Where P2P ? … over the clouds … into the clouds … aside the clouds?  <ul><li>R. Minerva, A. Manzalini, C. Moiso </li></ul>
P2P Technology (a simple view)  <ul><li>P2P Pros ... </li></ul><ul><ul><li>P2P system resources are often &quot;free&quot;...
P2P as a complementary technology for Cloud Computing ?  <ul><li>P2P “techniques are often useful in building datacenter-s...
Or as an Alternative ? P2P Range of Applicability … Distributed Computing File Sharing Collaboration Platforms Communicati...
Are Operators out of the emerging trend of the (Data) Service/Platform/Infrastructure as a Service ?
The Prevalent Paradigm For Services Is Client - Server <ul><li>Client Server paradigm is used in Web Interactions </li></u...
P2P Computing as a competitor of Client Server?  Capacity (HD System) =   (b i , s i , f i , p i ) Where: b i  = bandwid...
www.gapinvoid.com A Few Issues
Example of Projects trying to overcome P2P Cons ... The nanodatacenter  (http://www.nanodatacenters.eu/)
Autonomic Computing  <ul><li>What is it? (from wikipedia) </li></ul><ul><ul><li>IBM has defined the following four functio...
Example Of Waste Of Resources <ul><li>Actually a p2p Overlay Network is considered “infrastructure-less”, but ...  </li></...
Application of Gossiping Algorithm to FCAPS areas  (courtesy of CASCADAS) <ul><li>fault detection and recovery </li></ul><...
Simulation snapshots (from Cascadas) State of  Nodes  with distributed LB Legenda: Nodes  available to get traffic Nodes  ...
Cross Layer Design: The End Of The OSI Model??  http://www.uni-marburg.de/fb12/verteilte_systeme/forschung/adhoc_routing_e...
A glimpse to the future ...  <ul><li>DirecNet: A group of industry players is proposing an  open-standard  directional net...
Leveraging the TELCO infrastructure   www.gapinvoid.com
Incipit <ul><li>Positive Dilemmas : Network Operators should investigate disruptive scenarios for Future Communications an...
Architectural vision and principles All rights reserved
Next: Open Questions <ul><li>Which mix of networking and computing paradigms and technologies will enable the scenario (ch...
Further contacts <ul><li>roberto.minerva@telecomitalia.it  </li></ul><ul><li>[email_address] </li></ul><ul><li>[email_addr...
Upcoming SlideShare
Loading in …5
×

Cloud Camp Milan 2K9 Telecom Italia: Where P2P?

858
-1

Published on

Telecom Italia Future Centre envisions a P2P infrastructure supporting the Cloud

Published in: Technology, Sports
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
858
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
28
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

Cloud Camp Milan 2K9 Telecom Italia: Where P2P?

  1. 1. Where P2P ? … over the clouds … into the clouds … aside the clouds? <ul><li>R. Minerva, A. Manzalini, C. Moiso </li></ul>
  2. 2. P2P Technology (a simple view) <ul><li>P2P Pros ... </li></ul><ul><ul><li>P2P system resources are often &quot;free&quot;, coming from individuals which volunteer their machines' CPUs, storage, and bandwidth </li></ul></ul><ul><li>... and Cons </li></ul><ul><ul><li>P2P systems lack a centralized administrative entity that owns and controls the peer resources. This makes it hard to ensure high levels of availability and performance. </li></ul></ul><ul><ul><li>Decentralized control also limits trust. Users can inspect the memory and storage of a running application, meaning that applications cannot safely store confidential information unencrypted on peers. Nor can the application developer count on any particular quantity of resources being dedicated on a machine, or on any particular reliability of storage. These obstacles have made it difficult to monetize p2p services. It should come as no surprise that, so far, the most successful p2p applications have been free, with Skype being a notable exception. </li></ul></ul><ul><ul><li>The freeriding phenomenon (and the tragedy of commons) </li></ul></ul>Excerpts from http://berkeleyclouds.blogspot.com/
  3. 3. P2P as a complementary technology for Cloud Computing ? <ul><li>P2P “techniques are often useful in building datacenter-scale applications, including datacenter-scale applications that are hosted in the cloud” </li></ul><ul><li>Actually the Key-Value Store techniques are often exploited by big data centers </li></ul><ul><ul><li>Amazon Dynamo (see http://www.allthingsdistributed.com/2007/10/amazons_dynamo.html) </li></ul></ul><ul><ul><li>Google </li></ul></ul><ul><ul><li>Pando, Abacast, ... </li></ul></ul>Excerpts from http://berkeleyclouds.blogspot.com/ App 1 App 2 … Appl m DISTRIBUTED APPLICATIONS Node 1 Node 2 … Node n DISTRIBUTED HASH TABLE put (H(key), value); get (H(key), data); H(Key) is a hashing function of the Key
  4. 4. Or as an Alternative ? P2P Range of Applicability … Distributed Computing File Sharing Collaboration Platforms Communication DataStorage Search Engine Dark nets <ul><li>Freenet </li></ul><ul><li>F2F </li></ul><ul><li>GNUnet </li></ul><ul><li>… </li></ul><ul><li>[email_address] </li></ul><ul><li>… </li></ul><ul><li>Gnutella </li></ul><ul><li>Kazaa </li></ul><ul><li>Bit Torrent </li></ul><ul><li>… </li></ul><ul><li>Jabber </li></ul><ul><li>… </li></ul><ul><li>Skype </li></ul><ul><li>… </li></ul><ul><li>OceanStore </li></ul><ul><li>BitVault </li></ul><ul><li>Peeriodata </li></ul><ul><li>… </li></ul><ul><li>JXTA </li></ul><ul><li>Peers Toolkit </li></ul><ul><li>… </li></ul><ul><li>YACY </li></ul><ul><li>… </li></ul>P2P Systems
  5. 5. Are Operators out of the emerging trend of the (Data) Service/Platform/Infrastructure as a Service ?
  6. 6. The Prevalent Paradigm For Services Is Client - Server <ul><li>Client Server paradigm is used in Web Interactions </li></ul><ul><li>New Services are taking advantage of this consolidated technology </li></ul><ul><ul><li>Rich Internet Application </li></ul></ul><ul><ul><li>Cloud Computing </li></ul></ul><ul><ul><li>And others... </li></ul></ul><ul><li>But ... Can the Data Centers grow forever? </li></ul><ul><ul><li>Google maintains over 450,000 servers (estimates) </li></ul></ul><ul><ul><li>http://www.tnl.net/blog/2004/04/30/ how-many-google-machines / </li></ul></ul><ul><ul><li>Google Data Centers: $3,000 A Square Foot? </li></ul></ul><ul><ul><li>http://www.datacenterknowledge.com/archives/2007/11/12/google-data-centers-3000-a-square-foot/ </li></ul></ul><ul><ul><li>Estimates of the power required for over 450,000 servers range upwards of 20 megawatts , which cost on the order of US$2 million per month in electricity charges </li></ul></ul>Web Client (Browser) Web Client (Browser) Web Client (Browser) Internet Web Server http http http http
  7. 7. P2P Computing as a competitor of Client Server? Capacity (HD System) =  (b i , s i , f i , p i ) Where: b i = bandwidth of node i s i = storage of node i f i = files of node i p i = processing of node i Capacity (Centralized System) = {b S , s S , f S , p S } Where: b S = bandwidth of the Server System s S = storage of the Server System f S = files stored in the Sever System p S = processing in the Server System Optimization is a problem Optimization is a function of a business model
  8. 8. www.gapinvoid.com A Few Issues
  9. 9. Example of Projects trying to overcome P2P Cons ... The nanodatacenter (http://www.nanodatacenters.eu/)
  10. 10. Autonomic Computing <ul><li>What is it? (from wikipedia) </li></ul><ul><ul><li>IBM has defined the following four functional areas: </li></ul></ul><ul><ul><ul><li>Self-Configuration </li></ul></ul></ul><ul><ul><ul><li>Self-Healing </li></ul></ul></ul><ul><ul><ul><li>Self-Optimization </li></ul></ul></ul><ul><ul><ul><li>Self-Protection </li></ul></ul></ul><ul><li>Autonomic Networking follows the concept of Autonomic Computing . Its ultimate aim is to apply autonomic concepts to Networks. </li></ul><ul><li>Functions of an Autonomic Network: </li></ul><ul><ul><li>Autognostic, Configuration management, Policy management, Autodefense, Security </li></ul></ul><ul><ul><li>Connection Fabric (i.e., The connection fabric supports the interaction with all the elements and sub-systems of the autonomic system) </li></ul></ul><ul><li>Principles of Autonomic Networking </li></ul><ul><ul><li>Compartmentalization (how to implement the operational rules and administrative policies for a given communication context) </li></ul></ul><ul><ul><li>Function re-composition </li></ul></ul><ul><ul><li>Atomization </li></ul></ul><ul><ul><li>Closed control loop </li></ul></ul>http://www-03.ibm.com/servers/eserver/zseries/zos/sm/autonomic.html Why? Millions of pervasive nodes!! There is the need of a new approach Users should be “bothered” by such a cumbersome task!
  11. 11. Example Of Waste Of Resources <ul><li>Actually a p2p Overlay Network is considered “infrastructure-less”, but ... </li></ul><ul><ul><li>In reality it is using the network infrastructure ... </li></ul></ul><ul><ul><li>Without optimization </li></ul></ul><ul><ul><li>E.g., two nodes seen as adjacent by the p2p network can be very far each other. T-Lab suggests mechanisms to improve the situation </li></ul></ul><ul><li>There is the need to manage the network resources in order to give a fair service to ALL the users. </li></ul><ul><li>There is the need to cooperate </li></ul><ul><li>Needs for interoperability: means definition of common protocols and functions </li></ul>Overlay Net See for instance http://www.cambridge-mit.org/project/home/default.aspx?objid=2313 P4P and IETF ALTO are trying to solve these problems
  12. 12. Application of Gossiping Algorithm to FCAPS areas (courtesy of CASCADAS) <ul><li>fault detection and recovery </li></ul><ul><li>for each contract of type T there is a “back-up” contract, to be used if B fails; </li></ul><ul><li>the nodes in achieving(T) updates the back-up contract in case B’ fails; </li></ul><ul><li>the nodes in contracting(T) help A in case B and B’ fails; </li></ul><ul><li>load balancing </li></ul><ul><li>when B’ is under-loaded, B’ informs all its neighbors in achieving(T); </li></ul><ul><li>if B, one of the neighbors of B’, is overloaded, it answers to B’ by accepting the offer; </li></ul><ul><li>when A, with an active contract with B, sends a new request, B informs A to redirect its contract to B’; </li></ul><ul><li>Usable as the “stand-by” algorithm for power saving </li></ul>
  13. 13. Simulation snapshots (from Cascadas) State of Nodes with distributed LB Legenda: Nodes available to get traffic Nodes in “normal load” Nodes in “overload” State of Nodes without LB Thanks to A. Manzalini, C. Moiso
  14. 14. Cross Layer Design: The End Of The OSI Model?? http://www.uni-marburg.de/fb12/verteilte_systeme/forschung/adhoc_routing_emul <ul><li>Wireless Networks are pushing for a closer cooperation of functions in order to better respond to a fast changing communication environment: </li></ul><ul><ul><li>Reflective middleware (able to adapt) </li></ul></ul><ul><ul><li>Cross Layer Design (ability to get the relevant information from any OSI layer) </li></ul></ul><ul><ul><li>No Network Transparency </li></ul></ul><ul><ul><li>Protocol dependence of the middleware </li></ul></ul><ul><ul><li>Cognitive Layer (it can perceive current network conditions, and then plan, decide and act on those conditions) </li></ul></ul>
  15. 15. A glimpse to the future ... <ul><li>DirecNet: A group of industry players is proposing an open-standard directional networking system designed to provide 1-gigabit-per-second data communication with anyone in a network on the ground, in the air or at sea, within hundreds of miles . The planned mobile mesh network , known as DirecNet, will use a network-friendly data link waveform to provide secure Internet Protocol communications up to 1 gbps for all types of air and surface platforms. DirecNet would use fast-steered directional antennas to substantially boost link power and operating range, and to permit reuse of radio frequency (RF) spectrum . Any DirecNet node can serve as a relay . This will multiply connectivity and extend the range to beyond line of sight.”( http://www.military-information-technology.com/print_article.cfm?DocID =1539 ) </li></ul><ul><ul><li>The DirecNet™ Task Force anticipates the completion of the specification within 2 years ( https://www.opengroup.org/conference-live/uploads/40/11007/Forum_Reports.pdf#search=%22goals%20direcnet%20military%22 ) </li></ul></ul>
  16. 16. Leveraging the TELCO infrastructure www.gapinvoid.com
  17. 17. Incipit <ul><li>Positive Dilemmas : Network Operators should investigate disruptive scenarios for Future Communications and Services in order to be aware of how to transform their biz models and exploit network and service infrastructures; </li></ul><ul><li>One of the most challenging scenario is characterized by: </li></ul><ul><ul><li>High pervasiveness (computing systems distributed and connected everywhere); </li></ul></ul><ul><ul><li>Connectivity as a commodity; </li></ul></ul><ul><ul><li>Structure as Network of Networks (adaptive networks); </li></ul></ul><ul><ul><li>Intelligence at the edges (terminals and end points); </li></ul></ul><ul><li>This scenario is highly disruptive as it implies moving intelligence at the edge of the network reinforcing the end-to-end argument and an open environment for services; </li></ul><ul><li>There is a need of understanding: </li></ul><ul><ul><li>The potential evolution of this scenario (in terms of architectures, technologies and services); </li></ul></ul><ul><ul><li>Which is the role of the Network Operator (biz model, architectures, technologies, …); </li></ul></ul>
  18. 18. Architectural vision and principles All rights reserved
  19. 19. Next: Open Questions <ul><li>Which mix of networking and computing paradigms and technologies will enable the scenario (characterized by high pervasivity, with connectivity as a commodity and Network of Networks) ? </li></ul><ul><li>How to optimize allocation, sharing and management of pervasive resources, to guarantee the best Users’ experience whilst reducing the systems and Operators’ costs ? </li></ul><ul><li>How to ensure the sustainability of the entire ecosystem, to avoid “Tragedy of Commons” due to unplanned usage of shared resources ? </li></ul><ul><li>How to create, nurture and protect an ecosystem ? </li></ul>
  20. 20. Further contacts <ul><li>roberto.minerva@telecomitalia.it </li></ul><ul><li>[email_address] </li></ul><ul><li>[email_address] </li></ul>http://www.gapingvoid.com/Moveable_Type/archives/2006_03.html
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×