SlideShare ist ein Scribd-Unternehmen logo
1 von 45
Downloaden Sie, um offline zu lesen
Welcome




                                         Grid on Demand

                                Willem Toorop and Alain van Hoof

                                         {wtoorop,ahoof}@os3.nl


                                           June 30, 2010




Willem Toorop and Alain van Hoof (OS3)        Grid on Demand       June 30, 2010   1 / 39
Introduction   Research Question


 Research Question




                Can Grid computing be offered as a Cloud service and what
                        type of applications benefit from this?




Willem Toorop and Alain van Hoof (OS3)        Grid on Demand                June 30, 2010   2 / 39
Introduction   The Grid and The Cloud


 The Grid and The Cloud: Sharing Resources


                       Sharing Resources to minimizing idle resources

             Resource                       Capacity          Goods
             Processor                      Flops             Compute
             Hard-disk memory               Bytes             Storage
             Network                        Bytes/sec         Communication Bandwidth

                                         Grid                                        Cloud (IaaS)
    Distribution                         By Collaboration                            By Cloud Provider
    Resource Type                        Heterogeneous                               Homogeneous
    Abstraction                          Middleware (open standards)                 Virtualization
    Sharing Guarantee                    Security infrastructure                     Financial infra



Willem Toorop and Alain van Hoof (OS3)            Grid on Demand                         June 30, 2010   3 / 39
Introduction   The Grid and The Cloud


 The Grid and The Cloud: Dividing the Resources

                                                  VO
           Grid                          User        User
                                                                                    Cloud

                     Grid                     Grid

                                                                             User              User

                                                                                     User

                               User       User
                                         VO


Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                        June 30, 2010   4 / 39
A Grid in the Cloud   Urgent Computing


 A Grid in The Cloud: Urgent Computing


                                                           GRID
                                                            on
                                                          Demand




  Using the elasticity and scalability of the Cloud and providing a Grid
  interface, current e-Science (computationally intensive science)
  applications can use a Grid on Demand when there is a high demand for
  resources for a short period of time.
  Example
  UrbanFlood (http://urbanflood.eu) wants to calculate flooding predictions
  when actual flooding happens, Grid on Demand can provide this.

Willem Toorop and Alain van Hoof (OS3)               Grid on Demand               June 30, 2010   5 / 39
A Grid in the Cloud   Grid on Demand


 Grid on Demand

             Job Submission Client



                                             OS: Ubuntu 10.04
                                             Grid: Globus 4.2.1
                                             PBS: Torque 2.6.8


                                                                   Compute Nodes




                                     Head Node




  Grid Interface: Globus Toolkit 4.2 (open standard, widely used)
  Queue Manager (Distribution of jobs to nodes): Torque 2.6.2
  Amazon EC2 Cloud Provider (de-facto standard with open API)

Willem Toorop and Alain van Hoof (OS3)                    Grid on Demand           June 30, 2010   6 / 39
Implementation   What makes the Grid, the Grid


 What makes the Grid, the Grid
 Typical Grid usage example spanning multiple organizations



                                                          Organization B


                                                  ta          Compute
                                      st 1 o
                                             f da                                acc
                                     1 2 te 12X                                      e
                                                                                dat ss
                                 use mpu                                           a
                                       o
          Organization C          to c                                                         Organization A
                                           use my data
                                           to compute X        Grid      store data
             Scheduler                                                                            Storage
                                                               User
                              use 2 nd
                                       1                                                 ata
                             to co 2 of da                                          ss d
                                  mpu 1 ta
                                        te X                                    acce
                                         2                    Compute

                                                          Organization D




Willem Toorop and Alain van Hoof (OS3)               Grid on Demand                              June 30, 2010   7 / 39
Implementation   What makes the Grid, the Grid


 Proxy certificates for delegation




  The Grid is a collaboration between multiple organizations.
         Grid users need to be authorized to use remote resources
         Those resources should be authorized to perform actions
         on behalf of the Grid user
  Proxy certificates enable delegation of authority




Willem Toorop and Alain van Hoof (OS3)           Grid on Demand                           June 30, 2010   8 / 39
Implementation   What makes the Grid, the Grid



      Grid user




    create proxy                Scheduler



                  compute X

                                create cert.
                                  request
                    sign this
                                                  Compute

                      Okay
                                         compute X




Willem Toorop and Alain van Hoof (OS3)            Grid on Demand                           June 30, 2010   9 / 39
Implementation   What makes the Grid, the Grid



      Grid user




    create proxy                Scheduler



                  compute X

                                create cert.
                                  request
                    sign this
                                                  Compute

                      Okay
                                         compute X
                                                               Virtual Organizations are based on
                                                               delegation by proxy certificates.



Willem Toorop and Alain van Hoof (OS3)            Grid on Demand                           June 30, 2010   9 / 39
Implementation   What makes the Grid, the Grid



      Grid user
                                                               Proxy certificates allow for
                                                               dynamic resource allocation,

    create proxy                Scheduler
                                                               But the hosts still need a
                                                               CA signed certificate.

                  compute X
                                                               This is a problem when hostname’s
                                create cert.                   are assigned dynamically!
                                  request
                    sign this
                                                  Compute

                      Okay
                                         compute X




Willem Toorop and Alain van Hoof (OS3)            Grid on Demand                           June 30, 2010   9 / 39
Implementation   What makes the Grid, the Grid



      Grid user
                                                               Proxy certificates allow for
                                                               dynamic resource allocation,

    create proxy                Scheduler
                                                               But the hosts still need a
                                                               CA signed certificate.

                  compute X
                                                               This is a problem when hostname’s
                                create cert.                   are assigned dynamically!
                                  request
                    sign this
                                                  Compute
                                                               Fixed CA in image?
                      Okay
                                         compute X




Willem Toorop and Alain van Hoof (OS3)            Grid on Demand                           June 30, 2010   9 / 39
Implementation   What makes the Grid, the Grid



      Grid user
                                                               Proxy certificates allow for
                                                               dynamic resource allocation,

    create proxy                Scheduler
                                                               But the hosts still need a
                                                               CA signed certificate.

                  compute X
                                                               This is a problem when hostname’s
                                create cert.                   are assigned dynamically!
                                  request
                    sign this
                                                  Compute
                                                               Fixed CA in image?
                      Okay
                                         compute X             Dynamic CA on every Launch?




Willem Toorop and Alain van Hoof (OS3)            Grid on Demand                           June 30, 2010   9 / 39
Implementation   Amazon Elastic Block Store


 Easy Image management with Amazon Elastic Block Store
                                                                configure

                        launch
                        instance IA                             Running
         (A, S)                          Pending
                          VS ← S                               (IA , VS , H)        term
                                                                                         inate




                                                           p
                                                        sto
                                                                                                 Shutting-down

                                                    Stopping                   Pending
                                                                                                 Terminated




                                                                          rt
                                                                       sta
                                                                                                     IA
                                                                                      inate
                                                                                 term
                               create AMI A                     Stopped
         (A , S )
                                  S ← VS                        (IA , VS )


         Life cycle of Amazon Machine Images using Elastic Block Storage
                    A = Amazon Machine Image, S = Snapshot,
                    I = Instance, V = Volume, H = Hostname

Willem Toorop and Alain van Hoof (OS3)             Grid on Demand                                June 30, 2010   10 / 39
Implementation    EBS for configuration stages


 EBS for configuration stages
                                  configure                                                  configure

            launch                                 provide Amazon Access Credentials
            instance IA           Running                  (configure cluster)               Running
   (A, S)
            VS ← S               (IA , VS , H)                                             (IA , VS , H)




                                                        sh shar




                                                                        sh wn
                                                          for




                                                                               ng
                                                          ut



                                                                     for utdo
                            shutdown




                                                                                      shutdown
                             for reuse




                                                                                       for reuse
                                                            do ing




                                                                           ari
                                           start




                                                                                                     start
                                                              wn

                                                                        sh
     launch IA                                                                                                           launch IA
     VS ← S                                                                                                              VS ← S
                                   Stopped                      Stopped                      Stopped
                                   (IA , VS )                   (IA , VS )                   (IA , VS )

                                         create AMI A                 create AMI A                 create AMI A
                                         S ← VS                       S ← VS                       S ← VS

                                    (A , S )                    (A , S )                    (A , S )




Willem Toorop and Alain van Hoof (OS3)                     Grid on Demand                                    June 30, 2010    11 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   12 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   13 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   14 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   15 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   16 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   17 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   18 / 39
Web Interface   Launching Grid on Demand




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                      June 30, 2010   19 / 39
Web Interface   Configuring the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                    June 30, 2010   20 / 39
Web Interface   Configuring the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                    June 30, 2010   21 / 39
Web Interface   Configuring the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                    June 30, 2010   22 / 39
Web Interface   Configuring the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                    June 30, 2010   23 / 39
Web Interface   Real Grid certificate usage




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                        June 30, 2010   24 / 39
Web Interface   Real Grid certificate usage




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                        June 30, 2010   25 / 39
Web Interface   Real Grid certificate usage




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                        June 30, 2010   26 / 39
Web Interface   Elasticity of the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                       June 30, 2010   27 / 39
Web Interface   Elasticity of the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                       June 30, 2010   28 / 39
Web Interface   Elasticity of the cluster




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                       June 30, 2010   29 / 39
Web Interface   Saving your settings




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                  June 30, 2010   30 / 39
Web Interface   Saving your settings




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                  June 30, 2010   31 / 39
Web Interface   Saving your settings




Willem Toorop and Alain van Hoof (OS3)          Grid on Demand                  June 30, 2010   32 / 39
“Real use” and Performance   WS-VLAM and WAVE


 “Real use” and Performance test


  To test the possibilities and performance of Grid on Demand a Biomedical
  Application and a workflow manager are used




Willem Toorop and Alain van Hoof (OS3)              Grid on Demand              June 30, 2010   33 / 39
“Real use” and Performance   WS-VLAM and WAVE


 “Real use” and Performance test


  To test the possibilities and performance of Grid on Demand a Biomedical
  Application and a workflow manager are used
  Biomedical Application: WAVE
  Parallel (MonteCarlo simulation) application




Willem Toorop and Alain van Hoof (OS3)              Grid on Demand              June 30, 2010   33 / 39
“Real use” and Performance   WS-VLAM and WAVE


 “Real use” and Performance test


  To test the possibilities and performance of Grid on Demand a Biomedical
  Application and a workflow manager are used
  Biomedical Application: WAVE
  Parallel (MonteCarlo simulation) application

  Workflow Manager
         A (graphical) tool to assist complex e-Science application creation
         Creates a series of jobsubmissions
         WS-VLAM created by UvA SNE Group
         Connects to Globus Grid Interface



Willem Toorop and Alain van Hoof (OS3)              Grid on Demand              June 30, 2010   33 / 39
“Real use” and Performance          Connecting the Grid on Demand to a Workflow Manager


 Connecting the Grid on Demand to a Workflow Manager




                        WAVE
                      Biomedical
                       Compute                     OS: Ubuntu 10.04
                      Application
                                                   Grid: Globus 4.2.1
                                                   PBS: Torque 2.6.8




                                                                         Compute Nodes

                                           Head Node




Willem Toorop and Alain van Hoof (OS3)                    Grid on Demand                                June 30, 2010    34 / 39
“Real use” and Performance   Preliminary performance results: total execution time


 Preliminary performance results: total execution time



  Grid on demand compared to a 32 node physical UvA cluster (DAS3) with
                         Globus Grid interface

                     Grid                          Jobs       Total execution time
                     DAS3                          28         00:42:58
                     Grid on Demand                28         00:46:22
                     DAS3                          98         02:46:36
                     Grid on Demand                98         00:52:26




Willem Toorop and Alain van Hoof (OS3)              Grid on Demand                               June 30, 2010       35 / 39
“Real use” and Performance          Preliminary performance results: 30 Jobs


 Preliminary performance results of job pending and
 running time: 30 jobs


                                                     Performance on DAS3 - 30 Jobs                                                                Performance on Grid on Demand 30 Jobs
                       01:20:00                                                                                     01:20:00
                                      Running time                                                                                 Running time
                                      Pending time                                                                                 Pending time
                       01:10:00                                                                                     01:10:00


                       01:00:00                                                                                     01:00:00


                       00:50:00                                                                                     00:50:00
     Time (HH:MM:SS)




                                                                                                  Time (HH:MM:SS)
                       00:40:00                                                                                     00:40:00


                       00:30:00                                                                                     00:30:00


                       00:20:00                                                                                     00:20:00


                       00:10:00                                                                                     00:10:00


                       00:00:00                                                                                     00:00:00
                                  0            5     10           15           20    25      30                                0            5        10            15          20         25   30
                                                              Job Number                                                                                       Job Number




Willem Toorop and Alain van Hoof (OS3)                                                    Grid on Demand                                                                 June 30, 2010         36 / 39
“Real use” and Performance              Preliminary performance results: 100 Jobs


 Preliminary performance results of job pending and
 running time: 100 jobs


                                                           Performance on DAS3 - 100 Jobs                                                                     Performance on Grid on Demand - 100 Jobs

                                      Running time                                                                                            Running time
                       02:30:00       Pending time                                                                             02:30:00       Pending time

                       02:15:00                                                                                                02:15:00

                       02:00:00                                                                                                02:00:00

                       01:45:00                                                                                                01:45:00
     Time (HH:MM:SS)




                                                                                                             Time (HH:MM:SS)
                       01:30:00                                                                                                01:30:00

                       01:15:00                                                                                                01:15:00

                       01:00:00                                                                                                01:00:00

                       00:45:00                                                                                                00:45:00

                       00:30:00                                                                                                00:30:00

                       00:15:00                                                                                                00:15:00

                       00:00:00                                                                                                00:00:00
                                  0      10      20   30        40       50     60      70   80   90   100                                0              20             40                60             80   100
                                                                     Job Number                                                                                              Job Number




Willem Toorop and Alain van Hoof (OS3)                                                            Grid on Demand                                                                       June 30, 2010          37 / 39
Conclusion


 Conclusion




         Grid on Demand can offer Grid as a Cloud service
         Parallel applications run/scale very well on Grid on Demand
         Grid on Demand can be a solution for Urgent Computing demands




Willem Toorop and Alain van Hoof (OS3)       Grid on Demand    June 30, 2010   38 / 39
The End


 Questions




Willem Toorop and Alain van Hoof (OS3)    Grid on Demand   June 30, 2010   39 / 39

Weitere ähnliche Inhalte

Was ist angesagt?

Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...
Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...
Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...
T. E. BOGALE
 
Space time coding in mimo
Space time coding in mimo Space time coding in mimo
Space time coding in mimo
ILA SHARMA
 
space time codes
space time codesspace time codes
space time codes
jie ren
 
Hoydis massive mimo and het nets benefits and challenges (1)
Hoydis   massive mimo and het nets benefits and challenges (1)Hoydis   massive mimo and het nets benefits and challenges (1)
Hoydis massive mimo and het nets benefits and challenges (1)
nwiffen
 

Was ist angesagt? (20)

Mimo tutorial by-fuyun_ling
Mimo tutorial by-fuyun_lingMimo tutorial by-fuyun_ling
Mimo tutorial by-fuyun_ling
 
Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...
Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...
Beamforming for Multiuser Massive MIMO Systems: Digital versus Hybrid Analog-...
 
Strategies to Combat Pilot Contamination in Massive MIMO Systems
Strategies to Combat Pilot Contamination in Massive MIMO SystemsStrategies to Combat Pilot Contamination in Massive MIMO Systems
Strategies to Combat Pilot Contamination in Massive MIMO Systems
 
Parallel implementation of geodesic distance transform with application in su...
Parallel implementation of geodesic distance transform with application in su...Parallel implementation of geodesic distance transform with application in su...
Parallel implementation of geodesic distance transform with application in su...
 
Deep Learning with PyTorch
Deep Learning with PyTorchDeep Learning with PyTorch
Deep Learning with PyTorch
 
MIMO Calculation
MIMO Calculation MIMO Calculation
MIMO Calculation
 
Massive mimo
Massive mimoMassive mimo
Massive mimo
 
Channel Models for Massive MIMO
Channel Models for Massive MIMOChannel Models for Massive MIMO
Channel Models for Massive MIMO
 
Presentation
PresentationPresentation
Presentation
 
Space time coding in mimo
Space time coding in mimo Space time coding in mimo
Space time coding in mimo
 
Mimo
MimoMimo
Mimo
 
MIMO Antenna and Technology installation
MIMO Antenna and Technology installationMIMO Antenna and Technology installation
MIMO Antenna and Technology installation
 
Performance Analysis of Massive MIMO Downlink System with Imperfect Channel S...
Performance Analysis of Massive MIMO Downlink System with Imperfect Channel S...Performance Analysis of Massive MIMO Downlink System with Imperfect Channel S...
Performance Analysis of Massive MIMO Downlink System with Imperfect Channel S...
 
Scalable Parallel Computing on Clouds
Scalable Parallel Computing on CloudsScalable Parallel Computing on Clouds
Scalable Parallel Computing on Clouds
 
Ship Detection from SAR Imagery Using CUDA and Performance Analysis of the Sy...
Ship Detection from SAR Imagery Using CUDA and Performance Analysis of the Sy...Ship Detection from SAR Imagery Using CUDA and Performance Analysis of the Sy...
Ship Detection from SAR Imagery Using CUDA and Performance Analysis of the Sy...
 
space time codes
space time codesspace time codes
space time codes
 
Towards 5G – Base Stations, Antennas and Fibre Everywhere
Towards 5G – Base Stations, Antennas and Fibre EverywhereTowards 5G – Base Stations, Antennas and Fibre Everywhere
Towards 5G – Base Stations, Antennas and Fibre Everywhere
 
Hoydis massive mimo and het nets benefits and challenges (1)
Hoydis   massive mimo and het nets benefits and challenges (1)Hoydis   massive mimo and het nets benefits and challenges (1)
Hoydis massive mimo and het nets benefits and challenges (1)
 
第13回 配信講義 計算科学技術特論A(2021)
第13回 配信講義 計算科学技術特論A(2021)第13回 配信講義 計算科学技術特論A(2021)
第13回 配信講義 計算科学技術特論A(2021)
 
Massive MIMO: Bristol - Lund Joint Field Trial Experiments and Record Breakin...
Massive MIMO: Bristol - Lund Joint Field Trial Experiments and Record Breakin...Massive MIMO: Bristol - Lund Joint Field Trial Experiments and Record Breakin...
Massive MIMO: Bristol - Lund Joint Field Trial Experiments and Record Breakin...
 

Andere mochten auch (6)

Taxes 2011 122211
Taxes 2011 122211Taxes 2011 122211
Taxes 2011 122211
 
Daily Freeman digital initiatives 2012
Daily Freeman digital initiatives 2012Daily Freeman digital initiatives 2012
Daily Freeman digital initiatives 2012
 
Digital initiatives
Digital initiativesDigital initiatives
Digital initiatives
 
Dutchess County Executive race forum questions
Dutchess County Executive race forum questionsDutchess County Executive race forum questions
Dutchess County Executive race forum questions
 
Google glass and journalism
Google glass and journalismGoogle glass and journalism
Google glass and journalism
 
Journalism and social media
Journalism and social mediaJournalism and social media
Journalism and social media
 

Ähnlich wie Grid on Demand

Data Communication and Internet
Data Communication and InternetData Communication and Internet
Data Communication and Internet
Anuradha Udunuwara
 
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
eSAT Journals
 
Three dimension hamiltonian broadcast
Three dimension hamiltonian broadcastThree dimension hamiltonian broadcast
Three dimension hamiltonian broadcast
IJCNCJournal
 
CloudCamp Milan 2009: Telecom Italia
CloudCamp Milan 2009: Telecom ItaliaCloudCamp Milan 2009: Telecom Italia
CloudCamp Milan 2009: Telecom Italia
Gabriele Bozzi
 

Ähnlich wie Grid on Demand (20)

Sector - Presentation at Cloud Computing & Its Applications 2009
Sector - Presentation at Cloud Computing & Its Applications 2009Sector - Presentation at Cloud Computing & Its Applications 2009
Sector - Presentation at Cloud Computing & Its Applications 2009
 
From Cloud to Fog: the Tao of IT Infrastructure Decentralization
From Cloud to Fog: the Tao of IT Infrastructure DecentralizationFrom Cloud to Fog: the Tao of IT Infrastructure Decentralization
From Cloud to Fog: the Tao of IT Infrastructure Decentralization
 
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHM
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHMY-HAMILTONIAN LAYERS BROADCAST ALGORITHM
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHM
 
Data Communication and Internet
Data Communication and InternetData Communication and Internet
Data Communication and Internet
 
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHM
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHMY-HAMILTONIAN LAYERS BROADCAST ALGORITHM
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHM
 
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHM
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHMY-HAMILTONIAN LAYERS BROADCAST ALGORITHM
Y-HAMILTONIAN LAYERS BROADCAST ALGORITHM
 
Experimental simulation and real world study on wi fi ad-hoc mode for differe...
Experimental simulation and real world study on wi fi ad-hoc mode for differe...Experimental simulation and real world study on wi fi ad-hoc mode for differe...
Experimental simulation and real world study on wi fi ad-hoc mode for differe...
 
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
 
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
Performance evaluation of rapid and spray and-wait dtn routing protocols unde...
 
Three dimension hamiltonian broadcast
Three dimension hamiltonian broadcastThree dimension hamiltonian broadcast
Three dimension hamiltonian broadcast
 
Project Matsu: Elastic Clouds for Disaster Relief
Project Matsu: Elastic Clouds for Disaster ReliefProject Matsu: Elastic Clouds for Disaster Relief
Project Matsu: Elastic Clouds for Disaster Relief
 
Network Performance Enhancement for 1G-EPON by DBA Algorithms
Network Performance Enhancement for 1G-EPON by DBA AlgorithmsNetwork Performance Enhancement for 1G-EPON by DBA Algorithms
Network Performance Enhancement for 1G-EPON by DBA Algorithms
 
Radio propagation models in wireless
Radio propagation models in wirelessRadio propagation models in wireless
Radio propagation models in wireless
 
Machine learning for decentralized and flying radio devices
Machine learning for decentralized and flying radio devicesMachine learning for decentralized and flying radio devices
Machine learning for decentralized and flying radio devices
 
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
 
Sucha_ICC_2012
Sucha_ICC_2012Sucha_ICC_2012
Sucha_ICC_2012
 
DWDM-RAM: DARPA-Sponsored Research for Data Intensive Service-on-Demand Advan...
DWDM-RAM: DARPA-Sponsored Research for Data Intensive Service-on-Demand Advan...DWDM-RAM: DARPA-Sponsored Research for Data Intensive Service-on-Demand Advan...
DWDM-RAM: DARPA-Sponsored Research for Data Intensive Service-on-Demand Advan...
 
Broadcast wormhole routed 3-d mesh
Broadcast wormhole routed 3-d meshBroadcast wormhole routed 3-d mesh
Broadcast wormhole routed 3-d mesh
 
Lessons Learned from a Year's Worth of Benchmarking Large Data Clouds (Robert...
Lessons Learned from a Year's Worth of Benchmarking Large Data Clouds (Robert...Lessons Learned from a Year's Worth of Benchmarking Large Data Clouds (Robert...
Lessons Learned from a Year's Worth of Benchmarking Large Data Clouds (Robert...
 

Kürzlich hochgeladen

Kürzlich hochgeladen (20)

🐬 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)
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
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
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
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
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
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
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 

Grid on Demand

  • 1. Welcome Grid on Demand Willem Toorop and Alain van Hoof {wtoorop,ahoof}@os3.nl June 30, 2010 Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 1 / 39
  • 2. Introduction Research Question Research Question Can Grid computing be offered as a Cloud service and what type of applications benefit from this? Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 2 / 39
  • 3. Introduction The Grid and The Cloud The Grid and The Cloud: Sharing Resources Sharing Resources to minimizing idle resources Resource Capacity Goods Processor Flops Compute Hard-disk memory Bytes Storage Network Bytes/sec Communication Bandwidth Grid Cloud (IaaS) Distribution By Collaboration By Cloud Provider Resource Type Heterogeneous Homogeneous Abstraction Middleware (open standards) Virtualization Sharing Guarantee Security infrastructure Financial infra Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 3 / 39
  • 4. Introduction The Grid and The Cloud The Grid and The Cloud: Dividing the Resources VO Grid User User Cloud Grid Grid User User User User User VO Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 4 / 39
  • 5. A Grid in the Cloud Urgent Computing A Grid in The Cloud: Urgent Computing GRID on Demand Using the elasticity and scalability of the Cloud and providing a Grid interface, current e-Science (computationally intensive science) applications can use a Grid on Demand when there is a high demand for resources for a short period of time. Example UrbanFlood (http://urbanflood.eu) wants to calculate flooding predictions when actual flooding happens, Grid on Demand can provide this. Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 5 / 39
  • 6. A Grid in the Cloud Grid on Demand Grid on Demand Job Submission Client OS: Ubuntu 10.04 Grid: Globus 4.2.1 PBS: Torque 2.6.8 Compute Nodes Head Node Grid Interface: Globus Toolkit 4.2 (open standard, widely used) Queue Manager (Distribution of jobs to nodes): Torque 2.6.2 Amazon EC2 Cloud Provider (de-facto standard with open API) Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 6 / 39
  • 7. Implementation What makes the Grid, the Grid What makes the Grid, the Grid Typical Grid usage example spanning multiple organizations Organization B ta Compute st 1 o f da acc 1 2 te 12X e dat ss use mpu a o Organization C to c Organization A use my data to compute X Grid store data Scheduler Storage User use 2 nd 1 ata to co 2 of da ss d mpu 1 ta te X acce 2 Compute Organization D Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 7 / 39
  • 8. Implementation What makes the Grid, the Grid Proxy certificates for delegation The Grid is a collaboration between multiple organizations. Grid users need to be authorized to use remote resources Those resources should be authorized to perform actions on behalf of the Grid user Proxy certificates enable delegation of authority Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 8 / 39
  • 9. Implementation What makes the Grid, the Grid Grid user create proxy Scheduler compute X create cert. request sign this Compute Okay compute X Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 9 / 39
  • 10. Implementation What makes the Grid, the Grid Grid user create proxy Scheduler compute X create cert. request sign this Compute Okay compute X Virtual Organizations are based on delegation by proxy certificates. Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 9 / 39
  • 11. Implementation What makes the Grid, the Grid Grid user Proxy certificates allow for dynamic resource allocation, create proxy Scheduler But the hosts still need a CA signed certificate. compute X This is a problem when hostname’s create cert. are assigned dynamically! request sign this Compute Okay compute X Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 9 / 39
  • 12. Implementation What makes the Grid, the Grid Grid user Proxy certificates allow for dynamic resource allocation, create proxy Scheduler But the hosts still need a CA signed certificate. compute X This is a problem when hostname’s create cert. are assigned dynamically! request sign this Compute Fixed CA in image? Okay compute X Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 9 / 39
  • 13. Implementation What makes the Grid, the Grid Grid user Proxy certificates allow for dynamic resource allocation, create proxy Scheduler But the hosts still need a CA signed certificate. compute X This is a problem when hostname’s create cert. are assigned dynamically! request sign this Compute Fixed CA in image? Okay compute X Dynamic CA on every Launch? Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 9 / 39
  • 14. Implementation Amazon Elastic Block Store Easy Image management with Amazon Elastic Block Store configure launch instance IA Running (A, S) Pending VS ← S (IA , VS , H) term inate p sto Shutting-down Stopping Pending Terminated rt sta IA inate term create AMI A Stopped (A , S ) S ← VS (IA , VS ) Life cycle of Amazon Machine Images using Elastic Block Storage A = Amazon Machine Image, S = Snapshot, I = Instance, V = Volume, H = Hostname Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 10 / 39
  • 15. Implementation EBS for configuration stages EBS for configuration stages configure configure launch provide Amazon Access Credentials instance IA Running (configure cluster) Running (A, S) VS ← S (IA , VS , H) (IA , VS , H) sh shar sh wn for ng ut for utdo shutdown shutdown for reuse for reuse do ing ari start start wn sh launch IA launch IA VS ← S VS ← S Stopped Stopped Stopped (IA , VS ) (IA , VS ) (IA , VS ) create AMI A create AMI A create AMI A S ← VS S ← VS S ← VS (A , S ) (A , S ) (A , S ) Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 11 / 39
  • 16. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 12 / 39
  • 17. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 13 / 39
  • 18. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 14 / 39
  • 19. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 15 / 39
  • 20. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 16 / 39
  • 21. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 17 / 39
  • 22. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 18 / 39
  • 23. Web Interface Launching Grid on Demand Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 19 / 39
  • 24. Web Interface Configuring the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 20 / 39
  • 25. Web Interface Configuring the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 21 / 39
  • 26. Web Interface Configuring the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 22 / 39
  • 27. Web Interface Configuring the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 23 / 39
  • 28. Web Interface Real Grid certificate usage Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 24 / 39
  • 29. Web Interface Real Grid certificate usage Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 25 / 39
  • 30. Web Interface Real Grid certificate usage Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 26 / 39
  • 31. Web Interface Elasticity of the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 27 / 39
  • 32. Web Interface Elasticity of the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 28 / 39
  • 33. Web Interface Elasticity of the cluster Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 29 / 39
  • 34. Web Interface Saving your settings Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 30 / 39
  • 35. Web Interface Saving your settings Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 31 / 39
  • 36. Web Interface Saving your settings Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 32 / 39
  • 37. “Real use” and Performance WS-VLAM and WAVE “Real use” and Performance test To test the possibilities and performance of Grid on Demand a Biomedical Application and a workflow manager are used Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 33 / 39
  • 38. “Real use” and Performance WS-VLAM and WAVE “Real use” and Performance test To test the possibilities and performance of Grid on Demand a Biomedical Application and a workflow manager are used Biomedical Application: WAVE Parallel (MonteCarlo simulation) application Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 33 / 39
  • 39. “Real use” and Performance WS-VLAM and WAVE “Real use” and Performance test To test the possibilities and performance of Grid on Demand a Biomedical Application and a workflow manager are used Biomedical Application: WAVE Parallel (MonteCarlo simulation) application Workflow Manager A (graphical) tool to assist complex e-Science application creation Creates a series of jobsubmissions WS-VLAM created by UvA SNE Group Connects to Globus Grid Interface Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 33 / 39
  • 40. “Real use” and Performance Connecting the Grid on Demand to a Workflow Manager Connecting the Grid on Demand to a Workflow Manager WAVE Biomedical Compute OS: Ubuntu 10.04 Application Grid: Globus 4.2.1 PBS: Torque 2.6.8 Compute Nodes Head Node Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 34 / 39
  • 41. “Real use” and Performance Preliminary performance results: total execution time Preliminary performance results: total execution time Grid on demand compared to a 32 node physical UvA cluster (DAS3) with Globus Grid interface Grid Jobs Total execution time DAS3 28 00:42:58 Grid on Demand 28 00:46:22 DAS3 98 02:46:36 Grid on Demand 98 00:52:26 Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 35 / 39
  • 42. “Real use” and Performance Preliminary performance results: 30 Jobs Preliminary performance results of job pending and running time: 30 jobs Performance on DAS3 - 30 Jobs Performance on Grid on Demand 30 Jobs 01:20:00 01:20:00 Running time Running time Pending time Pending time 01:10:00 01:10:00 01:00:00 01:00:00 00:50:00 00:50:00 Time (HH:MM:SS) Time (HH:MM:SS) 00:40:00 00:40:00 00:30:00 00:30:00 00:20:00 00:20:00 00:10:00 00:10:00 00:00:00 00:00:00 0 5 10 15 20 25 30 0 5 10 15 20 25 30 Job Number Job Number Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 36 / 39
  • 43. “Real use” and Performance Preliminary performance results: 100 Jobs Preliminary performance results of job pending and running time: 100 jobs Performance on DAS3 - 100 Jobs Performance on Grid on Demand - 100 Jobs Running time Running time 02:30:00 Pending time 02:30:00 Pending time 02:15:00 02:15:00 02:00:00 02:00:00 01:45:00 01:45:00 Time (HH:MM:SS) Time (HH:MM:SS) 01:30:00 01:30:00 01:15:00 01:15:00 01:00:00 01:00:00 00:45:00 00:45:00 00:30:00 00:30:00 00:15:00 00:15:00 00:00:00 00:00:00 0 10 20 30 40 50 60 70 80 90 100 0 20 40 60 80 100 Job Number Job Number Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 37 / 39
  • 44. Conclusion Conclusion Grid on Demand can offer Grid as a Cloud service Parallel applications run/scale very well on Grid on Demand Grid on Demand can be a solution for Urgent Computing demands Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 38 / 39
  • 45. The End Questions Willem Toorop and Alain van Hoof (OS3) Grid on Demand June 30, 2010 39 / 39