Distributed Systems (5DV147) What is Replication? Replication. Replication requirements. Problems that you may find. Replication.

Size: px
Start display at page:

Download "Distributed Systems (5DV147) What is Replication? Replication. Replication requirements. Problems that you may find. Replication."

Transcription

1 Distributed Systems (DV47) Replication Fall 20 Replication What is Replication? Make multiple copies of a data object and ensure that all copies are identical Two Types of access; reads, and writes (updates) Reasons, have a backup plan: Handle more work (e.g. web-servers) Keep data safe (fault tolerance) Reduce latencies (DN's and aching) Keep data available Motivation 4 Replication requirements Transparency (illusion of a single copy) lients must be unaware of replication onsistency Obtain identical results from different copies (is that true?) lient Logical object Physical Object Physical Object Not always identical: Some have received updates Motivation Problems that you may find Multiple clients access replicas oncurrent access, rather than exclusive Operations are interleaved How do we ensure correctness? Replica placement Placing servers Placing content Overhead required to keep replicas up to date Global synchronization (Atomic operations) Motivation 6

2 Types of ordering adapted to replication Some definitions orrectness FIFO if a client issues r and then r, any correct Replica Manager that handles r handles r before it ausal if the issuing of r happened-before issuing r, then any correct Replica Manager that handles r handles r before it Total if a correct Replica Manager handles r before r, then any correct that handles r handles r before it Sequential consistency property Order of operations is consistent with the program order in which each individual process executed them Linearizability property Order of operations is consistent with the real times at which the operations occurred during execution Basic correctness property An interleaved sequence of operations must meet the specification of a single correct copy of the object(s), i.e., clients can not make a difference between replicated systems and single copy ones. 7 8 Example of interleaved operations for 2 clients: orrectness : A, B, 2: d, e, f Real Order during execution: A, B, d,, e, f An interleaving with sequential consistency: A, B, d, e, f, Interleaving with linearizability: A, B, d,, e, f 9 0 Passive (primary-backup) replication Passive replication One primary replica manager, many backup replicas If primary fails, backups can take its place (election!) Implements linearizability if: Primary A failing primary is replaced by a unique backup s agree on which operations were performed before primary crashed View-synchronous group communication! Figure adapted from Instructor s Guide for oulouris, Dollimore, Kindberg and Blair, Distributed Systems: oncepts and Design Edn. Pearson Education 202 based on Figure 8. 2

3 Steps of passive replication. Request Front end issues request with unique ID 2. oordination Primary checks if request has been carried out, if so, returns cached response. Execution Perform operation, cache results 4. Agreement Primary sends updated state to backups, backups reply with Ack.. Response Primary sends result to front end, which forwards to the client Primary 2 4 What happens if the primary crashes? Before agreement After agreement Active replication 4 Active replication s play equivalent roles All replica managers carry out all operations Front ends multicast one request at a time (FIFO) Requests are totally ordered Implements sequential consistency Tolerate Byzantine failures Models of Replication Steps of active replication. Request Front end adds unique identifier to request, multicasts to s 2. oordination Totally ordered request delivery to s. Execution Each executes request 4. Agreement Not needed. Response All s respond to front end, front end interprets response and forwards response to client Replication: models Figure adapted from Instructor s Guide for oulouris, Dollimore, Kindberg and Blair, Distributed Systems: oncepts and Design Edn. Pearson Education 202 based on Figure Advantages of Active replication omparing active and passive replication Simple Same code everywhere Failure transparent 7 Both handle crash failures (but differently) Only active can handle arbitrary failures Passive may suffer from large overheads Optimizations? Send reads to backups in passive Lose linearizability property! Send reads to specific in active Lose fault tolerance Exploit commutativity of requests to avoid ordering requests in active 8

4 Semi Active Replication Intermediate soluyion between Active and Passive replication Main difference with active replication each time replicas have to make a non-deterministic decision, a process, called the leader, makes the choice and sends it to the followers 9 omparing active and passive replication Both handle crash failures (but differently) Only active can handle arbitrary failures Passive may suffer from large overheads Optimizations? Send reads to backups in passive Lose linearizability property! Send reads to specific in active Lose fault tolerance Exploit commutativity of requests to avoid ordering requests in active 20 Problem Replication vs coding 2 How do you make replicas In P2P systems loud Systems RAID and RAID 6 Option : Make replicas and copy the data :) Option 2: Use coding theory to come-up with something intelligent Network coding Erasure coding 22 What in erasure coding? Example: Replication vs Erasure coding () Suppose you have a large file that you want to replicate Divide that file into m pieces Run an erasure coding algorithm on the pieces to produce m+n pieces You will be able to reconstruct the file if you have any m pieces 2 One large file, let us say, of size TB. One large distributed system with 0000 servers If you replicate the file on machines in your network, you require TB to host the file and its replicas To have higher redundancy, you need more space If the three machines fail, file lost 24

5 Some probability For Replication Let Ɛ be the maximum probability of unavailability tolerated for an object o a is the average node availability Ɛ = P(object o is unavailable) = P( all k replicas of o are unavailable) = P (one replica is unavailable) k = ( - a) k Taking the log of both sides: k= log Ɛ / log(-a) 2 26 Example: Replication vs Erasure coding (2) Take the same file But chop it in 0 parts (m) of equal size, i.e., 00 GB Set n in the erasure coding algorithm to Run the algorithm to produce m+n pieces, all of size 00 GB Distribute on machines out of the 000 machines, i.e., total disk size used,. TB Now, if up to of the machines fail, you will still be able to reproduce the file And that is black magic (Using Galois Fields and XoRs) You're just too good to be true Points against coding Sounds like we just solved the problem of data replication But have we? an you think of why are people still using good ol' normal replication? 29 omplexity added to the system More complex systems, more bugs, harder testing, longer implementation times Download/read latency Now you need to get your data from m machines with variable latency What if you just want to read the first 00 lines in a text file? Easy with replication Not easy with coding 0

6 Required Readings Summary Optional Readings Summary Erasure oding vs. Replication: A Quantitative omparison Extra reading (some bonus questions will be based on this paper) A Tutorial on Reed Solomon oding for Fault-Tolerance in Understanding Replication in Databases and Distributed Systems (Until page, the rest is highly recommended to read, but optional) RAID-like Systems by James S. Plank Available: Note, you probably know everything you need as background to understand this. It will take some of you outside their comfort zone (Mathematics, yucky!), but it is worth your effort! I will be happy to help anyone after the 2 nd of October on this :) 2 Next Lecture onsistency

Avoid a single point of failure by replicating the server Increase scalability by sharing the load among replicas

Avoid a single point of failure by replicating the server Increase scalability by sharing the load among replicas 3. Replication Replication Goal: Avoid a single point of failure by replicating the server Increase scalability by sharing the load among replicas Problems: Partial failures of replicas and messages No

More information

Distributed Software Systems

Distributed Software Systems Consistency and Replication Distributed Software Systems Outline Consistency Models Approaches for implementing Sequential Consistency primary-backup approaches active replication using multicast communication

More information

Replication architecture

Replication architecture Replication INF 5040 autumn 2007 lecturer: Roman Vitenberg INF5040, Roman Vitenberg 1 Replication architecture Client Front end Replica Client Front end Server Replica INF5040, Roman Vitenberg 2 INF 5040

More information

Overview Motivating Examples Interleaving Model Semantics of Correctness Testing, Debugging, and Verification

Overview Motivating Examples Interleaving Model Semantics of Correctness Testing, Debugging, and Verification Introduction Overview Motivating Examples Interleaving Model Semantics of Correctness Testing, Debugging, and Verification Advanced Topics in Software Engineering 1 Concurrent Programs Characterized by

More information

Distributed Systems Lecture 1 1

Distributed Systems Lecture 1 1 Distributed Systems Lecture 1 1 Distributed Systems Lecturer: Therese Berg therese.berg@it.uu.se. Recommended text book: Distributed Systems Concepts and Design, Coulouris, Dollimore and Kindberg. Addison

More information

Distributed Storage Networks and Computer Forensics

Distributed Storage Networks and Computer Forensics Distributed Storage Networks 5 Raid-6 Encoding Technical Faculty Winter Semester 2011/12 RAID Redundant Array of Independent Disks Patterson, Gibson, Katz, A Case for Redundant Array of Inexpensive Disks,

More information

Algorithms and Methods for Distributed Storage Networks 5 Raid-6 Encoding Christian Schindelhauer

Algorithms and Methods for Distributed Storage Networks 5 Raid-6 Encoding Christian Schindelhauer Algorithms and Methods for Distributed Storage Networks 5 Raid-6 Encoding Institut für Informatik Wintersemester 2007/08 RAID Redundant Array of Independent Disks Patterson, Gibson, Katz, A Case for Redundant

More information

Middleware and Distributed Systems. System Models. Dr. Martin v. Löwis. Freitag, 14. Oktober 11

Middleware and Distributed Systems. System Models. Dr. Martin v. Löwis. Freitag, 14. Oktober 11 Middleware and Distributed Systems System Models Dr. Martin v. Löwis System Models (Coulouris et al.) Architectural models of distributed systems placement of parts and relationships between them e.g.

More information

Distributed Data Management

Distributed Data Management Introduction Distributed Data Management Involves the distribution of data and work among more than one machine in the network. Distributed computing is more broad than canonical client/server, in that

More information

Software Replication

Software Replication Software Replication Motivation Assure the availability of an object (service) despite failures Assuming p the failure probability of an object O. O s availability is 1-p. Replicating an object O on n

More information

COSC 6374 Parallel Computation. Parallel I/O (I) I/O basics. Concept of a clusters

COSC 6374 Parallel Computation. Parallel I/O (I) I/O basics. Concept of a clusters COSC 6374 Parallel Computation Parallel I/O (I) I/O basics Spring 2008 Concept of a clusters Processor 1 local disks Compute node message passing network administrative network Memory Processor 2 Network

More information

Google File System. Web and scalability

Google File System. Web and scalability Google File System Web and scalability The web: - How big is the Web right now? No one knows. - Number of pages that are crawled: o 100,000 pages in 1994 o 8 million pages in 2005 - Crawlable pages might

More information

RAID Storage, Network File Systems, and DropBox

RAID Storage, Network File Systems, and DropBox RAID Storage, Network File Systems, and DropBox George Porter CSE 124 February 24, 2015 * Thanks to Dave Patterson and Hong Jiang Announcements Project 2 due by end of today Office hour today 2-3pm in

More information

Massive Data Storage

Massive Data Storage Massive Data Storage Storage on the "Cloud" and the Google File System paper by: Sanjay Ghemawat, Howard Gobioff, and Shun-Tak Leung presentation by: Joshua Michalczak COP 4810 - Topics in Computer Science

More information

Input / Ouput devices. I/O Chapter 8. Goals & Constraints. Measures of Performance. Anatomy of a Disk Drive. Introduction - 8.1

Input / Ouput devices. I/O Chapter 8. Goals & Constraints. Measures of Performance. Anatomy of a Disk Drive. Introduction - 8.1 Introduction - 8.1 I/O Chapter 8 Disk Storage and Dependability 8.2 Buses and other connectors 8.4 I/O performance measures 8.6 Input / Ouput devices keyboard, mouse, printer, game controllers, hard drive,

More information

Lecture 36: Chapter 6

Lecture 36: Chapter 6 Lecture 36: Chapter 6 Today s topic RAID 1 RAID Redundant Array of Inexpensive (Independent) Disks Use multiple smaller disks (c.f. one large disk) Parallelism improves performance Plus extra disk(s) for

More information

COSC 6374 Parallel Computation. Parallel I/O (I) I/O basics. Concept of a clusters

COSC 6374 Parallel Computation. Parallel I/O (I) I/O basics. Concept of a clusters COSC 6374 Parallel I/O (I) I/O basics Fall 2012 Concept of a clusters Processor 1 local disks Compute node message passing network administrative network Memory Processor 2 Network card 1 Network card

More information

BENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB

BENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB BENCHMARKING CLOUD DATABASES CASE STUDY on HBASE, HADOOP and CASSANDRA USING YCSB Planet Size Data!? Gartner s 10 key IT trends for 2012 unstructured data will grow some 80% over the course of the next

More information

Finding a needle in Haystack: Facebook s photo storage IBM Haifa Research Storage Systems

Finding a needle in Haystack: Facebook s photo storage IBM Haifa Research Storage Systems Finding a needle in Haystack: Facebook s photo storage IBM Haifa Research Storage Systems 1 Some Numbers (2010) Over 260 Billion images (20 PB) 65 Billion X 4 different sizes for each image. 1 Billion

More information

Review. Lecture 21: Reliable, High Performance Storage. Overview. Basic Disk & File System properties CSC 468 / CSC 2204 11/23/2006

Review. Lecture 21: Reliable, High Performance Storage. Overview. Basic Disk & File System properties CSC 468 / CSC 2204 11/23/2006 S 468 / S 2204 Review Lecture 2: Reliable, High Performance Storage S 469HF Fall 2006 ngela emke rown We ve looked at fault tolerance via server replication ontinue operating with up to f failures Recovery

More information

The Pros and Cons of Erasure Coding & Replication vs. RAID in Next-Gen Storage Platforms. Abhijith Shenoy Engineer, Hedvig Inc.

The Pros and Cons of Erasure Coding & Replication vs. RAID in Next-Gen Storage Platforms. Abhijith Shenoy Engineer, Hedvig Inc. The Pros and Cons of Erasure Coding & Replication vs. RAID in Next-Gen Storage Platforms Abhijith Shenoy Engineer, Hedvig Inc. @hedviginc The need for new architectures Business innovation Time-to-market

More information

PIONEER RESEARCH & DEVELOPMENT GROUP

PIONEER RESEARCH & DEVELOPMENT GROUP SURVEY ON RAID Aishwarya Airen 1, Aarsh Pandit 2, Anshul Sogani 3 1,2,3 A.I.T.R, Indore. Abstract RAID stands for Redundant Array of Independent Disk that is a concept which provides an efficient way for

More information

File System Reliability (part 2)

File System Reliability (part 2) File System Reliability (part 2) Main Points Approaches to reliability Careful sequencing of file system opera@ons Copy- on- write (WAFL, ZFS) Journalling (NTFS, linux ext4) Log structure (flash storage)

More information

Guide to SATA Hard Disks Installation and RAID Configuration

Guide to SATA Hard Disks Installation and RAID Configuration Guide to SATA Hard Disks Installation and RAID Configuration 1. Guide to SATA Hard Disks Installation...2 1.1 Serial ATA (SATA) Hard Disks Installation...2 2. Guide to RAID Configurations...3 2.1 Introduction

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

COMP 7970 Storage Systems

COMP 7970 Storage Systems COMP 797 Storage Systems Dr. Xiao Qin Department of Computer Science and Software Engineering Auburn University http://www.eng.auburn.edu/~xqin xqin@auburn.edu COMP 797, Auburn University Slide 3b- Problems

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

StorTrends RAID Considerations

StorTrends RAID Considerations StorTrends RAID Considerations MAN-RAID 04/29/2011 Copyright 1985-2011 American Megatrends, Inc. All rights reserved. American Megatrends, Inc. 5555 Oakbrook Parkway, Building 200 Norcross, GA 30093 Revision

More information

PARALLELS CLOUD STORAGE

PARALLELS CLOUD STORAGE PARALLELS CLOUD STORAGE Performance Benchmark Results 1 Table of Contents Executive Summary... Error! Bookmark not defined. Architecture Overview... 3 Key Features... 5 No Special Hardware Requirements...

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

Software-Based Replication for Fault Tolerance

Software-Based Replication for Fault Tolerance Theme Feature Software-Based Replication for Fault Tolerance Replication handled by software on off-the-shelf hardware costs less than using specialized hardware. Although an intuitive concept, replication

More information

RAID Overview: Identifying What RAID Levels Best Meet Customer Needs. Diamond Series RAID Storage Array

RAID Overview: Identifying What RAID Levels Best Meet Customer Needs. Diamond Series RAID Storage Array ATTO Technology, Inc. Corporate Headquarters 155 Crosspoint Parkway Amherst, NY 14068 Phone: 716-691-1999 Fax: 716-691-9353 www.attotech.com sales@attotech.com RAID Overview: Identifying What RAID Levels

More information

Distributed systems Lecture 6: Elec3ons, consensus, and distributed transac3ons. Dr Robert N. M. Watson

Distributed systems Lecture 6: Elec3ons, consensus, and distributed transac3ons. Dr Robert N. M. Watson Distributed systems Lecture 6: Elec3ons, consensus, and distributed transac3ons Dr Robert N. M. Watson 1 Last 3me Saw how we can build ordered mul3cast Messages between processes in a group Need to dis3nguish

More information

TECHNIQUES FOR DATA REPLICATION ON DISTRIBUTED DATABASES

TECHNIQUES FOR DATA REPLICATION ON DISTRIBUTED DATABASES Constantin Brâncuşi University of Târgu Jiu ENGINEERING FACULTY SCIENTIFIC CONFERENCE 13 th edition with international participation November 07-08, 2008 Târgu Jiu TECHNIQUES FOR DATA REPLICATION ON DISTRIBUTED

More information

Agenda. Enterprise Application Performance Factors. Current form of Enterprise Applications. Factors to Application Performance.

Agenda. Enterprise Application Performance Factors. Current form of Enterprise Applications. Factors to Application Performance. Agenda Enterprise Performance Factors Overall Enterprise Performance Factors Best Practice for generic Enterprise Best Practice for 3-tiers Enterprise Hardware Load Balancer Basic Unix Tuning Performance

More information

Guide to SATA Hard Disks Installation and RAID Configuration

Guide to SATA Hard Disks Installation and RAID Configuration Guide to SATA Hard Disks Installation and RAID Configuration 1. Guide to SATA Hard Disks Installation... 2 1.1 Serial ATA (SATA) Hard Disks Installation... 2 2. Guide to RAID Configurations... 3 2.1 Introduction

More information

Database Replication Techniques: a Three Parameter Classification

Database Replication Techniques: a Three Parameter Classification Database Replication Techniques: a Three Parameter Classification Matthias Wiesmann Fernando Pedone André Schiper Bettina Kemme Gustavo Alonso Département de Systèmes de Communication Swiss Federal Institute

More information

High Availability and Clustering

High Availability and Clustering High Availability and Clustering AdvOSS-HA is a software application that enables High Availability and Clustering; a critical requirement for any carrier grade solution. It implements multiple redundancy

More information

A Framework for Highly Available Services Based on Group Communication

A Framework for Highly Available Services Based on Group Communication A Framework for Highly Available Services Based on Group Communication Alan Fekete fekete@cs.usyd.edu.au http://www.cs.usyd.edu.au/ fekete Department of Computer Science F09 University of Sydney 2006,

More information

CHAPTER 4 RAID. Section Goals. Upon completion of this section you should be able to:

CHAPTER 4 RAID. Section Goals. Upon completion of this section you should be able to: HPTER 4 RI s it was originally proposed, the acronym RI stood for Redundant rray of Inexpensive isks. However, it has since come to be known as Redundant rray of Independent isks. RI was originally described

More information

SAN Conceptual and Design Basics

SAN Conceptual and Design Basics TECHNICAL NOTE VMware Infrastructure 3 SAN Conceptual and Design Basics VMware ESX Server can be used in conjunction with a SAN (storage area network), a specialized high speed network that connects computer

More information

Dr Markus Hagenbuchner markus@uow.edu.au CSCI319. Distributed Systems

Dr Markus Hagenbuchner markus@uow.edu.au CSCI319. Distributed Systems Dr Markus Hagenbuchner markus@uow.edu.au CSCI319 Distributed Systems CSCI319 Chapter 8 Page: 1 of 61 Fault Tolerance Study objectives: Understand the role of fault tolerance in Distributed Systems. Know

More information

CS 61C: Great Ideas in Computer Architecture. Dependability: Parity, RAID, ECC

CS 61C: Great Ideas in Computer Architecture. Dependability: Parity, RAID, ECC CS 61C: Great Ideas in Computer Architecture Dependability: Parity, RAID, ECC Instructor: Justin Hsia 8/08/2013 Summer 2013 Lecture #27 1 Review of Last Lecture MapReduce Data Level Parallelism Framework

More information

Outline. Database Management and Tuning. Overview. Hardware Tuning. Johann Gamper. Unit 12

Outline. Database Management and Tuning. Overview. Hardware Tuning. Johann Gamper. Unit 12 Outline Database Management and Tuning Hardware Tuning Johann Gamper 1 Free University of Bozen-Bolzano Faculty of Computer Science IDSE Unit 12 2 3 Conclusion Acknowledgements: The slides are provided

More information

Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at

Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at Lecture 3: Scaling by Load Balancing 1. Comments on reviews i. 2. Topic 1: Scalability a. QUESTION: What are problems? i. These papers look at distributing load b. QUESTION: What is the context? i. How

More information

CSE-E5430 Scalable Cloud Computing Lecture 2

CSE-E5430 Scalable Cloud Computing Lecture 2 CSE-E5430 Scalable Cloud Computing Lecture 2 Keijo Heljanko Department of Computer Science School of Science Aalto University keijo.heljanko@aalto.fi 14.9-2015 1/36 Google MapReduce A scalable batch processing

More information

Peer-to-peer Cooperative Backup System

Peer-to-peer Cooperative Backup System Peer-to-peer Cooperative Backup System Sameh Elnikety Mark Lillibridge Mike Burrows Rice University Compaq SRC Microsoft Research Abstract This paper presents the design and implementation of a novel backup

More information

Lecture 18: Reliable Storage

Lecture 18: Reliable Storage CS 422/522 Design & Implementation of Operating Systems Lecture 18: Reliable Storage Zhong Shao Dept. of Computer Science Yale University Acknowledgement: some slides are taken from previous versions of

More information

CSE-E5430 Scalable Cloud Computing P Lecture 5

CSE-E5430 Scalable Cloud Computing P Lecture 5 CSE-E5430 Scalable Cloud Computing P Lecture 5 Keijo Heljanko Department of Computer Science School of Science Aalto University keijo.heljanko@aalto.fi 12.10-2015 1/34 Fault Tolerance Strategies for Storage

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

Cloud Storage. Parallels. Performance Benchmark Results. White Paper. www.parallels.com

Cloud Storage. Parallels. Performance Benchmark Results. White Paper. www.parallels.com Parallels Cloud Storage White Paper Performance Benchmark Results www.parallels.com Table of Contents Executive Summary... 3 Architecture Overview... 3 Key Features... 4 No Special Hardware Requirements...

More information

In Memory Accelerator for MongoDB

In Memory Accelerator for MongoDB In Memory Accelerator for MongoDB Yakov Zhdanov, Director R&D GridGain Systems GridGain: In Memory Computing Leader 5 years in production 100s of customers & users Starts every 10 secs worldwide Over 15,000,000

More information

Hadoop Scalability at Facebook. Dmytro Molkov (dms@fb.com) YaC, Moscow, September 19, 2011

Hadoop Scalability at Facebook. Dmytro Molkov (dms@fb.com) YaC, Moscow, September 19, 2011 Hadoop Scalability at Facebook Dmytro Molkov (dms@fb.com) YaC, Moscow, September 19, 2011 How Facebook uses Hadoop Hadoop Scalability Hadoop High Availability HDFS Raid How Facebook uses Hadoop Usages

More information

RAID. RAID 0 No redundancy ( AID?) Just stripe data over multiple disks But it does improve performance. Chapter 6 Storage and Other I/O Topics 29

RAID. RAID 0 No redundancy ( AID?) Just stripe data over multiple disks But it does improve performance. Chapter 6 Storage and Other I/O Topics 29 RAID Redundant Array of Inexpensive (Independent) Disks Use multiple smaller disks (c.f. one large disk) Parallelism improves performance Plus extra disk(s) for redundant data storage Provides fault tolerant

More information

How To Write A Hexadecimal Program

How To Write A Hexadecimal Program The mathematics of RAID-6 H. Peter Anvin First version 20 January 2004 Last updated 20 December 2011 RAID-6 supports losing any two drives. syndromes, generally referred P and Q. The way

More information

CHAPTER 2 MODELLING FOR DISTRIBUTED NETWORK SYSTEMS: THE CLIENT- SERVER MODEL

CHAPTER 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 information

Hadoop and Map-Reduce. Swati Gore

Hadoop and Map-Reduce. Swati Gore Hadoop and Map-Reduce Swati Gore Contents Why Hadoop? Hadoop Overview Hadoop Architecture Working Description Fault Tolerance Limitations Why Map-Reduce not MPI Distributed sort Why Hadoop? Existing Data

More information

Facebook: Cassandra. Smruti R. Sarangi. Department of Computer Science Indian Institute of Technology New Delhi, India. Overview Design Evaluation

Facebook: Cassandra. Smruti R. Sarangi. Department of Computer Science Indian Institute of Technology New Delhi, India. Overview Design Evaluation Facebook: Cassandra Smruti R. Sarangi Department of Computer Science Indian Institute of Technology New Delhi, India Smruti R. Sarangi Leader Election 1/24 Outline 1 2 3 Smruti R. Sarangi Leader Election

More information

RADOS: A Scalable, Reliable Storage Service for Petabyte- scale Storage Clusters

RADOS: A Scalable, Reliable Storage Service for Petabyte- scale Storage Clusters RADOS: A Scalable, Reliable Storage Service for Petabyte- scale Storage Clusters Sage Weil, Andrew Leung, Scott Brandt, Carlos Maltzahn {sage,aleung,scott,carlosm}@cs.ucsc.edu University of California,

More information

Christian Schindelhauer Technical Faculty Computer-Networks and Telematics University of Freiburg

Christian Schindelhauer Technical Faculty Computer-Networks and Telematics University of Freiburg DAAD Summerschool Curitiba 2011 Aspects of Large Scale High Speed Computing Building Blocks of a Cloud Storage Networks 2: Virtualization of Storage: RAID, SAN and Virtualization Christian Schindelhauer

More information

Nutanix Tech Note. Failure Analysis. 2013 All Rights Reserved, Nutanix Corporation

Nutanix Tech Note. Failure Analysis. 2013 All Rights Reserved, Nutanix Corporation Nutanix Tech Note Failure Analysis A Failure Analysis of Storage System Architectures Nutanix Scale-out v. Legacy Designs Types of data to be protected Any examination of storage system failure scenarios

More information

Disk Array Data Organizations and RAID

Disk Array Data Organizations and RAID Guest Lecture for 15-440 Disk Array Data Organizations and RAID October 2010, Greg Ganger 1 Plan for today Why have multiple disks? Storage capacity, performance capacity, reliability Load distribution

More information

DSS. The Data Storage Services (DSS) Strategy at CERN. Jakub T. Moscicki. (Input from J. Iven, M. Lamanna A. Pace, A. Peters and A.

DSS. The Data Storage Services (DSS) Strategy at CERN. Jakub T. Moscicki. (Input from J. Iven, M. Lamanna A. Pace, A. Peters and A. The Data Storage Services () Strategy at CERN Jakub T. Moscicki (Input from J. Iven, M. Lamanna A. Pace, A. Peters and A. Wiebalck) HEPiX Spring 2012 Workshop Prague, April 2012 The big picture Situation

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

Overview. File Management. File System Properties. File Management

Overview. File Management. File System Properties. File Management File Management Lecture 15b 1 2 File Management File management system consists of system utility programs that run as privileged applications Input to applications is by means of a file Output is saved

More information

RAID HARDWARE. On board SATA RAID controller. RAID drive caddy (hot swappable) SATA RAID controller card. Anne Watson 1

RAID HARDWARE. On board SATA RAID controller. RAID drive caddy (hot swappable) SATA RAID controller card. Anne Watson 1 RAID HARDWARE On board SATA RAID controller SATA RAID controller card RAID drive caddy (hot swappable) Anne Watson 1 RAID The word redundant means an unnecessary repetition. The word array means a lineup.

More information

Snapshots in Hadoop Distributed File System

Snapshots in Hadoop Distributed File System Snapshots in Hadoop Distributed File System Sameer Agarwal UC Berkeley Dhruba Borthakur Facebook Inc. Ion Stoica UC Berkeley Abstract The ability to take snapshots is an essential functionality of any

More information

Data Corruption In Storage Stack - Review

Data Corruption In Storage Stack - Review Theoretical Aspects of Storage Systems Autumn 2009 Chapter 2: Double Disk Failures André Brinkmann Data Corruption in the Storage Stack What are Latent Sector Errors What is Silent Data Corruption Checksum

More information

How To Create A P2P Network

How To Create A P2P Network Peer-to-peer systems INF 5040 autumn 2007 lecturer: Roman Vitenberg INF5040, Frank Eliassen & Roman Vitenberg 1 Motivation for peer-to-peer Inherent restrictions of the standard client/server model Centralised

More information

Name: 1. CS372H: Spring 2009 Final Exam

Name: 1. CS372H: Spring 2009 Final Exam Name: 1 Instructions CS372H: Spring 2009 Final Exam This exam is closed book and notes with one exception: you may bring and refer to a 1-sided 8.5x11- inch piece of paper printed with a 10-point or larger

More information

Fault Tolerance in the Internet: Servers and Routers

Fault Tolerance in the Internet: Servers and Routers Fault Tolerance in the Internet: Servers and Routers Sana Naveed Khawaja, Tariq Mahmood Research Associates Department of Computer Science Lahore University of Management Sciences Motivation Client Link

More information

How To Understand The Concept Of A Distributed System

How To Understand The Concept Of A Distributed System Distributed Operating Systems Introduction Ewa Niewiadomska-Szynkiewicz and Adam Kozakiewicz ens@ia.pw.edu.pl, akozakie@ia.pw.edu.pl Institute of Control and Computation Engineering Warsaw University of

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

e Shandor Simon Director, Networking Services Latin School of Chicago

e Shandor Simon Director, Networking Services Latin School of Chicago Lessons Learned about Consolidation, Virtualization at and Disaster Recovery e Shandor Simon Director, Networking Services Latin School of Chicago Agenda The Latin School of Chicago Why redundancy and

More information

Fault Tolerance in Virtualized Data Centers:

Fault Tolerance in Virtualized Data Centers: storage without boundaries Whitepaper Fault Tolerance in Virtualized Data Centers: Leveraging the Resilience of VMware FT and StorTrends itx High Availability CERTIFIED Table of Contents Introduction 3

More information

Magnus: Peer to Peer Backup System

Magnus: Peer to Peer Backup System Magnus: Peer to Peer Backup System Naveen Gattu, Richard Huang, John Lynn, Huaxia Xia Department of Computer Science University of California, San Diego Abstract Magnus is a peer-to-peer backup system

More information

PipeCloud : Using Causality to Overcome Speed-of-Light Delays in Cloud-Based Disaster Recovery. Razvan Ghitulete Vrije Universiteit

PipeCloud : Using Causality to Overcome Speed-of-Light Delays in Cloud-Based Disaster Recovery. Razvan Ghitulete Vrije Universiteit PipeCloud : Using Causality to Overcome Speed-of-Light Delays in Cloud-Based Disaster Recovery Razvan Ghitulete Vrije Universiteit Introduction /introduction Ubiquity: the final frontier Internet needs

More information

Price/performance Modern Memory Hierarchy

Price/performance Modern Memory Hierarchy Lecture 21: Storage Administration Take QUIZ 15 over P&H 6.1-4, 6.8-9 before 11:59pm today Project: Cache Simulator, Due April 29, 2010 NEW OFFICE HOUR TIME: Tuesday 1-2, McKinley Last Time Exam discussion

More information

A Practical Approach of Storage Strategy for Grid Computing Environment

A Practical Approach of Storage Strategy for Grid Computing Environment A Practical Approach of Storage Strategy for Grid Computing Environment Kalim Qureshi Abstract -- An efficient and reliable fault tolerance protocol plays an important role in making the system more stable.

More information

DELL RAID PRIMER DELL PERC RAID CONTROLLERS. Joe H. Trickey III. Dell Storage RAID Product Marketing. John Seward. Dell Storage RAID Engineering

DELL RAID PRIMER DELL PERC RAID CONTROLLERS. Joe H. Trickey III. Dell Storage RAID Product Marketing. John Seward. Dell Storage RAID Engineering DELL RAID PRIMER DELL PERC RAID CONTROLLERS Joe H. Trickey III Dell Storage RAID Product Marketing John Seward Dell Storage RAID Engineering http://www.dell.com/content/topics/topic.aspx/global/products/pvaul/top

More information

Fault-Tolerant Computing

Fault-Tolerant Computing Fault-Tolerant Computing Software Design Methods Nov.. 2007 Algorithm Design Methods Slide 1 About This Presentation This presentation has been prepared for the graduate course ECE 257A (Fault-Tolerant

More information

Chapter 6. 6.1 Introduction. Storage and Other I/O Topics. p. 570( 頁 585) Fig. 6.1. I/O devices can be characterized by. I/O bus connections

Chapter 6. 6.1 Introduction. Storage and Other I/O Topics. p. 570( 頁 585) Fig. 6.1. I/O devices can be characterized by. I/O bus connections Chapter 6 Storage and Other I/O Topics 6.1 Introduction I/O devices can be characterized by Behavior: input, output, storage Partner: human or machine Data rate: bytes/sec, transfers/sec I/O bus connections

More information

Exchange DAG backup and design best practices

Exchange DAG backup and design best practices Exchange DAG backup and design best practices Brien M. Posey Modern Data Protection Built for Virtualization Database Availability Groups (DAGs) are the primary fault-tolerant mechanism used for protecting

More information

technology brief RAID Levels March 1997 Introduction Characteristics of RAID Levels

technology brief RAID Levels March 1997 Introduction Characteristics of RAID Levels technology brief RAID Levels March 1997 Introduction RAID is an acronym for Redundant Array of Independent Disks (originally Redundant Array of Inexpensive Disks) coined in a 1987 University of California

More information

Network Attached Storage. Jinfeng Yang Oct/19/2015

Network Attached Storage. Jinfeng Yang Oct/19/2015 Network Attached Storage Jinfeng Yang Oct/19/2015 Outline Part A 1. What is the Network Attached Storage (NAS)? 2. What are the applications of NAS? 3. The benefits of NAS. 4. NAS s performance (Reliability

More information

Chapter 10: Scalability

Chapter 10: Scalability Chapter 10: Scalability Contents Clustering, Load balancing, DNS round robin Introduction Enterprise web portal applications must provide scalability and high availability (HA) for web services in order

More information

Big Data With Hadoop

Big Data With Hadoop With Saurabh Singh singh.903@osu.edu The Ohio State University February 11, 2016 Overview 1 2 3 Requirements Ecosystem Resilient Distributed Datasets (RDDs) Example Code vs Mapreduce 4 5 Source: [Tutorials

More information

Note: Correction to the 1997 Tutorial on Reed-Solomon Coding

Note: Correction to the 1997 Tutorial on Reed-Solomon Coding Note: Correction to the 1997 utorial on Reed-Solomon Coding James S Plank Ying Ding University of ennessee Knoxville, N 3799 [plank,ying]@csutkedu echnical Report U-CS-03-504 Department of Computer Science

More information

Global Server Load Balancing

Global Server Load Balancing White Paper Overview Many enterprises attempt to scale Web and network capacity by deploying additional servers and increased infrastructure at a single location, but centralized architectures are subject

More information

Separating Agreement from Execution for Byzantine Fault-Tolerant Services

Separating Agreement from Execution for Byzantine Fault-Tolerant Services Separating Agreement from Execution for Byzantine Fault-Tolerant Services Rethinking Replicated State Machines Jian Yin, Jean-Philippe Martin, Arun enkataramani, Lorenzo Alvisi and Mike Dahlin jianyin@us.ibm.com,

More information

BME CLEARING s Business Continuity Policy

BME CLEARING s Business Continuity Policy BME CLEARING s Business Continuity Policy Contents 1. Introduction 1 2. General goals of the Continuity Policy 1 3. Scope of BME CLEARING s Business Continuity Policy 1 4. Recovery strategies 2 5. Distribution

More information

A SURVEY OF POPULAR CLUSTERING TECHNOLOGIES

A SURVEY OF POPULAR CLUSTERING TECHNOLOGIES A SURVEY OF POPULAR CLUSTERING TECHNOLOGIES By: Edward Whalen Performance Tuning Corporation INTRODUCTION There are a number of clustering products available on the market today, and clustering has become

More information

Appendix A Core Concepts in SQL Server High Availability and Replication

Appendix A Core Concepts in SQL Server High Availability and Replication Appendix A Core Concepts in SQL Server High Availability and Replication Appendix Overview Core Concepts in High Availability Core Concepts in Replication 1 Lesson 1: Core Concepts in High Availability

More information

CS420: Operating Systems

CS420: Operating Systems NK YORK COLLEGE OF PENNSYLVANIA HG OK 2 RAID YORK COLLEGE OF PENNSYLVAN James Moscola Department of Physical Sciences York College of Pennsylvania Based on Operating System Concepts, 9th Edition by Silberschatz,

More information

Get Success in Passing Your Certification Exam at first attempt!

Get Success in Passing Your Certification Exam at first attempt! Get Success in Passing Your Certification Exam at first attempt! Exam : E20-598 Title : Backup Recovery - Avamar Specialist Exam for Storage Administrators Version : Demo 1.Which hash type represents an

More information

The Microsoft Large Mailbox Vision

The Microsoft Large Mailbox Vision WHITE PAPER The Microsoft Large Mailbox Vision Giving users large mailboxes without breaking your budget Introduction Giving your users the ability to store more e mail has many advantages. Large mailboxes

More information

Sistemas Operativos: Input/Output Disks

Sistemas Operativos: Input/Output Disks Sistemas Operativos: Input/Output Disks Pedro F. Souto (pfs@fe.up.pt) April 28, 2012 Topics Magnetic Disks RAID Solid State Disks Topics Magnetic Disks RAID Solid State Disks Magnetic Disk Construction

More information

Fault-Tolerant Framework for Load Balancing System

Fault-Tolerant Framework for Load Balancing System Fault-Tolerant Framework for Load Balancing System Y. K. LIU, L.M. CHENG, L.L.CHENG Department of Electronic Engineering City University of Hong Kong Tat Chee Avenue, Kowloon, Hong Kong SAR HONG KONG Abstract:

More information

How To Understand The Power Of A Content Delivery Network (Cdn)

How To Understand The Power Of A Content Delivery Network (Cdn) Overview 5-44 5-44 Computer Networking 5-64 Lecture 8: Delivering Content Content Delivery Networks Peter Steenkiste Fall 04 www.cs.cmu.edu/~prs/5-44-f4 Web Consistent hashing Peer-to-peer CDN Motivation

More information