DOC PREVIEW
Cloud Computing Lecture #1

This preview shows page 1-2-21-22 out of 22 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 22 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 22 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 22 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 22 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 22 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

1Cloud Computing Lecture #1What is Cloud Computing?What is Cloud Computing?(and an intro to parallel/distributed processing)Jimmy LinThe iSchoolUniversity of MarylandUniversity of MarylandWednesday, September 3, 2008This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United StatesSee http://creativecommons.org/licenses/by-nc-sa/3.0/us/ for detailsSome material adapted from slides by Christophe Bisciglia, Aaron Kimball, & Sierra Michels-Slettvet, Google Distributed Computing Seminar, 2007 (licensed under Creation Commons Attribution 3.0 License)Source: http://www.free-pictures-photos.com/2What is Cloud Computing?1. Web-scale problems2. Large data centersff f3. Different models of computing4. Highly-interactive Web applicationsTheiSchoolUniversityofMaryland1. Web-Scale Problems| Characteristics:z Definitely data-intensivez May also be processing intensive| Examples:z Crawling, indexing, searching, mining the Webz “Post-genomics” life sciences researchz Other scientific data (physics, astronomers, etc.)z Sensor networkszWeb 2.0 applicationsTheiSchoolUniversityofMarylandzWeb 2.0 applicationsz …3How much data?| Wayback Machine has 2 PB + 20 TB/month (2006) | Google processes 20 PB a day (2008)“|“all words ever spoken by human beings” ~ 5 EB| NOAA has ~1 PB climate data (2007)| CERN’s LHC will generate 15 PB a year (2008)640K ought to be TheiSchoolUniversityofMarylandgenough for anybody.Maximilien Brice, © CERN4Maximilien Brice, © CERNThere’s nothing like more data!s/inspiration/data/g;TheiSchoolUniversityofMaryland(Banko and Brill, ACL 2001)(Brants et al., EMNLP 2007)5What to do with more data?| Answering factoid questionsz Pattern matching on the Webz Works amazingly well| Learning relationsz Start with seed instancesz Search for patterns on the Webz Using patterns to find more instancesWho shot Abraham Lincoln? → X shot Abraham LincolnWolfgang Amadeus Mozart (17561791)TheiSchoolUniversityofMarylandBirthday-of(Mozart, 1756)Birthday-of(Einstein, 1879)Wolfgang Amadeus Mozart (1756 -1791)Einstein was born in 1879PERSON (DATE –PERSON was born in DATE(Brill et al., TREC 2001; Lin, ACM TOIS 2007)(Agichtein and Gravano, DL 2000; Ravichandran and Hovy, ACL 2002; … )2. Large Data Centers| Web-scale problems? Throw more machines at it!| Clear trend: centralization of computing resources in large data centersdata centersz Necessary ingredients: fiber, juice, and spacez What do Oregon, Iceland, and abandoned mines have in common?| Important Issues:z RedundancyEffi iTheiSchoolUniversityofMarylandzEfficiencyz Utilizationz Management6Source: Harper’s (Feb, 2008)Maximilien Brice, © CERN7Key Technology: VirtualizationAppAppAppHardwareOperating SystemApp App AppTraditional StackHardwareOSAppAppAppHypervisorOS OSVirtualized StackTheiSchoolUniversityofMaryland3. Different Computing Models| Utility computingzWhy buy machines when you can rent cycles?“Why do it yourself if you can pay someone to do it for you?”zWhy buy machines when you can rent cycles?z Examples: Amazon’s EC2, GoGrid, AppNexus| Platform as a Service (PaaS)z Give me nice API and take care of the implementationz Example: Google App Engine| Software as a Service (SaaS)TheiSchoolUniversityofMaryland()z Just run it for me!z Example: Gmail84. Web Applications | A mistake on top of a hack built on sand held together by duct tape?|What is the nature of software applications?|What is the nature of software applications?z From the desktop to the browserz SaaS == Web-based applicationsz Examples: Google Maps, Facebook| How do we deliver highly-interactive Web-based applications?TheiSchoolUniversityofMarylandzAJAX (asynchronous JavaScript and XML)z For better, or for worse…What is the course about?| MapReduce: the “back-end” of cloud computingz Batch-oriented processing of large datasets|Ajax: the“front-end”of cloud computing|Ajax: the frontend of cloud computingz Highly-interactive Web-based applications| Computing “in the clouds”z Amazon’s EC2/S3 as an example of utility computingTheiSchoolUniversityofMaryland9Amazon Web Services| Elastic Compute Cloud (EC2)z Rent computing resources by the hourz Basic unit of accounting = instance-hourz Additional costs for bandwidth| Simple Storage Service (S3)z Persistent storagez Charge by the GB/monthz Additional costs for bandwidth|You’ll be using EC2/S3 for course assignments!TheiSchoolUniversityofMaryland|You ll be using EC2/S3 for course assignments!This course is not for you…| If you’re not genuinely interested in the topic| If you’re not ready to do a lot of programmingf| If you’re not open to thinking about computing in new ways| If you can’t cope with uncertainly, unpredictability, poor documentation, and immature software| If you can’t put in the timeTheiSchoolUniversityofMarylandOtherwise, this will be a richly rewarding course!10Source: http://davidzinger.wordpress.com/2007/05/page/2/Cloud Computing Zen| Don’t get frustrated (take a deep breath)…z This is bleeding edge technologyz Those W$*#T@F! moments| Be patient… z This is the second first time I’ve taught this course| Be flexible…z There will be unanticipated issues along the way| Be constructive…TheiSchoolUniversityofMarylandz Tell me how I can make everyone’s experience better11Source: WikipediaSource: Wikipedia12Source: WikipediaSource: Wikipedia13Things to go over…| Course schedule| Assignments and deliverablesC/S|Amazon EC2/S3TheiSchoolUniversityofMarylandWeb-Scale Problems?| Don’t hold your breath:z Biocomputingz Nanocomputingz Quantum computingz …| It all boils down to…z Divide-and-conquerz Throwing more hardware at the problemTheiSchoolUniversityofMarylandSimple to understand… a lifetime to master…14Divide and Conquer“Work”Partitionw1w2w3r1r2r3“worker” “worker” “worker”TheiSchoolUniversityofMaryland“Result”CombineDifferent Workers| Different threads in the same core| Different cores in the same CPUff C| Different CPUs in a multi-processor system| Different machines in a distributed systemTheiSchoolUniversityofMaryland15Choices, Choices, Choices| Commodity vs. “exotic” hardware| Number of machines vs. processor vs. coresf| Bandwidth of memory vs. disk vs. network| Different programming


Cloud Computing Lecture #1

Download Cloud Computing Lecture #1
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Cloud Computing Lecture #1 and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Cloud Computing Lecture #1 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?