SlideShare a Scribd company logo
Research
University of Stuttgart
Universitätsstr. 38
70569 Stuttgart
Germany
Phone +49-711-685 88337
Fax +49-711-685 88472
Santiago Gómez Sáez and Frank Leymann
Institute of Architecture of Application Systems
{gomez-saez,leymann}@iaas.uni-stuttgart.de
Design Support for
Performance-aware Cloud
Application (Re-)Distribution
ESOCC PhD 2014
Research
© Santiago Gómez Sáez 2
Agenda
 Motivation & Problem Statement
 Related Works
 Research Challenges
 Work in Progress
 Approach
 Experiments
 Research Plan
33© Santiago Gómez Sáez
Research
Motivation – Efficient Application Distribution
WebShop: WAR
Apache_Tomcat:
Servlet_Container
Ubuntu10.04:
Virt_Linux_OS
IBM_Server:
Physical_Server
Product_DB:
SQL_DB
MySQL:
SQL_RDBMS_Server
AWS_EC2_m1.
xlarge:
AWS_EC2
Ubuntu13.10:
Virt_Linux_OS
MySQL:
SQL_RDBMS_Server
AWS_RDS_mediu
mDB: AWS_RDS
MySQL:
SQL_DBaaS
AWS_EC2_
m1.medium:
AWS_EC2
Ubuntu13.0:
Virt_Linux_OS
AWS_Elastic_BeansTalk:
Application_Container
 Partial vs. Complete Migration
 Multiple deployment options
 Multi-dimensional & Evolving problem
 Application workload behavior fluctuations
 Resources Demands Evolution
Performance-aware specification
Workload specification
alt_hosted_on
hosted_on
interacts-with
Andrikopoulos et al.: Optimal Distribution of Applications in the Cloud. In: Proceedings of CAiSE’14
Application specific
Alternative node
44© Santiago Gómez Sáez
Research
Motivation - Perspectives & Approaches
Performance-aware Specification
Workload Model Derivation & Characterization
Application Workload Evolution Monitoring
Top-down Bottom-up
Gómez Sáez et al.: Towards Dynamic Application Distribution Support for Performance Optimization in the Cloud. Proceedings of CLOUD 2014.
55© Santiago Gómez Sáez
Research
Related Works
 Cloud application design
 topology specification -> TOSCA, Blueprints, AWS Cloud Formation
 workload specification -> GT-CWSL
 Cloud application design decision support
 MADCAT
 Palladio Component Model
 CloudMig
 MOCCA
 Elasticity
 VM auto scaling techniques & algorithms
 proactive vs. reactive
 Performance expectation vs. resource allocation specification
66© Santiago Gómez Sáez
Research
Research Challenges
 How to partially or completely specify during the design
phase
 the Cloud Application topology and
 its performance-aware aspects?
 Alternative topologies space derivation & pruning
 How to analyze the application workload behavior &
evolution
 towards deriving & assessing
 an efficient application (re-)distribution &
 profitable resources configuration?
77© Santiago Gómez Sáez
Research
 Participants
 Application Developer
 Application design and realization
 Application topology specification, e.g. using TOSCA
 Application Cloud Distribution Design Support System
 Application (Re-)distribution towards
 proactively react to fluctuating workloads
 Topology+ : enriched application topology model with
 performance awareness (e.g. expected throughput/operation or
component, resource consumption)
 application workload characteristics (e.g. probability matrix of operations)
 Topology*: viable topology describing application distribution alternatives and
specifying
 Cloud services
 dynamic resource adaptation configurations
WiP – Performance Aware Application (Re-)Distribution Process
88© Santiago Gómez Sáez
Research
WiP – Performance Aware Application (Re-)Distribution Process
Re-distribution
Model
Application
Topology
Enrich
Topology
Model
Derive WL
Model &
Topology
Alternatives
Deployment
&
Production
Evaluate
(Re-)
Distribution
Performance Evolution
Performance
Registration
Monitor &
Analysis
Functional annotation
Performance-aware
annotation
Legend
• Requirements
• Capabilities
• Constraints
• Expected Performance
• Workload Behavior
• Topology+
• Workload Model Derivation
• Cloud Offerings Matching
• Similarity & utility-based Analysis
• Topologies*
• Topology* instance
• Synthetic Workload Generation
• Distribution Performance Evaluation
• Demanded vs. Provided
Performance
• Workload behavior Patterns
• Statistical Classification
Collaborative Loop
• Proactiveness
• Workload Fluctuation
• Application Performance Evolution
• Optimize performance vs. cost
tradeoff
Gómez Sáez et al.: Towards Dynamic Application Distribution Support for Performance Optimization in the Cloud. Proceedings of CLOUD 2014.
99© Santiago Gómez Sáez
Research
WebShop: WAR
…
Ubuntu10.04:
Virt_Linux_OS
IBM_Server:
Physical_Server
Product_DB:
SQL_DB
MySQL:
SQL_RDBMS_Server
AWS_EC2_m1.
xlarge:
AWS_EC2
Ubuntu13.10:
Virt_Linux_OS
AWS_RDS_xlarge
DB: AWS_RDS
MySQL:
SQL_DBaaS
alt_hosted_on
hosted_on
WL Specification
Ubuntu10.04:
Virt_Linux_OS
FlexiScale4vCPU:
FlexiScale_VM
on-premise
Interacts-with
IaaS DBaaS
WiP - Experiments
Gómez Sáez et al.: Towards Dynamic Application Distribution Support for Performance Optimization in the Cloud. Proceedings of CLOUD 2014.
 TPC-H Benchmark as the basis
 Workload model derivation
 Different workload characteristics
1010© Santiago Gómez Sáez
Research
WiP – Experimental Results
Legend
CL: Compute Low
CM: Compute Medium
CH: Compute High
1111© Santiago Gómez Sáez
Research
Research Plan
 Flesh out the individual process tasks
 application topology specification
 application topology enrichment
 application workload analysis & generation
 relationship between developer preferences & application performance
 …
 Performance experiments on application upper layers
 WordPress
 MediaWiki
 Performance evaluation & analysis of the overall process
 distribution vs. redistribution
 re-configuration Santiago Gómez Sáez
E-mail: gomez-saez@iaas.uni-stuttgart.de
Institute of Architecture of Applications Systems (IAAS)
University of Stuttgart (Germany)
12
Thanks for your attention!!

More Related Content

What's hot

Improving resource utilisation in the cloud environment using multivariate pr...
Improving resource utilisation in the cloud environment using multivariate pr...Improving resource utilisation in the cloud environment using multivariate pr...
Improving resource utilisation in the cloud environment using multivariate pr...Shrabanee Swagatika
 
ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...
ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...
ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...
Big Data Value Association
 
Kicking off of the ETSAP-TIAM cooperation and version control project
Kicking off of the ETSAP-TIAM cooperation and version control projectKicking off of the ETSAP-TIAM cooperation and version control project
Kicking off of the ETSAP-TIAM cooperation and version control project
IEA-ETSAP
 
WOBC AutoDISE Brief
WOBC AutoDISE BriefWOBC AutoDISE Brief
WOBC AutoDISE Brief
phase3-120A
 
Auto dise paper
Auto dise paper  Auto dise paper
Auto dise paper
phase3-120A
 
More on my LinkedIn Summary
More on my LinkedIn SummaryMore on my LinkedIn Summary
More on my LinkedIn SummaryMike Eghtebas
 
ADF Mapping Data Flows Training V2
ADF Mapping Data Flows Training V2ADF Mapping Data Flows Training V2
ADF Mapping Data Flows Training V2
Mark Kromer
 

What's hot (7)

Improving resource utilisation in the cloud environment using multivariate pr...
Improving resource utilisation in the cloud environment using multivariate pr...Improving resource utilisation in the cloud environment using multivariate pr...
Improving resource utilisation in the cloud environment using multivariate pr...
 
ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...
ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...
ExtremeEarth: Hopsworks, a data-intensive AI platform for Deep Learning with ...
 
Kicking off of the ETSAP-TIAM cooperation and version control project
Kicking off of the ETSAP-TIAM cooperation and version control projectKicking off of the ETSAP-TIAM cooperation and version control project
Kicking off of the ETSAP-TIAM cooperation and version control project
 
WOBC AutoDISE Brief
WOBC AutoDISE BriefWOBC AutoDISE Brief
WOBC AutoDISE Brief
 
Auto dise paper
Auto dise paper  Auto dise paper
Auto dise paper
 
More on my LinkedIn Summary
More on my LinkedIn SummaryMore on my LinkedIn Summary
More on my LinkedIn Summary
 
ADF Mapping Data Flows Training V2
ADF Mapping Data Flows Training V2ADF Mapping Data Flows Training V2
ADF Mapping Data Flows Training V2
 

Similar to Design_Support_Cloud_Application_Redistribution

Learning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsLearning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain Environments
Pooyan Jamshidi
 
Cloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloudCloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloud
JPINFOTECH JAYAPRAKASH
 
Cloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloudCloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloud
JPINFOTECH JAYAPRAKASH
 
Opportunities and Challenges for Running Scientific Workflows on the Cloud
Opportunities and Challenges for Running Scientific Workflows on the Cloud Opportunities and Challenges for Running Scientific Workflows on the Cloud
Opportunities and Challenges for Running Scientific Workflows on the Cloud
lyingcom
 
Webinar How to Achieve True Scalability in SaaS Applications
Webinar How to Achieve True Scalability in SaaS ApplicationsWebinar How to Achieve True Scalability in SaaS Applications
Webinar How to Achieve True Scalability in SaaS Applications
Techcello
 
Power up! Mass Migrations at Speed and Scale - Accenture
Power up! Mass Migrations at Speed and Scale - AccenturePower up! Mass Migrations at Speed and Scale - Accenture
Power up! Mass Migrations at Speed and Scale - Accenture
Amazon Web Services
 
Journey to Containerized Application / Google Container Engine
Journey to Containerized Application / Google Container EngineJourney to Containerized Application / Google Container Engine
Journey to Containerized Application / Google Container Engine
Google Cloud Platform - Japan
 
5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf
5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf
5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf
bocaha3988
 
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
IOSR Journals
 
Migrating thousands of workloads to AWS at enterprise scale
Migrating thousands of workloads to AWS at enterprise scaleMigrating thousands of workloads to AWS at enterprise scale
Migrating thousands of workloads to AWS at enterprise scale
Tom Laszewski
 
Best Practices for Building Successful Cloud Projects
Best Practices for Building Successful Cloud ProjectsBest Practices for Building Successful Cloud Projects
Best Practices for Building Successful Cloud ProjectsNati Shalom
 
Re-Platforming Applications for the Cloud
Re-Platforming Applications for the CloudRe-Platforming Applications for the Cloud
Re-Platforming Applications for the Cloud
Carter Wickstrom
 
Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...
Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...
Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...
Santiago Gómez Sáez
 
Data Science on Google Cloud Platform
Data Science on Google Cloud PlatformData Science on Google Cloud Platform
Data Science on Google Cloud Platform
Virot "Ta" Chiraphadhanakul
 
Techcello at a glance
Techcello at a glanceTechcello at a glance
Techcello at a glanceTechcello
 
The REMICS model-driven process for migrating legacy applications to the cloud
The REMICS model-driven process for migrating legacy applications to the cloudThe REMICS model-driven process for migrating legacy applications to the cloud
The REMICS model-driven process for migrating legacy applications to the cloud
Marcos Almeida
 
Muves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalMuves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalElastic Grid, LLC.
 
Technology Overview
Technology OverviewTechnology Overview
Technology Overview
Liran Zelkha
 
Adopting the Cloud
Adopting the CloudAdopting the Cloud
Adopting the Cloud
Tapio Rautonen
 

Similar to Design_Support_Cloud_Application_Redistribution (20)

Learning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain EnvironmentsLearning Software Performance Models for Dynamic and Uncertain Environments
Learning Software Performance Models for Dynamic and Uncertain Environments
 
Cloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloudCloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloud
 
Cloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloudCloud ftp a case study of migrating traditional applications to the cloud
Cloud ftp a case study of migrating traditional applications to the cloud
 
Opportunities and Challenges for Running Scientific Workflows on the Cloud
Opportunities and Challenges for Running Scientific Workflows on the Cloud Opportunities and Challenges for Running Scientific Workflows on the Cloud
Opportunities and Challenges for Running Scientific Workflows on the Cloud
 
Webinar How to Achieve True Scalability in SaaS Applications
Webinar How to Achieve True Scalability in SaaS ApplicationsWebinar How to Achieve True Scalability in SaaS Applications
Webinar How to Achieve True Scalability in SaaS Applications
 
Power up! Mass Migrations at Speed and Scale - Accenture
Power up! Mass Migrations at Speed and Scale - AccenturePower up! Mass Migrations at Speed and Scale - Accenture
Power up! Mass Migrations at Speed and Scale - Accenture
 
Journey to Containerized Application / Google Container Engine
Journey to Containerized Application / Google Container EngineJourney to Containerized Application / Google Container Engine
Journey to Containerized Application / Google Container Engine
 
5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf
5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf
5280f370-306b-cf3f-1733-cb491ed1492b_-1245741489.pdf
 
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...Multicloud Deployment of Computing Clusters for Loosely  Coupled Multi Task C...
Multicloud Deployment of Computing Clusters for Loosely Coupled Multi Task C...
 
Migrating thousands of workloads to AWS at enterprise scale
Migrating thousands of workloads to AWS at enterprise scaleMigrating thousands of workloads to AWS at enterprise scale
Migrating thousands of workloads to AWS at enterprise scale
 
Best Practices for Building Successful Cloud Projects
Best Practices for Building Successful Cloud ProjectsBest Practices for Building Successful Cloud Projects
Best Practices for Building Successful Cloud Projects
 
Re-Platforming Applications for the Cloud
Re-Platforming Applications for the CloudRe-Platforming Applications for the Cloud
Re-Platforming Applications for the Cloud
 
Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...
Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...
Evaluating Caching Strategies for Cloud Data Access using an Enterprise Serv...
 
Artist essoc 2013_12092013
Artist essoc 2013_12092013Artist essoc 2013_12092013
Artist essoc 2013_12092013
 
Data Science on Google Cloud Platform
Data Science on Google Cloud PlatformData Science on Google Cloud Platform
Data Science on Google Cloud Platform
 
Techcello at a glance
Techcello at a glanceTechcello at a glance
Techcello at a glance
 
The REMICS model-driven process for migrating legacy applications to the cloud
The REMICS model-driven process for migrating legacy applications to the cloudThe REMICS model-driven process for migrating legacy applications to the cloud
The REMICS model-driven process for migrating legacy applications to the cloud
 
Muves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 FinalMuves3 Elastic Grid Java One2009 Final
Muves3 Elastic Grid Java One2009 Final
 
Technology Overview
Technology OverviewTechnology Overview
Technology Overview
 
Adopting the Cloud
Adopting the CloudAdopting the Cloud
Adopting the Cloud
 

Recently uploaded

Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
informapgpstrackings
 
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Globus
 
Lecture 1 Introduction to games development
Lecture 1 Introduction to games developmentLecture 1 Introduction to games development
Lecture 1 Introduction to games development
abdulrafaychaudhry
 
2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx
Georgi Kodinov
 
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Globus
 
Into the Box 2024 - Keynote Day 2 Slides.pdf
Into the Box 2024 - Keynote Day 2 Slides.pdfInto the Box 2024 - Keynote Day 2 Slides.pdf
Into the Box 2024 - Keynote Day 2 Slides.pdf
Ortus Solutions, Corp
 
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus
 
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...
Shahin Sheidaei
 
Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
Matt Welsh
 
Why React Native as a Strategic Advantage for Startup Innovation.pdf
Why React Native as a Strategic Advantage for Startup Innovation.pdfWhy React Native as a Strategic Advantage for Startup Innovation.pdf
Why React Native as a Strategic Advantage for Startup Innovation.pdf
ayushiqss
 
Accelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with PlatformlessAccelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with Platformless
WSO2
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
Globus
 
A Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdfA Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdf
kalichargn70th171
 
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Globus
 
Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024
Globus
 
Developing Distributed High-performance Computing Capabilities of an Open Sci...
Developing Distributed High-performance Computing Capabilities of an Open Sci...Developing Distributed High-performance Computing Capabilities of an Open Sci...
Developing Distributed High-performance Computing Capabilities of an Open Sci...
Globus
 
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...
Hivelance Technology
 
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Anthony Dahanne
 
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdfDominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
AMB-Review
 
Quarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden ExtensionsQuarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden Extensions
Max Andersen
 

Recently uploaded (20)

Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
Field Employee Tracking System| MiTrack App| Best Employee Tracking Solution|...
 
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
Climate Science Flows: Enabling Petabyte-Scale Climate Analysis with the Eart...
 
Lecture 1 Introduction to games development
Lecture 1 Introduction to games developmentLecture 1 Introduction to games development
Lecture 1 Introduction to games development
 
2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx2024 RoOUG Security model for the cloud.pptx
2024 RoOUG Security model for the cloud.pptx
 
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
Innovating Inference - Remote Triggering of Large Language Models on HPC Clus...
 
Into the Box 2024 - Keynote Day 2 Slides.pdf
Into the Box 2024 - Keynote Day 2 Slides.pdfInto the Box 2024 - Keynote Day 2 Slides.pdf
Into the Box 2024 - Keynote Day 2 Slides.pdf
 
Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024Globus Compute wth IRI Workflows - GlobusWorld 2024
Globus Compute wth IRI Workflows - GlobusWorld 2024
 
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...
Gamify Your Mind; The Secret Sauce to Delivering Success, Continuously Improv...
 
Large Language Models and the End of Programming
Large Language Models and the End of ProgrammingLarge Language Models and the End of Programming
Large Language Models and the End of Programming
 
Why React Native as a Strategic Advantage for Startup Innovation.pdf
Why React Native as a Strategic Advantage for Startup Innovation.pdfWhy React Native as a Strategic Advantage for Startup Innovation.pdf
Why React Native as a Strategic Advantage for Startup Innovation.pdf
 
Accelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with PlatformlessAccelerate Enterprise Software Engineering with Platformless
Accelerate Enterprise Software Engineering with Platformless
 
Enhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdfEnhancing Research Orchestration Capabilities at ORNL.pdf
Enhancing Research Orchestration Capabilities at ORNL.pdf
 
A Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdfA Comprehensive Look at Generative AI in Retail App Testing.pdf
A Comprehensive Look at Generative AI in Retail App Testing.pdf
 
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
Exploring Innovations in Data Repository Solutions - Insights from the U.S. G...
 
Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024Globus Connect Server Deep Dive - GlobusWorld 2024
Globus Connect Server Deep Dive - GlobusWorld 2024
 
Developing Distributed High-performance Computing Capabilities of an Open Sci...
Developing Distributed High-performance Computing Capabilities of an Open Sci...Developing Distributed High-performance Computing Capabilities of an Open Sci...
Developing Distributed High-performance Computing Capabilities of an Open Sci...
 
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...
Multiple Your Crypto Portfolio with the Innovative Features of Advanced Crypt...
 
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
Paketo Buildpacks : la meilleure façon de construire des images OCI? DevopsDa...
 
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdfDominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
Dominate Social Media with TubeTrivia AI’s Addictive Quiz Videos.pdf
 
Quarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden ExtensionsQuarkus Hidden and Forbidden Extensions
Quarkus Hidden and Forbidden Extensions
 

Design_Support_Cloud_Application_Redistribution

  • 1. Research University of Stuttgart Universitätsstr. 38 70569 Stuttgart Germany Phone +49-711-685 88337 Fax +49-711-685 88472 Santiago Gómez Sáez and Frank Leymann Institute of Architecture of Application Systems {gomez-saez,leymann}@iaas.uni-stuttgart.de Design Support for Performance-aware Cloud Application (Re-)Distribution ESOCC PhD 2014
  • 2. Research © Santiago Gómez Sáez 2 Agenda  Motivation & Problem Statement  Related Works  Research Challenges  Work in Progress  Approach  Experiments  Research Plan
  • 3. 33© Santiago Gómez Sáez Research Motivation – Efficient Application Distribution WebShop: WAR Apache_Tomcat: Servlet_Container Ubuntu10.04: Virt_Linux_OS IBM_Server: Physical_Server Product_DB: SQL_DB MySQL: SQL_RDBMS_Server AWS_EC2_m1. xlarge: AWS_EC2 Ubuntu13.10: Virt_Linux_OS MySQL: SQL_RDBMS_Server AWS_RDS_mediu mDB: AWS_RDS MySQL: SQL_DBaaS AWS_EC2_ m1.medium: AWS_EC2 Ubuntu13.0: Virt_Linux_OS AWS_Elastic_BeansTalk: Application_Container  Partial vs. Complete Migration  Multiple deployment options  Multi-dimensional & Evolving problem  Application workload behavior fluctuations  Resources Demands Evolution Performance-aware specification Workload specification alt_hosted_on hosted_on interacts-with Andrikopoulos et al.: Optimal Distribution of Applications in the Cloud. In: Proceedings of CAiSE’14 Application specific Alternative node
  • 4. 44© Santiago Gómez Sáez Research Motivation - Perspectives & Approaches Performance-aware Specification Workload Model Derivation & Characterization Application Workload Evolution Monitoring Top-down Bottom-up Gómez Sáez et al.: Towards Dynamic Application Distribution Support for Performance Optimization in the Cloud. Proceedings of CLOUD 2014.
  • 5. 55© Santiago Gómez Sáez Research Related Works  Cloud application design  topology specification -> TOSCA, Blueprints, AWS Cloud Formation  workload specification -> GT-CWSL  Cloud application design decision support  MADCAT  Palladio Component Model  CloudMig  MOCCA  Elasticity  VM auto scaling techniques & algorithms  proactive vs. reactive  Performance expectation vs. resource allocation specification
  • 6. 66© Santiago Gómez Sáez Research Research Challenges  How to partially or completely specify during the design phase  the Cloud Application topology and  its performance-aware aspects?  Alternative topologies space derivation & pruning  How to analyze the application workload behavior & evolution  towards deriving & assessing  an efficient application (re-)distribution &  profitable resources configuration?
  • 7. 77© Santiago Gómez Sáez Research  Participants  Application Developer  Application design and realization  Application topology specification, e.g. using TOSCA  Application Cloud Distribution Design Support System  Application (Re-)distribution towards  proactively react to fluctuating workloads  Topology+ : enriched application topology model with  performance awareness (e.g. expected throughput/operation or component, resource consumption)  application workload characteristics (e.g. probability matrix of operations)  Topology*: viable topology describing application distribution alternatives and specifying  Cloud services  dynamic resource adaptation configurations WiP – Performance Aware Application (Re-)Distribution Process
  • 8. 88© Santiago Gómez Sáez Research WiP – Performance Aware Application (Re-)Distribution Process Re-distribution Model Application Topology Enrich Topology Model Derive WL Model & Topology Alternatives Deployment & Production Evaluate (Re-) Distribution Performance Evolution Performance Registration Monitor & Analysis Functional annotation Performance-aware annotation Legend • Requirements • Capabilities • Constraints • Expected Performance • Workload Behavior • Topology+ • Workload Model Derivation • Cloud Offerings Matching • Similarity & utility-based Analysis • Topologies* • Topology* instance • Synthetic Workload Generation • Distribution Performance Evaluation • Demanded vs. Provided Performance • Workload behavior Patterns • Statistical Classification Collaborative Loop • Proactiveness • Workload Fluctuation • Application Performance Evolution • Optimize performance vs. cost tradeoff Gómez Sáez et al.: Towards Dynamic Application Distribution Support for Performance Optimization in the Cloud. Proceedings of CLOUD 2014.
  • 9. 99© Santiago Gómez Sáez Research WebShop: WAR … Ubuntu10.04: Virt_Linux_OS IBM_Server: Physical_Server Product_DB: SQL_DB MySQL: SQL_RDBMS_Server AWS_EC2_m1. xlarge: AWS_EC2 Ubuntu13.10: Virt_Linux_OS AWS_RDS_xlarge DB: AWS_RDS MySQL: SQL_DBaaS alt_hosted_on hosted_on WL Specification Ubuntu10.04: Virt_Linux_OS FlexiScale4vCPU: FlexiScale_VM on-premise Interacts-with IaaS DBaaS WiP - Experiments Gómez Sáez et al.: Towards Dynamic Application Distribution Support for Performance Optimization in the Cloud. Proceedings of CLOUD 2014.  TPC-H Benchmark as the basis  Workload model derivation  Different workload characteristics
  • 10. 1010© Santiago Gómez Sáez Research WiP – Experimental Results Legend CL: Compute Low CM: Compute Medium CH: Compute High
  • 11. 1111© Santiago Gómez Sáez Research Research Plan  Flesh out the individual process tasks  application topology specification  application topology enrichment  application workload analysis & generation  relationship between developer preferences & application performance  …  Performance experiments on application upper layers  WordPress  MediaWiki  Performance evaluation & analysis of the overall process  distribution vs. redistribution  re-configuration Santiago Gómez Sáez E-mail: gomez-saez@iaas.uni-stuttgart.de Institute of Architecture of Applications Systems (IAAS) University of Stuttgart (Germany)
  • 12. 12 Thanks for your attention!!

Editor's Notes

  1. Take into account using the linear program solving (for optimization) What about if there is no solution in the space of alternative topologies?
  2. Make an animation here with the perspective and the background
  3. TOSCA: cloud application portability among Cloud infrastructures MADCAT: methodological approach targeting the creation of structured native applications covering all phases of its life cycle and including iterative refinement and documentation of decisions made during the application life cycle. Palladio component model: model driven performance prediction aimed at identify the performance bottlenecks of software architectures. CloudMiG: cloud migration support towards comparing and planning the migration of an application to the Cloud. Simulation techinques for monitored workloads. It requires the modeling of cloud environments with the help of cloud profiles. MOCCA: cloud application topology optimization through the introduction of variability points and optimization techniques based on non functional requirements. Elasticity Studies demonstrate that achieving an optimal application throughput is complex and involves more than simply increasing the number of VMs, and it requires an analysis on the application profile, as there may be concrete resources scaling configurations that negatively impact on the applications performance. They deployed two variants of an application with two different profiles. Application scaling required understanding the application profile as well as dependencies among the application components. Different auto-scaling techniques and algorithms are presented in several works. However, to take advantage of the flexibility that auto-scaling techniques offer, it is necessary to adjust it to the incoming workload behavior, and therefore the application profile, enabling dynamicity for the thresholds. Reactive: AWS autoscaling through the specification of thresholds. Proactive: time series analysis Performance expectation: Quasar resource management system: based on the specification on performance constraints and letting Quasar determine the most appropriate resource configuration in order to satisfy such constraints. It uses classification techniques to determine the impact of the amount of resources for the workload performance. Such approaches either focus on providing the means to specify a concrete application distribution, support during the initial phases of the application design, focus on selecting the most efficient Cloud provider or best resource configuration. In this work we go a step further by providing the means to application developers to (re-)distribute their application wrt available Cloud offerings to cope with fluctuating workloads.
  4. Providing therefore the Cloud application developers with such design support to optimally distribute and re-distribute the application to cope with uctuating workloads and performance demands raises several challenges. Such decision support must cover the complete application life-cycle, dene the underpinning concepts, and provide the required mechanisms towards targeting the analysis and evaluation of the evolutionary aspects of the application performance, e.g. its workload uctuation.