EnggRoom

Full Version: TCP-PR(TCP for persistent packet reordering)
You're currently viewing a stripped down version of our content. View the full version with proper formatting.
Abstract(IEEE paper-2003)

Most standard implementations of TCP perform poorly when packets are reordered. In this paper, we propose a new version of TCP that maintains high throughput when reordering occurs and yet, when packet reordering does not occur, is friendly to other versions of TCP. The proposed TCP variant, or TCP-PR, does not rely on duplicate acknowledgments to detect a packet loss. Instead, timers are maintained to keep track of how long ago a packet was transmitted. In case the corresponding acknowledgment has not yet arrived and the elapsed time since the packet was sent is larger than a given threshold, the packet is assumed lost. Because TCP-PR does not rely on duplicate acknowledgments, packet reordering (including out-or-order acknowledgments) has no effect on TCP-PR’s performance.

Due to the scheduling algorithms used, different packet sizes and arrivals times may result in the reordering of packets entering on a single interface. While the exact cause of packet reordering lies in the details of the scheduling algorithm, a more general reason is that parallel paths are employed for economic reasons; it is cheaper to build multiple moderate speed paths than a single very high-speed path. The result of seeking this increase in cost efficiency is that packets may sometimes be reordered. TCP-PR is a transport protocol compatible with multipath routing, hence it will not limit the drive for efficiency at the lower layers.