Efficient Monitoring in Actor-based Mobile Hybrid Cloud Framework. Kirill Mechitov, Reza Shiftehfar, and Gul Agha
|
|
- Brianne Bryan
- 8 years ago
- Views:
Transcription
1 Efficient Monitoring in Actor-based Mobile Hybrid Cloud Framework Kirill Mechitov, Reza Shiftehfar, and Gul Agha
2 Motivation: mobile cloud Mobile apps Huge variety Many developers/organizations Increasingly complex and resource-heavy Enabling custom cloud-based optimization requires: Skilled developer time Keeping up with rapid changes in both mobile and cloud environments Manual vs. automatic App developer implements cloud-based optimization Or let the system manage it 2
3 Motivation: hybrid cloud Public cloud Affordable, efficient, scalable Privacy & security issues Private cloud Full control over code & data More expensive/less efficient Hybrid cloud Combine both public & private clouds benefits Avoid some of the drawbacks 3
4 Mobile Cloud Computing (MCC) Cloud Computing Access to virtually unlimited, elastic computing and storage Efficient, scalable, affordable Cloud + Mobile Enable new functionality Remove mobile device limitations Improve performance Reduce energy consumption How to implement? Use code offloading Credit: cloudcomputingdoc.com 4
5 Background: code offloading Full VM emulation Run mobile device emulator in the cloud Universal solution, but expensive Application partitioning Run some components on the mobile device and some in the cloud How to partition? Let the app developer do it Let the system do it, statically Let the system do it, dynamically 5
6 IMCM: Illinois Mobile Cloud Manager Code offloading: Automatic Dynamic Fine-grained Parallel Supports: Hybrid cloud with multiple cloud spaces Provides: Policy-based control by cloud provider, app developer, user 6
7 IMCM publications ICT-BDCS 2015 Performance optimization in IMCM Best paper award CCGrid 2016 (submitted) Energy-aware optimization 7
8 IMCM framework Max app performance Min mobile energy consumption Min cloud cost Min network data usage Application Target Goal Org/App/User Policy Application Policy Access Restrictions User preferences Policy Manager Application actions Network parameters User context Application profiling Energy estimator System Properties Elasticity Manager Offloading Plan Target goal Profiled exec Profiled comm System Monitor Decision Maker Application Component Distribution 8
9 Today: efficient monitoring in IMCM Max app performance Min mobile energy consumption Min cloud cost Min network data usage Application Target Goal Org/App/User Policy Application Policy Access Restrictions User preferences Policy Manager Application actions Network parameters User context Application profiling Energy estimator System Properties Elasticity Manager Offloading Plan Target goal Profiled exec Profiled comm System Monitor Decision Maker Application Component Distribution 9
10 IMCM System Monitor Monitoring is used for: Performance estimation Energy consumption estimation Security policies Efficiency is key If overhead is too high, there is no point in using MCC Our approach Implement monitoring at the actor system level Shift overhead costs to relatively infrequent actions Focus on distributed application behavior, not local code 10
11 Actor model Programming model Natural concurrency Decentralization No shared state Scalability Location transparency -> Transparent migration Implementation: SALSA* Full actor semantics Lightweight actors Migration support Portability (Java-based) 11
12 What is an actor? Behavior (code) State Thread Actor name (address) Mailbox 12
13 What can an actor do? Send message Receive message (execute method) Create a new actor Migrate to a different location 13
14 SALSA actors module demo; behavior HelloWorld { /* The act(...) message handler is invoked automatically and is used to bootstrap salsa programs. */ void act( String[] argv ) { standardoutput<-print( "Hello" standardoutput<-print( "World!" ); } } 14
15 IMCM System Monitor What to monitor? Application actions At the level of actor primitives (create, migrate, send/receive) System actions Offloading decisions, costs System/environment conditions Performance, energy, connection speed, resource availability When to notify? Changes in monitored parameters Changes in org/user/system policies Violation of existing policies 15
16 Application actions The actor system is involved when: Actor sends a message Message arrives Message handler is executed Message handler finishes execution Actor creation initiated (local) Actor creation completed (local or remote) Migration is initiated (local) Migration request received (remote) Migration completed (remote) Can intervene and control app behavior at these points without modifying application code 16
17 System actions The actor system is involved in: Offloading decision (when, where, and which actors) System-initiated migration System-initiated actor creation 17
18 Metadata: actor attributes Describe properties of actors Creating user Creating actor Current location Etc. Two types of attributes: Static do not change at runtime E.g., creating actor Dynamic can change E.g., location 18
19 Metadata: dynamically updated structures Message send graph Call graph Actor creation graph For permission/restriction inheritance Actor name knowledge set Who can send messages to this actor Actor semantics: actor names cannot be guessed 19
20 Action control system Requirements Fine granularity Support policies defined by organization, developer, and end-user Covers all possible app and system actions Action control system based on: The requested action The specified policy Attributes of the requester Attributes of the recipient Attributes of the resource 20
21 Authorization framework model The authorization model includes the following parties: Owner organization (cloud space and/or data) Developers of the application that uses cloud resources End-users of the application Who defines authorization policy? The organization that owns data and cloud resources (organizationwide policy) The application developer can further restrict these organization-wide accesses (application-specific policy) The application user (user-specific policy) 21
22 Example: satellite ISP customer privacy policy 22
23 Policy definition & enforcement Authorization policy Hard (immutable) E.g., cloud provider policy Soft (customizable) E.g., user-defined policy Grammar to define rules Attribute based Static & dynamic binding Rule structure: <Subject, Object, Action, Sign, Type> 23
24 Implementation: action monitoring Rules from multiple applicable policies are merged Organization, developer, end-user policies Hard policy rules take precedence over soft policy rules Rules checked for every invocation of each app and system action, so must be efficient Sort rules to prioritize early DENY decision Sort rules to prioritize static-only checks Cache lookups to dramatically speed up most frequent actions Invalidate cache on dynamic attribute change Use dynamic metadata to speed up lookups 24
25 Implementation: heuristics In typical applications, most of the time is spent in the message handler Actor migration is quite infrequent Local actor creation is much more frequent than remote actor creation Local message sends are much more frequent than remote message sends 25
26 Example: face recognition app 26
27 Example: face recognition app Components with different computation, bandwidth, energy characteristics Some data inputs/outputs may be restricted to specific systems or users 27
28 Example: face recognition app Hard policy Different types of users: General public Law enforcement 28
29 Example: face recognition app Soft policy Different user expectations: Type 1: No additional privacy concerns Type 2: Privacy concerned users Type 3: Extremely cautious users Type 1 Type 2 Type 3 29
30 Example: face recognition app Policy: information security for sensitive data Protect access to database of faces located on private cloud Rule examples for actors that can access the database: Must be created only at <location> Cannot migrate away from <location> Cannot send messages outside <application> Actor creation inherits restrictions 30
31 Example: face recognition app Sample private cloud rules for restricted code and data access E.g., no send, migration from private to public cloud 31
32 Evaluation System Monitor overhead: WIP IMCM overhead (includes monitor): acceptable IMCM performance overall: awesome! Significant speedups vs. mobile-only sequential and parallel execution 32
33 Some benchmark results Raw speedup: inherent parallelism gain Offload speedup: including the cost of offloading 33
34 Face recognition app speedup 34
35 IMCM overhead 35
36 IMCM framework summary Bridge the gap between mobile application and cloud computing Separate application logic from component distribution decisions Allow dynamic distribution of components based on run-time changes Support policy-based definition of security/privacy constraints 36
37 Questions? Thank you! 37
IMCM: A Flexible Fine-Grained Adaptive Framework for Parallel Mobile Hybrid Cloud Applications
Open System Laboratory of University of Illinois at Urbana Champaign presents: Outline: IMCM: A Flexible Fine-Grained Adaptive Framework for Parallel Mobile Hybrid Cloud Applications A Fine-Grained Adaptive
More informationA Fine-Grained Adaptive Middleware Framework for Parallel Mobile Hybrid Cloud Applications
A Fine-Grained Adaptive Middleware Framework for Parallel Mobile Hybrid Cloud Applications Reza Shiftehfar Department of Computer Science U. of Illinois at Urbana-Champaign Email: sshifte2@illinois.edu
More informationParametric Analysis of Mobile Cloud Computing using Simulation Modeling
Parametric Analysis of Mobile Cloud Computing using Simulation Modeling Arani Bhattacharya Pradipta De Mobile System and Solutions Lab (MoSyS) The State University of New York, Korea (SUNY Korea) StonyBrook
More informationACTOR-BASED MODEL FOR CONCURRENT PROGRAMMING. Sander Sõnajalg
ACTOR-BASED MODEL FOR CONCURRENT PROGRAMMING Sander Sõnajalg Contents Introduction to concurrent programming Shared-memory model vs. actor model Main principles of the actor model Actors for light-weight
More informationData sharing in the Big Data era
www.bsc.es Data sharing in the Big Data era Anna Queralt and Toni Cortes Storage System Research Group Introduction What ignited our research Different data models: persistent vs. non persistent New storage
More informationCSci 8980 Mobile Cloud Computing. MCC Overview
CSci 8980 Mobile Cloud Computing MCC Overview Papers Students can do: 1 long paper or 2 short papers Extra credit: add another By 8am tomorrow, I will randomly assign papers unless I hear from you Protocol:
More informationVStore++: Virtual Storage Services for Mobile Devices
VStore++: Virtual Storage Services for Mobile Devices Sudarsun Kannan, Karishma Babu, Ada Gavrilovska, and Karsten Schwan Center for Experimental Research in Computer Systems Georgia Institute of Technology
More informationMizan: A System for Dynamic Load Balancing in Large-scale Graph Processing
/35 Mizan: A System for Dynamic Load Balancing in Large-scale Graph Processing Zuhair Khayyat 1 Karim Awara 1 Amani Alonazi 1 Hani Jamjoom 2 Dan Williams 2 Panos Kalnis 1 1 King Abdullah University of
More informationIntroduction to Track on Engineering Virtualized Services
Introduction to Track on Engineering Virtualized Services Reiner Hähnle 1 and Einar Broch Johnsen 2 1 Technical University of Darmstadt, Germany haehnle@cs.tu-darmstadt.de 2 Dept. of Informatics, University
More informationPerformance Management for Cloudbased STC 2012
Performance Management for Cloudbased Applications STC 2012 1 Agenda Context Problem Statement Cloud Architecture Need for Performance in Cloud Performance Challenges in Cloud Generic IaaS / PaaS / SaaS
More informationSPEEDING UP AND AUGMENTING MOBILE DEVICE APPLICATIONS USING ACTORS AND CLOUD COMPUTING
SPEEDING UP AND AUGMENTING MOBILE DEVICE APPLICATIONS USING ACTORS AND CLOUD COMPUTING by Pratik Patel A Thesis Submitted to the Graduate Faculty of Rensselaer Polytechnic Institute in Partial Fulfillment
More informationMobile Cloud Computing. Chamitha de Alwis, PhD Senior Lecturer University of Sri Jayewardenepura chamitha@sjp.ac.lk
Mobile Cloud Computing Chamitha de Alwis, PhD Senior Lecturer University of Sri Jayewardenepura chamitha@sjp.ac.lk Mobile Computing Rapid progress of mobile computing have become a powerful trend in the
More informationMulti-GPU Load Balancing for Simulation and Rendering
Multi- Load Balancing for Simulation and Rendering Yong Cao Computer Science Department, Virginia Tech, USA In-situ ualization and ual Analytics Instant visualization and interaction of computing tasks
More informationRelational Databases in the Cloud
Contact Information: February 2011 zimory scale White Paper Relational Databases in the Cloud Target audience CIO/CTOs/Architects with medium to large IT installations looking to reduce IT costs by creating
More informationCloud Federations in Contrail
Cloud Federations in Contrail Emanuele Carlini 1,3, Massimo Coppola 1, Patrizio Dazzi 1, Laura Ricci 1,2, GiacomoRighetti 1,2 " 1 - CNR - ISTI, Pisa, Italy" 2 - University of Pisa, C.S. Dept" 3 - IMT Lucca,
More informationCloud/SaaS enablement of existing applications
Cloud/SaaS enablement of existing applications GigaSpaces: Nati Shalom, CTO & Founder About GigaSpaces Technologies Enabling applications to run a distributed cluster as if it was a single machine 75+
More informationStudy of Various Load Balancing Techniques in Cloud Environment- A Review
International Journal of Computer Sciences and Engineering Open Access Review Paper Volume-4, Issue-04 E-ISSN: 2347-2693 Study of Various Load Balancing Techniques in Cloud Environment- A Review Rajdeep
More informationFebruary 2014. Considerations When Choosing a Secure Web Gateway
February 2014 Considerations When Choosing a Secure Web Gateway Introduction Evaluating a Secure Web Gateway (SWG) can be a complicated process and nothing is better than testing a solution in your own
More informationADAPTIVE LOAD BALANCING ALGORITHM USING MODIFIED RESOURCE ALLOCATION STRATEGIES ON INFRASTRUCTURE AS A SERVICE CLOUD SYSTEMS
ADAPTIVE LOAD BALANCING ALGORITHM USING MODIFIED RESOURCE ALLOCATION STRATEGIES ON INFRASTRUCTURE AS A SERVICE CLOUD SYSTEMS Lavanya M., Sahana V., Swathi Rekha K. and Vaithiyanathan V. School of Computing,
More informationSoftware Configuration Management Using Vesta
Allan Heydon Roy Levin Timothy Mann Yuan Yu Software Configuration Management Using Vesta Springer Contents Preface vii Part I Introducing Vesta 1 Introduction 5 1.1 Some Scenarios 6 1.2 The Connguration
More informationA Distributed Event Messaging System for Mobile Agent Communication
A Distributed Event Messaging System for Mobile Agent Communication John McCormick, Daria Chacón, Susan McGrath, and Craig Stoneking Lockheed Martin Advanced Technology Laboratories Federal Street A&E
More informationCHAPTER 2 MODELLING FOR DISTRIBUTED NETWORK SYSTEMS: THE CLIENT- SERVER MODEL
CHAPTER 2 MODELLING FOR DISTRIBUTED NETWORK SYSTEMS: THE CLIENT- SERVER MODEL This chapter is to introduce the client-server model and its role in the development of distributed network systems. The chapter
More informationFile System Client and Server
COMP 790-088 -- Distributed File Systems With Case Studies: Andrew and Google 1 File System Client and Server Server request (e.g., read) response (e.g., file block) Client 2 Factors Encouraging Migration
More informationBlobSeer: Towards efficient data storage management on large-scale, distributed systems
: Towards efficient data storage management on large-scale, distributed systems Bogdan Nicolae University of Rennes 1, France KerData Team, INRIA Rennes Bretagne-Atlantique PhD Advisors: Gabriel Antoniu
More informationSecuring Elastic Applications for Cloud Computing. Many to One Virtualization
Securing Elastic Applications for Cloud Computing Many to One Virtualization Xinwen Zhang, Joshua Schiffman, Simon Gibbs, Anugeetha Kunjithapatham, and Sangoh Jeong Samsung Information Systems America
More informationCloud Computing. Cloud computing:
Cloud computing: Cloud Computing A model of data processing in which high scalability IT solutions are delivered to multiple users: as a service, on a mass scale, on the Internet. Network services offering:
More informationResource Containers: A new facility for resource management in server systems
CS 5204 Operating Systems Resource Containers: A new facility for resource management in server systems G. Banga, P. Druschel, Rice Univ. J. C. Mogul, Compaq OSDI 1999 Outline Background Previous Approaches
More informationCloud Computing. Up until now
Cloud Computing Lecture 20 Cloud Platform Comparison & Load 2011-2012 Up until now Introduction, Definition of Cloud Computing Pre-Cloud Large Scale Computing: Grid Computing Content Distribution Networks
More informationSecurity & Privacy Issues in Mobile Cloud Computing
Security & Privacy Issues in Mobile Cloud Computing Manmohan Chaturvedi,1, Sapna Malik, Preeti Aggarwal and Shilpa Bahl Ansal University, Gurgaon- 122011, India 1 mmchaturvedi@ansaluniversity.edu.in Indian
More informationAmit Sheth & Ajith Ranabahu, 2010. Presented by Mohammad Hossein Danesh
Amit Sheth & Ajith Ranabahu, 2010 Presented by Mohammad Hossein Danesh 1 Agenda Introduction to Cloud Computing Research Motivation Semantic Modeling Can Help Use of DSLs Solution Conclusion 2 3 Motivation
More informationDynamic Load Balancing in Charm++ Abhinav S Bhatele Parallel Programming Lab, UIUC
Dynamic Load Balancing in Charm++ Abhinav S Bhatele Parallel Programming Lab, UIUC Outline Dynamic Load Balancing framework in Charm++ Measurement Based Load Balancing Examples: Hybrid Load Balancers Topology-aware
More informationPerformance Monitoring and Analysis System for MUSCLE-based Applications
Polish Infrastructure for Supporting Computational Science in the European Research Space Performance Monitoring and Analysis System for MUSCLE-based Applications W. Funika, M. Janczykowski, K. Jopek,
More informationA Novel Approach for Efficient Load Balancing in Cloud Computing Environment by Using Partitioning
A Novel Approach for Efficient Load Balancing in Cloud Computing Environment by Using Partitioning 1 P. Vijay Kumar, 2 R. Suresh 1 M.Tech 2 nd Year, Department of CSE, CREC Tirupati, AP, India 2 Professor
More informationMPI and Hybrid Programming Models. William Gropp www.cs.illinois.edu/~wgropp
MPI and Hybrid Programming Models William Gropp www.cs.illinois.edu/~wgropp 2 What is a Hybrid Model? Combination of several parallel programming models in the same program May be mixed in the same source
More informationUsing Linux as Hypervisor with KVM
Using Linux as Hypervisor with KVM Qumranet Inc. Andrea Arcangeli andrea@qumranet.com (some slides from Avi Kivity) CERN - Geneve 15 Sep 2008 Agenda Overview/feature list KVM design vs other virtualization
More informationClonecloud: Elastic execution between mobile device and cloud [1]
Clonecloud: Elastic execution between mobile device and cloud [1] ACM, Intel, Berkeley, Princeton 2011 Cloud Systems Utility Computing Resources As A Service Distributed Internet VPN Reliable and Secure
More informationReliable Adaptable Network RAM
Reliable Adaptable Network RAM Tia Newhall, Daniel Amato, Alexandr Pshenichkin Computer Science Department, Swarthmore College Swarthmore, PA 19081, USA Abstract We present reliability solutions for adaptable
More informationTowards Elastic Application Model for Augmenting Computing Capabilities of Mobile Platforms. Mobilware 2010
Towards lication Model for Augmenting Computing Capabilities of Mobile Platforms Mobilware 2010 Xinwen Zhang, Simon Gibbs, Anugeetha Kunjithapatham, and Sangoh Jeong Computer Science Lab. Samsung Information
More informationAndroid Developer Fundamental 1
Android Developer Fundamental 1 I. Why Learn Android? Technology for life. Deep interaction with our daily life. Mobile, Simple & Practical. Biggest user base (see statistics) Open Source, Control & Flexibility
More informationiservdb The database closest to you IDEAS Institute
iservdb The database closest to you IDEAS Institute 1 Overview 2 Long-term Anticipation iservdb is a relational database SQL compliance and a general purpose database Data is reliable and consistency iservdb
More informationAPPLICATION DELIVERY
RIVERBED DELIVERY THE FIRST DELIVERY CONTROLLER (ADC) DESIGNED FOR ANY CLOUD OR Greater flexibility VIRTUALIZED ENVIRONMENT GARTNER MAGIC QUADRANT RECOGNITION We re a Visionary in the 2012 Magic Quadrant
More informationPerformance Optimization For Operational Risk Management Application On Azure Platform
Performance Optimization For Operational Risk Management Application On Azure Platform Ashutosh Sabde, TCS www.cmgindia.org 1 Contents Introduction Functional Requirements Non Functional Requirements Business
More informationAn enterprise- grade cloud management platform that enables on- demand, self- service IT operating models for Global 2000 enterprises
agility PLATFORM Product Whitepaper An enterprise- grade cloud management platform that enables on- demand, self- service IT operating models for Global 2000 enterprises ServiceMesh 233 Wilshire Blvd,
More informationTo Java SE 8, and Beyond (Plan B)
11-12-13 To Java SE 8, and Beyond (Plan B) Francisco Morero Peyrona EMEA Java Community Leader 8 9...2012 2020? Priorities for the Java Platforms Grow Developer Base Grow Adoption
More informationPerformance Management for Cloud-based Applications STC 2012
Performance Management for Cloud-based Applications STC 2012 1 Agenda Context Problem Statement Cloud Architecture Key Performance Challenges in Cloud Challenges & Recommendations 2 Context Cloud Computing
More informationElastic Calculator : A Mobile Application for windows mobile using Mobile Cloud Services
Elastic Calculator : A Mobile Application for windows mobile using Mobile Cloud Services K.Lakshmi Narayanan* & Nadesh R.K # School of Information Technology and Engineering, VIT University Vellore, India
More informationSurvey on Application Models using Mobile Cloud Technology
Survey on Application Models using Mobile Cloud Technology Vinayak D. Shinde 1, Usha S Patil 2, Anjali Dwivedi 3 H.O.D., Dept of Computer Engg, Shree L.R. Tiwari College of Engineering, Mira Road, Mumbai,
More informationA Comparative Study of cloud and mcloud Computing
A Comparative Study of cloud and mcloud Computing Ms.S.Gowri* Ms.S.Latha* Ms.A.Nirmala Devi* * Department of Computer Science, K.S.Rangasamy College of Arts and Science, Tiruchengode. s.gowri@ksrcas.edu
More informationf...-. I enterprise Amazon SimpIeDB Developer Guide Scale your application's database on the cloud using Amazon SimpIeDB Prabhakar Chaganti Rich Helms
Amazon SimpIeDB Developer Guide Scale your application's database on the cloud using Amazon SimpIeDB Prabhakar Chaganti Rich Helms f...-. I enterprise 1 3 1 1 I ; i,acaessiouci' cxperhs;;- diotiilea PUBLISHING
More informationScheduling and Monitoring of Internally Structured Services in Cloud Federations
Scheduling and Monitoring of Internally Structured Services in Cloud Federations Lars Larsson, Daniel Henriksson and Erik Elmroth {larsson, danielh, elmroth}@cs.umu.se Where are the VMs now? Cloud hosting:
More informationhttp://oraclearchworld.wordpress.com/ Oracle SOA Infrastructure Deployment Models/Patterns
http://oraclearchworld.wordpress.com/ Oracle SOA Infrastructure Deployment Models/Patterns by Kathiravan Udayakumar This article will introduce various SOA Infrastructure deployment patterns available
More informationSharePoint 2013 Migration Readiness
SharePoint 2013 Migration Readiness Decision Points around Migrating to SharePoint 2013 MARK ECKERT Contents Purpose... 1 SharePoint 2013 Implementation Options... 1 On-premise installation... 1 Cloud...
More informationCOMP5426 Parallel and Distributed Computing. Distributed Systems: Client/Server and Clusters
COMP5426 Parallel and Distributed Computing Distributed Systems: Client/Server and Clusters Client/Server Computing Client Client machines are generally single-user workstations providing a user-friendly
More informationIntroduction to Database Systems CSE 444. Lecture 24: Databases as a Service
Introduction to Database Systems CSE 444 Lecture 24: Databases as a Service CSE 444 - Spring 2009 References Amazon SimpleDB Website Part of the Amazon Web services Google App Engine Datastore Website
More informationThe evolution of data archiving
The evolution of data archiving 1 1 How archiving needs to change for the modern enterprise Today s enterprises are buried by data, and this problem is being exacerbated by the unfettered growth of unstructured
More informationService-Oriented Architectures
Architectures Computing & 2009-11-06 Architectures Computing & SERVICE-ORIENTED COMPUTING (SOC) A new computing paradigm revolving around the concept of software as a service Assumes that entire systems
More informationUbiquitous access Inherently distributed Many, diverse clients (single purpose rich) Unlimited computation and data on demand
Ubiquitous access Inherently distributed Many, diverse clients (single purpose rich) Unlimited computation and data on demand Moore s Law (Dennard scaling) is running out Scale out, not scale up Inescapably
More informationMODAClouds. An FP7 Integrated Project
MODAClouds An FP7 Integrated Project MODAClouds the consortium FP7 Integrated Project (n. 318484) Duration: Oct. 1 st, 2012 Sept 30 th, 2015 28 July, 2014 e-infrastructure Services for Society 2 MODAClouds
More informationDISTRIBUTED SYSTEMS [COMP9243] Lecture 9a: Cloud Computing WHAT IS CLOUD COMPUTING? 2
DISTRIBUTED SYSTEMS [COMP9243] Lecture 9a: Cloud Computing Slide 1 Slide 3 A style of computing in which dynamically scalable and often virtualized resources are provided as a service over the Internet.
More informationAndroid Application Development Course Program
Android Application Development Course Program Part I Introduction to Programming 1. Introduction to programming. Compilers, interpreters, virtual machines. Primitive data types, variables, basic operators,
More informationAgenda. Distributed System Structures. Why Distributed Systems? Motivation
Agenda Distributed System Structures CSCI 444/544 Operating Systems Fall 2008 Motivation Network structure Fundamental network services Sockets and ports Client/server model Remote Procedure Call (RPC)
More informationReal Time Scheduling Basic Concepts. Radek Pelánek
Real Time Scheduling Basic Concepts Radek Pelánek Basic Elements Model of RT System abstraction focus only on timing constraints idealization (e.g., zero switching time) Basic Elements Basic Notions task
More informationWrite a technical report Present your results Write a workshop/conference paper (optional) Could be a real system, simulation and/or theoretical
Identify a problem Review approaches to the problem Propose a novel approach to the problem Define, design, prototype an implementation to evaluate your approach Could be a real system, simulation and/or
More informationDatabase Application Developer Tools Using Static Analysis and Dynamic Profiling
Database Application Developer Tools Using Static Analysis and Dynamic Profiling Surajit Chaudhuri, Vivek Narasayya, Manoj Syamala Microsoft Research {surajitc,viveknar,manojsy}@microsoft.com Abstract
More informationWeb hosting and caching: Speed up content delivery for a better customer experience
Web hosting and caching: Speed up content delivery for a better customer experience The cloud offers many benefits in terms of speeding up information delivery and there are cost benefits too. You can
More informationA Novel Cloud Based Elastic Framework for Big Data Preprocessing
School of Systems Engineering A Novel Cloud Based Elastic Framework for Big Data Preprocessing Omer Dawelbeit and Rachel McCrindle October 21, 2014 University of Reading 2008 www.reading.ac.uk Overview
More informationComparison of Cloud vs. Tape Backup Performance and Costs with Oracle Database
JIOS, VOL. 35, NO. 1 (2011) SUBMITTED 02/11; ACCEPTED 06/11 UDC 004.75 Comparison of Cloud vs. Tape Backup Performance and Costs with Oracle Database University of Ljubljana Faculty of Computer and Information
More informationSix Strategies for Building High Performance SOA Applications
Six Strategies for Building High Performance SOA Applications Uwe Breitenbücher, Oliver Kopp, Frank Leymann, Michael Reiter, Dieter Roller, and Tobias Unger University of Stuttgart, Institute of Architecture
More informationMigration Scenario: Migrating Batch Processes to the AWS Cloud
Migration Scenario: Migrating Batch Processes to the AWS Cloud Produce Ingest Process Store Manage Distribute Asset Creation Data Ingestor Metadata Ingestor (Manual) Transcoder Encoder Asset Store Catalog
More informationLoad Imbalance Analysis
With CrayPat Load Imbalance Analysis Imbalance time is a metric based on execution time and is dependent on the type of activity: User functions Imbalance time = Maximum time Average time Synchronization
More informationMjolnirr: private PaaS as distributed computing evolution
Mjolnirr: private PaaS as distributed computing evolution Gleb Radchenko, Dmitry Savchenko gleb.radchenko@susu.ru South Ural State University, Russia Problem definition Cloud computing enables resource
More informationOracle Total Recall with Oracle Database 11g Release 2
An Oracle White Paper September 2009 Oracle Total Recall with Oracle Database 11g Release 2 Introduction: Total Recall = Total History... 1 Managing Historical Data: Current Approaches... 2 Application
More informationBeyond brokering: Proactive Role of Cloud Federations in Resource Management
Beyond brokering: Proactive Role of Cloud Federations in Resource Management Massimo Coppola (CNR-ISTI)! contrail is co-funded by the EC 7th Framework Programme under Grant greement nr. 257438 http://contrail-project.eu
More informationScalable Internet Services and Load Balancing
Scalable Services and Load Balancing Kai Shen Services brings ubiquitous connection based applications/services accessible to online users through Applications can be designed and launched quickly and
More informationSWARM: A Parallel Programming Framework for Multicore Processors. David A. Bader, Varun N. Kanade and Kamesh Madduri
SWARM: A Parallel Programming Framework for Multicore Processors David A. Bader, Varun N. Kanade and Kamesh Madduri Our Contributions SWARM: SoftWare and Algorithms for Running on Multicore, a portable
More informationMaking Multicore Work and Measuring its Benefits. Markus Levy, president EEMBC and Multicore Association
Making Multicore Work and Measuring its Benefits Markus Levy, president EEMBC and Multicore Association Agenda Why Multicore? Standards and issues in the multicore community What is Multicore Association?
More informationA Comparison Of Shared Memory Parallel Programming Models. Jace A Mogill David Haglin
A Comparison Of Shared Memory Parallel Programming Models Jace A Mogill David Haglin 1 Parallel Programming Gap Not many innovations... Memory semantics unchanged for over 50 years 2010 Multi-Core x86
More informationDecision Support for Mobile Cloud Computing Applications via Model Checking
Decision Support for Mobile Cloud Computing Applications via Model Checking Luca Aceto Reykjavik University, Iceland Andrea Morichetta, Francesco Tiezzi IMT Institute for Advanced Studies Lucca, Italy
More informationVALUE PROPOSITION FOR SERVICE PROVIDERS. Helping Service Providers accelerate adoption of the cloud
VALUE PROPOSITION FOR SERVICE PROVIDERS Helping Service Providers accelerate adoption of the cloud Partnership with Service Providers Enabling Your Cloud Services in Complex Environments Today s challenge
More informationReverse Auction-based Resource Allocation Policy for Service Broker in Hybrid Cloud Environment
Reverse Auction-based Resource Allocation Policy for Service Broker in Hybrid Cloud Environment Sunghwan Moon, Jaekwon Kim, Taeyoung Kim, Jongsik Lee Department of Computer and Information Engineering,
More informationConcurrent Technologies Corporation (CTC) is an independent, nonprofit, applied scientific research and development professional services
Concurrent Technologies Corporation (CTC) is an independent, nonprofit, applied scientific research and development professional services organization providing innovative management and technology-based
More informationPage 1. Editor Patrick Blandin, Centre Henri Tudor, Luxembourg
ITEA- 2 (09008) Newsletter 10/2012 Page 1 Summary of the 4 Demos presented at Co-Summit 2012 Demo 1 File based Broadcast Content Delivery Broadcaster and Mobile/Telecom Operators are facing the challenge
More informationUnderstanding the Benefits of IBM SPSS Statistics Server
IBM SPSS Statistics Server Understanding the Benefits of IBM SPSS Statistics Server Contents: 1 Introduction 2 Performance 101: Understanding the drivers of better performance 3 Why performance is faster
More informationBridging the Gaps in Mobility Decision Making
Bridging the Gaps in Mobility Decision Making Why gaining visibility is the first step to fixing the lack of control that exists in today s mobile enterprise Wandera WHITE PAPER Page 2 Table of Contents
More informationMobile Cloud Computing: Paradigms and Challenges 移 动 云 计 算 : 模 式 与 挑 战
Mobile Cloud Computing: Paradigms and Challenges 移 动 云 计 算 : 模 式 与 挑 战 Jiannong Cao Internet & Mobile Computing Lab Department of Computing Hong Kong Polytechnic University Email: csjcao@comp.polyu.edu.hk
More informationBSC vision on Big Data and extreme scale computing
BSC vision on Big Data and extreme scale computing Jesus Labarta, Eduard Ayguade,, Fabrizio Gagliardi, Rosa M. Badia, Toni Cortes, Jordi Torres, Adrian Cristal, Osman Unsal, David Carrera, Yolanda Becerra,
More informationScheduling Support for Heterogeneous Hardware Accelerators under Linux
Scheduling Support for Heterogeneous Hardware Accelerators under Linux Tobias Wiersema University of Paderborn Paderborn, December 2010 1 / 24 Tobias Wiersema Linux scheduler extension for accelerators
More informationAchieving a High-Performance Virtual Network Infrastructure with PLUMgrid IO Visor & Mellanox ConnectX -3 Pro
Achieving a High-Performance Virtual Network Infrastructure with PLUMgrid IO Visor & Mellanox ConnectX -3 Pro Whitepaper What s wrong with today s clouds? Compute and storage virtualization has enabled
More informationDistributed File Systems
Distributed File Systems File Characteristics From Andrew File System work: most files are small transfer files rather than disk blocks? reading more common than writing most access is sequential most
More informationCORBAservices. Naming. Part of the CORBA Naming Service Interface in IDL. CORBA Naming Service
CORBAservices CORBAservices are general purpose and application independent services. They resemble and enhance services commonly provided by an operating system: Service Collection Query Concurrency Transaction
More informationCloud Computing. Up until now
Cloud Computing Lecture 20 Cloud Platform Comparison & Load Balancing 2010-2011 Up until now Introduction, Definition of Cloud Computing Pre-Cloud Large Scale Computing: Grid Computing Content Distribution
More informationOperatin g Systems: Internals and Design Principle s. Chapter 10 Multiprocessor and Real-Time Scheduling Seventh Edition By William Stallings
Operatin g Systems: Internals and Design Principle s Chapter 10 Multiprocessor and Real-Time Scheduling Seventh Edition By William Stallings Operating Systems: Internals and Design Principles Bear in mind,
More informationA new era of PaaS. ericsson White paper Uen 284 23-3263 February 2015
ericsson White paper Uen 284 23-3263 February 2015 A new era of PaaS speed and safety for the hybrid cloud This white paper presents the benefits for operators and large enterprises of adopting a policydriven
More informationRealities of Migrating from On-Premise to the Cloud
Realities of Migrating from On-Premise to the Cloud Rand Morimoto, Ph.D., President Convergent Computing (CCO) @randsnet / randm@cco.com http://www.cco.com 2015 Client Conference About the Presenter(s)
More informationMAUI: Dynamically Splitting Apps Between the Smartphone and Cloud
MAUI: Dynamically Splitting Apps Between the Smartphone and Cloud Brad Karp UCL Computer Science CS M038 / GZ06 28 th February 2012 Limited Smartphone Battery Capacity iphone 4 battery: 1420 mah (@ 3.7
More informationA Lightweight Distributed Framework for Computational Offloading in Mobile Cloud Computing
A Lightweight Distributed Framework for Computational Offloading in Mobile Cloud Computing Muhammad Shiraz 1 *, Abdullah Gani 1, Raja Wasim Ahmad 1, Syed Adeel Ali Shah 1, Ahmad Karim 1, Zulkanain Abdul
More informationH2O A Lightweight Approach to Grid Computing
H2O A Lightweight Approach to Grid Computing Roberto Podesta ropode@dist.unige.it References Emory University (Atlanta, GA, USA) Distributed Computing Laboratory Director: Prof. Vaidy Sunderam Project
More informationTASK OFFLOADING BETWEEN SMARTPHONES AND DISTRIBUTED COMPUTATIONAL RESOURCES
TASK OFFLOADING BETWEEN SMARTPHONES AND DISTRIBUTED COMPUTATIONAL RESOURCES by Shigeru Imai A Thesis Submitted to the Graduate Faculty of Rensselaer Polytechnic Institute in Partial Fulfillment of the
More informationElasticity Management in the Cloud. José M. Bernabéu-Aubán
Elasticity Management in the Cloud José M. Bernabéu-Aubán The Cloud and its goals Innovation of the Cloud Utility model of computing Pay as you go Variabilize costs for everyone But the Infrastructure
More information