ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores
|
|
- Berniece Malone
- 8 years ago
- Views:
Transcription
1 ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores Ahmad Al-Shishtawy KTH Royal Institute of Technology Stockholm, Sweden Doctoral School Day in Cloud Computing Louvain-la-Neuve, Belgium, 20 Nov 2012
2 Outline Introduction 1 Introduction ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 2/33
3 Outline Introduction Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control 1 Introduction Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 3/33
4 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Problem All computing systems need to be managed ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
5 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Problem All computing systems need to be managed ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
6 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Problem Computing systems are getting more and more complex ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
7 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Problem Complexity means higher administration overheads ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
8 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Problem Complexity poses a barrier on further development ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
9 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Solution The Autonomic Computing initiative by IBM ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
10 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Solution Self-Management: Systems capable of managing themselves ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
11 Dealing with Complexity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Solution Use Autonomic Managers Autonomic Manager Autonomic Manager Autonomic Manager Autonomic Manager Analyze Plan Analyze Plan Analyze Plan Analyze Plan Monitor Knowledge Execute Monitor Knowledge Execute Monitor Knowledge Execute Monitor Knowledge Execute ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 4/33
12 Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control The Autonomic Computing Architecture A Generic Solution Managed Resource Touchpoint (Sensors & Actuators) Autonomic Manager Monitor Analyze Plan Execute Manager Interface Touch Point Autonomic Manager Analyze Plan Monitor Knowledge Execute Touch Point Knowledge Source Communication Manager Interface Managed Resource Managed Resource ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 5/33
13 Self-* Properties Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Inspired by the autonomic nervous system of the human body Feedback control from Control Theory Self-management along four main axes (self-* properties): self-configuration self-optimization self-healing self-protection ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 6/33
14 Web 2.0 Applications Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Increasing popularity of Web 2.0 applications (e.g., wikis, social networks, blogs) Pose new challenges on the underlying provisioning infrastructure Scale Highly dynamic workload Data centric Traditional solutions does not work anymore Vertical vs. horizontal scalability ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 7/33
15 Cloud Computing Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Provide the illusion of infinite resources (e.g., VMs) Pay-as-you-go pricing model Elastic services (Horizontal scalability) High load: Allocate more VMs to improve performance Low load: Release VMs to save money ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 8/33
16 The Need for Elasticity Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Web 2.0 applications frequently experience high workloads A service can become popular in just an hour The high level load does not last for long and keeping resources in the Cloud costs money This has led to Elastic Computing Ability of a system to grow and shrink at run-time in response to changes in workload Cloud computing allows on-the-fly requesting and releasing VMs Meet SLOs at a minimal cost ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 9/33
17 Elasticity versus Static Provisioning Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 10/33
18 Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Elasticity can be controlled either manually (by the sys-admin) or automatically (by a autonomic manager) Automation of elasticity can be achieved by providing an Elasticity Controller Helps to avoid SLO violations while keeping the cost low Automatically adds/removes VMs (servers, service instances) in response to changes in some SLO metrics, e.g., request latency, caused by changes in workload Can be built using elements of Control Theory and/or Machine Learning Feedback-loop (a.k.a. closed-loop) control Model Predictive Control (MPC) ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 11/33
19 Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Pay-as-you-go + Elastic services + Web 2.0 dynamic workload ==> Elasticity Controller ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 12/33
20 Feedback Control Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control Desired Value Error Feedback Control System + System - Controller Input Output The system s output (e.g., response time) is being monitored Controller calculates the control error Controller changes the control input (e.g., number of servers to add or remove) according to the amount and sign of the control error Advantage: controller can adapt to disturbance Disadvantages: oscillation, overshoot, possible instability ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 13/33
21 Feedforward Control Autonomic Computing Cloud Computing and Elastic Services Feedback versus Feedforward Control System State Feedforward Controller Control Input System System Output The system s output is not monitored Other system states and variables are monitored Controller relies on a model of the system to calculate necessary change Advantages: faster and avoids oscillation and overshoot Disadvantages: sensitive to unexpected disturbances that are not modeled ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 14/33
22 Outline Introduction Problem Definition Challenges ElastMan 1 Introduction 2 Problem Definition Challenges ElastMan 3 4 ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 15/33
23 Target System Problem Definition Challenges ElastMan Multi-Tier Web 2.0 Application Public / Private Cloud Environment P Presentation Tier P P P D A D P D A D A D Application Tier D A Data Tier D D A A Elasticity Controller Deployed in a Cloud Environment A P C Virtual Machine Hosting a Server D P A D D A A Physical Machine D P Horizontal Scalability (add more servers) Each server is a Virtual Machine running on a physical machine in a Cloud environment ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 16/33
24 Minimum Requirements Problem Definition Challenges ElastMan Horizontal scalability Sensors to monitor workload and performance (e.g., read latency) Actuators to add/remove storage servers Rebalancing ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 17/33
25 Elasticity Controller Problem Definition Challenges ElastMan Objective Control the elasticity of Cloud-based key-value stores by adding/removing resources in order to meet SLOs at a minimal cost SLO examples Average read latency in one minute interval is less than 10ms 99% of reads in one minute interval are performed in less than 10ms per read ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 18/33
26 Problem Definition Challenges ElastMan Challenges to Design an Elasticity Controller for Storage Actuator delays due to data movement (rebalancing) Interference with applications and sensor measurements Discrete storage units Nonlinearity due to diminishing reward of adding a storage unit with increasing scale 99th percentile is a relatively noisy signal VM performance is difficult to model and predict Highly dynamic workload that is composed of both gradual (diurnal) and sudden (spikes) variations ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 19/33
27 Problem Definition Challenges ElastMan ElastMan: Combining Feedback and Feedforward Control Feedback Monitor 99th percentile Classical PI controller We use it to handle diurnal workloads Can tolerate and adapt to modeling errors Feedforward Monitor workload A binary classifier using logistic regression We use it to handle spikes in workload Allows us to smooth the noisy 99th percentile signal Changes in workload can be: Slow day-night changes (diurnal) Rapid changes (spikes) ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 20/33
28 Modeling the Store Problem Definition Challenges ElastMan Typical approach Workload (noise) Control Input Number of Servers Key-Value Store System Output 99th percentile of reads Non linear (1+1 vs ) Workload treated as noise ElastMan approach Control Input Average Workload per Server Key-Value Store System Output 99th percentile of reads Control the number of servers indirectly by controlling the average workload per server Relies on near linear scalability of key-value stores ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 21/33
29 Problem Definition Challenges ElastMan Feedback and Feedforward Controllers SLO (Desired 99th Percentile of Read Latency) + _ Error New Average PI Throughput Controller per Server Actuator New Number of Nodes Measured 99th Percentile of Read Latency Key-Value Store Target System Smoothing Filter Measured Average Throughput per Server FF Binary Classifier New Average Throughput per Server Actuator New Number of Nodes Key-Value Store Measured 99th Percentile of Read Latency Target System ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 22/33
30 Binary Classifier Problem Definition Challenges ElastMan Training Data and Model Write Throughput (ops/second/server) Violate SLO Satisfy SLO Model Read Throughput (ops/second/server) ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 23/33
31 Combined Feedback and Feedforward Flow Chart Start Controller Measure Average Throughput per server (tp) and 99 percentile of read latency (R99p) Filter rp99 fr99p=f(r99p) Error in dead-zone Yes Do nothing! No Rebalancing No Yes If storage supports rebalance restart then use Feedforward controller designed for the store in rebalance mode FFR(tp) Large change in Throughput Yes Use Feedforward FF(tp) Binary Classifier No Use Feedback FB(fp99) PID Controller Calculate number of new VMs new_vms = total_throughput/new_throughput_per_server subject to: replication_degree <= new_vms <= max_vms Start rebalance instance rebalance(n) End
32 Outline Introduction 1 Introduction ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 25/33
33 Implemented ElastMan Elasticity Controller Evaluated with LinkedIn s Voldemort key-value store Deployed in our private Cloud based on OpenStack ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 26/33
34 Elasticlity Controller for the Voldemort Key-Value Store ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 27/33
35 Voldemont performance with fixed number of servers (18) 10 8 Elasticity Controller Read p99 (ms) Desired VMs Total Throughput (K requests/sec) Number of Servers
36 Voldemont performance with fixed number of servers (18) 10 8 Elasticity Controller Read p99 (ms) Desired VMs Total Throughput (K requests/sec) Number of Servers Diurnal Workload Spikes
37 ElastMan controller performance under gradual (diurnal) workload 10 8 Elasticity Controller Read p99 (ms) Desired VMs Total Throughput (K requests/sec) Number of Servers
38 ElastMan controller performance with rapid changes (spikes) in workload 10 8 Elasticity Controller Read p99 (ms) Desired VMs Total Throughput (K requests/sec) Number of Servers
39 Outline Introduction 1 Introduction ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 31/33
40 Conclusions ElastMan addresses the challenges of the variable performance of Cloud VMs, dynamic workload, and stringent performance requirements ElastMan combines and leverages the advantages of both feedback and feedforward control feedforward control quickly respond to rapid changes in workload feedback controller handle diurnal workload and to correct modeling errors in the feedforward control results show the feasibility of our approach ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 32/33
41 Future Work Investigate the controllers needed to control all tiers of a Web 2.0 application and the orchestration of the controllers in order to correctly achieve their goals Provide a feedforward controller for the store during rebalancing Distributed version of ElastMan ElastMan: Autonomic Elasticity Manager for Cloud-Based Key-Value Stores (A. Al-Shishtawy) 33/33
State-Space Feedback Control for Elastic Distributed Storage in a Cloud Environment
State-Space Feedback Control for Elastic Distributed Storage in a Cloud Environment M. Amir Moulavi Ahmad Al-Shishtawy Vladimir Vlassov KTH Royal Institute of Technology, Stockholm, Sweden ICAS 2012, March
More informationRMAC: Resource Management Across Clouds
RMAC: Resource Management Across Clouds Vladimir Vlassov vladv@kth.se Ahmad Al-Shishtawy ahmadas@kth.se Seif Haridi seif@sics.se KTH Royal Institute of Technology SICS Swedish Institute of Computer Science
More informationFeedback Autonomic Provisioning for guaranteeing performance (and reliability. - application to Big Data Systems
Feedback Autonomic Provisioning for guaranteeing performance (and reliability) - application to Big Data Systems Bogdan Robu bogdan.robu@gipsa-lab.fr HIPEAC - HPES Workshop Amsterdam 19-21.01.2015 Context
More informationClaus Pahl IC4, School of Computing, Dublin City University, Ireland. claus.pahl@computing.dcu.ie
Pooyan Jamshidi IC4, School of Computing, Dublin City University, Ireland. pooyan.jamshidi@computing.dcu.ie Autonomic Resource Provisioning for Cloud-Based Software Aakash Ahmad Lero, School of Computing,
More informationOn- Prem MongoDB- as- a- Service Powered by the CumuLogic DBaaS Platform
On- Prem MongoDB- as- a- Service Powered by the CumuLogic DBaaS Platform Page 1 of 16 Table of Contents Table of Contents... 2 Introduction... 3 NoSQL Databases... 3 CumuLogic NoSQL Database Service...
More informationManaging Traditional Workloads Together with Cloud Computing Workloads
Managing Traditional Workloads Together with Cloud Computing Workloads Table of Contents Introduction... 3 Cloud Management Challenges... 3 Re-thinking of Cloud Management Solution... 4 Teraproc Cloud
More informationFederation of Cloud Computing Infrastructure
IJSTE International Journal of Science Technology & Engineering Vol. 1, Issue 1, July 2014 ISSN(online): 2349 784X Federation of Cloud Computing Infrastructure Riddhi Solani Kavita Singh Rathore B. Tech.
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 informationPlanning the Migration of Enterprise Applications to the Cloud
Planning the Migration of Enterprise Applications to the Cloud A Guide to Your Migration Options: Private and Public Clouds, Application Evaluation Criteria, and Application Migration Best Practices Introduction
More informationTechnology Enablement
SOLUTION OVERVIEW 1 ABOUT TECHMILEAGE Founded in 2008 / Tempe, Arizona Over 100 engagements Full range of business & technology services Software Development, Big Data, Cloud/AWS, BI, Advanced Analytics
More informationClodoaldo Barrera Chief Technical Strategist IBM System Storage. Making a successful transition to Software Defined Storage
Clodoaldo Barrera Chief Technical Strategist IBM System Storage Making a successful transition to Software Defined Storage Open Server Summit Santa Clara Nov 2014 Data at the core of everything Data is
More informationEvaluation Methodology of Converged Cloud Environments
Krzysztof Zieliński Marcin Jarząb Sławomir Zieliński Karol Grzegorczyk Maciej Malawski Mariusz Zyśk Evaluation Methodology of Converged Cloud Environments Cloud Computing Cloud Computing enables convenient,
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 informationTowards a Resource Elasticity Benchmark for Cloud Environments. Presented By: Aleksey Charapko, Priyanka D H, Kevin Harper, Vivek Madesi
Towards a Resource Elasticity Benchmark for Cloud Environments Presented By: Aleksey Charapko, Priyanka D H, Kevin Harper, Vivek Madesi Introduction & Background Resource Elasticity Utility Computing (Pay-Per-Use):
More informationSistemi Operativi e Reti. Cloud Computing
1 Sistemi Operativi e Reti Cloud Computing Facoltà di Scienze Matematiche Fisiche e Naturali Corso di Laurea Magistrale in Informatica Osvaldo Gervasi ogervasi@computer.org 2 Introduction Technologies
More informationEWeb: Highly Scalable Client Transparent Fault Tolerant System for Cloud based Web Applications
ECE6102 Dependable Distribute Systems, Fall2010 EWeb: Highly Scalable Client Transparent Fault Tolerant System for Cloud based Web Applications Deepal Jayasinghe, Hyojun Kim, Mohammad M. Hossain, Ali Payani
More informationCloud Computing. MCSN - N. Tonellotto - Distributed Enabling Platforms 1
Cloud Computing 1 Definitions (I) We have redefined Cloud Computing to include everything that we already do. I do not understand what we would do differently other then change the working of some of our
More informationBest Cloud Hosting For SaaS (Singapore) Contractors
CUSTOMER CASE STUDY We provide hosting that makes SaaS providers say wow. SolidFire allows to deliver a clean and simple elastic cloud experience with a guaranteed level of performance new to cloud computing.
More informationTo Be or Not to Be in the Cloud
To Be or Not to Be in the Cloud Presented by: Frank DiRocco Product Manager Objectives 30 Is The Cloud for me? Characteristics of Cloud & Physical Environments Comparing Transaction Volumes Business Objective
More informationManaging Elasticity in the PaaS Service Model
Managing Elasticity in the PaaS Service Model Francesc D. Muñoz-Escoí, Josep M. Bernabeu-Aubán Instituto Universitario Mixto Tecnológico de Informática Universitat Politècnica de València 46022 Valencia
More informationCutting Through the Hype: Straight Talk About the Mainframe and Cloud Computing. Straight talk on cloud computing
Glenn Anderson, IBM Lab Services and Training Cutting Through the Hype: Straight Talk About the Mainframe and Cloud Computing Summer SHARE August 2014 Session 15593 Straight talk on cloud computing What
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 informationMicrosoft Private Cloud Fast Track
Microsoft Private Cloud Fast Track Microsoft Private Cloud Fast Track is a reference architecture designed to help build private clouds by combining Microsoft software with Nutanix technology to decrease
More informationNoSQL for SQL Professionals William McKnight
NoSQL for SQL Professionals William McKnight Session Code BD03 About your Speaker, William McKnight President, McKnight Consulting Group Frequent keynote speaker and trainer internationally Consulted to
More informationCloud based performance testing: Issues and challenges. HotTopiCS 2013 Junzan Zhou zhoujunzan@zju.edu.cn 2012.4.17
Cloud based performance testing: Issues and challenges HotTopiCS 2013 Junzan Zhou zhoujunzan@zju.edu.cn 2012.4.17 Agenda Introduction of performance testing Background Issues and Challenges Conclusion
More informationChallenges in Hybrid and Federated Cloud Computing
Cloud Day 2011 KTH-SICS Cloud Innovation Center and EIT ICT Labs Kista, Sweden, September 14th, 2011 Challenges in Hybrid and Federated Cloud Computing Ignacio M. Llorente Project Director Acknowledgments
More informationWHY ALL CLOUDS ARE NOT CREATED EQUAL ENTERPRISE CLOUD, PUBLIC CLOUD, CARRIER CLOUD
WHY ALL CLOUDS ARE NOT CREATED EQUAL ENTERPRISE CLOUD, PUBLIC CLOUD, CARRIER CLOUD STRATEGIC WHITE PAPER Cloud computing technology brings an unprecedented level of independence and liberation in deploying
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 informationTowards Elastic High Performance Distributed Storage Systems in the Cloud
Towards Elastic High Performance Distributed Storage Systems in the Cloud YING LIU Licentiate Thesis School of Information and Communication Technology KTH Royal Institute of Technology Stockholm, Sweden
More informationMaking a Smooth Transition to a Hybrid Cloud with Microsoft Cloud OS
Making a Smooth Transition to a Hybrid Cloud with Microsoft Cloud OS Transitioning from today s highly virtualized data center environments to a true cloud environment requires solutions that let companies
More informationChoices for implementing SMB 3 on non Windows Servers Dilip Naik HvNAS Pty Ltd Australians good at NAS protocols!
Choices for implementing SMB 3 on non Windows Servers Dilip Naik HvNAS Pty Ltd Australians good at NAS protocols! Focus & contents of this talk Why SMB 3? How SMB 3? Implementing an SMB 3 Server on Linux/UNIX
More informationSystem Models for Distributed and Cloud Computing
System Models for Distributed and Cloud Computing Dr. Sanjay P. Ahuja, Ph.D. 2010-14 FIS Distinguished Professor of Computer Science School of Computing, UNF Classification of Distributed Computing Systems
More informationHow In-Memory Data Grids Can Analyze Fast-Changing Data in Real Time
SCALEOUT SOFTWARE How In-Memory Data Grids Can Analyze Fast-Changing Data in Real Time by Dr. William Bain and Dr. Mikhail Sobolev, ScaleOut Software, Inc. 2012 ScaleOut Software, Inc. 12/27/2012 T wenty-first
More informationElasticity in Cloud Computing
Joseph Fourier University, ENSIMAG Master of Science in Informatics at Grenoble Distributed, Embedded, Mobile, Interactive and Parallel Systems Elasticity in Cloud Computing Realized by : Petr Sobeslavsky
More informationJean Arnaud, Sara Bouchenak. Performance, Availability and Cost of Self-Adaptive Internet Services
Jean Arnaud, Sara Bouchenak Performance, Availability and Cost of Self-Adaptive Internet Services Chapter of Performance and Dependability in Service Computing: Concepts, Techniques and Research Directions
More informationSoftware-Defined Networks Powered by VellOS
WHITE PAPER Software-Defined Networks Powered by VellOS Agile, Flexible Networking for Distributed Applications Vello s SDN enables a low-latency, programmable solution resulting in a faster and more flexible
More informationMicrosoft Private Cloud
Microsoft Private Cloud Lorenz Wolf, Solution Specialist Datacenter, Microsoft SoftwareOne @ Au Premier Zürich - 22.03.2011 What is PRIVATE CLOUD Private Public Public Cloud Private Cloud shared resources.
More informationSOFTWARE DEFINED NETWORKING
SOFTWARE DEFINED NETWORKING Bringing Networks to the Cloud Brendan Hayes DIRECTOR, SDN MARKETING AGENDA Market trends and Juniper s SDN strategy Network virtualization evolution Juniper s SDN technology
More informationDoes Cloud Computing Still Matter? A Mainframer s Update. The trouble with cloud.
Glenn Anderson, IBM Lab Services and Training Does Cloud Computing Still Matter? A Mainframer s Update STL CMG January 2014 2013 IBM Corporation The trouble with cloud. The term cloud computing is used
More informationAn Autonomic Auto-scaling Controller for Cloud Based Applications
An Autonomic Auto-scaling Controller for Cloud Based Applications Jorge M. Londoño-Peláez Escuela de Ingenierías Universidad Pontificia Bolivariana Medellín, Colombia Carlos A. Florez-Samur Netsac S.A.
More informationMonitoring Elastic Cloud Services
Monitoring Elastic Cloud Services trihinas@cs.ucy.ac.cy Advanced School on Service Oriented Computing (SummerSoc 2014) 30 June 5 July, Hersonissos, Crete, Greece Presentation Outline Elasticity in Cloud
More informationDATA-DRIVEN EFFICIENCY
DATA-DRIVEN EFFICIENCY Combining actionable information with market insights to work intelligently and reduce costs ACTIONABLE INTELLIGENCE Ericsson is driving the development of actionable intelligence
More informationSoftware defined networking. Your path to an agile hybrid cloud network
Software defined networking Your path to an agile hybrid cloud network Is your enterprise network ready for the latest business and consumer trends? Cloud How easily can your users connect to cloud resources?
More informationIT Security Risk Management Model for Cloud Computing: A Need for a New Escalation Approach.
IT Security Risk Management Model for Cloud Computing: A Need for a New Escalation Approach. Gunnar Wahlgren 1, Stewart Kowalski 2 Stockholm University 1: (wahlgren@dsv.su.se), 2: (stewart@dsv.su.se) ABSTRACT
More informationMobile Cloud Networking FP7 European Project: Radio Access Network as a Service
Optical switch WC-Pool (in a data centre) BBU-pool RAT 1 BBU-pool RAT 2 BBU-pool RAT N Mobile Cloud Networking FP7 European Project: Radio Access Network as a Service Dominique Pichon (Orange) 4th Workshop
More informationUnderstanding Virtualization and Cloud in the Enterprise
Understanding Virtualization and Cloud in the Enterprise James Staten Vice President, Principal Analyst Forrester Research Virtualization is evolving toward cloud but won t be subsumed by it 2 What s different
More informationIBM Spectrum Protect in the Cloud
IBM Spectrum Protect in the Cloud. Disclaimer IBM s statements regarding its plans, directions, and intent are subject to change or withdrawal without notice at IBM s sole discretion. Information regarding
More informationEasy Deployment of Mission-Critical Applications to the Cloud
Easy Deployment of Mission-Critical Applications to the Cloud Businesses want to move to the cloud to gain agility and reduce costs. But if your app needs re-architecting or new code that s neither easy
More informationWindows Azure and private cloud
Windows Azure and private cloud Joe Chou Senior Program Manager China Cloud Innovation Center Customer Advisory Team Microsoft Asia-Pacific Research and Development Group 1 Agenda Cloud Computing Fundamentals
More informationLOGO Resource Management for Cloud Computing
LOGO Resource Management for Cloud Computing Supervisor : Dr. Pham Tran Vu Presenters : Nguyen Viet Hung - 11070451 Tran Le Vinh - 11070487 Date : April 16, 2012 Contents Introduction to Cloud Computing
More informationHow To Manage Cloud Service Provisioning And Maintenance
Managing Cloud Service Provisioning and SLA Enforcement via Holistic Monitoring Techniques Vincent C. Emeakaroha Matrikelnr: 0027525 vincent@infosys.tuwien.ac.at Supervisor: Univ.-Prof. Dr. Schahram Dustdar
More informationCloud Computing. Introduction
Cloud Computing Introduction Computing in the Clouds Summary Think-Pair-Share According to Aaron Weiss, what are the different shapes the Cloud can take? What are the implications of these different shapes?
More informationHigh Availability of VistA EHR in Cloud. ViSolve Inc. White Paper February 2015. www.visolve.com
High Availability of VistA EHR in Cloud ViSolve Inc. White Paper February 2015 1 Abstract Inspite of the accelerating migration to cloud computing in the Healthcare Industry, high availability and uptime
More informationMachine Data Analytics with Sumo Logic
Machine Data Analytics with Sumo Logic A Sumo Logic White Paper Introduction Today, organizations generate more data in ten minutes than they did during the entire year in 2003. This exponential growth
More informationBuild and Manage Private and Hybrid Cloud. Urban Järund, Sr Regional Services Manager Nordics, Red Hat
Build and Manage Private and Hybrid Cloud Urban Järund, Sr Regional Services Manager Nordics, Red Hat CLOUD DEPLOYMENT MODELS HYBRID CLOUD Interoperable combination of private and public cloud. PRIVATE
More informationThe 5G Infrastructure Public-Private Partnership
The 5G Infrastructure Public-Private Partnership NetFutures 2015 5G PPP Vision 25/03/2015 19/06/2015 1 5G new service capabilities User experience continuity in challenging situations such as high mobility
More informationTechnology Insight Series
Evaluating Storage Technologies for Virtual Server Environments Russ Fellows June, 2010 Technology Insight Series Evaluator Group Copyright 2010 Evaluator Group, Inc. All rights reserved Executive Summary
More informationHYPER-CONVERGED INFRASTRUCTURE STRATEGIES
1 HYPER-CONVERGED INFRASTRUCTURE STRATEGIES MYTH BUSTING & THE FUTURE OF WEB SCALE IT 2 ROADMAP INFORMATION DISCLAIMER EMC makes no representation and undertakes no obligations with regard to product planning
More informationOverview. The Cloud. Characteristics and usage of the cloud Realities and risks of the cloud
Overview The purpose of this paper is to introduce the reader to the basics of cloud computing or the cloud with the aim of introducing the following aspects: Characteristics and usage of the cloud Realities
More informationCloud Computing Capacity Planning. Maximizing Cloud Value. Authors: Jose Vargas, Clint Sherwood. Organization: IBM Cloud Labs
Cloud Computing Capacity Planning Authors: Jose Vargas, Clint Sherwood Organization: IBM Cloud Labs Web address: ibm.com/websphere/developer/zones/hipods Date: 3 November 2010 Status: Version 1.0 Abstract:
More informationCloud computing opens new perspectives for hosting
ConPaaS: a Platform for Hosting Elastic Cloud Applications Guillaume Pierre Corina Stratan Vrije Universiteit Amsterdam Cloud computing opens new perspectives for hosting applications. From an application
More informationElastic VM for Rapid and Optimum Virtualized
Elastic VM for Rapid and Optimum Virtualized Resources Allocation Wesam Dawoud PhD. Student Hasso Plattner Institute Potsdam, Germany 5th International DMTF Academic Alliance Workshop on Systems and Virtualization
More informationCloud Computing Backgrounder
Cloud Computing Backgrounder No surprise: information technology (IT) is huge. Huge costs, huge number of buzz words, huge amount of jargon, and a huge competitive advantage for those who can effectively
More informationHigh Availability with Postgres Plus Advanced Server. An EnterpriseDB White Paper
High Availability with Postgres Plus Advanced Server An EnterpriseDB White Paper For DBAs, Database Architects & IT Directors December 2013 Table of Contents Introduction 3 Active/Passive Clustering 4
More informationCLOUD TECH SOLUTION AT INTEL INFORMATION TECHNOLOGY ICApp Platform as a Service
CLOUD TECH SOLUTION AT INTEL INFORMATION TECHNOLOGY ICApp Platform as a Service Open Data Center Alliance, Inc. 3855 SW 153 rd Dr. Beaverton, OR 97003 USA Phone +1 503-619-2368 Fax: +1 503-644-6708 Email:
More informationAffordable, Scalable, Reliable OLTP in a Cloud and Big Data World: IBM DB2 purescale
WHITE PAPER Affordable, Scalable, Reliable OLTP in a Cloud and Big Data World: IBM DB2 purescale Sponsored by: IBM Carl W. Olofson December 2014 IN THIS WHITE PAPER This white paper discusses the concept
More informationWHITE PAPER Virtualizing UC: Reaping the Benefits and Understanding the Issues for Real-Time Communications
WHITE PAPER Virtualizing UC: Reaping the Benefits and Understanding the Issues for Real-Time Communications Sponsored by: Avaya Abner Germanow October 2009 Jonathan Edwards PROBLEM DEFINITION Global Headquarters:
More informationConsumption IT. Michael Shepherd Business Development Manager. Cisco Public Sector May 1 st 2014
Consumption IT Michael Shepherd Business Development Manager Cisco Public Sector May 1 st 2014 Short Bio Cloud BDM in Public Sector (SLED + FED) Cisco for 14 + years Focused on cloud for 4 + years Awareness,
More informationVirtualclientTechnology 2011 July
WHAT S NEW IN VSPHERE VirtualclientTechnology 2011 July Agenda vsphere Platform Recap vsphere 5 Overview Infrastructure Services Compute, Storage, Network Applications Services Availability, Security,
More informationConsiderations for Adopting PaaS (Platform as a Service)
Considerations for Adopting PaaS (Platform as a Service) Michael Dolan (mdolan@pivotal.io) Senior Field Engineer April 2015 1 Becoming The Agile Enterprise To effectively achieve its missions, the Department
More informationState-Space Feedback Control for Elastic Distributed Storage in a Cloud Environment
State-Space Feedback Control for Elastic Distributed Storage in a Cloud Environment M. Amir Moulavi, Ahmad Al-Shishtawy, and Vladimir Vlassov KTH Royal Institute of Technology Stockholm, Sweden Email:
More informationRIDE THE SDN AND CLOUD WAVE WITH CONTRAIL
RIDE THE SDN AND CLOUD WAVE WITH CONTRAIL Pascal Geenens CONSULTING ENGINEER, JUNIPER NETWORKS pgeenens@juniper.net BUSINESS AGILITY Need to create and deliver new revenue opportunities faster Services
More informationApplying Control Theory to Application Performance Management in the Cloud
Applying Control Theory to Application Performance Management in the Cloud Xiaoyun Zhu CDS@20 August 7, 2014 2014 VMware Inc. All rights reserved. Virtualization a new computing paradigm Key benefits Higher
More informationIntroduction to Cloud Computing
Introduction to Cloud Computing Cloud Computing I (intro) 15 319, spring 2010 2 nd Lecture, Jan 14 th Majd F. Sakr Lecture Motivation General overview on cloud computing What is cloud computing Services
More informationSOLUTIONS PRODUCTS INDUSTRIES RESOURCES SUPPORT ABOUT US. 2012 ClearCube Technology, Inc. All rights reserved. Contact Support
1 of 1 9/28/2012 3:21 PM Contact Us 1-866-652-350 SmartVDI Host Platforms ClearCube s Smart Virtual Desktop Infrastructure (SmartVDI ) host platforms scale from 100s to 1000s of virtual desktops, with
More informationWhen Does Colocation Become Competitive With The Public Cloud? WHITE PAPER SEPTEMBER 2014
When Does Colocation Become Competitive With The Public Cloud? WHITE PAPER SEPTEMBER 2014 Table of Contents Executive Summary... 2 Case Study: Amazon Ec2 Vs In-House Private Cloud... 3 Aim... 3 Participants...
More informationIaaS Cloud Architectures: Virtualized Data Centers to Federated Cloud Infrastructures
IaaS Cloud Architectures: Virtualized Data Centers to Federated Cloud Infrastructures Dr. Sanjay P. Ahuja, Ph.D. 2010-14 FIS Distinguished Professor of Computer Science School of Computing, UNF Introduction
More informationWhen Does Colocation Become Competitive With The Public Cloud?
When Does Colocation Become Competitive With The Public Cloud? PLEXXI WHITE PAPER Affinity Networking for Data Centers and Clouds Table of Contents EXECUTIVE SUMMARY... 2 CASE STUDY: AMAZON EC2 vs IN-HOUSE
More informationPerformance and Scale in Cloud Computing
Performance and Scale in Cloud Computing A Joyent White Paper Executive Summary Poor application performance causes companies to lose customers, reduce employee productivity, and reduce bottom line revenue.
More information18/09/2015. DevOps. Prof. Filippo Lanubile. Outline. Definitions Collaboration in DevOps Automation in DevOps. Prof.
DevOps Outline Definitions Collaboration in DevOps Automation in DevOps 1 www.agilemanifesto.org/principles.html What is DevOps A set of practices that emphasize automation and collaboration between development
More informationAn architectural blueprint for autonomic computing.
Autonomic Computing White Paper An architectural blueprint for autonomic computing. June 2005 Third Edition Page 2 Contents 1. Introduction 3 Autonomic computing 4 Self-management attributes of system
More informationHow To Handle Big Data With A Data Scientist
III Big Data Technologies Today, new technologies make it possible to realize value from Big Data. Big data technologies can replace highly customized, expensive legacy systems with a standard solution
More informationCloud Computing. P a n a g i o t i s F o u z a s I T S o l u t i o n s M a n a g e r
C l a s s i f i c a t i o n I S O 2 7 0 0 1 : P u b l i c Cloud Computing Prospects & Challenges P a n a g i o t i s F o u z a s I T S o l u t i o n s M a n a g e r 1 OUTLINE Cloud Definition and Classification
More informationDriving workload automation across the enterprise
IBM Software Thought Leadership White Paper October 2011 Driving workload automation across the enterprise Simplifying workload management in heterogeneous environments 2 Driving workload automation across
More informationHiTech. White Paper. Storage-as-a-Service. SAN and NAS Reference Architectures leveraging Private Cloud Storage
HiTech White Paper -as-a-service SAN and NAS Reference Architectures leveraging Private Cloud About the Author Ankur Srivastava Ankur Srivastava is a Solution Architect working with the Hi Tech Industry
More informationWhite Paper. Cloud Performance Testing
White Paper Cloud Performance Testing Table of Contents Introduction and Background Information...2 Challenges & Limitations of On-Premise Model. 2 Cloud Scope and Service Models... 3 Why Cloud for Performance
More informationApplying Statistical Learning, Optimization, and Control to Application Performance Management in the Cloud
Applying Statistical Learning, Optimization, and Control to Application Performance Management in the Cloud Xiaoyun Zhu October 17, 2014 2014 VMware Inc. All rights reserved. Rapidly growing public cloud
More information3 Ways to build a SaaS Product. Asteor Software Inc Ram Kumar - Director Product Management
3 Ways to build a SaaS Product Asteor Software Inc Ram Kumar - Director Product Management SaaS without Multi-tenancy A separate server instance for each customer Separate Box Separate Shared Hosting Slice
More informationAutonomic IoT Systems Realizing Self-* Properties in IoT Systems
Autonomic IoT Systems Realizing Self-* Properties in IoT Systems Noor Bajunaid nbajunai@masonlive.gmu.edu CS 788 Fall 2015 1 IoT and CPS The internet of things is known as giving any object the ability
More informationOptimization of QoS for Cloud-Based Services through Elasticity and Network Awareness
Master Thesis: Optimization of QoS for Cloud-Based Services through Elasticity and Network Awareness Alexander Fedulov 1 Agenda BonFIRE Project overview Motivation General System Architecture Monitoring
More informationA Generic Auto-Provisioning Framework for Cloud Databases
A Generic Auto-Provisioning Framework for Cloud Databases Jennie Rogers 1, Olga Papaemmanouil 2 and Ugur Cetintemel 1 1 Brown University, 2 Brandeis University Instance Type Introduction Use Infrastructure-as-a-Service
More informationCloud DBMS: An Overview. Shan-Hung Wu, NetDB CS, NTHU Spring, 2015
Cloud DBMS: An Overview Shan-Hung Wu, NetDB CS, NTHU Spring, 2015 Outline Definition and requirements S through partitioning A through replication Problems of traditional DDBMS Usage analysis: operational
More informationOpenNebula Latest Innovations in Private Cloud Computing
OpenNebula Latest Innovations in Private Cloud Computing Ignacio M. Llorente OpenNebula Project Director OpenNebula Project. Creative Commons Attribution-NonCommercial-ShareAlike License Contents This
More informationLiferay Portal Performance. Benchmark Study of Liferay Portal Enterprise Edition
Liferay Portal Performance Benchmark Study of Liferay Portal Enterprise Edition Table of Contents Executive Summary... 3 Test Scenarios... 4 Benchmark Configuration and Methodology... 5 Environment Configuration...
More informationOutdated Architectures Are Holding Back the Cloud
Outdated Architectures Are Holding Back the Cloud Flash Memory Summit Open Tutorial on Flash and Cloud Computing August 11,2011 Dr John R Busch Founder and CTO Schooner Information Technology JohnBusch@SchoonerInfoTechcom
More informationFI-WARE Cloud Overview
FI-WAE Cloud Overview Presented by: Alex Glikson, IBM April 3 rd, 2013, Madrid http://www.fi-ware.eu http://www.fi-ppp.eu Agenda FI-WAE Cloud Generic Enablers Overview Demo 1 FI-WAE Cloud Generic Enablers
More informationThe public-cloud-computing market has
View from the Cloud Editor: George Pallis gpallis@cs.ucy.ac.cy Comparing Public- Cloud Providers Ang Li and Xiaowei Yang Duke University Srikanth Kandula and Ming Zhang Microsoft Research As cloud computing
More informationVariations in Performance and Scalability when Migrating n-tier Applications to Different Clouds
Variations in Performance and Scalability when Migrating n-tier Applications to Different Clouds Deepal Jayasinghe, Simon Malkowski, Qingyang Wang, Jack Li, Pengcheng Xiong, Calton Pu Outline Motivation
More information