SlideShare une entreprise Scribd logo
1  sur  21
Monitoring and Management
                          of P2P Overlays
              How to coordinate millions of autonomous peers
                 to provide controlled quality of service?




                                                                                                                                     KOM - Multimedia Communications Lab
                                                                                                                                       Prof. Dr.-Ing. Ralf Steinmetz (director)
                                                                                                                 Dept. of Electrical Engineering and Information Technology
                                                                                                                             Dept. of Computer Science (adjunct professor)
                                                                                                                                    TUD – Technische Universität Darmstadt
Dipl.-Math. Dipl.-Inform. Kalman Graffi                                                                                          Merckstr. 25, D-64283 Darmstadt, Germany
                                                                                                                               Tel.+49 6151 164959, Fax. +49 6151 166152
graffi@KOM.tu-darmstadt.de                                                                                                                         www.KOM.tu-darmstadt.de

Kalman-Graffi_IEEE-P2P-09_MonitoringAndManagement.ppt                                                                                                        17. Februar 2011
© author(s) of these slides 2008 including research results of the research network KOM and TU Darmstadt otherwise as specified at the respective slide
The Peer-to-Peer Paradigm

  Peer-to-peer systems
        Users build infrastructure
        Service is provided from users to users
        Peer-to-peer overlays
         Connecting all peers, providing new functionality                                                                  H(„my
                                                                                                                            data“)
                                                                                                                            = 3107           1008         1622      2011
                                                                                                                                     709                                      2207


         E.g. Distributed Hash Tables, keyword-based search                                                                  ?         611
                                                                                                                                                             3485          2906



                                                                                                                                                          12.5.7.31
                                                                                                                                                     peer-to-peer.info
                                                                                                                                         planet-lab.org
                                                                                                                                berkeley.edu                           61.51.166.150
                                                                                                                                                  95.7.6.10
                                                                                                                                             86.8.10.18                    7.31.10.25


  Evolution of applications / QoS demands
        File sharing
          No Quality of Service (QoS) requirements
        Voice over IP
          Real-time requirements
        Video-on-demand
          Real-time and bandwidth requirements
        Online community platforms
          Potential for high user interaction
    See: K. Graffi, AsKo, et al. “Peer-to-Peer Forschung - Überblick und Herausforderungen”                     KOM – Multimedia Communications Lab                                     2
In: it - Information Technology (Methods and Applications of Informatics and Information Technology), vol. 46, no. 5, p. 272-279, July 2007
Dynamics in P2P System

Various scenarios
  Distributed storage
  Content delivery                                  User
  Discovery and contacting of users                 Application
                                                    Manage-
Dynamics over time                                  ment
                                                    Overlay
  Network size
  Churn                                             Devices

Peer heterogeneity                                  Network
  Peer capacities
  Connectivity


Create a new overlay for every case?
  No, automated reconfiguring of established overlays!
  Management of P2P overlays
                                                 KOM – Multimedia Communications Lab   3
Problem Statement:
Self-X and Automated Reconfiguration
System goals are predefined
  Application and scenario specific
  e.g. Metric intervals
Examples
  Goal interval for hop count: [7,10]
  Standard deviation of peer load: max 500%
Goal
  Configuration should adapt to system goals
  Automated meeting of predefined metric intervals


Step 1: Monitor current system state
Step 2: Analysis state, plan new parameters
Step 3: Distribute and adopt new parameters on all peers

                                                     KOM – Multimedia Communications Lab   4
Self-Configuration Cycle in P2P Systems




                                          KOM – Multimedia Communications Lab   5
Monitoring: SkyEye.KOM

 Monitoring system state                                                  Quality requirements
       Applicable on all (KBR) struct. overlays                                 Performance: precise, fresh, robust
       Global view on system metrics                                            Costs: lightweight, minimal costs
       Statistical representation




K. Graffi et al. “SkyEye.KOM: An Information Management Over-Overlay for Getting the Oracle View on Structured P2P Systems”Communications Lab
                                                                                                          KOM – Multimedia IEEE ICPADS 2008     6
SkyEye.KOM – Architecture Design Decisions

Integrated vs. new layer
     New layer allows wider applicability


Reactive vs. proactive
     System state information is continuously interesting for all users


Monitoring topology: bus, ring, star, mesh, tree
     Tree structure alleviate information aggregation


Support for peer heterogeneity: heterogeneous vs. equal roles
     Load similar for all peers in all positions, no further roles needed


Position assignment: dynamic vs. deterministic
     Deterministic IDs used in topology, dynamically resolved with DHT
K. Graffi et al. “SkyEye.KOM: An Information Management Over-Overlay for Getting the Oracle View on Structured–P2P Systems” IEEE ICPADS 2008 7
                                                                                                        KOM Multimedia Communications Lab
Overview on SkyEye.KOM

Topology                                                    Statistic updates
      Tree based information architecture                       Periodically sent to parent peer
      Uses p2p overlay functionality                            Aggregated in each node ( same size)




                                                                     [µ,σ,σ²,Σ,
                                                                     min,max]
     0,09 0,2   0,3   0,4 0,51 0,6   0,75        0,9
0                                                      1
                                                             [µ,σ,σ²,Σ,
         50                  1                               min,max]
                                            10
45
                                                       15
         40                                  20        [µ,σ,σ²,Σ,
                        30
                                                       min,max]




                                                                                  KOM – Multimedia Communications Lab   8
Overview on SkyEye.KOM

Topology                                                    Statistic updates
      Tree based information architecture                      Periodically sent to parent peer
      Uses p2p overlay functionality                           Aggregated in each node ( same size)




                                                                                                   [µ,σ,σ²,Σ,
     0,09 0,2   0,3   0,4 0,51 0,6   0,75        0,9                                               min, max]
0                                                      1
                                                                                  [µ,σ,σ²,Σ,
         50                  1                                                    min, max]
                                            10
45
                                                       15
         40                                  20
                        30                                                                     [µ,σ,σ²,Σ,
                                                                                               min, max]




                                                                            KOM – Multimedia Communications Lab   9
Deriving a new Configuration

Root is deciding component                  Metric goals
                                                 Metrics       Analysis           Parameter
  P2P overlay parameterizable                                  and Plan
                                            Parameters
  Monitoring reveals current system state
  Predefined quality goals given
                                                                                        Metric
  Detects missed quality intervals                                                       goal

  Plans new configuration                                                                    Current
                                                                                             metric
  Spreads new configuration to
  all peers using SkyEye.KOM
                                                                                           Parameters
  Peers adopt locally the new rules



                                            Prevent configuration oscillation
                                                Give time for changes to take effect
                                                Introduce execution delay
                                                Analyze slope of value history
                                                Act only if small, i.e. changes settled

                                                               KOM – Multimedia Communications Lab 10
Analysis Point and Configuration Distribution

SkyEye.KOM topology
  SkyEye.KOM aggregates system statistics up the tree
  Every update message is acknowledged
   Global view from above
   Policy of new actions to implement


Root has global view
and can reach all leafs                [µ,σ,σ²,Σ, min, max]


  Root analyzes and           [µ,σ,σ²,Σ, min, max]
 pushes new
 configuration down
                          [µ,σ,σ²,Σ, min, max]



                                                              KOM – Multimedia Communications Lab 11
Analysis Point and Configuration Distribution

SkyEye.KOM topology
  SkyEye.KOM aggregates system statistics up the tree
  Every update message is acknowledged
   Global view from above
   Policy of new actions to implement


Root has global view
                                          [µ,σ,σ²,Σ,
and can reach all leafs                   min, max]

                                 + new parameter
  Root analyzes and              configuration
 pushes new
 configuration down



                                                        KOM – Multimedia Communications Lab 12
Simulation Setup

Evaluated in PeerfactSim.KOM                                  PeerfactSim.KOM
                                                               User

Simulation Setup                                               Application




                                                                                                 Simulation Engine
  IdealDHT: Dispatches messages to responsible peer            Manage-
                                                               ment
  5000 Nodes
                                                               Overlay
  Delay model: global network positioning
  Churn model: based on KAD measurements (Steiner et al.)      Transport

                                                               Network
Metrics
  Monitored and real metrics
  Relative monitoring error
  Monitoring age
  Traffic overhead


                                                            KOM – Multimedia Communications Lab 13
Monitoring Performance




Tree degree = 4
Update interval = 60sec
 K. Graffi, D. Stingl et al. “Monitoring and Management of Structured P2P Systems” submitted to IEEE P2P 2009
                                                                                                            KOM – Multimedia Communications Lab 14
Monitoring Costs




Tree degree = 4
Update interval = 60sec
 K. Graffi, D. Stingl et al. “Monitoring and Management of Structured P2P Systems” submitted to IEEE P2P 2009
                                                                                                            KOM – Multimedia Communications Lab 15
Case: Chord, Hop Count, Routing Table Size

Chord                                         H(„mydata“)
                                                = 3107
   Classic DHT, provides req. functionality                 709
                                                                        1008   1622          2011
                                                                                                           2207


   Adapted to consider new configuration
                                              ?
                                                                  611                               2906
                                                                                      3485




Parameter: Finger table (FT) size

Metric: Hop count (HC)

Analysis: Hop count interval [7,10]

Plan:
   Hop count large    FT +100%
   Hop count small    FT -10%




                                                      KOM – Multimedia Communications Lab 16
Starting with High Hop Count

Quick convergence towards preset quality interval
Analysis:
  Too large hop count is detected
       Finger table size: increase by 100%
  Initial FT size: 20, at end 80
  Quality goal is reached and kept




                                                KOM – Multimedia Communications Lab 17
Starting with Low Hop Count

Quick convergence towards preset quality interval
Analysis:
  Too small hop count is detected
       Finger table size: decrease by 10%
  Initial FT size: 160, at end 116
  Quality goal is reached and kept




                                                KOM – Multimedia Communications Lab 18
Summary

Management of P2P overlays
  Reach and hold preset quality intervals
  Through system management cycle

Coordinated resource usage
  Through reconfiguration
  Tunable optimization goals

Monitoring: SkyEye.KOM
  Global view on statistics of running system:
  avg./std./min./max on all metrics
  Precise yet cost effective monitoring

Analysis / Plan / Execute in Chord
  Automated rule application
  Preset quality intervals are reached/hold
                                                 KOM – Multimedia Communications Lab 19
Outlook

Future work
  Evaluate cycle in Kademlia
  Automatically detect rules
   Parameter-metric correlation
   Using machine learning and genetic algorithms


Implications
  Allows the usage of P2P overlays “off the shelf”
    For various scenarios / environments
  Monitoring and quality control
    P2P as mature IT architecture
    Interesting for industry
  Self-configuration framework can
  include and consider other functional layers

                                                     KOM – Multimedia Communications Lab 20
Questions?




             KOM – Multimedia Communications Lab 21

Contenu connexe

Similaire à IEEE P2P 2009 - Kalman Graffi - Monitoring and Management of Structured Peer-to-Peer Systems

Kalman Graffi - Monitoring and Management of P2P Systems - 2010
Kalman Graffi - Monitoring and Management of P2P Systems - 2010Kalman Graffi - Monitoring and Management of P2P Systems - 2010
Kalman Graffi - Monitoring and Management of P2P Systems - 2010Kalman Graffi
 
Kalman Graffi - 2rd Research Talk - 2009
Kalman Graffi - 2rd Research Talk - 2009Kalman Graffi - 2rd Research Talk - 2009
Kalman Graffi - 2rd Research Talk - 2009Kalman Graffi
 
Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...
Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...
Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...Kalman Graffi
 
Today's Top "RESTful" Services and Why They Are Not RESTful
Today's Top "RESTful" Services and Why They Are Not RESTfulToday's Top "RESTful" Services and Why They Are Not RESTful
Today's Top "RESTful" Services and Why They Are Not RESTfulDominik Renzel
 
Cyberinfrastructure and Applications Overview: Howard University June22
Cyberinfrastructure and Applications Overview: Howard University June22Cyberinfrastructure and Applications Overview: Howard University June22
Cyberinfrastructure and Applications Overview: Howard University June22marpierc
 
Cloud Camp Milan 2K9 Telecom Italia: Where P2P?
Cloud Camp Milan 2K9 Telecom Italia: Where P2P?Cloud Camp Milan 2K9 Telecom Italia: Where P2P?
Cloud Camp Milan 2K9 Telecom Italia: Where P2P?Gabriele Bozzi
 
CloudCamp Milan 2009: Telecom Italia
CloudCamp Milan 2009: Telecom ItaliaCloudCamp Milan 2009: Telecom Italia
CloudCamp Milan 2009: Telecom ItaliaGabriele Bozzi
 
FAIR Computational Workflows
FAIR Computational WorkflowsFAIR Computational Workflows
FAIR Computational Workflows Carole Goble
 
云计算及其应用
云计算及其应用云计算及其应用
云计算及其应用lantianlcdx
 
Big Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the FutureBig Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the FutureOdinot Stanislas
 
dagrep_v006_i004_p057_s16152
dagrep_v006_i004_p057_s16152dagrep_v006_i004_p057_s16152
dagrep_v006_i004_p057_s16152Lenore Mullin
 
Cassandra framework a service oriented distributed multimedia
Cassandra framework  a service oriented distributed multimediaCassandra framework  a service oriented distributed multimedia
Cassandra framework a service oriented distributed multimediaJoão Gabriel Lima
 
Discovery Engines for Big Data: Accelerating Discovery in Basic Energy Sciences
Discovery Engines for Big Data: Accelerating Discovery in Basic Energy SciencesDiscovery Engines for Big Data: Accelerating Discovery in Basic Energy Sciences
Discovery Engines for Big Data: Accelerating Discovery in Basic Energy SciencesIan Foster
 
Linking Programming models between Grids, Web 2.0 and Multicore
Linking Programming models between Grids, Web 2.0 and Multicore Linking Programming models between Grids, Web 2.0 and Multicore
Linking Programming models between Grids, Web 2.0 and Multicore Geoffrey Fox
 
CC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdfCC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdfHasanAfwaaz1
 
2023comp90024_Spartan.pdf
2023comp90024_Spartan.pdf2023comp90024_Spartan.pdf
2023comp90024_Spartan.pdfLevLafayette1
 
Parallel Computing 2007: Overview
Parallel Computing 2007: OverviewParallel Computing 2007: Overview
Parallel Computing 2007: OverviewGeoffrey Fox
 
Network Planning & Design: An Art or a Science?
Network Planning & Design: An Art or a Science?Network Planning & Design: An Art or a Science?
Network Planning & Design: An Art or a Science?Vishal Sharma, Ph.D.
 

Similaire à IEEE P2P 2009 - Kalman Graffi - Monitoring and Management of Structured Peer-to-Peer Systems (20)

Kalman Graffi - Monitoring and Management of P2P Systems - 2010
Kalman Graffi - Monitoring and Management of P2P Systems - 2010Kalman Graffi - Monitoring and Management of P2P Systems - 2010
Kalman Graffi - Monitoring and Management of P2P Systems - 2010
 
Kalman Graffi - 2rd Research Talk - 2009
Kalman Graffi - 2rd Research Talk - 2009Kalman Graffi - 2rd Research Talk - 2009
Kalman Graffi - 2rd Research Talk - 2009
 
Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...
Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...
Dagstuhl 2010 - Kalman Graffi - Alternative, more promising IT Paradigms for ...
 
Today's Top "RESTful" Services and Why They Are Not RESTful
Today's Top "RESTful" Services and Why They Are Not RESTfulToday's Top "RESTful" Services and Why They Are Not RESTful
Today's Top "RESTful" Services and Why They Are Not RESTful
 
grid computing
grid computinggrid computing
grid computing
 
Cyberinfrastructure and Applications Overview: Howard University June22
Cyberinfrastructure and Applications Overview: Howard University June22Cyberinfrastructure and Applications Overview: Howard University June22
Cyberinfrastructure and Applications Overview: Howard University June22
 
Cloud Camp Milan 2K9 Telecom Italia: Where P2P?
Cloud Camp Milan 2K9 Telecom Italia: Where P2P?Cloud Camp Milan 2K9 Telecom Italia: Where P2P?
Cloud Camp Milan 2K9 Telecom Italia: Where P2P?
 
CloudCamp Milan 2009: Telecom Italia
CloudCamp Milan 2009: Telecom ItaliaCloudCamp Milan 2009: Telecom Italia
CloudCamp Milan 2009: Telecom Italia
 
FAIR Computational Workflows
FAIR Computational WorkflowsFAIR Computational Workflows
FAIR Computational Workflows
 
云计算及其应用
云计算及其应用云计算及其应用
云计算及其应用
 
Big Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the FutureBig Data Beyond Hadoop*: Research Directions for the Future
Big Data Beyond Hadoop*: Research Directions for the Future
 
dagrep_v006_i004_p057_s16152
dagrep_v006_i004_p057_s16152dagrep_v006_i004_p057_s16152
dagrep_v006_i004_p057_s16152
 
Cassandra framework a service oriented distributed multimedia
Cassandra framework  a service oriented distributed multimediaCassandra framework  a service oriented distributed multimedia
Cassandra framework a service oriented distributed multimedia
 
Discovery Engines for Big Data: Accelerating Discovery in Basic Energy Sciences
Discovery Engines for Big Data: Accelerating Discovery in Basic Energy SciencesDiscovery Engines for Big Data: Accelerating Discovery in Basic Energy Sciences
Discovery Engines for Big Data: Accelerating Discovery in Basic Energy Sciences
 
Linking Programming models between Grids, Web 2.0 and Multicore
Linking Programming models between Grids, Web 2.0 and Multicore Linking Programming models between Grids, Web 2.0 and Multicore
Linking Programming models between Grids, Web 2.0 and Multicore
 
CC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdfCC LECTURE NOTES (1).pdf
CC LECTURE NOTES (1).pdf
 
2023comp90024_Spartan.pdf
2023comp90024_Spartan.pdf2023comp90024_Spartan.pdf
2023comp90024_Spartan.pdf
 
Parallel Computing 2007: Overview
Parallel Computing 2007: OverviewParallel Computing 2007: Overview
Parallel Computing 2007: Overview
 
ThreadModel rev 1.4
ThreadModel rev 1.4ThreadModel rev 1.4
ThreadModel rev 1.4
 
Network Planning & Design: An Art or a Science?
Network Planning & Design: An Art or a Science?Network Planning & Design: An Art or a Science?
Network Planning & Design: An Art or a Science?
 

Plus de Kalman Graffi

IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...
IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...
IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...Kalman Graffi
 
LibreSocial - P2P Framework for Social Networks - Overview
LibreSocial - P2P Framework for Social Networks - OverviewLibreSocial - P2P Framework for Social Networks - Overview
LibreSocial - P2P Framework for Social Networks - OverviewKalman Graffi
 
IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...
IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...
IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...Kalman Graffi
 
IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...
IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...
IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...Kalman Graffi
 
IEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia Case
IEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia CaseIEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia Case
IEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia CaseKalman Graffi
 
IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...
IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...
IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...Kalman Graffi
 
Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...
Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...
Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...Kalman Graffi
 
Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...
Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...
Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...Kalman Graffi
 
Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...
Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...
Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...Kalman Graffi
 
Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...
Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...
Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...Kalman Graffi
 
IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...
IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...
IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...Kalman Graffi
 
QuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocial
QuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocialQuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocial
QuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocialKalman Graffi
 
LifeSocial - A P2P-Platform for Secure Online Social Networks
LifeSocial - A P2P-Platform for Secure Online Social NetworksLifeSocial - A P2P-Platform for Secure Online Social Networks
LifeSocial - A P2P-Platform for Secure Online Social NetworksKalman Graffi
 
Kalman Graffi - 1 Slide - 2010
Kalman Graffi - 1 Slide - 2010Kalman Graffi - 1 Slide - 2010
Kalman Graffi - 1 Slide - 2010Kalman Graffi
 
Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...
Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...
Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...Kalman Graffi
 
Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...
Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...
Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...Kalman Graffi
 
2009 kalman.graffi emanics_aspects_ofautonomiccomputing_20090617
2009 kalman.graffi emanics_aspects_ofautonomiccomputing_200906172009 kalman.graffi emanics_aspects_ofautonomiccomputing_20090617
2009 kalman.graffi emanics_aspects_ofautonomiccomputing_20090617Kalman Graffi
 
Cebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer Systems
Cebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer SystemsCebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer Systems
Cebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer SystemsKalman Graffi
 
Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...
Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...
Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...Kalman Graffi
 
Kalman Graffi - 5 Slides Demo - 2008
Kalman Graffi - 5 Slides Demo - 2008Kalman Graffi - 5 Slides Demo - 2008
Kalman Graffi - 5 Slides Demo - 2008Kalman Graffi
 

Plus de Kalman Graffi (20)

IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...
IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...
IEEE CRS 2014 - Secure Distributed Data Structures for Peer-to-Peer-based Soc...
 
LibreSocial - P2P Framework for Social Networks - Overview
LibreSocial - P2P Framework for Social Networks - OverviewLibreSocial - P2P Framework for Social Networks - Overview
LibreSocial - P2P Framework for Social Networks - Overview
 
IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...
IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...
IEEE P2P 2013 - Bootstrapping Skynet: Calibration and Autonomic Self-Control ...
 
IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...
IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...
IEEE ICCCN 2013 - Continuous Gossip-based Aggregation through Dynamic Informa...
 
IEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia Case
IEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia CaseIEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia Case
IEEE ICC 2013 - Symbiotic Coupling of P2P and Cloud Systems: The Wikipedia Case
 
IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...
IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...
IEEE HPCS 2013 - Comparative Evaluation of Peer-to-Peer Systems Using Peerfac...
 
Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...
Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...
Kalman Graffi - IEEE NetSys 2013 - Ca-Re-Chord - A Churn Resistant Self-stabi...
 
Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...
Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...
Kalman Graffi - IEEE NetSys 2013 - Adding Capacity-Aware Storage Indirection ...
 
Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...
Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...
Kalman Graffi - IEEE ICC 2013 - Symbiotic Coupling of Peer-to-Peer and Cloud ...
 
Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...
Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...
Kalman Graffi - IEEE HPCS 2013 - Comparative Evaluation of P2P Systems Using ...
 
IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...
IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...
IEEE CCNC 2011: Kalman Graffi - LifeSocial.KOM: A Secure and P2P-based Soluti...
 
QuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocial
QuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocialQuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocial
QuaP2P Lunchtalk on Online Social Networks 2010 - LifeSocial
 
LifeSocial - A P2P-Platform for Secure Online Social Networks
LifeSocial - A P2P-Platform for Secure Online Social NetworksLifeSocial - A P2P-Platform for Secure Online Social Networks
LifeSocial - A P2P-Platform for Secure Online Social Networks
 
Kalman Graffi - 1 Slide - 2010
Kalman Graffi - 1 Slide - 2010Kalman Graffi - 1 Slide - 2010
Kalman Graffi - 1 Slide - 2010
 
Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...
Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...
Kalman Graffi - Sichere Digitale Soziale Netzwerke – Eine Chance für E-Learni...
 
Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...
Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...
Cebit 2009 - Kalman Graffi - LifeSocial.KOM - Eine dezentrale Plattform für s...
 
2009 kalman.graffi emanics_aspects_ofautonomiccomputing_20090617
2009 kalman.graffi emanics_aspects_ofautonomiccomputing_200906172009 kalman.graffi emanics_aspects_ofautonomiccomputing_20090617
2009 kalman.graffi emanics_aspects_ofautonomiccomputing_20090617
 
Cebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer Systems
Cebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer SystemsCebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer Systems
Cebit 2008 - PeerfactSim.KOM - A Simulator for Large Scale Peer-to-Peer Systems
 
Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...
Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...
Cebit 2008 - PeerfactSim.KOM - Ein Simulator für hochskalierede Peer-to-Peer ...
 
Kalman Graffi - 5 Slides Demo - 2008
Kalman Graffi - 5 Slides Demo - 2008Kalman Graffi - 5 Slides Demo - 2008
Kalman Graffi - 5 Slides Demo - 2008
 

Dernier

A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 

Dernier (20)

A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 

IEEE P2P 2009 - Kalman Graffi - Monitoring and Management of Structured Peer-to-Peer Systems

  • 1. Monitoring and Management of P2P Overlays How to coordinate millions of autonomous peers to provide controlled quality of service? KOM - Multimedia Communications Lab Prof. Dr.-Ing. Ralf Steinmetz (director) Dept. of Electrical Engineering and Information Technology Dept. of Computer Science (adjunct professor) TUD – Technische Universität Darmstadt Dipl.-Math. Dipl.-Inform. Kalman Graffi Merckstr. 25, D-64283 Darmstadt, Germany Tel.+49 6151 164959, Fax. +49 6151 166152 graffi@KOM.tu-darmstadt.de www.KOM.tu-darmstadt.de Kalman-Graffi_IEEE-P2P-09_MonitoringAndManagement.ppt 17. Februar 2011 © author(s) of these slides 2008 including research results of the research network KOM and TU Darmstadt otherwise as specified at the respective slide
  • 2. The Peer-to-Peer Paradigm Peer-to-peer systems Users build infrastructure Service is provided from users to users Peer-to-peer overlays Connecting all peers, providing new functionality H(„my data“) = 3107 1008 1622 2011 709 2207 E.g. Distributed Hash Tables, keyword-based search ? 611 3485 2906 12.5.7.31 peer-to-peer.info planet-lab.org berkeley.edu 61.51.166.150 95.7.6.10 86.8.10.18 7.31.10.25 Evolution of applications / QoS demands File sharing No Quality of Service (QoS) requirements Voice over IP Real-time requirements Video-on-demand Real-time and bandwidth requirements Online community platforms Potential for high user interaction See: K. Graffi, AsKo, et al. “Peer-to-Peer Forschung - Überblick und Herausforderungen” KOM – Multimedia Communications Lab 2 In: it - Information Technology (Methods and Applications of Informatics and Information Technology), vol. 46, no. 5, p. 272-279, July 2007
  • 3. Dynamics in P2P System Various scenarios Distributed storage Content delivery User Discovery and contacting of users Application Manage- Dynamics over time ment Overlay Network size Churn Devices Peer heterogeneity Network Peer capacities Connectivity Create a new overlay for every case? No, automated reconfiguring of established overlays! Management of P2P overlays KOM – Multimedia Communications Lab 3
  • 4. Problem Statement: Self-X and Automated Reconfiguration System goals are predefined Application and scenario specific e.g. Metric intervals Examples Goal interval for hop count: [7,10] Standard deviation of peer load: max 500% Goal Configuration should adapt to system goals Automated meeting of predefined metric intervals Step 1: Monitor current system state Step 2: Analysis state, plan new parameters Step 3: Distribute and adopt new parameters on all peers KOM – Multimedia Communications Lab 4
  • 5. Self-Configuration Cycle in P2P Systems KOM – Multimedia Communications Lab 5
  • 6. Monitoring: SkyEye.KOM Monitoring system state Quality requirements Applicable on all (KBR) struct. overlays Performance: precise, fresh, robust Global view on system metrics Costs: lightweight, minimal costs Statistical representation K. Graffi et al. “SkyEye.KOM: An Information Management Over-Overlay for Getting the Oracle View on Structured P2P Systems”Communications Lab KOM – Multimedia IEEE ICPADS 2008 6
  • 7. SkyEye.KOM – Architecture Design Decisions Integrated vs. new layer New layer allows wider applicability Reactive vs. proactive System state information is continuously interesting for all users Monitoring topology: bus, ring, star, mesh, tree Tree structure alleviate information aggregation Support for peer heterogeneity: heterogeneous vs. equal roles Load similar for all peers in all positions, no further roles needed Position assignment: dynamic vs. deterministic Deterministic IDs used in topology, dynamically resolved with DHT K. Graffi et al. “SkyEye.KOM: An Information Management Over-Overlay for Getting the Oracle View on Structured–P2P Systems” IEEE ICPADS 2008 7 KOM Multimedia Communications Lab
  • 8. Overview on SkyEye.KOM Topology Statistic updates Tree based information architecture Periodically sent to parent peer Uses p2p overlay functionality Aggregated in each node ( same size) [µ,σ,σ²,Σ, min,max] 0,09 0,2 0,3 0,4 0,51 0,6 0,75 0,9 0 1 [µ,σ,σ²,Σ, 50 1 min,max] 10 45 15 40 20 [µ,σ,σ²,Σ, 30 min,max] KOM – Multimedia Communications Lab 8
  • 9. Overview on SkyEye.KOM Topology Statistic updates Tree based information architecture Periodically sent to parent peer Uses p2p overlay functionality Aggregated in each node ( same size) [µ,σ,σ²,Σ, 0,09 0,2 0,3 0,4 0,51 0,6 0,75 0,9 min, max] 0 1 [µ,σ,σ²,Σ, 50 1 min, max] 10 45 15 40 20 30 [µ,σ,σ²,Σ, min, max] KOM – Multimedia Communications Lab 9
  • 10. Deriving a new Configuration Root is deciding component Metric goals Metrics Analysis Parameter P2P overlay parameterizable and Plan Parameters Monitoring reveals current system state Predefined quality goals given Metric Detects missed quality intervals goal Plans new configuration Current metric Spreads new configuration to all peers using SkyEye.KOM Parameters Peers adopt locally the new rules Prevent configuration oscillation Give time for changes to take effect Introduce execution delay Analyze slope of value history Act only if small, i.e. changes settled KOM – Multimedia Communications Lab 10
  • 11. Analysis Point and Configuration Distribution SkyEye.KOM topology SkyEye.KOM aggregates system statistics up the tree Every update message is acknowledged Global view from above Policy of new actions to implement Root has global view and can reach all leafs [µ,σ,σ²,Σ, min, max] Root analyzes and [µ,σ,σ²,Σ, min, max] pushes new configuration down [µ,σ,σ²,Σ, min, max] KOM – Multimedia Communications Lab 11
  • 12. Analysis Point and Configuration Distribution SkyEye.KOM topology SkyEye.KOM aggregates system statistics up the tree Every update message is acknowledged Global view from above Policy of new actions to implement Root has global view [µ,σ,σ²,Σ, and can reach all leafs min, max] + new parameter Root analyzes and configuration pushes new configuration down KOM – Multimedia Communications Lab 12
  • 13. Simulation Setup Evaluated in PeerfactSim.KOM PeerfactSim.KOM User Simulation Setup Application Simulation Engine IdealDHT: Dispatches messages to responsible peer Manage- ment 5000 Nodes Overlay Delay model: global network positioning Churn model: based on KAD measurements (Steiner et al.) Transport Network Metrics Monitored and real metrics Relative monitoring error Monitoring age Traffic overhead KOM – Multimedia Communications Lab 13
  • 14. Monitoring Performance Tree degree = 4 Update interval = 60sec K. Graffi, D. Stingl et al. “Monitoring and Management of Structured P2P Systems” submitted to IEEE P2P 2009 KOM – Multimedia Communications Lab 14
  • 15. Monitoring Costs Tree degree = 4 Update interval = 60sec K. Graffi, D. Stingl et al. “Monitoring and Management of Structured P2P Systems” submitted to IEEE P2P 2009 KOM – Multimedia Communications Lab 15
  • 16. Case: Chord, Hop Count, Routing Table Size Chord H(„mydata“) = 3107 Classic DHT, provides req. functionality 709 1008 1622 2011 2207 Adapted to consider new configuration ? 611 2906 3485 Parameter: Finger table (FT) size Metric: Hop count (HC) Analysis: Hop count interval [7,10] Plan: Hop count large FT +100% Hop count small FT -10% KOM – Multimedia Communications Lab 16
  • 17. Starting with High Hop Count Quick convergence towards preset quality interval Analysis: Too large hop count is detected Finger table size: increase by 100% Initial FT size: 20, at end 80 Quality goal is reached and kept KOM – Multimedia Communications Lab 17
  • 18. Starting with Low Hop Count Quick convergence towards preset quality interval Analysis: Too small hop count is detected Finger table size: decrease by 10% Initial FT size: 160, at end 116 Quality goal is reached and kept KOM – Multimedia Communications Lab 18
  • 19. Summary Management of P2P overlays Reach and hold preset quality intervals Through system management cycle Coordinated resource usage Through reconfiguration Tunable optimization goals Monitoring: SkyEye.KOM Global view on statistics of running system: avg./std./min./max on all metrics Precise yet cost effective monitoring Analysis / Plan / Execute in Chord Automated rule application Preset quality intervals are reached/hold KOM – Multimedia Communications Lab 19
  • 20. Outlook Future work Evaluate cycle in Kademlia Automatically detect rules Parameter-metric correlation Using machine learning and genetic algorithms Implications Allows the usage of P2P overlays “off the shelf” For various scenarios / environments Monitoring and quality control P2P as mature IT architecture Interesting for industry Self-configuration framework can include and consider other functional layers KOM – Multimedia Communications Lab 20
  • 21. Questions? KOM – Multimedia Communications Lab 21