the emperor s new consistency the case against weak consistency in data centers marcos k. aguilera microsoft research silicon valley

Size: px
Start display at page:

Download "the emperor s new consistency the case against weak consistency in data centers marcos k. aguilera microsoft research silicon valley"

Transcription

1 the emperor s new consistency the case against weak consistency in data centers marcos k. aguilera microsoft research silicon valley

2 synopsis weak consistency widely adopted today in data center systems we will argue: this trend will change strong consistency will be the norm reasons: technological, legal, sociological

3 types of consistency replica consistency data replicas should be in sync with each other therefore: equivalent to read from any replica need to look into the system to know data consistency invariants must hold for the data set the C in ACID assumes the user behaves well

4 types of consistency semantic consistency data operations return sensible results eg: linearizability, causal consistency, sequential consistency, read-own-writes, transaction isolation properties defined by behavior of interface to storage system typically replica consistency => semantic consistency semantic consistency + correct app => data consistency

5 types of consistency focus of this talk: semantic consistency don t care about how things are implemented don t want to get into correctness of application

6 weak consistency best effort operations can return any response eventual consistency eventually operations return correct responses causal consistency if an operation observes an effect then it observes its causes many others

7 consistency in data center systems yahoo pnuts: weak (timeline consistency) amazon s3: weak (eventual consistency) with option of slightly stronger consistency amazon simpledb: weak or strong microsoft azure: strong dynamo: weak (reads may not intersect writes) cops: weak (causal-plus consistency) walter: weak (parallel snapshot isolation) etc

8 inconsistency hard to contain => inconsistency propagates all the way to the end user

9 origins of weak consistency in data center systems

10 why weak consistency in data center storage systems in a nutshell: benefits > drawbacks benefits better performance and availability even more in geo-distributed applications can tolerate intermittent spikes in usage storage systems easier to develop no guarantees => system correct no matter what drawbacks users see stale data but only sometimes and users are tolerant

11 key argument benefits of weak consistency are shrinking technological reasons drawbacks of weak consistency are expanding technological, legal, and sociological reasons corollary: in the future, benefits < drawback next: explain factors leading to these changes

12 FACTORS: INCREASING DRAWBACKS OF WEAK CONSISTENCY

13 factor: increasing number of paid apps free apps => users tolerate strange behavior but more paid data center apps emerging social networks: facebook, linkedin, etc content provider: hulu, itunes store, netflix, etc online games: zynga, battle.net, etc online stores: amazon, most large retailers, etc office apps: office 365 business apps: salesforce, etc paying users + strange behavior = angry users

14 factor: people more reliant on data center apps daily communication, shopping, banking, content sharing, appointments, medical records, etc application provider subject to liability strange behavior can lead to losses

15 factor: more app layers, more integration user of app becomes another app bank records => financial software social network data => third-app vendors s, appointments => phone client humans can identify and tolerate inconsistency programs have harder time weaker invariants => more corner cases => complexity examples: references to inexistent objects, old versions

16 FACTORS: DECREASING BENEFITS OF WEAK CONSISTENCY

17 factor: network partitions will disappear causes of network partitions being addressed 1. lack of bandwidth or connectivity within data center: full bisection bandwidth networks across data centers: more infrastructure around world 2. failure-prone network elements being replaced with distributed fault-tolerant systems 3. operator errors better tools to manage network centralized management via software-defined networking

18 factor: wide-area latency shrinks currently, ping latencies still large 3-4 times larger than speed-of-light values due to switching delays, long paths sometimes more due to congestion speed-of-light values are small enough circumference of earth: 40,000 Km -> 133 ms Frankfurt-San Francisco: 9,000 Km -> 30 ms Frankfurt-Delhi: 7,500 Km -> 25 ms eventually get to these latencies

19 factor: number of apps growing relative to number of storage systems storage system = infrastructure for many apps today: many storage systems eg, 25+ NOSQL storage systems active area of development much functionality overlap, few will survive meanwhile: number of apps increases argument that it is easier to build a weakly consistent storage system loses force, because it makes it harder to develop apps

20 combination of factors more paid data center apps people more reliant on data center apps more app layers, more integration inconsistency angers users app provider subject to liability inconsistency creates complexity more drawbacks of weak consistency no network partitions smaller wide-area latency fewer storage systems relative to apps availability and performance advantage of weak consistency shrinks better to build stronger storage system and benefit many apps fewer benefits of weak consistency

21 factors that would undermine argument performance difference between weak and strong consistency really matters maybe, but ms not bad especially because operations generally can be batched society embraces inconsistency like software bugs, people just give up how I stopped worrying and learned to love the inconsistency

22 conclusion in the context of data center systems weak consistency creates challenges that will become more problematic weak consistency solves problems that will be solved differently

Geo-Replication in Large-Scale Cloud Computing Applications

Geo-Replication in Large-Scale Cloud Computing Applications Geo-Replication in Large-Scale Cloud Computing Applications Sérgio Garrau Almeida sergio.garrau@ist.utl.pt Instituto Superior Técnico (Advisor: Professor Luís Rodrigues) Abstract. Cloud computing applications

More information

geo-distributed storage in data centers marcos k. aguilera microsoft research silicon valley

geo-distributed storage in data centers marcos k. aguilera microsoft research silicon valley geo-distributed storage in data centers marcos k. aguilera microsoft research silicon valley context: large web applications examples microsoft: bing, hotmail, skype; google: search, gmail; yahoo!: search,

More information

The Cloud Trade Off IBM Haifa Research Storage Systems

The Cloud Trade Off IBM Haifa Research Storage Systems The Cloud Trade Off IBM Haifa Research Storage Systems 1 Fundamental Requirements form Cloud Storage Systems The Google File System first design consideration: component failures are the norm rather than

More information

INFO5011 Advanced Topics in IT: Cloud Computing Week 10: Consistency and Cloud Computing

INFO5011 Advanced Topics in IT: Cloud Computing Week 10: Consistency and Cloud Computing INFO5011 Advanced Topics in IT: Cloud Computing Week 10: Consistency and Cloud Computing Dr. Uwe Röhm School of Information Technologies! Notions of Consistency! CAP Theorem! CALM Conjuncture! Eventual

More information

Cloud data store services and NoSQL databases. Ricardo Vilaça Universidade do Minho Portugal

Cloud data store services and NoSQL databases. Ricardo Vilaça Universidade do Minho Portugal Cloud data store services and NoSQL databases Ricardo Vilaça Universidade do Minho Portugal Context Introduction Traditional RDBMS were not designed for massive scale. Storage of digital data has reached

More information

HAT not CAP: Highly Available Transactions

HAT not CAP: Highly Available Transactions HAT not CAP: Highly Available Transactions Talk at Dagstuhl Seminar 13081, February 19 2013 Draft Paper at http://arxiv.org/pdf/1302.0309.pdf Peter Bailis (UCBerkeley), Alan Fekete (U of Sydney), Ali Ghodsi

More information

CAP Theorem and Distributed Database Consistency. Syed Akbar Mehdi Lara Schmidt

CAP Theorem and Distributed Database Consistency. Syed Akbar Mehdi Lara Schmidt CAP Theorem and Distributed Database Consistency Syed Akbar Mehdi Lara Schmidt 1 Classical Database Model T2 T3 T1 Database 2 Databases these days 3 Problems due to replicating data Having multiple copies

More information

NoSQL Database Options

NoSQL Database Options NoSQL Database Options Introduction For this report, I chose to look at MongoDB, Cassandra, and Riak. I chose MongoDB because it is quite commonly used in the industry. I chose Cassandra because it has

More information

Replicated Data Consistency Explained Through Baseball

Replicated Data Consistency Explained Through Baseball Replicated Data Consistency Explained Through Baseball Doug Terry Microsoft Research Silicon Valley MSR Technical Report October 2011 Abstract Some cloud storage services, like Windows Azure, replicate

More information

Cloud Storage over Multiple Data Centers

Cloud Storage over Multiple Data Centers Cloud Storage over Multiple Data Centers Shuai MU, Maomeng SU, Pin GAO, Yongwei WU, Keqin LI, Albert ZOMAYA 0 Abstract The increasing popularity of cloud storage services has led many companies to migrate

More information

CS5412: ANATOMY OF A CLOUD

CS5412: ANATOMY OF A CLOUD 1 CS5412: ANATOMY OF A CLOUD Lecture VII Ken Birman How are cloud structured? 2 Clients talk to clouds using web browsers or the web services standards But this only gets us to the outer skin of the cloud

More information

Distributed Systems. Tutorial 12 Cassandra

Distributed Systems. Tutorial 12 Cassandra Distributed Systems Tutorial 12 Cassandra written by Alex Libov Based on FOSDEM 2010 presentation winter semester, 2013-2014 Cassandra In Greek mythology, Cassandra had the power of prophecy and the curse

More information

Surviving congestion in geo-distributed storage systems

Surviving congestion in geo-distributed storage systems Surviving congestion in geo-distributed storage systems Brian Cho University of Illinois at Urbana-Champaign Marcos K. Aguilera Microsoft Research Silicon Valley Abstract. We present Vivace, a key-value

More information

Highly available, scalable and secure data with Cassandra and DataStax Enterprise. GOTO Berlin 27 th February 2014

Highly available, scalable and secure data with Cassandra and DataStax Enterprise. GOTO Berlin 27 th February 2014 Highly available, scalable and secure data with Cassandra and DataStax Enterprise GOTO Berlin 27 th February 2014 About Us Steve van den Berg Johnny Miller Solutions Architect Regional Director Western

More information

RAMCloud and the Low- Latency Datacenter. John Ousterhout Stanford University

RAMCloud and the Low- Latency Datacenter. John Ousterhout Stanford University RAMCloud and the Low- Latency Datacenter John Ousterhout Stanford University Most important driver for innovation in computer systems: Rise of the datacenter Phase 1: large scale Phase 2: low latency Introduction

More information

The CAP theorem and the design of large scale distributed systems: Part I

The CAP theorem and the design of large scale distributed systems: Part I The CAP theorem and the design of large scale distributed systems: Part I Silvia Bonomi University of Rome La Sapienza www.dis.uniroma1.it/~bonomi Great Ideas in Computer Science & Engineering A.A. 2012/2013

More information

Introduction to NOSQL

Introduction to NOSQL Introduction to NOSQL Université Paris-Est Marne la Vallée, LIGM UMR CNRS 8049, France January 31, 2014 Motivations NOSQL stands for Not Only SQL Motivations Exponential growth of data set size (161Eo

More information

The NoSQL Ecosystem, Relaxed Consistency, and Snoop Dogg. Adam Marcus MIT CSAIL marcua@csail.mit.edu / @marcua

The NoSQL Ecosystem, Relaxed Consistency, and Snoop Dogg. Adam Marcus MIT CSAIL marcua@csail.mit.edu / @marcua The NoSQL Ecosystem, Relaxed Consistency, and Snoop Dogg Adam Marcus MIT CSAIL marcua@csail.mit.edu / @marcua About Me Social Computing + Database Systems Easily Distracted: Wrote The NoSQL Ecosystem in

More information

Consistency Trade-offs for SDN Controllers. Colin Dixon, IBM February 5, 2014

Consistency Trade-offs for SDN Controllers. Colin Dixon, IBM February 5, 2014 Consistency Trade-offs for SDN Controllers Colin Dixon, IBM February 5, 2014 The promises of SDN Separa&on of control plane from data plane Logical centraliza&on of control plane Common abstrac&ons for

More information

wow CPSC350 relational schemas table normalization practical use of relational algebraic operators tuple relational calculus and their expression in a declarative query language relational schemas CPSC350

More information

Consistency-Based Service Level Agreements for Cloud Storage

Consistency-Based Service Level Agreements for Cloud Storage Consistency-Based Service Level Agreements for Cloud Storage Douglas B. Terry, Vijayan Prabhakaran, Ramakrishna Kotla, Mahesh Balakrishnan, Marcos K. Aguilera, Hussam Abu-Libdeh Microsoft Research Silicon

More information

SQL VS. NO-SQL. Adapted Slides from Dr. Jennifer Widom from Stanford

SQL VS. NO-SQL. Adapted Slides from Dr. Jennifer Widom from Stanford SQL VS. NO-SQL Adapted Slides from Dr. Jennifer Widom from Stanford 55 Traditional Databases SQL = Traditional relational DBMS Hugely popular among data analysts Widely adopted for transaction systems

More information

Where We Are. References. Cloud Computing. Levels of Service. Cloud Computing History. Introduction to Data Management CSE 344

Where We Are. References. Cloud Computing. Levels of Service. Cloud Computing History. Introduction to Data Management CSE 344 Where We Are Introduction to Data Management CSE 344 Lecture 25: DBMS-as-a-service and NoSQL We learned quite a bit about data management see course calendar Three topics left: DBMS-as-a-service and NoSQL

More information

NoSQL Databases. Polyglot Persistence

NoSQL Databases. Polyglot Persistence The future is: NoSQL Databases Polyglot Persistence a note on the future of data storage in the enterprise, written primarily for those involved in the management of application development. Martin Fowler

More information

AUTOMATED MOBILE TESTING REQUIRES BOTH REAL DEVICES AND EMULATORS

AUTOMATED MOBILE TESTING REQUIRES BOTH REAL DEVICES AND EMULATORS WHITE PAPER AUTOMATED MOBILE TESTING REQUIRES BOTH REAL DEVICES AND EMULATORS SEPTEMBER 2015 Today, businesses compete in an increasingly mobile-centric marketplace. Mobile QA can no longer take a backseat

More information

IJRSET 2015 SPL Volume 2, Issue 11 Pages: 29-33

IJRSET 2015 SPL Volume 2, Issue 11 Pages: 29-33 CLOUD COMPUTING NEW TECHNOLOGIES 1 Gokul krishnan. 2 M, Pravin raj.k, 3 Ms. K.M. Poornima 1, 2 III MSC (software system), 3 Assistant professor M.C.A.,M.Phil. 1, 2, 3 Department of BCA&SS, 1, 2, 3 Sri

More information

Structured Data Storage

Structured Data Storage Structured Data Storage Xgen Congress Short Course 2010 Adam Kraut BioTeam Inc. Independent Consulting Shop: Vendor/technology agnostic Staffed by: Scientists forced to learn High Performance IT to conduct

More information

Eventually Consistent

Eventually Consistent Historical Perspective In an ideal world there would be only one consistency model: when an update is made all observers would see that update. The first time this surfaced as difficult to achieve was

More information

Transactions and ACID in MongoDB

Transactions and ACID in MongoDB Transactions and ACID in MongoDB Kevin Swingler Contents Recap of ACID transactions in RDBMSs Transactions and ACID in MongoDB 1 Concurrency Databases are almost always accessed by multiple users concurrently

More information

Outline. What is cloud computing? History Cloud service models Cloud deployment forms Advantages/disadvantages

Outline. What is cloud computing? History Cloud service models Cloud deployment forms Advantages/disadvantages Ivan Zapevalov 2 Outline What is cloud computing? History Cloud service models Cloud deployment forms Advantages/disadvantages 3 What is cloud computing? 4 What is cloud computing? Cloud computing is the

More information

Cloud Computing. Jussi Talaskivi Information Management Centre University of Jyväskylä

Cloud Computing. Jussi Talaskivi Information Management Centre University of Jyväskylä Cloud Computing Jussi Talaskivi Information Management Centre University of Jyväskylä About the presenter Information Systems Analyst Scrum master Web Content Management System (Plone) www.jyu.fi Koppa

More information

How the emergence of OpenFlow and SDN will change the networking landscape

How the emergence of OpenFlow and SDN will change the networking landscape How the emergence of OpenFlow and SDN will change the networking landscape Software-defined networking (SDN) powered by the OpenFlow protocol has the potential to be an important and necessary game-changer

More information

Communication System Design Projects

Communication System Design Projects Communication System Design Projects PROFESSOR DEJAN KOSTIC PRESENTER: KIRILL BOGDANOV KTH-DB Geo Distributed Key Value Store DESIGN AND DEVELOP GEO DISTRIBUTED KEY VALUE STORE. DEPLOY AND TEST IT ON A

More information

Distributed Data Stores

Distributed Data Stores Distributed Data Stores 1 Distributed Persistent State MapReduce addresses distributed processing of aggregation-based queries Persistent state across a large number of machines? Distributed DBMS High

More information

WINDOWS AZURE DATA MANAGEMENT

WINDOWS AZURE DATA MANAGEMENT David Chappell October 2012 WINDOWS AZURE DATA MANAGEMENT CHOOSING THE RIGHT TECHNOLOGY Sponsored by Microsoft Corporation Copyright 2012 Chappell & Associates Contents Windows Azure Data Management: A

More information

Consistency Management in Cloud Storage Systems

Consistency Management in Cloud Storage Systems Consistency Management in Cloud Storage Systems Houssem-Eddine Chihoub, Shadi Ibrahim, Gabriel Antoniu, María S. Pérez INRIA Rennes - Bretagne Atlantique Rennes, 35000, France {houssem-eddine.chihoub,

More information

Cloud Computing Trends

Cloud Computing Trends UT DALLAS Erik Jonsson School of Engineering & Computer Science Cloud Computing Trends What is cloud computing? Cloud computing refers to the apps and services delivered over the internet. Software delivered

More information

Design and Evolution of the Apache Hadoop File System(HDFS)

Design and Evolution of the Apache Hadoop File System(HDFS) Design and Evolution of the Apache Hadoop File System(HDFS) Dhruba Borthakur Engineer@Facebook Committer@Apache HDFS SDC, Sept 19 2011 Outline Introduction Yet another file-system, why? Goals of Hadoop

More information

SCALABILITY IN THE CLOUD

SCALABILITY IN THE CLOUD SCALABILITY IN THE CLOUD A TWILIO PERSPECTIVE twilio.com OUR SOFTWARE Twilio has built a 100 percent software-based infrastructure using many of the same distributed systems engineering and design principles

More information

BIG DATA COME NUOVO MOTORE DI SVILUPPO: VERSO L ECONOMIA DEI DATI

BIG DATA COME NUOVO MOTORE DI SVILUPPO: VERSO L ECONOMIA DEI DATI BIG DATA COME NUOVO MOTORE DI SVILUPPO: VERSO L ECONOMIA DEI DATI Roberto Masiero Co-Founder& Managing Director, The Innovation Group Roma, Big Data Analytics Conference 2013 The Industrial Economy Creation

More information

Existential Consistency: Measuring and Understanding Consistency at Facebook

Existential Consistency: Measuring and Understanding Consistency at Facebook Existential Consistency: Measuring and Understanding Consistency at Facebook Haonan Lu, Kaushik Veeraraghavan, Philippe Ajoux, Jim Hunt, Yee Jiun Song, Wendy Tobagus, Sanjeev Kumar, Wyatt Lloyd University

More information

The relative simplicity of common requests in Web. CAP and Cloud Data Management COVER FEATURE BACKGROUND: ACID AND CONSISTENCY

The relative simplicity of common requests in Web. CAP and Cloud Data Management COVER FEATURE BACKGROUND: ACID AND CONSISTENCY CAP and Cloud Data Management Raghu Ramakrishnan, Yahoo Novel systems that scale out on demand, relying on replicated data and massively distributed architectures with clusters of thousands of machines,

More information

Cloud Computing. Lecture 24 Cloud Platform Comparison 2014-2015

Cloud Computing. Lecture 24 Cloud Platform Comparison 2014-2015 Cloud Computing Lecture 24 Cloud Platform Comparison 2014-2015 1 Up until now Introduction, Definition of Cloud Computing Pre-Cloud Large Scale Computing: Grid Computing Content Distribution Networks Cycle-Sharing

More information

Rocket Engineering Corner Mainframe

Rocket Engineering Corner Mainframe Rocket Engineering Corner Mainframe A Conversation with Engineers at Rocket Software Topic: Mainframe storage management and cloud Rocket Software Engineering Participants: Bryan Smith -- Vice President,

More information

Platforms in the Cloud

Platforms in the Cloud Platforms in the Cloud Where Will Your Next Application Run? Jazoon, Zurich June 2011 Copyright 2011 Chappell & Associates An Organization without Cloud Computing Users A A A VM VM VM A A A Application

More information

Big Data Technology CS 236620, Technion, Spring 2014

Big Data Technology CS 236620, Technion, Spring 2014 Big Data Technology CS 236620, Technion, Spring 2014 System Design Principles Edward Bortnikov & Ronny Lempel Yahoo Labs, Haifa Data = Systems We need to Move, Store and Process data Big Data = Big Systems

More information

Big Data Management and NoSQL Databases

Big Data Management and NoSQL Databases NDBI040 Big Data Management and NoSQL Databases Lecture 4. Basic Principles Doc. RNDr. Irena Holubova, Ph.D. holubova@ksi.mff.cuni.cz http://www.ksi.mff.cuni.cz/~holubova/ndbi040/ NoSQL Overview Main objective:

More information

Automated Mobile Testing Requires Both Real Devices and Emulators

Automated Mobile Testing Requires Both Real Devices and Emulators WHITE PAPER Automated Mobile Testing Requires Both Real Devices and Emulators September 2015 Today, businesses compete in an increasingly mobile-centric marketplace. Mobile QA can no longer take a backseat

More information

Cloud DBMS: An Overview. Shan-Hung Wu, NetDB CS, NTHU Spring, 2015

Cloud 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 information

Cloud Service Model. Selecting a cloud service model. Different cloud service models within the enterprise

Cloud Service Model. Selecting a cloud service model. Different cloud service models within the enterprise Cloud Service Model Selecting a cloud service model Different cloud service models within the enterprise Single cloud provider AWS for IaaS Azure for PaaS Force fit all solutions into the cloud service

More information

Technical Writing - Definition of Cloud A Rational Perspective

Technical Writing - Definition of Cloud A Rational Perspective INTRODUCTIONS Storm Technology Who we are and what we do David Chappell IT strategist and international advisor The Cloud A Rational Perspective The cloud platforms An objective overview of the Windows

More information

Selling Windows Azure Projects IT INFRASTRUCTURE

Selling Windows Azure Projects IT INFRASTRUCTURE Selling Windows Azure Projects IT INFRASTRUCTURE A GUIDE FOR MICROSOFT SI PARTNERS Sponsored by Microsoft Corporation 1/ Why Should You Sell Infrastructure Projects that Use Windows Azure? 2/ Why Sell

More information

Should Business Move To The Cloud

Should Business Move To The Cloud MIS 220 Class Jiangpeng Li, Roy Prof. Wang Case Study 2 Should Business Move To The Cloud 1. What business benefits do cloud computing services provide? What problems do they solve? Cloud computing is

More information

How the Emergence of OpenFlow and SDN will Change the Networking Landscape

How the Emergence of OpenFlow and SDN will Change the Networking Landscape How the Emergence of OpenFlow and SDN will Change the Networking Landscape Software-Defined Networking (SDN) powered by the OpenFlow protocol has the potential to be an important and necessary game-changer

More information

How To Make Your Database More Efficient By Virtualizing It On A Server

How To Make Your Database More Efficient By Virtualizing It On A Server Virtualizing Pervasive Database Servers A White Paper From For more information, see our web site at Virtualizing Pervasive Database Servers Last Updated: 03/06/2014 As servers continue to advance in power,

More information

Conventionally, software testing has aimed at verifying functionality but the testing paradigm has changed for software services.

Conventionally, software testing has aimed at verifying functionality but the testing paradigm has changed for software services. 1 Conventionally, software testing has aimed at verifying functionality but the testing paradigm has changed for software services. Developing a full-featured and functioning software service is necessary;

More information

Towards secure and consistency dependable in large cloud systems

Towards secure and consistency dependable in large cloud systems Volume :2, Issue :4, 145-150 April 2015 www.allsubjectjournal.com e-issn: 2349-4182 p-issn: 2349-5979 Impact Factor: 3.762 Sahana M S M.Tech scholar, Department of computer science, Alvas institute of

More information

CLOUD PERFORMANCE TESTING - KEY CONSIDERATIONS (COMPLETE ANALYSIS USING RETAIL APPLICATION TEST DATA)

CLOUD PERFORMANCE TESTING - KEY CONSIDERATIONS (COMPLETE ANALYSIS USING RETAIL APPLICATION TEST DATA) CLOUD PERFORMANCE TESTING - KEY CONSIDERATIONS (COMPLETE ANALYSIS USING RETAIL APPLICATION TEST DATA) Abhijeet Padwal Performance engineering group Persistent Systems, Pune email: abhijeet_padwal@persistent.co.in

More information

Composite Data Virtualization Composite Data Virtualization And NOSQL Data Stores

Composite Data Virtualization Composite Data Virtualization And NOSQL Data Stores Composite Data Virtualization Composite Data Virtualization And NOSQL Data Stores Composite Software October 2010 TABLE OF CONTENTS INTRODUCTION... 3 BUSINESS AND IT DRIVERS... 4 NOSQL DATA STORES LANDSCAPE...

More information

Application Performance Analysis and Troubleshooting

Application Performance Analysis and Troubleshooting Exam : 1T6-520 Title : Application Performance Analysis and Troubleshooting Version : DEMO 1 / 6 1. When optimizing application efficiency, an improvement in efficiency from the current 90% to an efficiency

More information

The most comprehensive review and comparison of cloud storage services

The most comprehensive review and comparison of cloud storage services DriveHQ Other Cloud Services The most comprehensive review and comparison of cloud storage services 2003-2013, Drive Headquarters, Inc. Table of Contents 1. Introduction... 4 1.1 Why do we create these

More information

Web Email DNS Peer-to-peer systems (file sharing, CDNs, cycle sharing)

Web Email DNS Peer-to-peer systems (file sharing, CDNs, cycle sharing) 1 1 Distributed Systems What are distributed systems? How would you characterize them? Components of the system are located at networked computers Cooperate to provide some service No shared memory Communication

More information

Brewer s Conjecture and the Feasibility of Consistent, Available, Partition-Tolerant Web Services

Brewer s Conjecture and the Feasibility of Consistent, Available, Partition-Tolerant Web Services Brewer s Conjecture and the Feasibility of Consistent, Available, Partition-Tolerant Web Services Seth Gilbert Nancy Lynch Abstract When designing distributed web services, there are three properties that

More information

ecommerce Web Application at Scale

ecommerce Web Application at Scale ecommerce Web Application at Scale Atop concern for organizations with ecommerce Web sites, application developers and IT infrastructure managers is ensuring a successful end-user experience. It is crucial

More information

Apache Hadoop. Alexandru Costan

Apache Hadoop. Alexandru Costan 1 Apache Hadoop Alexandru Costan Big Data Landscape No one-size-fits-all solution: SQL, NoSQL, MapReduce, No standard, except Hadoop 2 Outline What is Hadoop? Who uses it? Architecture HDFS MapReduce Open

More information

Distribution transparency. Degree of transparency. Openness of distributed systems

Distribution transparency. Degree of transparency. Openness of distributed systems Distributed Systems Principles and Paradigms Maarten van Steen VU Amsterdam, Dept. Computer Science steen@cs.vu.nl Chapter 01: Version: August 27, 2012 1 / 28 Distributed System: Definition A distributed

More information

Introduction to NoSQL Databases. Tore Risch Information Technology Uppsala University 2013-03-05

Introduction to NoSQL Databases. Tore Risch Information Technology Uppsala University 2013-03-05 Introduction to NoSQL Databases Tore Risch Information Technology Uppsala University 2013-03-05 UDBL Tore Risch Uppsala University, Sweden Evolution of DBMS technology Distributed databases SQL 1960 1970

More information

Cloud Computing. Key Considerations for Adoption. Abstract. Ramkumar Dargha

Cloud Computing. Key Considerations for Adoption. Abstract. Ramkumar Dargha Cloud Computing Key Considerations for Adoption Ramkumar Dargha Abstract Cloud Computing technology and services have been witnessing quite a lot of attention for the past couple of years now. We believe

More information

Data Consistency Properties and the Trade offs in Commercial Cloud Storages: the Consumers Perspective

Data Consistency Properties and the Trade offs in Commercial Cloud Storages: the Consumers Perspective Data Consistency Properties and the Trade offs in Commercial Cloud Storages: the Consumers Perspective Hiroshi Wada, Alan Fekete, Liang Zhao, Kevin Lee and Anna Liu National ICT Australia NICTA School

More information

Distributed File System. MCSN N. Tonellotto Complements of Distributed Enabling Platforms

Distributed File System. MCSN N. Tonellotto Complements of Distributed Enabling Platforms Distributed File System 1 How do we get data to the workers? NAS Compute Nodes SAN 2 Distributed File System Don t move data to workers move workers to the data! Store data on the local disks of nodes

More information

SPANStore: Cost-Effective Geo-Replicated Storage Spanning Multiple Cloud Services

SPANStore: Cost-Effective Geo-Replicated Storage Spanning Multiple Cloud Services SPANStore: Cost-Effective Geo-Replicated Storage Spanning Multiple Cloud Services Zhe Wu, Michael Butkiewicz, Dorian Perkins, Ethan Katz-Bassett, and Harsha V. Madhyastha UC Riverside and USC Abstract

More information

ECE6130 Grid and Cloud Computing

ECE6130 Grid and Cloud Computing ECE6130 Grid and Cloud Computing Howie Huang Department of Electrical and Computer Engineering School of Engineering and Applied Science Cloud Computing Hardware Software Outline Research Challenges 2

More information

Using CORBA for Automated Stock Trading. Carlos O Ryan CTO Automated Trading Desk, LLC

Using CORBA for Automated Stock Trading. Carlos O Ryan CTO Automated Trading Desk, LLC Using CORBA for Automated Stock Trading Carlos O Ryan CTO Automated Trading Desk, LLC Background! ATD is a wholesale execution services company! An online or full service broker provides retail execution

More information

Cloud computing an insight

Cloud computing an insight Cloud computing an insight Overview IT infrastructure is changing according the fast-paced world s needs. People in the world want to stay connected with Work / Family-Friends. The data needs to be available

More information

The most comprehensive review and comparison of cloud storage services

The most comprehensive review and comparison of cloud storage services DriveHQ Carbonite The most comprehensive review and comparison of cloud storage services 2003-2013, Drive Headquarters, Inc. Table of Contents 1. Introduction... 3 2. Summary... 3 2.1 What is Carbonite's

More information

Overview. Timeline Cloud Features and Technology

Overview. Timeline Cloud Features and Technology Overview Timeline Cloud is a backup software that creates continuous real time backups of your system and data to provide your company with a scalable, reliable and secure backup solution. Storage servers

More information

References. Introduction to Database Systems CSE 444. Motivation. Basic Features. Outline: Database in the Cloud. Outline

References. Introduction to Database Systems CSE 444. Motivation. Basic Features. Outline: Database in the Cloud. Outline References Introduction to Database Systems CSE 444 Lecture 24: Databases as a Service YongChul Kwon Amazon SimpleDB Website Part of the Amazon Web services Google App Engine Datastore Website Part of

More information

Introduction to Database Systems CSE 444

Introduction to Database Systems CSE 444 Introduction to Database Systems CSE 444 Lecture 24: Databases as a Service YongChul Kwon References Amazon SimpleDB Website Part of the Amazon Web services Google App Engine Datastore Website Part of

More information

Amr El Abbadi. Computer Science, UC Santa Barbara amr@cs.ucsb.edu

Amr El Abbadi. Computer Science, UC Santa Barbara amr@cs.ucsb.edu Amr El Abbadi Computer Science, UC Santa Barbara amr@cs.ucsb.edu Collaborators: Divy Agrawal, Sudipto Das, Aaron Elmore, Hatem Mahmoud, Faisal Nawab, and Stacy Patterson. Client Site Client Site Client

More information

Internet Scale Storage Microsoft Storage Community

Internet Scale Storage Microsoft Storage Community Internet Scale Storage Microsoft Storage Community James Hamilton, 2011/11/30 VP & Distinguished Engineer, Amazon Web Services email: James@amazon.com web: mvdirona.com/jrh/work blog: perspectives.mvdirona.com

More information

How QoS differentiation enhances the OTT video streaming experience. Netflix over a QoS enabled

How QoS differentiation enhances the OTT video streaming experience. Netflix over a QoS enabled NSN White paper Netflix over a QoS enabled LTE network February 2013 How QoS differentiation enhances the OTT video streaming experience Netflix over a QoS enabled LTE network 2013 Nokia Solutions and

More information

Speak<geek> Tech Brief. RichRelevance Distributed Computing: creating a scalable, reliable infrastructure

Speak<geek> Tech Brief. RichRelevance Distributed Computing: creating a scalable, reliable infrastructure 3 Speak Tech Brief RichRelevance Distributed Computing: creating a scalable, reliable infrastructure Overview Scaling a large database is not an overnight process, so it s difficult to plan and implement

More information

Big Data Trends and HDFS Evolution

Big Data Trends and HDFS Evolution Big Data Trends and HDFS Evolution Sanjay Radia Founder & Architect Hortonworks Inc Page 1 Hello Founder, Hortonworks Part of the Hadoop team at Yahoo! since 2007 Chief Architect of Hadoop Core at Yahoo!

More information

Cloud Platforms, Challenges & Hadoop. Aditee Rele Karpagam Venkataraman Janani Ravi

Cloud Platforms, Challenges & Hadoop. Aditee Rele Karpagam Venkataraman Janani Ravi Cloud Platforms, Challenges & Hadoop Aditee Rele Karpagam Venkataraman Janani Ravi Cloud Platform Models Aditee Rele Microsoft Corporation Dec 8, 2010 IT CAPACITY Provisioning IT Capacity Under-supply

More information

Practical Online Filesystem Checking and Repair

Practical Online Filesystem Checking and Repair Practical Online Filesystem Checking and Repair Daniel Phillips Samsung Research America (Silicon Valley) d.phillips@partner.samsung.com 1 2013 SAMSUNG Electronics Co. Why we want online checking: Fsck

More information

Big Data on AWS. Services Overview. Bernie Nallamotu Principle Solutions Architect

Big Data on AWS. Services Overview. Bernie Nallamotu Principle Solutions Architect on AWS Services Overview Bernie Nallamotu Principle Solutions Architect \ So what is it? When your data sets become so large that you have to start innovating around how to collect, store, organize, analyze

More information

Cloud Computing Is In Your Future

Cloud Computing Is In Your Future Cloud Computing Is In Your Future Michael Stiefel www.reliablesoftware.com development@reliablesoftware.com http://www.reliablesoftware.com/dasblog/default.aspx Cloud Computing is Utility Computing Illusion

More information

The Age of BYOD A study of personal content streaming vs. video-on-demand for the hospitality industry

The Age of BYOD A study of personal content streaming vs. video-on-demand for the hospitality industry 1 The Age of BYOD A study of personal content streaming vs. video-on-demand for the hospitality industry Conducted by Hotel Internet Services January 2015 2015 Hotel Internet Services All Rights Reserved

More information

How to Choose Between Hadoop, NoSQL and RDBMS

How to Choose Between Hadoop, NoSQL and RDBMS How to Choose Between Hadoop, NoSQL and RDBMS Keywords: Jean-Pierre Dijcks Oracle Redwood City, CA, USA Big Data, Hadoop, NoSQL Database, Relational Database, SQL, Security, Performance Introduction A

More information

Cloud Computing 101 Dissipating the Fog 2012/Dec/xx Grid-Interop 2012

Cloud Computing 101 Dissipating the Fog 2012/Dec/xx Grid-Interop 2012 Cloud Computing 101 Dissipating the Fog 2012/Dec/xx Why the interest in Clouds? A method to avoid/defer CAPEX/OPEX and possibly accelerating implementation 2 It all started here - Timeshare Computers and

More information

Reducing Usage on a Service Plan

Reducing Usage on a Service Plan Reducing Usage on a Service Plan When purchasing a service plan you should carefully choose your data allowances based on the amount you estimate for business or personal use. However, people rarely account

More information

CREATING BUSINESS VALUE THROUGH INTEGRATION

CREATING BUSINESS VALUE THROUGH INTEGRATION CREATING BUSINESS VALUE THROUGH INTEGRATION WHAT BIZTALK SERVER AND SQL SERVER PROVIDE DAVID CHAPPELL DECEMBER 2009 SPONSORED BY MICROSOFT CORPORATION CONTENTS Why Integration Matters... 3 Application

More information

Speak<geek> Tech Brief. RichRelevance Infrastructure: a robust, retail- optimized foundation. richrelevance

Speak<geek> Tech Brief. RichRelevance Infrastructure: a robust, retail- optimized foundation. richrelevance 1 Speak Tech Brief RichRelevance Infrastructure: a robust, retail- optimized foundation richrelevance : a robust, retail-optimized foundation Internet powerhouses Google, Microsoft and Amazon may

More information

I Logs. Apache Kafka, Stream Processing, and Real-time Data Jay Kreps

I Logs. Apache Kafka, Stream Processing, and Real-time Data Jay Kreps I Logs Apache Kafka, Stream Processing, and Real-time Data Jay Kreps The Plan 1. What is Data Integration? 2. What is Apache Kafka? 3. Logs and Distributed Systems 4. Logs and Data Integration 5. Logs

More information

Achieving Data Center Networking Efficiency Breaking the Old Rules & Dispelling the Myths

Achieving Data Center Networking Efficiency Breaking the Old Rules & Dispelling the Myths WHITE PAPER Achieving Data Center Networking Efficiency Breaking the Old Rules & Dispelling the Myths The New Alternative: Scale-Out Fabrics for Scale-Out Data Centers...2 Legacy Core Switch Evolution,

More information

Web Technologies: RAMCloud and Fiz. John Ousterhout Stanford University

Web Technologies: RAMCloud and Fiz. John Ousterhout Stanford University Web Technologies: RAMCloud and Fiz John Ousterhout Stanford University The Web is Changing Everything Discovering the potential: New applications 100-1000x scale New development style New approach to deployment

More information

Mark Bennett. Search and the Virtual Machine

Mark Bennett. Search and the Virtual Machine Mark Bennett Search and the Virtual Machine Agenda Intro / Business Drivers What to do with Search + Virtual What Makes Search Fast (or Slow!) Virtual Platforms Test Results Trends / Wrap Up / Q & A Business

More information

Security in Changing IT Ecosystem: Virtualization and Cloud Computing

Security in Changing IT Ecosystem: Virtualization and Cloud Computing Security in Changing IT Ecosystem: Virtualization and Cloud Computing Dr. Dhiren Patel Indian Institute of Technology Gandhinagar, India dhiren@iitgn.ac.in Cloud Computing World is further shrinking!!!

More information

Modern Data Centers: Creating a New Value Proposition

Modern Data Centers: Creating a New Value Proposition Modern Data Centers: Creating a New Value Proposition América Latina 2008 Inter-secretarial Commission for the Development of Electronic Government Mexico City 24 May 2013 Data Center Consolidation Consolidating

More information