Sally Floyd. Issues in flexible resource management for datagram networks. In Proceedings of the 3rd Workshop on Very High Speed Networks, Maryland, March 1992.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....internetworking environment. Among them are the Stream Protocol Version II (ST II) 83] the Multipoint Congram oriented High performance Internet Protocol (MCHIP) 70] the Flow Protocol [96] a proposal for predicted service [17, 98] and a proposal for resource management in datagram networks [32]. However, none of these protocols provide both guaranteed bounded delay and bounded delay jitter services. In this chapter, we focus on the network layer data delivery protocol RTIP. RTIP provides a host to host, simplex, sequenced, unreliable, and guaranteed performance packet service. Some of ....

Sally Floyd. Issues in flexible resource management for datagram networks. In Proceedings of the 3rd Workshop on Very High Speed Networks, Maryland, March 1992.

.... have been the subjects of much discussion and research over the past several years Braden, Clark Shenker [Page 2] RFC1633 RFC.net Page 3 of 34 RFC 1633 Integrated Services Architecture June 1994 (the literature is much too large to list even a representative sample here; see the references in [CSZ92, Floyd92, Jacobson91, JSCZ93, Partridge92, SCZ93, RSVP93a] for a partial list) This work has led to the unified approach to integrated services support that is described in this memo. We believe that it is now time to begin the engineering that must precede deployment of integrated services in the Internet. Section 2 of this memo introduces the ....

Floyd, S., "Issues in Flexible Resource Management for Datagram Networks", Proceedings of the 3rd Workshop on Very High Speed Networks, March 1992.

....proposed in [CSZ92] unlike the guaranteed service mentioned in the same paper, which is based on deterministic bounds) does not offer a priori guarantees; thus, the quality of service that a client can obtain from it is not predictable. This is also the case of the approach described in [Flo92] whose differences from ours include its connectionless foundations and its discrete menu of service classes. 7 Conclusion The Tenet Group at the University of California at Berkeley and the International Computer Science Institute has been doing research in the field of multimedia ....

Sally Floyd. Issues in flexible resource management for datagram networks. In Proceedings of the 3rd Workshop on Very High Speed Networks, Maryland, March 1992.

....The simulations in this paper use gateways where there is one output queue for each output line, as in most gateways in current networks. RED gateways could also be used in routers with resource management where different classes of traffic are treated differently and each class has its own queue [6]. For example, in a router where interactive (TELNET) traffic and bulk data (FTP) traffic are in separate classes with separate queues (in order to give priority to the interactive traffic) each class could have a separate Random Early Detection queue. The general issue of resource management at ....

Floyd, S., "Issues in Flexible Resource Management for Datagram Networks", Proceedings of the 3rd Workshop on Very High Speed Networks, March, 1992.

....environment. Among them are: the Stream Protocol Version II (ST II) Top90] the Multipoint Congram oriend High performance Internet Protocol (MCHIP) Par90] the Flow Protocol [Zha89] a proposal for predicted service [CSZ92] and a proposal for resource management in datagram networks [Flo92] There have been two implementations of ST II [Seo91, PP91] but, to the best of our knowledge, no performance data have been reported. Also, to the best of our knowledge, none of the other proposed algorithms or protocols has been fully implemented yet. 6 Conclusion and Future Work We have ....

Sally Floyd. Issues in flexible resource management for datagram networks. In Proceedings of the 3rd Workshop on Very High Speed Networks, Maryland, March 1992.

....back off and let the audio take over which is probably not fair. Even so, when there is congestion, the resulting packet loss would impair the audio quality as well. Research is underway on DARTnet and elsewhere to develop resource management (or traffic control) algorithms to solve this problem [5,6,7]. These algorithms, running in the various levels of packet switches in the network, would give priority to real time traffic such as audio and video to achieve low delay and packet loss. At the same time, the algorithms would prevent real time traffic from using more than its fair share, as ....

S. Floyd, "Issues in Flexible Resource Management for Datagram Networks," presented at 3rd Workshop on Very High Speed Networks, March 1992.

....multipoint connections with statistical resource reservations and application oriented flow and error control. Because many research efforts (including our research group s work) are aimed at either creating new internet and transport protocols or extending existing ones to provide such services [5, 25, 9, 19, 23, 24, 18, 22, 11, 4], our assumptions about the underlying protocols are realistic. Application Layer. The specific class of applications targeted in this research include point to point as well as multipoint multimedia applications. Multimedia applications are characterized by their requirement for transport of ....

Floyd, S., "Issues in Flexible Resource Management for Datagram Networks," Preliminary Proceedings of Third Annual Workshop on Very High Speed Networks, Baltimore, pp. 238-250, March 1992. Universal Continuous Media I/O: Design and Implementation 23

....service, real time service, and controlled link sharing. The requirements and mechanisms for integrated services have been the subjects of much discussion and research over the past several years (the literature is much too large to list even a representative sample here; see the references in [CSZ92, Floyd92, Jacobson91, JSCZ93, Partridge92, SCZ93, RSVP93a] for a partial list) This work has led to the unified approach to integrated services support that is described in this memo. We believe that it is now time to begin the engineering that must precede deployment of integrated services in the Internet. Section 2 of this memo introduces the elements ....

Floyd, S., Issues in Flexible Resource Management for Datagram Networks, Proceedings of the 3rd Workshop on Very High Speed Networks, March 1992.

....the frequency with which the gateway drops packets also increases. There is no global synchronization. The higher throughput for the connections with shorter roundtrip times is due to the bias of TCP s window increase algorithm in favor of connections with shorter roundtrip times (as discussed in [6, 7]) For the simulation in Figure 3 the average link utilization is 76 . For the following second of the simulation, when all four sources are active, the average link utilization is 82 . This is not shown in Figure 3. triangle for RED, square for Drop Tail) Throughput ( Average ....

....The simulations in this paper use gateways where there is one output queue for each output line, as in most gateways in current networks. RED gateways could also be used in routers with resource management where different classes of traffic are treated differently and each class has its own queue [6]. For example, in a router where interactive (TELNET) traffic and bulk data (FTP) traffic are in separate classes with separate queues (in order to give priority to the interactive traffic) each class could have a separate Random Early Detection queue. The general issue of resource management at ....

Floyd, S., "Issues in Flexible Resource Management for Datagram Networks", Proceedings of the 3rd Workshop on Very High Speed Networks, March, 1992.

....the frequency with which the gateway drops packets also increases. There is no global synchronization. The higher throughput for the connections with shorter roundtrip times is due to the bias of TCP s window increase algorithm in favor of connections with shorter roundtrip times (as discussed in [6, 7]) For the simulation in Figure 3 the average link utilization is 76 . For the following second of the simulation, when all four sources are active, the average link utilization is 82 . This is not shown in Figure 3. triangle for RED, square for Drop Tail) Throughput ( Average Queue 0.4 ....

....The simulations in this paper use gateways where there is one output queue for each output line, as in most gateways in current networks. RED gateways could also be used in routers with resource management where different classes of traffic are treated differently and each class has its own queue [6]. For example, in a router where interactive (TELNET) traffic and bulk data (FTP) traffic are in separate classes with separate queues (in order to give priority to the interactive traffic) each class could have a separate Random Early Detection queue. The general issue of resource management at ....

Floyd, S., "Issues in Flexible Resource Management for Datagram Networks", Proceedings of the 3rd Workshop on Very High Speed Networks, March, 1992.

....the frequency with which the gateway drops packets also increases. There is no global synchronization. The higher throughput for the connections with shorter roundtrip times is due to the bias of TCP s window increase algorithm in favor of connections with shorter roundtrip times (as discussed in [6, 7]) For the simulation in Figure 3 the average link utilization is 76 . For the following second of the simulation, when all four sources are active, the average link utilization is 82 . This is not shown in Figure 3. Because RED gateways can control the average queue size while accommodating ....

....The simulations in this paper use gateways where there is one output queue for each output line, as in most gateways in current networks. RED gateways could also be used in routers with resource management where different classes of traffic are treated differently and each class has its own queue [6]. For example, in a router where interactive (TELNET) traffic and bulk data (FTP) traffic are in separate classes with separate queues (in order to give priority to the interactive traffic) each class could have a separate Random Early Detection queue. The general issue of resource management at ....

Floyd, S., "Issues in Flexible Resource Management for Datagram Networks", Proceedings of the 3rd Workshop on Very High Speed Networks, March, 1992.

No context found.

Sally Floyd. Issues in flexible resource management for datagram networks. In Proceedings of the 3rd Workshop on Very High Speed Networks, Maryland, March 1992.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC