1 maze a hybrid p2p file sharing system design by networking and distributed system lab at peking...

35
1 Maze Maze A Hybrid P2P file A Hybrid P2P file sharing system sharing system Design by Networking and Design by Networking and distributed System lab distributed System lab at Peking University at Peking University Presenter:Elaine Presenter:Elaine

Upload: rodney-blake-higgins

Post on 04-Jan-2016

214 views

Category:

Documents


1 download

TRANSCRIPT

Page 1: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

1

MazeMazeA Hybrid P2P file sharing A Hybrid P2P file sharing

systemsystem

Design by Networking Design by Networking and distributed System and distributed System lab at Peking Universitylab at Peking University

Presenter:ElainePresenter:Elaine

Page 2: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

2

OutlineOutline• The design of Maze (USENIX Worlds’ 04)

• An Empirical Study of Free-Riding Behavior in the Maze P2P File-Sharing System (IPTPS’05 )

• Robust Incentives via Multilevel Tit-for-tat (IPTPS’06 )

• P2P search mechanism in Maze (ACM INFOSCALE '06)

Page 3: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

3

What is Maze?What is Maze?• One of the first large scale academic

P2P-file sharing system• More than 2,300,000 Registers• Peak moment: more than 100K users• Average per day:30K users• 13TB of data are exchanged daily

Page 4: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

4

Structure of MazeStructure of Maze

(5) Clients contcat to multiple replicas and perform “swarm download”

Page 5: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

5

What will central sever log?What will central sever log?• Metadata

– owner ID – file name– File type– Size

• Each transaction information

• User’s reputation point

Page 6: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

6

Specialty in MazeSpecialty in Maze• Central metadata indexing and query processing

• Social network– Download network– Friend network

• Eventually need to reduce the dependencies upon the central server.

• These friends form the bases over which we plan to add P2P search capabilities.

• Maze forum

• Incentive model

Page 7: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

7

Incentive modelIncentive model• Maze Points system

1. New users are initialized with 4096 points.2. Uploads: +1.5 points per MB uploaded3. Downloads: -1 point per MB downloaded within 10

0MB, -0.7 per additional MB between 100MB and 400MB, -0.4/MB between 400MB and 800MB,and -0.1 per additional MB over 800.

4. Downloads requests are ordered by T = requestTime− 3 logP∗ , where P is a user’s point total.

5. Users with P < 512 have a download bandwidth quota of 300Kb/s.

Page 8: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

8

An Empirical Study of Free-Riding Behavior in

the Maze P2P File-Sharing System

Page 9: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

9

• In-depth analysis of the effectiveness of the incentive policies and how users react to them

• Definition of Free-riding behavior– Peers who only download without

contributing.

Page 10: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

11

Statistics suggest the existence of Statistics suggest the existence of free-ridingfree-riding

• Results are analyzed using logs from 9/28 to 10/28.• server-like users• client-like users• The ratio is 4.4:1. • We found that client-like users are responsible for

51% downloads but only 7.5% uploads. • So, a big portion free-Riders exist!

Page 11: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

12

• Are they not capable to contribute ? Or not willing to contribute?– What factors contributes to the free-riding b

ehavior?

Page 12: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

13

When a user’s point is low..When a user’s point is low..

• He can do:– Legal

• Contribution

– Illegal• Whitewashing• Sybil’s attack

Page 13: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

14

• The only way that the free-riders can survive the Maze system without cheating is through contribution

– From 9/28~10/28, we found that the top 10% popular files account for more than 98.8% of total transfer traffic, and over half of which were downloads from the client-like user.

– So they got lots of popular files!

• They can easily make back their deficits provided that

1. The Maze system can quickly direct queries to them and

2. Their contents are available

Page 14: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

15

The central index sever is indeed a The central index sever is indeed a factor!factor!

– Currently, new content of a peer does not make into the index until a few days later

– Adding more indexing servers.

– A more complete solution is to implement the P2P searching in the future releases

Page 15: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

16

Do they hide the files?Do they hide the files?– The study in [6] shows that 70% of Gnutella users do not have

any files to share– The average number of shared files of client-like users is 491,

versus 281 of the server-likeusers– Not the case in Maze

Page 16: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

17

So what mainly made them So what mainly made them become free riders?become free riders?

• Users with positive point changes have longer session time, on average 2.89 times more than those with negative point changes (218 minutes versus 75 minutes)

Page 17: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

18

Brief SummaryBrief Summary• Points system is effective in general

– But can’t avoid free-riders using account whitewashing.

• Query and search mechanism, and we can accomplish it by installing P2P searching mechanism and/or increase the frequency of updating the central index.

• More savvy incentive policies (e.g. encourage people to increase their online session durations and punish whitewashing behavior

Page 18: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

19

Robust Incentives via Multi-level

Tit-for-tat

Page 19: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

20

;.;.;.;.

• Private History– Giving higher priority to peers with whom he has successfully

downloaded • Shared History

– Non-subjective• Looking at the overall contribution of a peer

– subjective• Reputation is given by all other peers, weighted by the

reputation of the assigning peers

Page 20: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

21

Existent cheatingExistent cheating

• We analyzed the complete log of all transactions in the Maze system over a one month period, more detail in [11]

– Besides the expected free riding behavior and user whitewashing

– User collusion• Pair-wise collusion• Spam account collusion

– a form of whitewashing that allows whitewashed points to be collected at a single user

Page 21: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

22

The limitation of other incentive The limitation of other incentive systemssystems

• Private history coverage problem.– A one month download log only enforces Tit- for-Ta

t to only 2% of a peer’s upload

– Peer have no opinion of the requesting peer. The blind uploads bring a lot of opportunity for free-riders.

Page 22: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

23

• Share history– The Eigentrust Algorithm– Terminology

• Local trust value: cij. The opinion that peer i has of peer j, based on past experience.

• Global trust value: ti. The trust that the entire system places in peer i.

P1

P3

P7

P4

P2

P5

P8

0

5.0

0

2.0

0

9.0

0

1

0

0

0

0

6.0

0

3.0

0

5.0

0

0

1

2.0

0

0

0

0

5.0

0

04.054.0

9.0

0

1

P1P5

P3

Page 23: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

24

The MathThe Math

j

jkij cccik

'

Page 24: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

25

The Eigentrust AlgorithmThe Eigentrust Algorithm

• Fortunately, if n is large, the trust vector ->ti will converge to the same vector for every peer i.

Page 25: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

26

EigenTrust problemEigenTrust problem• Also EigenTrust helps to punish colluders in M

aze • But suffers from both false negatives and false

positives

Page 26: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

27

False negativesFalse negatives• Leg hugger

– High reputation peers randomly download from a colluder

• Example– Larry is a spam account colluder t

hat we detected. , e.g. Most of Larry’s 30GBs uploads are to other colluders

– 200MB uploads to some reputable peers boosts his rank nearly 100 times Another 734KB upload to one super peer further promotes its rank to 6.6*10-5.

– Larry gets a higher rank than most of peers who upload more than 30GB to legitimate users

Page 27: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

28

False positiveFalse positive• Satellite networks

– Encourage peers in satellite networks download from outsede peers

Page 28: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

29

So, each of the above incentives has their So, each of the above incentives has their own weakness..own weakness..

• Private history– Coverage

• Shared history– Non-subjective

• Solve above,but• Collusion

– Subjective• Solve above,but• False positive• False negative

The multi-level Tit-for-tat!

Page 29: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

30

Designing Multi-Trust incentiveDesigning Multi-Trust incentive

• M be a N X N matrix that defines a one step Rank among peers, i.e., Mi,j is peer j’s rank from i’s perspective.

• The two step rank matrix (one level indirect trust) can be expressed as M2. The entry (M2)i;j aggregates other peers one step rank to yield the rank of j from i’s perspective.

• Imposes service differentiation by looking at which tier j falls into when its downloading request arrives at i.– The smaller level it belongs to, the higher priority it is given.– Within the same tier, two peers will be ranked according to their val

ues in the matrix of that tier.

Page 30: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

31

Coverage experimentCoverage experiment

• Measurement Metrics:– Trust upload ratio

• which is the volume of traffic that are served by either a M friend, or a friend that is either a {M or M2} friend, over the total traffic in the system

– Using one month traffic log, simulated with incentive mechanism of Multi-Trust and Tit-for-tat.

a.k.a Tit-for-tat

Page 31: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

32

Comparism to Eigentrust

• First, we use the completed transactions in our one month traffic log to calculate a set of ranking values for each peer.

• Next, the evaluator node extracts download requests for the following two week period, and statistically sorts the requesters into a service queue according to their local subjective ranking. Peers with lower queue positions are served first, i.e., higher ranked.

• Metric– peers’ queue positions

• Expected results– True colluders will have queue positions no earlier than EigenTrust,

whereas local distributors will move up

Page 32: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

33

Colluder punishmentColluder punishment

Page 33: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

34

Leg-huggerLeg-hugger

• Larry downloads from 73 peers in the two weeks following our one month traffic log

• It gets high rank in the EigenTrust because of his high rank friend.

• In multitrust his high reputable friend still helps him getting into 16 (22%) peers’ trust list, but overall he is punished in all the other peers.

Page 34: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

35

Satellite clusterSatellite cluster• Wayne is the local distributor in one cluster. It downlo

ads from 14 peers in the next two weeks, among them there are 11 external peers and 3 internal peers (peer 9, 10 and 13).

Page 35: 1 Maze A Hybrid P2P file sharing system Design by Networking and distributed System lab at Peking University Presenter:Elaine

36

Brief summaryBrief summary• Multi-trust performs no worse than EigenTrust

in punishing pairwise or spam account colluders.

• Meanwhile, it solves the two problems brought by EigenTrust– dropping the high rank of leg-hugger peer– rising the low rank of local distributor inside its ow

n satellite cluster