Presentation Date : 16 Nov Measuring Bandwidth between PlanetLab Nodes Sung-Ju Lee, Puneet Sharma, Sujata Banerjee, Sujoy Basu Hewlett-Packard Laboratories, Palo Alto, CA Rodrigo Fonseca University of California, Berkeley, CA Published in the proceedings of PAM 2005 – Passive & Active Measurement Workshop
Presentation Date : 16 Nov Outline 1. Goals 2. Measurement Experience on PlanetLab 3. Measurement analysis 4. Conclusions
Presentation Date : 16 Nov Goals To understand the bandwidth characteristic of network paths connecting PlanetLab nodes. To obtain insights into potential trends that will enable scalable bandwidth estimation.
Presentation Date : 16 Nov Measurement experience on PlanetLab A.Methodology They did not develop a new bandwidth estimation tool. Rather, they measure the bandwidth/capacity of the links by different available tools and report their findings. They collected 2 two sets of data at two different time periods. First set – Aug. 11th, 2004 – Sep. 6th, 2004 Second set – Jan. 5th, 2005 – Jan. 18th, 2005
Presentation Date : 16 Nov Measurement experience on PlanetLab B.Tools they tried Per-hop capacity estimation tools pathchar and pchar – they can’t build them on the current PlanetLab nodes that run a Linux kernel version pathchar and pchar can only support Linux kernel and 2.3 respectively. Clink – program hang, they suspect it’s also the problem of the Linux kernel version.
Presentation Date : 16 Nov Measurement experience on PlanetLab End-to-end capacity tools bprobe – works only on SGI Irix. SProbe – it doesn’t report any value as detecting cross traffic. pathrate – the only capacity estimation tool they can successfully run on Planetlab.
Presentation Date : 16 Nov Measurement experience on PlanetLab End-to-end available bandwidth tools pathload – they ran into an invalid argument error on connect. IGI – they get poor accuracy with high variance in the estimation of the same pair on sequential attempts. Spruce – more accurate results than the above two tools but it requires the knowledge of the capacity of the path.
Presentation Date : 16 Nov Measurement experience on PlanetLab End-to-end available bandwidth tools pathChirp – failed to run on the version 3 rollout of PlanetLab (first set of data is obtained by the old version 2 of PlanetLab). Between the two measurement periods, PlanetLab upgraded their software from version 2 to version 3.
Presentation Date : 16 Nov Measurement Analysis They use pathrate version for the first set of data. Some negative values are found, then they reported to the authors of pathrate and use 2.4.1b for the second measurement. The collected bottleneck capacity data on 12,006 network paths from 279 nodes in the first set data and 21,861 paths from 178 nodes for the second set.
Presentation Date : 16 Nov Measurement Analysis End-to-end capacity statistics Set 1Set 2 No. of nodes Measurement period 8/11/04~9/6/041/5/05~1/18/05 PlanetLab version Version 2Version 3 No. of pairs 12,00621,861 Min. capacity 0.1 Mbps0.3 Mbps Max. capacity Mbps682.9 Mbps Ave. capacity Mbps64.03 Mbps Median capacity 24.5 Mbps91.4 Mbps Std. deviation Mbps43.78 Mbps
Presentation Date : 16 Nov Measurement Analysis End-to-end capacity statistics Capacity (C) Set 1Set 2 No. of Paths Per(%) No. of Paths Per(%) C < 20 Mbps Mbps ≦ C<50Mbps Mbps ≦ C<80Mbps Mbps ≦ C<120Mbps Mbps ≦ C<200Mbps Mbps ≦ C<500Mbps Mbps ≦ C
Presentation Date : 16 Nov Measurement Analysis Bandwidth capacity for all pairs measured
Presentation Date : 16 Nov Measurement Analysis Capacity by regions (Mbps)
Presentation Date : 16 Nov Measurement Analysis They define asymmetry factor between two nodes i and j, α i,j, where BW i,j is the bottleneck bandwidth from node i to node j
Presentation Date : 16 Nov Measurement Analysis Asymmetry factor distribution
Presentation Date : 16 Nov Measurement Analysis – Temporal Analysis Comparison of End-to-end capacity statistics of common node pairs in Sets1 and 2. Set 1Set 2 No. of common pairs 3,409 Measurement period 8/11/04~9/6/041/5/05~1/18/05 PlanetLab version Version 2Version 3 Min. capacity 0.1 Mbps0.5 Mbps Max. capacity Mbps152.6 Mbps Ave. capacity Mbps71.09 Mbps Median capacity 24.3 Mbps97.3 Mbps Std. deviation Mbps39.32 Mbps
Presentation Date : 16 Nov Measurement Analysis – Temporal Analysis End-to-end capacity distribution of common node pairs in Sets 1 and 2
Presentation Date : 16 Nov Measurement Analysis – Temporal Analysis Asymmetry factor distribution of common pairs in Sets 1 and 2
Presentation Date : 16 Nov Measurement Analysis – Correlation Study Motivation: look for the relationship or trend between latency & bandwidth (capacity). The define two metrics for studying the capacity and latency correlation. Relative bandwidth correlation metric Relative bandwidth correlation penalty metric
Presentation Date : 16 Nov Measurement Analysis – Correlation Study Bandwidth/delay correlation
Presentation Date : 16 Nov Measurement Analysis – Correlation Study Cummulative distribution function of bandwidth/delay correlation Set 1.Set 2.
Presentation Date : 16 Nov Conclusions Present the analysis from the two sets of data. Show the problems of the deployments of the network measurement tools on PlanetLab. The capacity of paths may have an order of magnitude difference even when they are sourced from the same node and similarly for the same receiver. Paths between two nodes do net necessarily show capacity symmetry.
Presentation Date : 16 Nov Conclusions They observed bandwidth limit violations that may be caused by the inaccuracy of the tool itself. They also observed interplay between the traffic shaper for bandwidth limiting and the pathrate probing scheme. In some cases, they measured end-to-end capacity of 100 Mbps even though the source was bandwidth limited to 500 Kbps.