Exploring the performance benefits of end-to-end path switching

Abstract

This paper explores the feasibility of improving the performance of end-to-end data transfers between different sites through path switching. Our study is focused on both the logic that controls path switching decisions and the configurations required to achieve sufficient path diversity. Specifically, we investigate two common approaches offering path diversity -multi-homing and overlay networks -and investigate their characteristics in the context of a representative wide-area testbed. We explore the end-to-end delay and loss characteristics of different paths and find that substantial improvements can potentially be achived by path switching, especially in lowering end-to-end losses. Based on this assessment, we develop a simple pathswitching mechanism capable of realizing those performance improvements. Our experimental study demonstrates that substantial performance improvements are indeed achievable using this approach. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Author(s)Shu

IP packet interleaving for UDP bursty losses

“…We also observe that the duration of such good and bad periods is generally between 50 and 100 s. Tests performed with other traffic profiles evidence the same behavior. This result, confirming previous results in literature [28], motivates our choice of evaluating the status of the network every 1 minute. Regarding the burstiness of the losses, 50% of the flows experience losses over this network scenario, and they can be divided in 4 classes.…”

“…4.2.1, to choose the measurement period we study the literature and we analyze the time behavior of the losses over the satellite network. In [28] the authors perform a long-term measurement campaign, and report the long-term delay and loss rate measured over different paths connecting the same hosts. The results show that there is high variability in the loss rate, and, if observed with a resolution of 1 minute (i.e.…”

CAM04-4: AS Path Inference by Exploiting Known AS Paths

“…Meanwhile, the information of AS Path length is also useful. An example is that Tao et al [14] shows that the AS Path length change dominates the end-to-end delay performance and can be utilized to estimate the end-to-end delay in the overlay network to choose the best relay nodes. Also, Gao et al [8] find that the AS path length information can help conduct ingress interdomain traffic engineering.…”

Dynamic overlay routing based on available bandwidth estimation: A simulation study

“…Overlay networks have been the subject of significant research and practical interest recently [1][2][3][4][5][6][7]. The initial motivation for overlay networks was mainly due to the following three shortcomings of the IP routing infrastructure (referred to as the native network).…”