Floyd, R.W. (1987) private communication, June.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....student evaluations done at MSU. It was determined that TOP had helped the students with concepts, in that they answered qualitative test questions noticeably better than previous classes had. At NCA T in the Spring of 1999, three TOP modules and three WebTOP submodules were used by the professor [7] in a computer lab to demonstrate concepts, and the students worked with the modules on their own outside of class. 6. Conclusions and Future Work WebTOP represents a complete system for studying a variety of topics in optics. Upon completion, WebTOP will contain all of the TOP modules. Despite ....

Floyd James, private communication.

....Intuition suggests that ACK compression should indeed be associated with periods of reduced available bandwidth, since the compressed ACKs result from non empty queues on the return path. Increased queue length should increase the round trip time, thus decreasing the available bandwidth [5]. 20 OBSERVING TCP DYNAMICS IN REAL NETWORKS 0 4000 1000 2000 3000 time (seconds since start of connection) 0 1e 07 2e 06 4e 06 6e 06 8e 06 SEQ number (bytes) median ACK bw = 7269 bytes sec Figure 22: Connection with reduced average bandwidth associated with frequent ....

Sally Floyd. Private communication. 1991.

....TCP implementations. However, SACK is generally viewed as a method to address data recovery; it has not been widely investigated to address congestion control issues. Floyd pointed out that multiple segment losses can cause Reno TCP to lose its Self clock, resulting in a retransmission timeout [Flo95, Flo92]. These timeouts can cause a substantial performance degradation. During the timeout interval, no data is sent. In addition, the timeout is followed by a period of Slow start. This sequence of events underutilizes the network over several round trip times, which results in a significant ....

Sally Floyd, February 1992. Private communication.

....consistency tests (as described in Section 3) for ensuring that the total resources promised to the different partitions do not exceed the resources available at the node. 6. Related Work Sally Floyd and Van Jacobson have designed a scheme, the FJ scheme, for network resource partitioning [Floyd93]. Their primary motivation is to provide a service in which the virtual subnetworks are used by the network s managers to control and equitably distribute the available bandwidth between different entities. In FJ scheme, the network observes the data rates for different connections, and, when the ....

S. Floyd, Private communication, March 1993.

....resources in the immediate partition. This implies that the admission tests for advance reservations can be completely isolated from the admission tests for immediate channels. 5. Related Work Sally Floyd and Van Jacobson have designed a scheme, the FJ scheme, for network resource partitioning [7]. Their primary motivation is to provide a service in which the virtual subnetworks are used by the network s managers to control and equitably distribute the available bandwidth among different entities. In the FJ scheme, the network observes the data rates for different traffic classes, and, ....

S. Floyd, Private communication, March 1993.

No context found.

Floyd, R.W. (1987) private communication, June.

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