The Google Cluster Google. The Google Floor Plan.

Slides:



Advertisements
Similar presentations
Clustering Technology For Scaleability Jim Gray Microsoft Research
Advertisements

RISC and Pipelining Prof. Sin-Min Lee Department of Computer Science.
12-CRS-0106 REVISED 8 FEB 2013 PRESENTS Meeting Notice feeds and iCal Functionality.
Performance What differences do we see in performance? Almost all computers operate correctly (within reason) Most computers implement useful operations.
CHAPTER 5.
Higher Computing Computer Systems 3. Computer Performance.
The Next I.T. Tsunami Paul A. Strassmann. Copyright © 2005, Paul A. Strassmann - IP4IT - 11/15/05 2 Perspective Months  Weeks.
Clarke, R. J (2001) t909-02: 1 Office Automation & Intranets BUSS 909 Tutorial 2 Researching on the WWW.
2/25/2004 The Google Cluster Architecture February 25, 2004.
Resources. Overview Problem Report WebCT Faculty & Student Support Searching.
S.1 Review: The Memory Hierarchy Increasing distance from the processor in access time L1$ L2$ Main Memory Secondary Memory Processor (Relative) size of.
1  1998 Morgan Kaufmann Publishers Chapter Seven Large and Fast: Exploiting Memory Hierarchy.
Review CPSC 321 Andreas Klappenecker Announcements Tuesday, November 30, midterm exam.
1 Lecture 2: System Metrics and Pipelining Today’s topics: (Sections 1.6, 1.7, 1.9, A.1)  Quantitative principles of computer design  Measuring cost.
Algorithms (Contd.). How do we describe algorithms? Pseudocode –Combines English, simple code constructs –Works with various types of primitives Could.
14 1 Chapter 14 Database Connectivity and Web Development Database Systems: Design, Implementation, and Management, Seventh Edition, Rob and Coronel.
1  1998 Morgan Kaufmann Publishers Chapter Seven Large and Fast: Exploiting Memory Hierarchy.
1 Implementing the Emulab-PlanetLab Portal: Experiences and Lessons Learned Kirk Webb Mike Hibler Robert Ricci Austin Clements Jay Lepreau University of.
Csci4203/ece43631 Review Quiz. 1)It is less expensive 2)It is usually faster 3)Its average CPI is smaller 4)It allows a faster clock rate 5)It has a simpler.
1 SRAM: –value is stored on a pair of inverting gates –very fast but takes up more space than DRAM (4 to 6 transistors) DRAM: –value is stored as a charge.
Fall 2001CS 4471 Chapter 2: Performance CS 447 Jason Bakos.
CS402 PPP # 2 MIPS BASIC INFORMATION By George Koutsogiannakis 1.
CalStan 3/2011 VIRAM-1 Floorplan – Tapeout June 01 Microprocessor –256-bit media processor –12-14 MBytes DRAM – Gops –2W at MHz –Industrial.
1 CSE SUNY New Paltz Chapter Seven Exploiting Memory Hierarchy.
LEARN THE QUICK AND EASY WAY! VISUAL QUICKSTART GUIDE HTML and CSS 8th Edition Chapter 21: Publishing Your Pages on the Web.
CS246 Search Engine Scale. Junghoo "John" Cho (UCLA Computer Science) 2 High-Level Architecture  Major modules for a search engine? 1. Crawler  Page.
The College of Saint Rose CSC 460 / CIS 560 – Search and Information Retrieval David Goldschmidt, Ph.D. from Search Engines: Information Retrieval in Practice,
Systems Development Life Cycle Dirt Sport Custom.
System Analysis (Part 2) The System Development Life Cycle Problem Selection and Feasibility Study.
Measuring System Performance The speed of a computer is often referred to as THROUGHPUT. This is very difficult to measure. It can be done with Measures.
Large-scale Incremental Processing Using Distributed Transactions and Notifications Daniel Peng and Frank Dabek Google, Inc. OSDI Feb 2012 Presentation.
Advanced Computer Architecture Fundamental of Computer Design Instruction Set Principles and Examples Pipelining:Basic and Intermediate Concepts Memory.
McLean HIGHER COMPUTER NETWORKING Lesson 7 Search engines Description of search engine methods.
CS211 - Fernandez - 1 CS211 Graduate Computer Architecture Network 3: Clusters, Examples.
Computer Organization and Architecture Tutorial 1 Kenneth Lee.
PPRD WEBSITE MANUAL ABOUT THE WEBSITE  This website is by the people, for the people and of the people living in Pratham Paradise.
EEL 5708 Cluster computers. Case study: Google Lotzi Bölöni.
CSCI-365 Computer Organization Lecture Note: Some slides and/or pictures in the following are adapted from: Computer Organization and Design, Patterson.
Operating System 1 COMPUTER SYSTEM OVERVIEW Achmad Arwan, S.Kom.
How Computers Work Lecture 12 Page 1 How Computers Work Lecture 12 Introduction to Pipelining.
1 Lecture 2: Performance, MIPS ISA Today’s topics:  Performance equations  MIPS instructions Reminder: canvas and class webpage:
Computer Organization Instruction Set Architecture (ISA) Instruction Set Architecture (ISA), or simply Architecture, of a computer is the.
1  2004 Morgan Kaufmann Publishers Locality A principle that makes having a memory hierarchy a good idea If an item is referenced, temporal locality:
HDice Michael Lowry December 1, 2010 Remote Access Review.
EGRE 426 Computer Organization and Design Chapter 4.
1 Chapter Seven. 2 SRAM: –value is stored on a pair of inverting gates –very fast but takes up more space than DRAM (4 to 6 transistors) DRAM: –value.
The Google Cluster Architecture Written By: Luiz André Barroso Jeffrey Dean Urs Hölzle Presented By: Omkar Kasinadhuni Simerjeet Kaur.
1  2004 Morgan Kaufmann Publishers Fallacies and Pitfalls Fallacy: the rated mean time to failure of disks is 1,200,000 hours, so disks practically never.
1 Thinking What are the top three ways that you use your computer? What type of programs do you use for these functions? 2 Web Search What is.
Internet Searching How many Search Engines are there? What is a spider and how is it important to the Internet? What are the three main parts of a search.
Crawling When the Google visit your website for the purpose of tracking, Google does this with help of machine, known as web crawler, spider, Google bot,
Introduction and approval process
Advanced Topics in Concurrency and Reactive Programming: Case Study – Google Cluster Majeed Kassis.
SEARCH ENGINES & WEB CRAWLER Akshay Ghadge Roll No: 107.
Program Planning Templates
For basic Internet searches for news articles or interviews with the person you are researching, try Bing &/or Google. News search will help you find where.
Figure 13.1 MIPS Single Clock Cycle Implementation.
Different Architectures
SEO JAYAM WEB SOLUTIONS.
Data Hazards Data Hazard
NASS Web Site Projected to launch in December 2005, this will satisfy a USDA initiative to standardize the “look and feel” of the Department’s agency web.
Chapter 3 Getting Started.
CS246 Search Engine Scale.
Single Cycle vs. Multiple Cycle
Database Connectivity and Web Development
Identify Different Chinese People with Identical Names on the Web
Google POV Google 0.1 Understand the structure of links on the web.
CS246: Search-Engine Scale
Chapter 2: Performance CS 447 Jason Bakos Fall 2001 CS 447.
Computer Organization and Design Chapter 4
Presentation transcript:

The Google Cluster Google

The Google Floor Plan

A Google Rack of PCs

One Google PC

Google Factoids In 2000 Google served 1000 queries per second Google crawls the entire web every month December 2000 (three years ago) Google used 6000 processors and 12,000 disks totaling 1 petabyte of data Searches have been growing about 90% a year at Google

More Google Factoids Software is the weak link – the biggest source of failures in Google is software About 20 machines a day are rebooted Rebooting actually done manually 2-3% of the PCs must be replaced each year Disk and dram failures account for 95% of these

How is Pipelining Implemented? Study over section 8.3; know the 5 clock cycle implementation for MIPS shown on page A-27 and 28

Events on Pipe Stages Study over figure A-19