetEm/tc tangle. Master thesis. Anders G. UNIVERSITY OF OSLO Department of Informatics Implementing Rate Control in NetEm Untying the NetEm/tc tangle Master thesis Anders G. Moe 19th August 2013 Implementing Rate Control in NetEm Anders G. Moe

More information

Quality of Service (QoS) Computer network and QoS ATM. QoS parameters. QoS ATM QoS implementations Integrated Services Differentiated Services

Quality of Service (QoS) Computer network and QoS ATM. QoS parameters. QoS ATM QoS implementations Integrated Services Differentiated Services 1 Computer network and QoS QoS ATM QoS implementations Integrated Services Differentiated Services Quality of Service (QoS) The data transfer requirements are defined with different QoS parameters + e.g.,

More information

Real-Time Protocol (RTP)

Real-Time Protocol (RTP) Real-Time Protocol (RTP) Provides standard packet format for real-time application Typically runs over UDP Specifies header fields below Payload Type: 7 bits, providing 128 possible different types of

More information

CHAPTER 3 EFFECTIVE ADMISSION CONTROL MECHANISM IN WIRELESS MESH NETWORKS

CHAPTER 3 EFFECTIVE ADMISSION CONTROL MECHANISM IN WIRELESS MESH NETWORKS 28 CHAPTER 3 EFFECTIVE ADMISSION CONTROL MECHANISM IN WIRELESS MESH NETWORKS Introduction Measurement-based scheme, that constantly monitors the network, will incorporate the current network state in the

More information

EVALUATION OF QOS PARAMETERS FOR IPTV

EVALUATION OF QOS PARAMETERS FOR IPTV EVALUATION OF QOS PARAMETERS FOR IPTV Ancuta Sanda BUZILA, Gabriel LAZAR, Tudor BLAGA, Virgil DOBROTA Technical University of Cluj Napoca, Communications Department George Baritiu 26-28, 400027 Cluj-Napoca,

More information

Quality of Service (QoS)

Quality of Service (QoS) Quality of Service (QoS) The Internet was originally designed for best-effort service without guarantee of predictable performance. Best-effort service is often sufficient for a traffic that is not sensitive

More information

fair-queue aggregate-limit

fair-queue aggregate-limit Quality of Service Commands aggregate-limit aggregate-limit To set the maximum number of packets in all queues combined for VIP-distributed weighted fair queueing (DWFQ), use the aggregate-limit interface

More information

Implementation of a leaky bucket module for simulations in NS-3

Implementation of a leaky bucket module for simulations in NS-3 Implementation of a leaky bucket module for simulations in NS-3 P. Baltzis 2, C. Bouras 1,2, K. Stamos 1,2,3, G. Zaoudis 1,2 1 Computer Technology Institute and Press Diophantus Patra, Greece 2 Computer

More information

Configuring QoS. Finding Feature Information. Prerequisites for QoS

Configuring QoS. Finding Feature Information. Prerequisites for QoS Finding Feature Information, page 1 Prerequisites for QoS, page 1 Restrictions for QoS, page 3 Information About QoS, page 4 How to Configure QoS, page 28 Monitoring Standard QoS, page 80 Configuration

More information

Configuring QoS. Understanding QoS CHAPTER

Configuring QoS. Understanding QoS CHAPTER 29 CHAPTER This chapter describes how to configure quality of service (QoS) by using automatic QoS (auto-qos) commands or by using standard QoS commands on the Catalyst 3750 switch. With QoS, you can provide

More information

H3C S9500 QoS Technology White Paper

H3C S9500 QoS Technology White Paper H3C Key words: QoS, quality of service Abstract: The Ethernet technology is widely applied currently. At present, Ethernet is the leading technology in various independent local area networks (LANs), and

More information

PROTOCOLS FOR COMMUNICATION BETWEEN QOS AGENTS: COPS AND SDP

PROTOCOLS FOR COMMUNICATION BETWEEN QOS AGENTS: COPS AND SDP PROTOCOLS FOR COMMUNICATION BETWEEN QOS AGENTS: COPS AND SDP Daniel Zinca 1, Virgil Dobrota 1, Cristian-Mihai Vancea 1, Gabriel Lazar 1 Department of Communications Technical University of Cluj-Napoca

More information

Configuring QoS CHAPTER

Configuring QoS CHAPTER CHAPTER 34 This chapter describes how to use different methods to configure quality of service (QoS) on the Catalyst 3750 Metro switch. With QoS, you can provide preferential treatment to certain types

More information

Internetworking with Different QoS Mechanism Environments

Internetworking with Different QoS Mechanism Environments Internetworking with Different QoS Mechanism Environments ERICA BUSSIKI FIGUEIREDO, PAULO ROBERTO GUARDIEIRO Laboratory of Computer Networks, Faculty of Electrical Engineering Federal University of Uberlândia

More information

DiffServ Architecture: Impact of scheduling on QoS

DiffServ Architecture: Impact of scheduling on QoS DiffServ Architecture: Impact of scheduling on QoS Abstract: Scheduling is one of the most important components in providing a differentiated service at the routers. Due to the varying traffic characteristics

More information

Advanced Mechanisms for Available Rate Usage in ATM and Differentiated Services Networks

Advanced Mechanisms for Available Rate Usage in ATM and Differentiated Services Networks Advanced Mechanisms for Available Rate Usage in ATM and Differentiated Services Networks Roland Bless, Dirk Holzhausen, Hartmut Ritter, Klaus Wehrle Institute of Telematics, University of Karlsruhe Zirkel

More information

Sections Describing Standard Software Features

Sections Describing Standard Software Features 30 CHAPTER This chapter describes how to configure quality of service (QoS) by using automatic-qos (auto-qos) commands or by using standard QoS commands. With QoS, you can give preferential treatment to

More information

Configuring QoS CHAPTER

Configuring QoS CHAPTER CHAPTER 37 This chapter describes how to configure quality of service (QoS) by using automatic QoS (auto-qos) commands or by using standard QoS commands on the Catalyst 3750-E or 3560-E switch. With QoS,

More information

A DiffServ transport network to bring 3G access to villages in the Amazon forest: a case study

A DiffServ transport network to bring 3G access to villages in the Amazon forest: a case study A DiffServ transport network to bring 3G access to villages in the Amazon forest: a case study based on the EC FP7 project Wireless Technologies for isolated rural communities in developing countries based

More information

Traffic Engineering 2015/2016. Fernando M. Silva. Instituto Superior Técnico. QoS, Scheduling & priority queues.

Traffic Engineering 2015/2016. Fernando M. Silva. Instituto Superior Técnico. QoS, Scheduling & priority queues. Traffic Engineering 2015/2016 QoS, Scheduling & priority queues fernando.silva@tecnico.ulisboa.pt Instituto Superior Técnico Trafffic Engineering 2015/16 1 Outline Traffic optimization & QoS Scheduling

More information

Internet QoS 1. Integrated Service 2. Differentiated Service 3. Linux Traffic Control

Internet QoS 1. Integrated Service 2. Differentiated Service 3. Linux Traffic Control Internet QoS 1. Integrated Service 2. Differentiated Service 3. Linux Traffic Control weafon 2001/9/27 Concept of IntServ Network A flow is the basic management unit Supporting accurate quality control.

More information

Lottery Scheduling for Flexible and Fine-grained Bandwidth Management in Wireless LANs

Lottery Scheduling for Flexible and Fine-grained Bandwidth Management in Wireless LANs Lottery Scheduling for Flexible and Fine-grained Bandwidth Management in Wireless LANs Shravan Rayanchu Sharad Saha Department of Computer Sciences, University of Wisconsin, Madison, WI 537, USA {shravan,

More information

Lecture 24: Scheduling and QoS

Lecture 24: Scheduling and QoS Lecture 24: Scheduling and QoS CSE 123: Computer Networks Alex C. Snoeren HW 4 due Wednesday Lecture 24 Overview Scheduling (Weighted) Fair Queuing Quality of Service basics Integrated Services Differentiated

More information

Impact of End-to-end QoS Connectivity on the Performance of Remote Wireless Local Networks

Impact of End-to-end QoS Connectivity on the Performance of Remote Wireless Local Networks Impact of End-to-end QoS Connectivity on the Performance of Remote Wireless Local Networks Veselin Rakocevic School of Engineering and Mathematical Sciences City University London EC1V HB, UK V.Rakocevic@city.ac.uk

More information

Emulation of a Space Based Internet Communication Link: Design and Implementation. Sandhya Rallapalli Gary Minden

Emulation of a Space Based Internet Communication Link: Design and Implementation. Sandhya Rallapalli Gary Minden The University of Kansas Technical Report Emulation of a Space Based Internet Communication Link: Design and Implementation Sandhya Rallapalli Gary Minden ITTC-FY2003-24350-04 September 2002 Project Sponsor:

More information

Network Support for Multimedia

Network Support for Multimedia Network Support for Multimedia Daniel Zappala CS 460 Computer Networking Brigham Young University Network Support for Multimedia 2/33 make the best of best effort use application-level techniques use CDNs

More information

Before configuring standard QoS, you must have a thorough understanding of these items: Standard QoS concepts.

Before configuring standard QoS, you must have a thorough understanding of these items: Standard QoS concepts. Prerequisites for Quality of Service, on page 1 QoS Components, on page 2 QoS Terminology, on page 2 Information About QoS, on page 3 QoS Implementation, on page 4 QoS Wired Model, on page 8 Classification,

More information

Before configuring standard QoS, you must have a thorough understanding of these items:

Before configuring standard QoS, you must have a thorough understanding of these items: Finding Feature Information, page 1 Prerequisites for QoS, page 1 QoS Components, page 2 QoS Terminology, page 3 Information About QoS, page 3 Restrictions for QoS on Wired Targets, page 41 Restrictions

More information

TD(06) Management Committee and Technical Meeting. Delft, 9-10 February, 2006

TD(06) Management Committee and Technical Meeting. Delft, 9-10 February, 2006 5P P COST TD(06)010 th 290 Management Committee and Technical Meeting Delft, 9-10 February, 2006 Evaluating and Improving Alternative Multicast Solutions: CastGate and CastGate with PIM-SM Tudor Mihai

More information

Real-Time Networking for Quality of Service on TDM based Ethernet

Real-Time Networking for Quality of Service on TDM based Ethernet Real-Time Networking for Quality of Service on TDM based Ethernet Badri Prasad Subramanyan Master s Thesis Defense 26 th Jan 2005 Committee: Dr. Douglas Niehaus Dr. David Andrews Dr. Jerry James Presentation

More information

Advanced Computer Networks

Advanced Computer Networks Advanced Computer Networks QoS in IP networks Prof. Andrzej Duda duda@imag.fr Contents QoS principles Traffic shaping leaky bucket token bucket Scheduling FIFO Fair queueing RED IntServ DiffServ http://duda.imag.fr

More information

Internet Services & Protocols. Quality of Service Architecture

Internet Services & Protocols. Quality of Service Architecture Department of Computer Science Institute for System Architecture, Chair for Computer Networks Internet Services & Protocols Quality of Service Architecture Dr.-Ing. Stephan Groß Room: INF 3099 E-Mail:

More information

Configuring QoS CHAPTER

Configuring QoS CHAPTER CHAPTER 36 This chapter describes how to configure quality of service (QoS) by using automatic QoS (auto-qos) commands or by using standard QoS commands on the Catalyst 3750 switch. With QoS, you can provide

More information

Resource allocation in networks. Resource Allocation in Networks. Resource allocation

Resource allocation in networks. Resource Allocation in Networks. Resource allocation Resource allocation in networks Resource Allocation in Networks Very much like a resource allocation problem in operating systems How is it different? Resources and jobs are different Resources are buffers

More information

Worksheet 8. Linux as a router, packet filtering, traffic shaping

Worksheet 8. Linux as a router, packet filtering, traffic shaping Worksheet 8 Linux as a router, packet filtering, traffic shaping Linux as a router Capable of acting as a router, firewall, traffic shaper (so are most other modern operating systems) Tools: netfilter/iptables

More information

Mohammad Hossein Manshaei 1393

Mohammad Hossein Manshaei 1393 Mohammad Hossein Manshaei manshaei@gmail.com 1393 Voice and Video over IP Slides derived from those available on the Web site of the book Computer Networking, by Kurose and Ross, PEARSON 2 Multimedia networking:

More information

Lecture Outline. Bag of Tricks

Lecture Outline. Bag of Tricks Lecture Outline TELE302 Network Design Lecture 3 - Quality of Service Design 1 Jeremiah Deng Information Science / Telecommunications Programme University of Otago July 15, 2013 2 Jeremiah Deng (Information

More information

Performance Analysis of Stream Control Transmission Protocol

Performance Analysis of Stream Control Transmission Protocol Buletinul tiinific al Universitii "Politehnica" din Timioara Seria ELECTRONIC i TELECOMUNICAII TRANSACTIONS on ELECTRONICS and COMMUNICATIONS Tom 49(63), Fascicola 1-2, 2004 Performance Analysis of Stream

More information

QoS Featured Wireless Virtualization based on Hardware

QoS Featured Wireless Virtualization based on Hardware QoS Featured Wireless Virtualization based on 802.11 Hardware Cong Wang and Michael Zink Department of Electrical and Computer Engineering University of Massachusetts, Amherst, MA 01003 {cwang, zink} @ecs.umass.edu

More information

Lecture 13. Quality of Service II CM0256

Lecture 13. Quality of Service II CM0256 Lecture 13 Quality of Service II CM0256 Types of QoS Best Effort Services Integrated Services -- resource reservation network resources are assigned according to the application QoS request and subject

More information

A Preferred Service Architecture for Payload Data Flows. Ray Gilstrap, Thom Stone, Ken Freeman

A Preferred Service Architecture for Payload Data Flows. Ray Gilstrap, Thom Stone, Ken Freeman A Preferred Service Architecture for Payload Data Flows Ray Gilstrap, Thom Stone, Ken Freeman NASA Research and Engineering Network NASA Advanced Supercomputing Division NASA Ames Research Center Outline

More information

Testing IP Differentiated Services Implementations

Testing IP Differentiated Services Implementations Testing IP Differentiated Services Implementations Carlos Parada, Jorge Carapinha, Francisco Fontes, Solange Lima and Paulo Carvalho {carlos-f-parada, jorgec, fontes}@ptinovacao.pt, Portugal Telecom INovação,

More information

Sections Describing Standard Software Features

Sections Describing Standard Software Features 27 CHAPTER This chapter describes how to configure quality of service (QoS) by using automatic-qos (auto-qos) commands or by using standard QoS commands. With QoS, you can give preferential treatment to

More information

ip rsvp reservation-host

ip rsvp reservation-host Quality of Service Commands ip rsvp reservation-host ip rsvp reservation-host To enable a router to simulate a host generating Resource Reservation Protocol (RSVP) RESV messages, use the ip rsvp reservation-host

More information

Chapter -6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION

Chapter -6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION Chapter -6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION Chapter 6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION 6.1 Introduction Supporting Quality of Service

More information

A Linux Implementation of a Differentiated Services Router

A Linux Implementation of a Differentiated Services Router A Linux Implementation of a Differentiated Services Router Torsten Braun, Hans Joachim Einsiedler 1, Matthias Scheidegger, Günther Stattenberger, Karl Jonas 2, Heinrich J. Stüttgen 2 Institute of Computer

More information

ETSF10 Internet Protocols Transport Layer Protocols

ETSF10 Internet Protocols Transport Layer Protocols ETSF10 Internet Protocols Transport Layer Protocols 2012, Part 2, Lecture 2.2 Kaan Bür, Jens Andersson Transport Layer Protocols Special Topic: Quality of Service (QoS) [ed.4 ch.24.1+5-6] [ed.5 ch.30.1-2]

More information

DiffServ Architecture: Impact of scheduling on QoS

DiffServ Architecture: Impact of scheduling on QoS DiffServ Architecture: Impact of scheduling on QoS Introduction: With the rapid growth of the Internet, customers are demanding multimedia applications such as telephony and video on demand, to be available

More information

Quality of Service II

Quality of Service II Quality of Service II Patrick J. Stockreisser p.j.stockreisser@cs.cardiff.ac.uk Lecture Outline Common QoS Approaches Best Effort Integrated Services Differentiated Services Integrated Services Integrated

More information

Congestion Management Overview

Congestion Management Overview Congestion management features allow you to control congestion by determining the order in which packets are sent out an interface based on priorities assigned to those packets. Congestion management entails

More information

Congestion Control and Resource Allocation

Congestion Control and Resource Allocation Congestion Control and Resource Allocation Lecture material taken from Computer Networks A Systems Approach, Third Edition,Peterson and Davie, Morgan Kaufmann, 2007. Advanced Computer Networks Congestion

More information

Module objectives. Integrated services. Support for real-time applications. Real-time flows and the current Internet protocols

Module objectives. Integrated services. Support for real-time applications. Real-time flows and the current Internet protocols Integrated services Reading: S. Keshav, An Engineering Approach to Computer Networking, chapters 6, 9 and 4 Module objectives Learn and understand about: Support for real-time applications: network-layer

More information

CS519: Computer Networks. Lecture 5, Part 5: Mar 31, 2004 Queuing and QoS

CS519: Computer Networks. Lecture 5, Part 5: Mar 31, 2004 Queuing and QoS : Computer Networks Lecture 5, Part 5: Mar 31, 2004 Queuing and QoS Ways to deal with congestion Host-centric versus router-centric Reservation-based versus feedback-based Window-based versus rate-based

More information

CS 498: Network Systems Laboratory Laboratory Assignment 4: Implementation of AQM as Kernel Modules in Linux

CS 498: Network Systems Laboratory Laboratory Assignment 4: Implementation of AQM as Kernel Modules in Linux CS 498: Network Systems Laboratory Laboratory Assignment 4: Implementation of AQM as Kernel Modules in Linux I. Introduction Jennifer C. Hou and Honghai Zhang Department of Computer Science University

More information

Defining QoS for Multiple Policy Levels

Defining QoS for Multiple Policy Levels CHAPTER 13 In releases prior to Cisco IOS Release 12.0(22)S, you can specify QoS behavior at only one level. For example, to shape two outbound queues of an interface, you must configure each queue separately,

More information

A performance study of packet scheduling algorithms for coordinating colocated Bluetooth and IEEE b in a Linux machine

A performance study of packet scheduling algorithms for coordinating colocated Bluetooth and IEEE b in a Linux machine Title A performance study of packet scheduling algorithms for coordinating colocated Bluetooth and IEEE 82.11b in a Linux machine Author(s) Yip, HK; Kwok, YK Citation The 7th International Symposium on

More information

EE 122: Differentiated Services

EE 122: Differentiated Services What is the Problem? EE 122: Differentiated Services Ion Stoica Nov 18, 2002 Goal: provide support for wide variety of applications: - Interactive TV, IP telephony, on-line gamming (distributed simulations),

More information

Wireless Networks (CSC-7602) Lecture 8 (15 Oct. 2007)

Wireless Networks (CSC-7602) Lecture 8 (15 Oct. 2007) Wireless Networks (CSC-7602) Lecture 8 (15 Oct. 2007) Seung-Jong Park (Jay) http://www.csc.lsu.edu/~sjpark 1 Today Wireline Fair Schedulling Why? Ideal algorithm Practical algorithms Wireless Fair Scheduling

More information

What Is Congestion? Computer Networks. Ideal Network Utilization. Interaction of Queues

What Is Congestion? Computer Networks. Ideal Network Utilization. Interaction of Queues 168 430 Computer Networks Chapter 13 Congestion in Data Networks What Is Congestion? Congestion occurs when the number of packets being transmitted through the network approaches the packet handling capacity

More information

QoS Technology White Paper

QoS Technology White Paper QoS Technology White Paper Keywords: QoS, service model, IntServ, DiffServ, congestion management, congestion avoidance, queuing technology, traffic policing, traffic shaping, link efficiency mechanism.

More information

Principles. IP QoS DiffServ. Agenda. Principles. L74 - IP QoS Differentiated Services Model. L74 - IP QoS Differentiated Services Model

Principles. IP QoS DiffServ. Agenda. Principles. L74 - IP QoS Differentiated Services Model. L74 - IP QoS Differentiated Services Model Principles IP QoS DiffServ Differentiated Services Architecture DSCP, CAR Integrated Services Model does not scale well flow based traffic overhead (RSVP messages) routers must maintain state information

More information

Dropping Packets in Ubuntu Linux using tc and iptables

Dropping Packets in Ubuntu Linux using tc and iptables Dropping Packets in Ubuntu Linux using tc and... 1 Dropping Packets in Ubuntu Linux using tc and iptables By Steven Gordon on Tue, 18/01/2011-8:13pm There are two simple ways to randomly drop packets on

More information

Quality of Service (QoS)

Quality of Service (QoS) Quality of Service (QoS) EE 122: Intro to Communication Networks Fall 2007 (WF 4-5:30 in Cory 277) Vern Paxson TAs: Lisa Fowler, Daniel Killebrew & Jorge Ortiz http://inst.eecs.berkeley.edu/~ee122/ Materials

More information

Unit 2 Packet Switching Networks - II

Unit 2 Packet Switching Networks - II Unit 2 Packet Switching Networks - II Dijkstra Algorithm: Finding shortest path Algorithm for finding shortest paths N: set of nodes for which shortest path already found Initialization: (Start with source

More information

Announcements. Quality of Service (QoS) Goals of Today s Lecture. Scheduling. Link Scheduling: FIFO. Link Scheduling: Strict Priority

Announcements. Quality of Service (QoS) Goals of Today s Lecture. Scheduling. Link Scheduling: FIFO. Link Scheduling: Strict Priority Announcements Quality of Service (QoS) Next week I will give the same lecture on both Wednesday (usual ) and next Monday Same and room Reminder, no lecture next Friday due to holiday EE : Intro to Communication

More information

Cross-layer based adaptive wireless traffic control for per-flow and per-station fairness

Cross-layer based adaptive wireless traffic control for per-flow and per-station fairness RESEARCH Open Access Cross-layer based adaptive wireless traffic control for per-flow and per-station fairness Vasaka Visoottiviseth 1*, Akkasit Trunganont 1 and Siwaruk Siwamogsatham 2 Abstract In the

More information

of-service Support on the Internet

of-service Support on the Internet Quality-of of-service Support on the Internet Dept. of Computer Science, University of Rochester 2008-11-24 CSC 257/457 - Fall 2008 1 Quality of Service Support Some Internet applications (i.e. multimedia)

More information

Contents. QoS overview 1

Contents. QoS overview 1 Contents QoS overview 1 QoS service models 1 Best-effort service model 1 IntServ model 1 DiffServ model 1 QoS techniques overview 1 Deploying QoS in a network 2 QoS processing flow in a device 2 Configuring

More information

Topic 4b: QoS Principles. Chapter 9 Multimedia Networking. Computer Networking: A Top Down Approach

Topic 4b: QoS Principles. Chapter 9 Multimedia Networking. Computer Networking: A Top Down Approach Topic 4b: QoS Principles Chapter 9 Computer Networking: A Top Down Approach 7 th edition Jim Kurose, Keith Ross Pearson/Addison Wesley April 2016 9-1 Providing multiple classes of service thus far: making

More information

Internet Quality of Service: an Overview

Internet Quality of Service: an Overview Internet Quality of Service: an Overview W. Zhao and et al, Columbia University presented by 리준걸 2006.10.25 INC Lab, Seoul Nat l University Outline Introduce QoS framework IntServ DiffServ Detailed mechanism

More information

Networking Quality of service

Networking Quality of service System i Networking Quality of service Version 6 Release 1 System i Networking Quality of service Version 6 Release 1 Note Before using this information and the product it supports, read the information

More information

Distributed Queue Dual Bus

Distributed Queue Dual Bus Distributed Queue Dual Bus IEEE 802.3 to 802.5 protocols are only suited for small LANs. They cannot be used for very large but non-wide area networks. IEEE 802.6 DQDB is designed for MANs It can cover

More information

In-Band Flow Establishment for End-to-End QoS in RDRN. Saravanan Radhakrishnan

In-Band Flow Establishment for End-to-End QoS in RDRN. Saravanan Radhakrishnan In-Band Flow Establishment for End-to-End QoS in RDRN Saravanan Radhakrishnan Organization Introduction Motivation QoS architecture Flow Establishment Protocol QoS Layer Experiments and Results Conclusion

More information

Overview Computer Networking What is QoS? Queuing discipline and scheduling. Traffic Enforcement. Integrated services

Overview Computer Networking What is QoS? Queuing discipline and scheduling. Traffic Enforcement. Integrated services Overview 15-441 15-441 Computer Networking 15-641 Lecture 19 Queue Management and Quality of Service Peter Steenkiste Fall 2016 www.cs.cmu.edu/~prs/15-441-f16 What is QoS? Queuing discipline and scheduling

More information

DOWNLOAD OR READ : VOICE QUALITY QOS SECOND EDITION PDF EBOOK EPUB MOBI

DOWNLOAD OR READ : VOICE QUALITY QOS SECOND EDITION PDF EBOOK EPUB MOBI DOWNLOAD OR READ : VOICE QUALITY QOS SECOND EDITION PDF EBOOK EPUB MOBI Page 1 Page 2 voice quality qos second edition voice quality qos second pdf voice quality qos second edition voice quality qos second

More information

Problems with IntServ. EECS 122: Introduction to Computer Networks Differentiated Services (DiffServ) DiffServ (cont d)

Problems with IntServ. EECS 122: Introduction to Computer Networks Differentiated Services (DiffServ) DiffServ (cont d) Problems with IntServ EECS 122: Introduction to Computer Networks Differentiated Services (DiffServ) Computer Science Division Department of Electrical Engineering and Computer Sciences University of California,

More information

Chapter 4 NETWORK HARDWARE

Chapter 4 NETWORK HARDWARE Chapter 4 NETWORK HARDWARE 1 Network Devices As Organizations grow, so do their networks Growth in number of users Geographical Growth Network Devices : Are products used to expand or connect networks.

More information

Using Time Division Multiplexing to support Real-time Networking on Ethernet

Using Time Division Multiplexing to support Real-time Networking on Ethernet Using Time Division Multiplexing to support Real-time Networking on Ethernet Hariprasad Sampathkumar 25 th January 2005 Master s Thesis Defense Committee Dr. Douglas Niehaus, Chair Dr. Jeremiah James,

More information

UNIT 2 TRANSPORT LAYER

UNIT 2 TRANSPORT LAYER Network, Transport and Application UNIT 2 TRANSPORT LAYER Structure Page No. 2.0 Introduction 34 2.1 Objective 34 2.2 Addressing 35 2.3 Reliable delivery 35 2.4 Flow control 38 2.5 Connection Management

More information

CSCI Spring Final Exam Solution

CSCI Spring Final Exam Solution CSCI 4211 16Spring Final Exam Solution 1. When an IP packet arrives a router, how the router decides what is the next router (output link) this packet to be forwarded to? What are the routing table and

More information

The Network Layer and Routers

The Network Layer and Routers The Network Layer and Routers Daniel Zappala CS 460 Computer Networking Brigham Young University 2/18 Network Layer deliver packets from sending host to receiving host must be on every host, router in

More information

Lecture 14: Performance Architecture

Lecture 14: Performance Architecture Lecture 14: Performance Architecture Prof. Shervin Shirmohammadi SITE, University of Ottawa Prof. Shervin Shirmohammadi CEG 4185 14-1 Background Performance: levels for capacity, delay, and RMA. Performance

More information

Tutorial 9 : TCP and congestion control part I

Tutorial 9 : TCP and congestion control part I Lund University ETSN01 Advanced Telecommunication Tutorial 9 : TCP and congestion control part I Author: Antonio Franco Course Teacher: Emma Fitzgerald January 27, 2015 Contents I Before you start 3 II

More information