[Nrg-l] Reminder: NRG Talk: 20March 2006
evijay at cs.bu.edu
Mon Mar 20 16:34:46 EST 2006
Begin forwarded message:
> From: Vijay Erramilli <evijay at cs.bu.edu>
> Date: March 19, 2006 5:54:37 PM EST
> To: nrg-l at cs.bu.edu
> Subject: [Nrg-l] NRG Talk: 20March 2006
> Hi all,
> Extremely sorry for the late announcement, but Jorge
> will be presenting the following paper tomorrow(Monday) at NRG:
> "Tomography based Overlay Network Monitoring"
> -Yan Chen, David Bindel and Randy H. Katz
> The paper appeared at IMC 2003.
> When: 5:00PM, 20 March Monday 2006
> Where: Grad Lounge, Research Lab
> The abstract and link to the paper follow.
> Hope all of you can make it,
> Overlay network monitoring enables distributed Internet ap-
> plications to detect and recover from path outages and peri-
> ods of degraded performance within seconds. For an overlay
> network with n end hosts, existing systems either require
> O(n2) measurements, and thus lack scalability, or can only
> estimate the latency but not congestion or failures. Unlike
> other network tomography systems, we characterize end-to-
> end losses (this extends to any additive metrics, including
> latency) rather than individual link losses. We nd a mini-
> mal basis set of k linearly independent paths that can fully
> describe all the O(n2) paths. We selectively monitor and
> measure the loss rates of these paths, then apply them to es-
> timate the loss rates of all other paths. By extensively study-
> ing synthetic and real topologies, we nd that for reasonably
> large n (e.g., 100), k is only in the range of O(n log n). This
> is explained by the moderately hierarchical nature of Inter-
> net routing.
> Our scheme only assumes the knowledge of underlying IP
> topology, and any link can become lossy or return to normal.
> In addition, our technique is tolerant to topology measure-
> ment inaccuracies, and is adaptive to topology changes.
> Nrg-l mailing list
> Nrg-l at cs.bu.edu
More information about the Nrg-l