1. Grid Computing, 7700
Guest !
Dr Ian Taylor

2. P2P and Grids Grid computing What is P2P Globus
Service-based Grid computing
Grids and P2P
What is P2P
Why P2P - history
P2P definition
Gnutella
Scalability

3. Grid Computing: Globus Tools GT2
Recap: consists of four elements:
Resource Management: to allocate resources provided by a Grid - GRAM
Data Management: involves accessing and managing data – GridFTP, GASS
Information Services: to provide information about Grid services - MDS
And of course:
Security: to provide authentication, delegation and authorization

4. Get To Know Your Grid
Foster I, Kesselman C and Tuecke S, (2001) The Anatomy of the Grid: Enabling Scalable Virtual Organizations
“The Grid is flexible, secure, coordinated resource sharing among dynamic collections of individuals, institutions, and resources
The concept of Virtual Organisations

5. A Globus Grid Middleware (Globus) Users/Clients Internet Routing GSI
X. 509 VO VO
Resources
MDS
GRAM
MDS
Middleware
(Globus)
MDS
GridFTP
Mutual Authentication
Single Sign-on VO

6. Web Service Client Server (WSDL) XML (SOAP) = XML + Envelope Web
Interface
(WSDL)
(SOAP) =
XML + Envelope
A program sends a request to a remote Web service containing an XML message and (optionally) receives a response. The specifics about how such services
are represented, advertised, discovered and communicated with
are all defined by Web service standards, such as WSDL, UDDI and SOAP,
described later in this chapter.

7. OGSA + WSRF Open services Grid Architecture (OGSA)
Web services -> Grid services = "a Web service that provides a set of well-defined interfaces and that follows specific conventions”
The implementation:
WSRF - Web Services Resource Framework
- Adding (stateful) resources to Web services
WSDL
GRAM
GridFTP
MDS
Data Replica
OGSA

8. Globus V.4 Services Web (WSRF) Middleware (Globus) Users/Clients
Internet
Routing
GSI
X. 509 VO VO
Services
Web
(WSRF)
Resources
MDS
GRAM
MDS
Middleware
(Globus)
MDS
GridFTP
Mutual Authentication
Single Sign-on VO

9. P2P Interface P2P (XML?) Jxta,P2PS, Middleware Users/Clients Internet
Routing
GSI?
X. 509
Group
Group
Interface
P2P
(XML?)
Resources
Rendezvous
Nodes
Jxta Pipes
Servents
Jxta,P2PS,
Middleware
Super
Peers?
Gnuella
Single Sign-on?
Authorization?
Grouping Mechanisms

10. P2P and Grids? Are the converging? Yes!
Scalability: P2P has address scalable networks
Decentralized: P2P Super peer nets
Many architecture are movning this way
File Services: Bittorrent, GRID Torrent??
Etc …
Ok, so what’s P2P

11. What’s Exciting ? 0.5 Billion currently ‘Connected Devices’
With a CPU capability more than 100 times that of an early 1990s supercomputer
Gartner Group – 90% of CPU power is wasted
Mobile Devices - 1 billion currently, estimated 1.5 billion within 5 years. Capability is increasing
Potential demonstrated by – so far used 1 million years of CPU time
Feb2003: press release: United Devices are using their meta-processor to help US DoD to find a cure for smallpox
Leveraging previously unused resources
P2P research is concerned in addressing some of the key difficulties of current distributed computing:
scalability
reliability
interoperability.
2 Million Machines
Department of defence

12. Historical P2P
Peer to Peer (P2P) - originally used to describe the communication of two peers.
The internet started as peer to peer system e.g. ARPANET
goal - to share computing resources around the USA using different networks
UCLA, SRI, Utah and Santa Barabara
all had equal status – P2P
From late 1960’s until 1994, machines were assumed to be switch on, connected and had an IP address assigned
Then, invention of Mosaic and WWW led to a different type of user….
For example, a telephone conversation is peer to peer. In fact, the internet started as peer to peer
telephone conversation is peer to peer.
In fact, the internet started as peer to peer system
Its challenge was to connect a set of distributed resources, using different network connectivity, within one common network architecture
dial-up modems
Clients
IP addresses changing
unpredictable
The 1990's Client-Server Internet
Late 1990’s Naptser, then Gnutella 2000 – the new P2P

13. Modern Peer to Peer
What is an P2P application?
P2P is a class of applications that takes advantage of resources e.g. storage, cycles, content, human presence, available at the edges of the Internet – Clay Shirky
Computers/devices “at the edges of the internet” are those:
Operating within transient environments - computers come and go frequently
They can be behind a firewall or NAT systems
Have to operate outside of DNS
Often have to deal with differing transport protocols, devices and operating systems

14. Application P2P Network
A P2P Network
Application
P2P Network
NAT
Firewall
Bluetooth
TCP/IP
TCP/IP
HTTP
TCP/IP XP
Linux

15. Example 2: File Sharing with Napster
Launched in May 1999, by Shawn Fanning (19) and Sean Parker (20)
Allowed Users to MP3 Files - compression format, good quality but 1/12th original size
April 2000 – Metallica starts law suit – Huge and long court case
November 2000 – Napster has 38 Million members
July 2001 – Napster ordered offline, June 2002 bankrupt
Brokered/Hybrid P2P
Main Server
File List:
UserC song.mp3
UserD another.mp3
…..
1. Construct Database
Users connect to Napster Server
Server builds up a list of available songs and locations
3. Server searches database. Finds song on User C’s machine
User B …
User A
2. User A searches for song.mp3
4. Server informs User A of the location of song.mp3
April 13, 2000: Heavy metal rock group Metallica sues Napster for copyright infringement and racketeering. Rapper Dr. Dre files suit two weeks later.
May 3, 2000: Metallica drummer Lars Ulrich and the band's attorney produce list of more than 335,000 Internet user names of people the band says are illegally sharing their songs using Napster.
May 5, 2000: U.S. District Judge Marilyn Hall Patel rules that Napster is not entitled to "safe harbor" under the Digital Millennium Copyright Act.
July 26, 2000: Patel grants the RIAA's request for a preliminary injunction and orders Napster shut down.
July 28, 2000: The 9th U.S. Circuit Court of Appeals stays the lower court injunction, ruling that "substantial questions" were raised about the merits and form of Patel's injunction.
Oct. 2, 2000: Appeals court hears oral arguments.
Oct. 31, 2000: Napster announces partnership with Bertelsmann AG to develop a membership-based distribution system that would guarantee payments to artists. Under the deal, Bertelsmann agrees to drop lawsuit against Napster and make its music catalog available to Napster, while gaining the right to buy a stake in the service.
Feb. 12, 2001: In a clear victory for the recording industry, the 9th Circuit Court of Appeals rules that Napster must prevent its subscribers from gaining access to content on its search index that could potentially infringe copyrights.
Feb. 20, 2001: Napster offers $1 billion to record companies if they drop their suit. The recording industry scoffs at the offer.
Feb. 21, 2001: 9th Circuit Appeals Court orders Napster to cease trading copy written songs. First, the U.S. District Court for Northern California must rewrite its injunction closing Napster.
March 2, 2001: As a concession, Napster lawyer offers that the service will install software over the weekend to partially satisfy the order to stop trading copy written songs. Lawyer David Boies says the software would block trading of a million songs that had been singled out in months past by record labels and artists including Dr. Dre and Metallica. But those songs are still being traded after the weekend.
June 26, 2001: A group of 150 British independent record labels sign on to be a part of Napster's upcoming subscription service.
December 10, 2001: appeal failed
December 11, 2001: EMI launch MusicNet a subscription service & Sony/ Universal's Pressplay launches subscription service.
March 2002: Appeal failed
May: 2002: Bertelsmann acquires Napster's assets and commits to paying $8 million to cover Napster's debts.
June: 2002: Napster files for Chapter 11 bankruptcy
User D
(Another.mp3)
User C
(Song.mp3)
5. User A connects to User C and downloads song.mp3

16. GNU: Recursive Acronym
The ‘Animal’ GNU: Either of two large African antelopes (Connochaetes gnou or
C. taurinus) having a drooping mane and beard, a long tufted tail,
and curved horns in both sexes. Also called wildebeest.
GNU: Recursive Acronym
GNU’s Not Unix …. +
Gnutella =
GNU
Nutella
Nutella: a hazelnut chocolate spread produced by the Italian confectioner Ferrero ….

17. + AOL History Of Gnutella Gnutella, GNU GPL, 0.56 (Feb 2000) Gnullsoft
Gnutella IRC
#gnutella
gnutella.nerdherd.net
Open Source
Developers
(Bryan Mayland)
Gnutella
Spec
Justin Frankel +
Tom Pepper
NullSoft

18. We are Geeky and Rich !
And now I am trying to be cool … and writing songs …

19. Gnutella is a protocol for distributed search
What is Gnutella? ?
Gnutella is a protocol for distributed search
peer-to-peer comms
decentralized model
No third party lookup
Two stages :
Join Network … later
Use Network
Discover other peers
Search other peers
Gnutalla networks are dumb.
Just a bunch of nodes connected together with 3 or 4 connections each
What’s the only way they can communicate??
- They have to asked their neighbours – and then ask their neighbours to ask their neighbours
- peers provide client-side interfaces for issuing queries and viewing search results AND accept search queries from other peers
Due to its distributed nature, a network of Gnutella nodes is highly fault-tolerant i.e. operation of the network will not be interrupted if a subset go offline.

20. Searching a Gnutella Network: Broadcasting
3-D Cayley Tree
Shape 24 is Laptop, Group 25 is the GnuCache Appearing
Oval 30 is sending the message to GnuCache
Group 21 is the Gnutella node appearing
Searching in Gnutella involves broadcasting a Query message to all connected peers. Each connected peer will send it to their connected peers (say 3) and so on. Typically, this search will run 7 hops. If the number of connected peers, c=3 and the hops i.e. TTL=7 then the total number of peers searched (in a fully connected network) will be:
S = c + c2 +c3 + ….. ch = = 3279 Nodes

21. Searching a Gnutella Network: From one Node
Shape 24 is Laptop, Group 25 is the GnuCache Appearing
Oval 30 is sending the message to GnuCache
Group 21 is the Gnutella node appearing

22. Searching a Gnutella Network: All nodes
Shape 24 is Laptop, Group 25 is the GnuCache Appearing
Oval 30 is sending the message to GnuCache
Group 21 is the Gnutella node appearing

23. Social Networks
Stanley Milgram (Harvard professor) – 1967 social networking experiment
How many ‘social hops’ would it take for messages to traverse through the US population (200 million)
Posted 160 letters randomly chosen people in Omaha, Nebraska
Boston
Omaha
Asked them to try to pass these letters to a stockbroker working in Boston, Massachusetts
Rules:
use intermediacies whom they know on a first name basis
chosen intelligently
make a note at each hop
He posted 160 letters to randomly chosen people living in Omaha, Nebraska and asked them to try to pass these letters to a stockbroker he knew working in Boston, Massachusetts. The rules were that they could only pass the letter to intermediaries known to them on a first-name basis. Such intermediaries should be chosen intelligently so that they might bring the letter closer to the stockbroker. For example, this decision could be because they may know someone who is geographically closer e.g. they may know someone in Illinois, or that they may know someone who may know someone who lives near Boston. Therefore, the friend given the letter would pass it on to another friend, and so on until the letter reached someone who knew the target personally and could give it to him directly. At each stage of the journey the intermediaries noted their details on the package.
In the end, 42 letters made it through to the stockbroker. The interest fact was that the average number of hops (i.e. through intermediaries) each letter passed through was 5.5. The Milgram experiment demonstrated concretely for the first time what has become popularly known as the small-world effect. This phenomenon is familiar to anybody who has used the expression “small world, isn’t it!” upon discovering a mutual acquaintance shared with a stranger.
42 letters made it !!
Average of 5.5 hops
Demonstrated the ‘small world effect’
Proved that the social network of the United States is indeed connected with a path-length (number of hops) of around 6 – The 6 degrees of separation !
Does this mean that it takes 6 hops to traverse 200 million people??

24. Lessons Learned from Milgrim’s Experiment
Social circles are highly clustered
A few members have wide-ranging connections
these form a bridge between far-flung social clusters
this bridging plays a critical role in bringing the network closer together
For example
A quarter of all letters passed through a local storekeeper
A half were mediated by just 3 people
He posted 160 letters to randomly chosen people living in Omaha, Nebraska and asked them to try to pass these letters to a stockbroker he knew working in Boston, Massachusetts. The rules were that they could only pass the letter to intermediaries known to them on a first-name basis. Such intermediaries should be chosen intelligently so that they might bring the letter closer to the stockbroker. For example, this decision could be because they may know someone who is geographically closer e.g. they may know someone in Illinois, or that they may know someone who may know someone who lives near Boston. Therefore, the friend given the letter would pass it on to another friend, and so on until the letter reached someone who knew the target personally and could give it to him directly. At each stage of the journey the intermediaries noted their details on the package.
In the end, 42 letters made it through to the stockbroker. The interest fact was that the average number of hops (i.e. through intermediaries) each letter passed through was 5.5. The Milgram experiment demonstrated concretely for the first time what has become popularly known as the small-world effect. This phenomenon is familiar to anybody who has used the expression “small world, isn’t it!” upon discovering a mutual acquaintance shared with a stranger.
Lessons Learned
These people acted as gateways or hubs between the source and the wider world
A small number of bridges dramatically reduces the number of hops

25. From Social Networks to Computer Networks…
There are a number of similarities to social networks
People = peers
Intermediaries = Hubs, Gateways or Rendezvous Nodes (JXTA speak...)
Number of intermediaries passed through = number of hops
Are P2P Networks Special then?
P2P networks are more like social networks than other types of computer network because they are often:
Self Organizing
Ad-Hoc
Employ clustering techniques based on prior interactions (like we form relationships)
Decentralized discovery and communication (like we form neighbourhoods, villages, cities etc)

26. Decentralized
Gnutella
Freenet
Internet routing

27. Centralized + Decentralized
New Wave of P2P
Clip2 Gnutella Reflector (next)
FastTrack
KaZaA
Morpheus
Like Social Networks perhaps ?

28. The Gnutella Network Today
The figure below is a view of the topology of a Gnutella network as shown on the LimeWire web site, the popular Gnutella file-sharing client. Notice how the power-law or centralized-decentralized structure is demonstrated.