SlideShare uma empresa Scribd logo
1 de 19
Baixar para ler offline
Starting for the cloud
    -- two issuses in cluster:
resource allocation and overload
           management
  Ziyou Wang, Yan Li, Chao You, Minghui Zhou
                Peking University
            wangzy06@sei.pku.edu.cn
               zhmh@pku.edu.cn

             OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                             www.ow2.org.
Agenda
    Cloud Computing: Challenges
    Resource Allocation
         Shared cluster
         Resource allocation planning
    Overload Management
         Examples
         Automatic degradation mechanism
         Considerations

                      OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
Cloud Computing: Challenges
 The emergence of cloud computing makes it a cost-efficient way
  for application providers to lease the computing resources from a
  third provider
    Benefit: increase resource utilization, improve business agility,
      decrease power consumption…
 But how to effectively allocate various resources in cloud to
  different applications is still an open problem.
 When the applications host in the cloud face with overload, which
  means the demand on at least one of the cloud’s resources exceeds
  the capacity of that resource, what can we do to handle this
  situation?
 … …

                    OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
Shared Cluster
 Considering one kind of cloud implementation: the workloads of
  different web applications are not correlated, a large-scale cluster,
  called shared cluster or data center, is maintained to host a large
  number of applications simultaneously
    Each application runs on a subset of nodes
    Each node may run multiple applications              Enterprises
                                Users




                                              Third parties


                    OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
Resource Allocation: a scenario
 As the cluster’s resources are no longer occupied by one
  application, it requires the cluster to allocate the resources on
  demand                                                                              Applica>on	
  users	
  



    For example
            An increaseinstances
            Place new of
                re-allocate                                                                               Dispatcher	
  
            appworkload
            in the dataworkload
                 A,C’s center


                                             Node	
  1	
                                                        Node	
  16	
  

                                                  app	
  A	
          app	
  C	
                                 app	
  A	
        app	
  B	
     Node	
  150	
  

                                                          middleware                                                     middleware                 app	
  C	
      app	
  D	
  
                                                                                                                                                            middleware
                                                                                 High-­‐throughput	
  	
  
                               Node	
  99	
                                      low-­‐latency	
  network	
  

                                   app	
  B	
          app	
  A	
  
                                                                                                                       Other	
                    Repository	
  
                                           middleware                                                                  nodes	
  
                                                                                                                …                                       Apps	
  

                                                                                                     Shared	
  cluster	
  



                       OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                         www.ow2.org.
Self-adaptive Resource Allocation
              Model

                                      Self-­‐adap4ve	
  	
  
                                   resource	
  	
  alloca4on	
  	
  

 Requests   Resource	
  alloca>on	
  	
                      Resource	
  alloca>on	
  
                 planning	
                                      execu>on	
  	
  




            OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                              www.ow2.org.
Our Resource Allocation Work
                            Middleware
                  Resource	
  	
                                  Dispatcher                       Management	
  	
  
       …          alloca>on	
      …                                                                Console
                  	
  planning
                                                       messages                requests
                                                                                                         commands
          coopera>on
                                                                                                    Middleware
Resource	
  alloca>on	
         Communicator
    planning                                                                   VM                             VM
                                   Local	
  valuator
                                                                     customized	
     …              customized	
  
                                                              app	
  a    JOnAS               app	
  x    JOnAS
Resource	
  alloca>on	
      Resource	
  par>>oner
    execu>on                       App	
  deployer                       Virtual	
  Machine	
  Monitor



                      Repository            For the resource allocation planning, we propose a
                                            decentralized resource allocation planning approach
                                            •  odes decide their own resource allocation
                                             N
                                            •  arket-based coordination is adopted to help them
                                             M
                                            make the resource decision
                                            Until now, the approach is evaluated with a serial of
                                            simulated experiments, and is being implemented in
                                            the cluster with JO2nAS


                                      OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                                        www.ow2.org.
Resource Allocation Planning
 To support application prioritization, applications can be assign
  with the different utility values. Accordingly, the goal of resource
  management is to maximize the total utility values of the requests
  satisfied
 Inspired by human market, we model the shared cluster as a
  market, where shares of application requests are treated as goods
  and nodes as dealers to exchange goods
 Basing on local valuation of the goods, each node autonomously
  and continuously trades with others in order to find an application
  share combination which fits the node’s resource constrains and
  maximize its income


                   OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                     www.ow2.org.
Resource Allocation Planning
 When a node wants to sell, more than one node may want to buy.
  To make the seller transfer the goods to the appropriate buyers, an
  auction mechanism is adopted
                          4. inform   (app C , 30% to n50, 20% to
                                      n65)
                                                                                      Sell C 30%
          Dispatcher
                                                               Node 1           4. notify               2.2       want C, 35%
        N1: … (app C, 70%)                          3. sort                                   Node 50
                                                               app A app C
        N50: …                                                                                app A app B             ...
                                                                  middleware
        N65: …(app C, 10%)                                                                         middleware 2.1 valuation
        N100: …                                          (appC, 50%, 100 req/ 1. multicast                              Nodes
                                       4 notify          s)
                                                                                                                      app




                                                                                                         ...
                 update
                                       Sell C 20%                                                                           middleware
                                                                      Node 65                 Node 100
        N1: … (app C, 20%)
                                                      2.1 valuation
        N50: … (app C,30%)
                                                                      app B app C       ...   app B app D
                                                                                                                       ...
                                                         2.2
        N65: …(app C, 30%)
                                                                         middleware                middleware
        N100: …                                                want C, 20%                            2.1 valuation




                                      OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                                        www.ow2.org.
Our Resource Allocation Work
                            Middleware
                  Resource	
  	
                                  Dispatcher                       Management	
  	
  
       …          alloca>on	
      …                                                                Console
                  	
  planning
                                                       messages                requests
                                                                                                         commands
          coopera>on
                                                                                                    Middleware
Resource	
  alloca>on	
         Communicator
    planning                                                                   VM                             VM
                                   Local	
  valuator
                                                                     customized	
     …              customized	
  
                                                              app	
  a    JOnAS               app	
  x    JOnAS
Resource	
  alloca>on	
      Resource	
  par>>oner
    execu>on                       App	
  deployer                       Virtual	
  Machine	
  Monitor



                      Repository
                                              For the resource allocation execution
                                              • ntegrate a VMM into the middleware
                                               I
                                              •  utomatically load the app and partition the resource at
                                               A
                                              runtime via VMM
                                              •  ustomize JOnAS for the app, and store the customized
                                               C
                                              image in the repository
                                              •  roportionally workload dispatching
                                               P
                                              Now, we use Open VZ, a lightweight OS level VMM, as a
                                              case study, and are trying to integrate OpenVZ into the
                                              middleware

                                           OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                                             www.ow2.org.
Agenda
    Cloud Computing: Challenges
    Resource Allocation
         Shared cluster
         Resource allocation planning
    Overload Management
         Examples
         Automatic degradation mechanism
         Considerations

                      OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
Examples
 On September 11th 2001, for instance, the workload on a
  popular news web site increased by an order of magnitude in
  30 min, with the workload doubling every 7 min in that
  period.




 April 21th 2010, is the China National Mourning for Yushu
  Quake Victims. Theatre and sporting performances are
  cancelled, karaoke bars shut and the culture ministry has
  ordered suspension of all online music, games, comics, films
  and TV shows.
 Too many people choose to visit an online shopping site.
                    OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
When overload happens?
 Overload prevention is a critical goal so that a system can remain
  operational in the presence of overload even when the incoming
  request rate is several times greater than the system’s capacity.

 It is well known that the workload seen by Internet applications
  varies over multiple time-scales and often in an unpredictable
  fashion.

 Unexpected things are always happening:
    Featured on national television or in a major newspaper.
    Under-provisioning for sales-boosting holidays

                   OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                     www.ow2.org.
The TaoBao Architecture
 Apache + Application Server + MySQL
 200+ applications, thousands of components
 12k servers
 2k~3k java servers
                                                                 Shop
                                 Search                          Cart




 Product                      Product Recommendation
 Browsing


              /46



                    OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
The Reality – Manual Service
            Degradation
 In response to overload:
    CNN replaced its front page with simple HTML page that could
      be transmitted in a single Ethernet packet .
    Taobao turned off a sub system.
 All these techniques are implemented manually, though a better
  approach would be to degrade service gracefully and automatically
  in response to load.
    Which point causes overload?
    Which resource is the bottleneck?
    Which service should be degraded or turned off?
    All user be affected or not?

                  OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                    www.ow2.org.
Automatic Degradation Mechanism
  Overload Priority defines the priorities of different services and
   degradation actions can be taken.
  Overload Detection is responsible for signaling the occurrence of
   instable status of the application.
  Overload Localization is triggered to locate the bottleneck of resources.
  Overload Controller will take appropriate actions to degrade some
   unnecessary services to release more resources to support key services.
                                  Mechanism



                                               Overload




                                                                    Degradation
                    Overload Priority         Overload Controller                 Service        Service             Service



                                                                                       Service             Service


                                                     Overload




                    OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
Automatic Application Degradation
  Node level degradation                  Cluster level degradation
  Fine-grained                            Coarse-grained
      Component level degradation              Sub-system level degradation
      Middleware level degradation        Resource management
                                           Service differentiation




                         OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                           www.ow2.org.
Considerations
 Hard to be transparent to the user ( what can de degraded?
  sometimes how?)

 Using it alone can contribute to delay overload, but it needs to be
  combined with other techniques to be fully effective.
    Dynamic resource allocation
    Admission control
    Service differentiation
    … …




                    OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                                      www.ow2.org.
OW2 Annual Conference 2010, November 24-25, La Cantine, Paris.
                                                  www.ow2.org.

Mais conteúdo relacionado

Destaque

Internet Threats and Risk Mitigation
Internet Threats and Risk MitigationInternet Threats and Risk Mitigation
Internet Threats and Risk MitigationBrandProtect
 
Participating in AppHub, the European Open Source Marketplace
Participating in AppHub, the European Open Source MarketplaceParticipating in AppHub, the European Open Source Marketplace
Participating in AppHub, the European Open Source MarketplaceOW2
 
TDC 2012 - Métricas de código na arquitetura
TDC 2012 - Métricas de código na arquiteturaTDC 2012 - Métricas de código na arquitetura
TDC 2012 - Métricas de código na arquiteturaLeandro Daniel
 
Vol 02 chapter 11 2012
Vol 02 chapter 11 2012Vol 02 chapter 11 2012
Vol 02 chapter 11 2012dphil002
 
LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora.
 LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora. LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora.
LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora.OW2
 
Fossology, OW2con11, Nov 24-25, Paris
Fossology, OW2con11, Nov 24-25, ParisFossology, OW2con11, Nov 24-25, Paris
Fossology, OW2con11, Nov 24-25, ParisOW2
 
Palacio Gobierno del Ecuador
Palacio Gobierno del EcuadorPalacio Gobierno del Ecuador
Palacio Gobierno del EcuadorPablo Guaña
 
Profile_ Ikwhan chang
Profile_ Ikwhan changProfile_ Ikwhan chang
Profile_ Ikwhan changMatthew Chang
 
Component Based Software OW2 Conference Nov10
Component Based Software OW2 Conference Nov10Component Based Software OW2 Conference Nov10
Component Based Software OW2 Conference Nov10OW2
 
CompatibleOne OW2 Conference Nov10
CompatibleOne OW2 Conference Nov10CompatibleOne OW2 Conference Nov10
CompatibleOne OW2 Conference Nov10OW2
 
Wildi 2009 Resume
Wildi 2009 ResumeWildi 2009 Resume
Wildi 2009 ResumeWildi
 
Contrail Project, OW2con11, Nov 24-25, Paris
Contrail Project, OW2con11, Nov 24-25, ParisContrail Project, OW2con11, Nov 24-25, Paris
Contrail Project, OW2con11, Nov 24-25, ParisOW2
 
American Tortoise Rescue The Clock Is Ticking
American Tortoise Rescue  The Clock Is TickingAmerican Tortoise Rescue  The Clock Is Ticking
American Tortoise Rescue The Clock Is Tickingtellem
 
Beowulf summary
Beowulf summaryBeowulf summary
Beowulf summaryMr. Euc@s
 
Cloud workload guidelines
Cloud workload guidelinesCloud workload guidelines
Cloud workload guidelinesJen Wei Lee
 
OW2 Next Gen Quality Program
OW2 Next Gen Quality ProgramOW2 Next Gen Quality Program
OW2 Next Gen Quality ProgramOW2
 
Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2
Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2
Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2OW2
 
Antelink OW2 Conference Nov10
Antelink OW2 Conference Nov10Antelink OW2 Conference Nov10
Antelink OW2 Conference Nov10OW2
 
Open Source BI OW2 Conference Nov10
Open Source BI OW2 Conference Nov10Open Source BI OW2 Conference Nov10
Open Source BI OW2 Conference Nov10OW2
 

Destaque (20)

Internet Threats and Risk Mitigation
Internet Threats and Risk MitigationInternet Threats and Risk Mitigation
Internet Threats and Risk Mitigation
 
Life21
Life21Life21
Life21
 
Participating in AppHub, the European Open Source Marketplace
Participating in AppHub, the European Open Source MarketplaceParticipating in AppHub, the European Open Source Marketplace
Participating in AppHub, the European Open Source Marketplace
 
TDC 2012 - Métricas de código na arquitetura
TDC 2012 - Métricas de código na arquiteturaTDC 2012 - Métricas de código na arquitetura
TDC 2012 - Métricas de código na arquitetura
 
Vol 02 chapter 11 2012
Vol 02 chapter 11 2012Vol 02 chapter 11 2012
Vol 02 chapter 11 2012
 
LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora.
 LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora. LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora.
LemonLDAP::NG - the New Generation WebSSO !, David Coutadeur, Linagora.
 
Fossology, OW2con11, Nov 24-25, Paris
Fossology, OW2con11, Nov 24-25, ParisFossology, OW2con11, Nov 24-25, Paris
Fossology, OW2con11, Nov 24-25, Paris
 
Palacio Gobierno del Ecuador
Palacio Gobierno del EcuadorPalacio Gobierno del Ecuador
Palacio Gobierno del Ecuador
 
Profile_ Ikwhan chang
Profile_ Ikwhan changProfile_ Ikwhan chang
Profile_ Ikwhan chang
 
Component Based Software OW2 Conference Nov10
Component Based Software OW2 Conference Nov10Component Based Software OW2 Conference Nov10
Component Based Software OW2 Conference Nov10
 
CompatibleOne OW2 Conference Nov10
CompatibleOne OW2 Conference Nov10CompatibleOne OW2 Conference Nov10
CompatibleOne OW2 Conference Nov10
 
Wildi 2009 Resume
Wildi 2009 ResumeWildi 2009 Resume
Wildi 2009 Resume
 
Contrail Project, OW2con11, Nov 24-25, Paris
Contrail Project, OW2con11, Nov 24-25, ParisContrail Project, OW2con11, Nov 24-25, Paris
Contrail Project, OW2con11, Nov 24-25, Paris
 
American Tortoise Rescue The Clock Is Ticking
American Tortoise Rescue  The Clock Is TickingAmerican Tortoise Rescue  The Clock Is Ticking
American Tortoise Rescue The Clock Is Ticking
 
Beowulf summary
Beowulf summaryBeowulf summary
Beowulf summary
 
Cloud workload guidelines
Cloud workload guidelinesCloud workload guidelines
Cloud workload guidelines
 
OW2 Next Gen Quality Program
OW2 Next Gen Quality ProgramOW2 Next Gen Quality Program
OW2 Next Gen Quality Program
 
Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2
Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2
Ow2stack, the OW2 Community Cloud Testbed, Xiaolong Kong, OW2
 
Antelink OW2 Conference Nov10
Antelink OW2 Conference Nov10Antelink OW2 Conference Nov10
Antelink OW2 Conference Nov10
 
Open Source BI OW2 Conference Nov10
Open Source BI OW2 Conference Nov10Open Source BI OW2 Conference Nov10
Open Source BI OW2 Conference Nov10
 

Semelhante a Starting for the Cloud, OW2 Conference Nov10

Cloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergenceCloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergenceDavid Karam
 
Cloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergenceCloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergenceDavid Karam
 
Jonas On Windows Azure OW2con11, Nov 24-25, Paris
Jonas On Windows Azure OW2con11, Nov 24-25, ParisJonas On Windows Azure OW2con11, Nov 24-25, Paris
Jonas On Windows Azure OW2con11, Nov 24-25, ParisOW2
 
Sirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, Paris
Sirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, ParisSirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, Paris
Sirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, ParisOW2
 
OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...
OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...
OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...OW2
 
OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...
OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...
OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...OW2
 
Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...
Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...
Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...OW2
 
new business models in the cloud changing IT sourcing
new business models in the cloud changing IT sourcingnew business models in the cloud changing IT sourcing
new business models in the cloud changing IT sourcingHans van Grieken
 
Cloud Architectures for Alpha Dogs!
Cloud Architectures for Alpha Dogs!Cloud Architectures for Alpha Dogs!
Cloud Architectures for Alpha Dogs!Vikas Gupta
 
Windows Azure Platform - The Color of Cloud Computing
Windows Azure Platform - The Color of Cloud ComputingWindows Azure Platform - The Color of Cloud Computing
Windows Azure Platform - The Color of Cloud ComputingGeorge Kanellopoulos
 
Cloud Application Platforms – Reality & Promise
Cloud Application Platforms – Reality & PromiseCloud Application Platforms – Reality & Promise
Cloud Application Platforms – Reality & PromiseIntel Corporation
 
Lenovo: The Cloud Over BYOD
Lenovo: The Cloud Over BYODLenovo: The Cloud Over BYOD
Lenovo: The Cloud Over BYODLenovo Education
 
AbiCloud Webinar 1.0
AbiCloud Webinar 1.0AbiCloud Webinar 1.0
AbiCloud Webinar 1.0Abiquo, Inc.
 
RunningQuantumOnQuantumAtNicira.pdf
RunningQuantumOnQuantumAtNicira.pdfRunningQuantumOnQuantumAtNicira.pdf
RunningQuantumOnQuantumAtNicira.pdfOpenStack Foundation
 
Parallel and Distributed Computing: BOINC Grid Implementation Paper
Parallel and Distributed Computing: BOINC Grid Implementation PaperParallel and Distributed Computing: BOINC Grid Implementation Paper
Parallel and Distributed Computing: BOINC Grid Implementation PaperRodrigo Neves
 
Your Firm In The Cloud
Your Firm In The CloudYour Firm In The Cloud
Your Firm In The CloudBCS ProSoft
 
Utility metered cloud slideshare
Utility metered cloud   slideshareUtility metered cloud   slideshare
Utility metered cloud slideshareValencell, Inc.
 
Application Performance Management in the Clouds - Lessons Learned
Application Performance Management in the Clouds - Lessons LearnedApplication Performance Management in the Clouds - Lessons Learned
Application Performance Management in the Clouds - Lessons LearnedMichael Kopp
 

Semelhante a Starting for the Cloud, OW2 Conference Nov10 (20)

Cloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergenceCloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergence
 
Cloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergenceCloud Computing, SOA and Web 2.0, an inevitable convergence
Cloud Computing, SOA and Web 2.0, an inevitable convergence
 
Jonas On Windows Azure OW2con11, Nov 24-25, Paris
Jonas On Windows Azure OW2con11, Nov 24-25, ParisJonas On Windows Azure OW2con11, Nov 24-25, Paris
Jonas On Windows Azure OW2con11, Nov 24-25, Paris
 
Sirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, Paris
Sirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, ParisSirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, Paris
Sirocco Open Source Multi Cloud Manager, OW2con11, Nov 24-25, Paris
 
OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...
OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...
OpenCloudware: the Cloud application lifecycle management platform, OW2con'12...
 
OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...
OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...
OpenCloudware The Cloud applicaton lifecycle management platform, OW2con'12, ...
 
Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...
Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...
Using Community Clouds for Load Testing- the ProActive CLIF solution, OW2con'...
 
new business models in the cloud changing IT sourcing
new business models in the cloud changing IT sourcingnew business models in the cloud changing IT sourcing
new business models in the cloud changing IT sourcing
 
Cloud Architectures for Alpha Dogs!
Cloud Architectures for Alpha Dogs!Cloud Architectures for Alpha Dogs!
Cloud Architectures for Alpha Dogs!
 
Windows Azure Platform - The Color of Cloud Computing
Windows Azure Platform - The Color of Cloud ComputingWindows Azure Platform - The Color of Cloud Computing
Windows Azure Platform - The Color of Cloud Computing
 
Cloud Application Platforms – Reality & Promise
Cloud Application Platforms – Reality & PromiseCloud Application Platforms – Reality & Promise
Cloud Application Platforms – Reality & Promise
 
CloudSpurt customer
CloudSpurt customerCloudSpurt customer
CloudSpurt customer
 
Lenovo: The Cloud Over BYOD
Lenovo: The Cloud Over BYODLenovo: The Cloud Over BYOD
Lenovo: The Cloud Over BYOD
 
AbiCloud Webinar 1.0
AbiCloud Webinar 1.0AbiCloud Webinar 1.0
AbiCloud Webinar 1.0
 
RunningQuantumOnQuantumAtNicira.pdf
RunningQuantumOnQuantumAtNicira.pdfRunningQuantumOnQuantumAtNicira.pdf
RunningQuantumOnQuantumAtNicira.pdf
 
Parallel and Distributed Computing: BOINC Grid Implementation Paper
Parallel and Distributed Computing: BOINC Grid Implementation PaperParallel and Distributed Computing: BOINC Grid Implementation Paper
Parallel and Distributed Computing: BOINC Grid Implementation Paper
 
"Parallel and Distributed Computing: BOINC Grid Implementation" por Rodrigo N...
"Parallel and Distributed Computing: BOINC Grid Implementation" por Rodrigo N..."Parallel and Distributed Computing: BOINC Grid Implementation" por Rodrigo N...
"Parallel and Distributed Computing: BOINC Grid Implementation" por Rodrigo N...
 
Your Firm In The Cloud
Your Firm In The CloudYour Firm In The Cloud
Your Firm In The Cloud
 
Utility metered cloud slideshare
Utility metered cloud   slideshareUtility metered cloud   slideshare
Utility metered cloud slideshare
 
Application Performance Management in the Clouds - Lessons Learned
Application Performance Management in the Clouds - Lessons LearnedApplication Performance Management in the Clouds - Lessons Learned
Application Performance Management in the Clouds - Lessons Learned
 

Mais de OW2

OW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in Roma
OW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in RomaOW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in Roma
OW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in RomaOW2
 
GLPi v.10, les fonctionnalités principales et l'offre cloud
GLPi v.10, les fonctionnalités principales et l'offre cloudGLPi v.10, les fonctionnalités principales et l'offre cloud
GLPi v.10, les fonctionnalités principales et l'offre cloudOW2
 
Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...
Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...
Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...OW2
 
FusionIAM : la gestion des identités et des accés open source
FusionIAM : la gestion des identités et des accés open sourceFusionIAM : la gestion des identités et des accés open source
FusionIAM : la gestion des identités et des accés open sourceOW2
 
OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...
OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...
OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...OW2
 
SFScon'20 Bringing the User into the Equation
SFScon'20 Bringing the User into the EquationSFScon'20 Bringing the User into the Equation
SFScon'20 Bringing the User into the EquationOW2
 
Towards a sustainable solution to open source sustainability, OW2online20, Ju...
Towards a sustainable solution to open source sustainability, OW2online20, Ju...Towards a sustainable solution to open source sustainability, OW2online20, Ju...
Towards a sustainable solution to open source sustainability, OW2online20, Ju...OW2
 
Advanced proactive and polymorphing cloud application adaptation with MORPHEM...
Advanced proactive and polymorphing cloud application adaptation with MORPHEM...Advanced proactive and polymorphing cloud application adaptation with MORPHEM...
Advanced proactive and polymorphing cloud application adaptation with MORPHEM...OW2
 
Open Source governance and the Eclipse Foundation, OW2online, June 2020
Open Source governance and the Eclipse Foundation, OW2online, June 2020Open Source governance and the Eclipse Foundation, OW2online, June 2020
Open Source governance and the Eclipse Foundation, OW2online, June 2020OW2
 
Open source contribution policies, OW2online, June 2020
Open source contribution policies, OW2online, June 2020Open source contribution policies, OW2online, June 2020
Open source contribution policies, OW2online, June 2020OW2
 
Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...
Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...
Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...OW2
 
Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020
Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020
Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020OW2
 
Open Source Compliance at Orange, OW2online, June 2020
Open Source Compliance at Orange, OW2online, June 2020Open Source Compliance at Orange, OW2online, June 2020
Open Source Compliance at Orange, OW2online, June 2020OW2
 
Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020
Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020
Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020OW2
 
Intelligent package management with FASTEN, OW2online, June 2020
Intelligent package management with FASTEN, OW2online, June 2020Intelligent package management with FASTEN, OW2online, June 2020
Intelligent package management with FASTEN, OW2online, June 2020OW2
 
DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020
DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020
DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020OW2
 
Enabling DevOps for IoT software development, powered by Open Source, OW2onli...
Enabling DevOps for IoT software development, powered by Open Source, OW2onli...Enabling DevOps for IoT software development, powered by Open Source, OW2onli...
Enabling DevOps for IoT software development, powered by Open Source, OW2onli...OW2
 
Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...
Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...
Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...OW2
 
Cacti and Big Data at Orange France, OW2online, June 2020
Cacti and Big Data at Orange France, OW2online, June 2020Cacti and Big Data at Orange France, OW2online, June 2020
Cacti and Big Data at Orange France, OW2online, June 2020OW2
 
Open Source Geographic Information System at Orange, OW2online, June 2020
Open Source Geographic Information System at Orange, OW2online, June 2020Open Source Geographic Information System at Orange, OW2online, June 2020
Open Source Geographic Information System at Orange, OW2online, June 2020OW2
 

Mais de OW2 (20)

OW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in Roma
OW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in RomaOW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in Roma
OW2 and RIOS teaming up to boost the open source impact, Nov. 2022 in Roma
 
GLPi v.10, les fonctionnalités principales et l'offre cloud
GLPi v.10, les fonctionnalités principales et l'offre cloudGLPi v.10, les fonctionnalités principales et l'offre cloud
GLPi v.10, les fonctionnalités principales et l'offre cloud
 
Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...
Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...
Centreon: superviser le Cloud et le Legacy à partir d'une même plateforme, po...
 
FusionIAM : la gestion des identités et des accés open source
FusionIAM : la gestion des identités et des accés open sourceFusionIAM : la gestion des identités et des accés open source
FusionIAM : la gestion des identités et des accés open source
 
OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...
OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...
OW2 Association Européenne aux racines grenobloises, transformer l'industrie ...
 
SFScon'20 Bringing the User into the Equation
SFScon'20 Bringing the User into the EquationSFScon'20 Bringing the User into the Equation
SFScon'20 Bringing the User into the Equation
 
Towards a sustainable solution to open source sustainability, OW2online20, Ju...
Towards a sustainable solution to open source sustainability, OW2online20, Ju...Towards a sustainable solution to open source sustainability, OW2online20, Ju...
Towards a sustainable solution to open source sustainability, OW2online20, Ju...
 
Advanced proactive and polymorphing cloud application adaptation with MORPHEM...
Advanced proactive and polymorphing cloud application adaptation with MORPHEM...Advanced proactive and polymorphing cloud application adaptation with MORPHEM...
Advanced proactive and polymorphing cloud application adaptation with MORPHEM...
 
Open Source governance and the Eclipse Foundation, OW2online, June 2020
Open Source governance and the Eclipse Foundation, OW2online, June 2020Open Source governance and the Eclipse Foundation, OW2online, June 2020
Open Source governance and the Eclipse Foundation, OW2online, June 2020
 
Open source contribution policies, OW2online, June 2020
Open source contribution policies, OW2online, June 2020Open source contribution policies, OW2online, June 2020
Open source contribution policies, OW2online, June 2020
 
Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...
Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...
Software development at scale, pandemic lockdown and oss ecosystems, OW2onlin...
 
Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020
Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020
Overview of the OpenChain Reference Tooling Work Group, OW2online20, June 2020
 
Open Source Compliance at Orange, OW2online, June 2020
Open Source Compliance at Orange, OW2online, June 2020Open Source Compliance at Orange, OW2online, June 2020
Open Source Compliance at Orange, OW2online, June 2020
 
Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020
Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020
Ideas, methods and tools for OSS Compliance assessment, OW2online, June 2020
 
Intelligent package management with FASTEN, OW2online, June 2020
Intelligent package management with FASTEN, OW2online, June 2020Intelligent package management with FASTEN, OW2online, June 2020
Intelligent package management with FASTEN, OW2online, June 2020
 
DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020
DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020
DECODER, a Smarter Environment for DevOps Teams , OW2online, June 2020
 
Enabling DevOps for IoT software development, powered by Open Source, OW2onli...
Enabling DevOps for IoT software development, powered by Open Source, OW2onli...Enabling DevOps for IoT software development, powered by Open Source, OW2onli...
Enabling DevOps for IoT software development, powered by Open Source, OW2onli...
 
Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...
Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...
Upcoming Challenges in Artificial Intelligence Research and Development, OW2o...
 
Cacti and Big Data at Orange France, OW2online, June 2020
Cacti and Big Data at Orange France, OW2online, June 2020Cacti and Big Data at Orange France, OW2online, June 2020
Cacti and Big Data at Orange France, OW2online, June 2020
 
Open Source Geographic Information System at Orange, OW2online, June 2020
Open Source Geographic Information System at Orange, OW2online, June 2020Open Source Geographic Information System at Orange, OW2online, June 2020
Open Source Geographic Information System at Orange, OW2online, June 2020
 

Último

Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAshyamraj55
 
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...Aggregage
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioChristian Posta
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8DianaGray10
 
AI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarAI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarPrecisely
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding TeamAdam Moalla
 
20230202 - Introduction to tis-py
20230202 - Introduction to tis-py20230202 - Introduction to tis-py
20230202 - Introduction to tis-pyJamie (Taka) Wang
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?IES VE
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Will Schroeder
 
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfJamie (Taka) Wang
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1DianaGray10
 
Machine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfMachine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfAijun Zhang
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationIES VE
 
Linked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesLinked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesDavid Newbury
 
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostMatt Ray
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsSafe Software
 
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...DianaGray10
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Commit University
 
Designing A Time bound resource download URL
Designing A Time bound resource download URLDesigning A Time bound resource download URL
Designing A Time bound resource download URLRuncy Oommen
 

Último (20)

Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPAAnypoint Code Builder , Google Pub sub connector and MuleSoft RPA
Anypoint Code Builder , Google Pub sub connector and MuleSoft RPA
 
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
The Data Metaverse: Unpacking the Roles, Use Cases, and Tech Trends in Data a...
 
Comparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and IstioComparing Sidecar-less Service Mesh from Cilium and Istio
Comparing Sidecar-less Service Mesh from Cilium and Istio
 
UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8UiPath Studio Web workshop series - Day 8
UiPath Studio Web workshop series - Day 8
 
AI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity WebinarAI You Can Trust - Ensuring Success with Data Integrity Webinar
AI You Can Trust - Ensuring Success with Data Integrity Webinar
 
9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team9 Steps For Building Winning Founding Team
9 Steps For Building Winning Founding Team
 
20230202 - Introduction to tis-py
20230202 - Introduction to tis-py20230202 - Introduction to tis-py
20230202 - Introduction to tis-py
 
How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?How Accurate are Carbon Emissions Projections?
How Accurate are Carbon Emissions Projections?
 
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
Apres-Cyber - The Data Dilemma: Bridging Offensive Operations and Machine Lea...
 
20230104 - machine vision
20230104 - machine vision20230104 - machine vision
20230104 - machine vision
 
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
activity_diagram_combine_v4_20190827.pdfactivity_diagram_combine_v4_20190827.pdf
 
Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1Secure your environment with UiPath and CyberArk technologies - Session 1
Secure your environment with UiPath and CyberArk technologies - Session 1
 
Machine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdfMachine Learning Model Validation (Aijun Zhang 2024).pdf
Machine Learning Model Validation (Aijun Zhang 2024).pdf
 
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve DecarbonizationUsing IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
Using IESVE for Loads, Sizing and Heat Pump Modeling to Achieve Decarbonization
 
Linked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond OntologiesLinked Data in Production: Moving Beyond Ontologies
Linked Data in Production: Moving Beyond Ontologies
 
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCostKubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
KubeConEU24-Monitoring Kubernetes and Cloud Spend with OpenCost
 
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration WorkflowsIgniting Next Level Productivity with AI-Infused Data Integration Workflows
Igniting Next Level Productivity with AI-Infused Data Integration Workflows
 
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
Connector Corner: Extending LLM automation use cases with UiPath GenAI connec...
 
Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)Crea il tuo assistente AI con lo Stregatto (open source python framework)
Crea il tuo assistente AI con lo Stregatto (open source python framework)
 
Designing A Time bound resource download URL
Designing A Time bound resource download URLDesigning A Time bound resource download URL
Designing A Time bound resource download URL
 

Starting for the Cloud, OW2 Conference Nov10

  • 1. Starting for the cloud -- two issuses in cluster: resource allocation and overload management Ziyou Wang, Yan Li, Chao You, Minghui Zhou Peking University wangzy06@sei.pku.edu.cn zhmh@pku.edu.cn OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 2. Agenda   Cloud Computing: Challenges   Resource Allocation   Shared cluster   Resource allocation planning   Overload Management   Examples   Automatic degradation mechanism   Considerations OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 3. Cloud Computing: Challenges  The emergence of cloud computing makes it a cost-efficient way for application providers to lease the computing resources from a third provider  Benefit: increase resource utilization, improve business agility, decrease power consumption…  But how to effectively allocate various resources in cloud to different applications is still an open problem.  When the applications host in the cloud face with overload, which means the demand on at least one of the cloud’s resources exceeds the capacity of that resource, what can we do to handle this situation?  … … OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 4. Shared Cluster  Considering one kind of cloud implementation: the workloads of different web applications are not correlated, a large-scale cluster, called shared cluster or data center, is maintained to host a large number of applications simultaneously  Each application runs on a subset of nodes  Each node may run multiple applications Enterprises Users Third parties OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 5. Resource Allocation: a scenario  As the cluster’s resources are no longer occupied by one application, it requires the cluster to allocate the resources on demand Applica>on  users    For example An increaseinstances Place new of re-allocate Dispatcher   appworkload in the dataworkload A,C’s center Node  1   Node  16   app  A   app  C   app  A   app  B   Node  150   middleware middleware app  C   app  D   middleware High-­‐throughput     Node  99   low-­‐latency  network   app  B   app  A   Other   Repository   middleware nodes   … Apps   Shared  cluster   OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 6. Self-adaptive Resource Allocation Model Self-­‐adap4ve     resource    alloca4on     Requests Resource  alloca>on     Resource  alloca>on   planning   execu>on     OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 7. Our Resource Allocation Work Middleware Resource     Dispatcher Management     … alloca>on   … Console  planning messages requests commands coopera>on Middleware Resource  alloca>on   Communicator planning VM VM Local  valuator customized   … customized   app  a JOnAS app  x JOnAS Resource  alloca>on   Resource  par>>oner execu>on App  deployer Virtual  Machine  Monitor Repository For the resource allocation planning, we propose a decentralized resource allocation planning approach •  odes decide their own resource allocation N •  arket-based coordination is adopted to help them M make the resource decision Until now, the approach is evaluated with a serial of simulated experiments, and is being implemented in the cluster with JO2nAS OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 8. Resource Allocation Planning  To support application prioritization, applications can be assign with the different utility values. Accordingly, the goal of resource management is to maximize the total utility values of the requests satisfied  Inspired by human market, we model the shared cluster as a market, where shares of application requests are treated as goods and nodes as dealers to exchange goods  Basing on local valuation of the goods, each node autonomously and continuously trades with others in order to find an application share combination which fits the node’s resource constrains and maximize its income OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 9. Resource Allocation Planning  When a node wants to sell, more than one node may want to buy. To make the seller transfer the goods to the appropriate buyers, an auction mechanism is adopted 4. inform (app C , 30% to n50, 20% to n65) Sell C 30% Dispatcher Node 1 4. notify 2.2 want C, 35% N1: … (app C, 70%) 3. sort Node 50 app A app C N50: … app A app B ... middleware N65: …(app C, 10%) middleware 2.1 valuation N100: … (appC, 50%, 100 req/ 1. multicast Nodes 4 notify s) app ... update Sell C 20% middleware Node 65 Node 100 N1: … (app C, 20%) 2.1 valuation N50: … (app C,30%) app B app C ... app B app D ... 2.2 N65: …(app C, 30%) middleware middleware N100: … want C, 20% 2.1 valuation OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 10. Our Resource Allocation Work Middleware Resource     Dispatcher Management     … alloca>on   … Console  planning messages requests commands coopera>on Middleware Resource  alloca>on   Communicator planning VM VM Local  valuator customized   … customized   app  a JOnAS app  x JOnAS Resource  alloca>on   Resource  par>>oner execu>on App  deployer Virtual  Machine  Monitor Repository For the resource allocation execution • ntegrate a VMM into the middleware I •  utomatically load the app and partition the resource at A runtime via VMM •  ustomize JOnAS for the app, and store the customized C image in the repository •  roportionally workload dispatching P Now, we use Open VZ, a lightweight OS level VMM, as a case study, and are trying to integrate OpenVZ into the middleware OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 11. Agenda   Cloud Computing: Challenges   Resource Allocation   Shared cluster   Resource allocation planning   Overload Management   Examples   Automatic degradation mechanism   Considerations OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 12. Examples  On September 11th 2001, for instance, the workload on a popular news web site increased by an order of magnitude in 30 min, with the workload doubling every 7 min in that period.  April 21th 2010, is the China National Mourning for Yushu Quake Victims. Theatre and sporting performances are cancelled, karaoke bars shut and the culture ministry has ordered suspension of all online music, games, comics, films and TV shows.  Too many people choose to visit an online shopping site. OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 13. When overload happens?  Overload prevention is a critical goal so that a system can remain operational in the presence of overload even when the incoming request rate is several times greater than the system’s capacity.  It is well known that the workload seen by Internet applications varies over multiple time-scales and often in an unpredictable fashion.  Unexpected things are always happening:  Featured on national television or in a major newspaper.  Under-provisioning for sales-boosting holidays OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 14. The TaoBao Architecture  Apache + Application Server + MySQL  200+ applications, thousands of components  12k servers  2k~3k java servers Shop Search Cart Product Product Recommendation Browsing /46 OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 15. The Reality – Manual Service Degradation  In response to overload:  CNN replaced its front page with simple HTML page that could be transmitted in a single Ethernet packet .  Taobao turned off a sub system.  All these techniques are implemented manually, though a better approach would be to degrade service gracefully and automatically in response to load.  Which point causes overload?  Which resource is the bottleneck?  Which service should be degraded or turned off?  All user be affected or not? OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 16. Automatic Degradation Mechanism   Overload Priority defines the priorities of different services and degradation actions can be taken.   Overload Detection is responsible for signaling the occurrence of instable status of the application.   Overload Localization is triggered to locate the bottleneck of resources.   Overload Controller will take appropriate actions to degrade some unnecessary services to release more resources to support key services. Mechanism Overload Degradation Overload Priority Overload Controller Service Service Service Service Service Overload OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 17. Automatic Application Degradation   Node level degradation   Cluster level degradation   Fine-grained   Coarse-grained   Component level degradation   Sub-system level degradation   Middleware level degradation   Resource management   Service differentiation OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 18. Considerations  Hard to be transparent to the user ( what can de degraded? sometimes how?)  Using it alone can contribute to delay overload, but it needs to be combined with other techniques to be fully effective.  Dynamic resource allocation  Admission control  Service differentiation  … … OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.
  • 19. OW2 Annual Conference 2010, November 24-25, La Cantine, Paris. www.ow2.org.