Project topics and materials
Get Complete Project Material File(s) Now! »
Preliminary Analysis and Issues
Given the black box approach based on passive measurement, several issues could undermine the significance of the results unless carefully dealt with. The first issue is that the NAPA-WINE peer induced a bias during the experiments. Recall that among NAPA-WINE peers there are several high-bandwidth peers, located in Europe only. Furthermore, all peers within the same institution are in the same LAN, and AS. This possibly represents an uncommon population subset. A quantification of the induced bias is given in Tab. 3.2. It reports the percentage of i) NAPAWINE peers over all peers observed during each experiment, and ii) bytes exchanged among NAPA-WINE peers over all exchanged bytes. Results are reported considering contributors only, or all peers. As first important remark, NAPA-WINE peers clearly prefer to exchange data among them. For example, considering contributors in the PPLive experiment, NAPA-WINE peers contribute to more than 3.5%of exchanged data, even if they represent less than 1%of the contributing peers. Similarly, they are about 10% and 30% of peers for SopCast and TVAnts respectively, but they contribute to 18% and 56% of exchanged bytes. We stress that by restricting the analysis to the set of peers other than NAPA-WINE, it will be possible to highlight and quantify which properties of the NAPA-WINE peers cause such a strong bias. To solve the issue concerning the induced bias, we introduce the set P′(p) ⊂ P(p). Subset P′(p) is constituted by the peers inP(p) excluding the NAPA-WINE peers, formally P′(p) = P(p) \W. We evaluate the preference metrics also over the filtered set, getting P′D, P′U ,B′D ,B′U , accordingly. Intuitively, restricting the observation to P′ is equivalent to consider peers not involved in the experiment. For example, we expect that a preference versus a metric noticed in the full contributor set should be noticeable also in the set deprived of NAPA-WINE peers. In case the bias is still evident, this means that the preference was not artificially induced by NAPA-WINE peers.
Another problem concerns the fact that it exists a correlation between the considered metrics: for example, peers within the same subnetwork (NET=1) traverse paths of zero hop (HOP=0), belong to the same Autonomous System (AS) and Country (CC) as well. It may be therefore difficult to properly isolate the impact of each metric. At the same time, this correlation is likely to hold for the NAPA-WINE peers mainly, since they form “clouds” of high-bandwidth PCs within the same LAN, CC, and AS. Considering the set P′, where the correlation related to the locality among peers is smaller, it will be possible to identify which metric has the highest impact. All the observed parameters can be evaluated considering separately the download and upload direction of traffic, e.g., we can observe from (to) which countries the NAPA-WINE peers prefer to download (upload) the content. Notice that, for HOP metric, we can only directly measure HOP(e, p), but not HOP(p, e) which can be in general different from HOP(e, p) due to Internet path asymmetry. However, we point out that the adoption of a coarse-granularity should minimize this issue. Indeed, it is likely that HOP(e, p) ∈ HOPP , then HOP(p, e) ∈ HOPP as well, i.e., it is unlikely that the reverse path HOP(p, e) is short when the direct path HOP(e, p) is long. Finally, note that to compute the SYM metric it is necessary to compare the amount of transmitted and received data between any pair of peers.
NET Awareness
We now evaluate the potential preference to exchange traffic with peers in the same subnet (NET). The set of peers in the same subnet includes only NAPA-WINE peers, i.e., P′ = ∅. Results show that also in this case, PPLive and TVAnts only exhibit NET awareness, for both upload and download directions. Indeed, about 10% and 18% of the bytes are received from about 1% and 7% of hosts which are in the same subnet respectively. Conversely, SopCast does not show any evidence of subnet awareness. However, the NET preference can be also enforced by the AS preference. Looking at the ratio between P over B for the AS and NET preferences, we observe that they are very similar. This points out that peers in the same autonomous system but not in the same NET are equally preferred as the peers in the same NET (and in the same AS). Therefore, the AS preference is stronger than the NET preference. Notice also that the AS locality is overall quite marginal, so that the majority of the traffic is still coming from other ASs. As such, there is large margin to improve the network friendliness of P2P-TV applications.
SYM Incentive Mechanism
Considering P2P file sharing applications, incentives mechanisms have been successfully introduced to improve system performance. For example, BitTorrent clients play a tit-for-tat game with other peers, so that the more a peer sends to a neighbor, the more it will receive from it. This enforces a sort of symmetry between the amount of bytes sent and received by peers. We explore whether there exists some incentive mechanism that enforces symmetry in P2PTV systems as well. Results are reported in Tab. 3.3: Even if we arbitrarily report SYM under the download section of the table, we recall that it is a metric that requires to compare the amount of traffic exchanged in both directions (upload and download) between two peers. Considering non NAPA-WINE peers, it emerges that only a small percentage (from 5% considering PPLive to 13% considering SopCast) of the links are symmetrical. Moreover, the amount of data exchanged between these peers is not predominant (less than 12%). This suggests that P2P-TV systems do not enforce any tit-for-tat like mechanism. Indeed, being the download rate constrained by the actual video rate, these systems are engineered in such a way that peers with limited upload capacity can receive the video stream anyway, even if they are not able to re-distribute it.
This is highlighted in Fig. 3.3, which reports the amount of transmitted versus received bytes considering contributing peers. Intuitively, if a tit-for-tat like incentive mechanism were implemented,
then a strong correlation should be observed so that points accumulate along the y = x diagonal. Log/log scale is used to better represent results. The area between the TX/RX=2 and TX/RX=1/2 lines corresponds to symmetrical exchanges as previously defined. Looking at Fig. 3.3, it can be seen that the wide majority of points fall outside this area, as already reported in Tab. 3.3. Only in the SopCast case, a cloud of points lies in the symmetry strip, though such points correspond to moderate amount of data (i.e., few thousand Bytes). Considering PPLive, we observe that a lot of points accumulate along the y = 10x line, corresponding to peers that mostly download data from the NAPA-WINE peers2. The dense points accumulating around y = 104 and x = 104 are also a consequence of a private mechanism of the application. Summarizing, no evidence of a symmetric tit-for-tat like incentive emerges for any system.
Table of contents :
1 Introduction
1.1 Foreword
1.2 The Big Picture
I Measuring network awareness
2 Preliminary discussion
2.1 Related Work
2.2 Passive Data Set
3 Passive Analysis
3.1 Preliminary Results
3.2 A Framework for Peer Selection Analysis
3.3 Experimental Results
3.4 Dynamics of Contacted Peers
3.5 Conclusions
4 Hybrid Analysis
4.1 Methodology
4.2 Experimental Results: Path-wise Metric
4.3 Experimental Results: Peer-wise metric
4.4 Conclusions
5 A comprehensive framework to test Network Awareness
5.1 Analysis Process
5.2 Features Definition
5.3 Metric Definition
5.4 Experimental Results
5.5 Conclusions
II Implementing network awareness
6 Simulation Analysis
6.1 Related work
6.2 Framework Description
6.3 Simulation Results: Impact of L7 and L3
6.4 Simulation Results: L3/L7 Interaction
6.5 Conclusions
7 Emulation Analysis
7.1 Related work
7.2 ModelNet-TE Emulator
7.3 Scenario and methodology
7.4 Experimental Results
7.5 Conclusions
8 Conclusions
8.1 Summary
8.2 Future Work
A List of publications
A.1 Published
A.2 Under Review
Bibliography
