11 Yeah! That’s what I’d like to know. Indranil Gupta (Indy) Lecture 2 What(’s in) the Cloud? January 20, 2011 CS 525 Advanced Distributed Systems Spring 2011 All Slides © IG

2 Clouds are Water Vapor Oracle has a Cloud Computing Center. And yet… Larry Ellison’s Rant on Cloud Computing 2

33 The Hype! Gartner - Cloud computing revenue will soar faster than expected and will exceed $150 billion within five years. Forrester - Cloud-Based Is Often Cheaper Than On-Premise Vivek Kundra, CTO of Obama Government: “Growing adoption of cloud computing could improve data sharing and promote collaboration among federal, state and local governments.” E.g: fedbizopps.gov Merrill Lynch: “By 2011 the volume of cloud computing market opportunity would amount to $160bn, including $95bn in business and productivity apps ( , office, CRM, etc.) and $65bn in online advertising.” IDC: “Spending on IT cloud services will triple in the next 5 years, reaching $42 billion and capturing 25% of IT spending growth in 2012.” Sources: and

4 Ha ha hype! It’s a bunch of tripe, since no one is probably making or saving money.

5 $$$ Ingo Elfering, Vice President of Information Technology Strategy, GlaxoSmithKline: “With Online Services, we are able to reduce our IT operational costs by roughly 30% of what we’re spending now and introduce a variable cost subscription model for these technologies that allows us to more rapidly scale or divest our investment as necessary as we undergo a transformational change in the pharmaceutical industry” Jim Swartz, CIO, Sybase: “At Sybase, a private cloud of virtual servers inside its data centre has saved nearly $US2 million annually since 2006, Swartz says, because the company can share computing power and storage resources across servers.” Dave Power, Associate Information Consultant at Eli Lilly and Company: “With AWS, Powers said, a new server can be up and running in three minutes (it used to take Eli Lilly seven and a half weeks to deploy a server internally) and a 64-node Linux cluster can be online in five minutes (compared with three months internally). The deployment time is really what impressed us. It's just shy of instantaneous." Sources: and

6 Alright, alright. But for heaven’s sake, can someone tell me what is a cloud?

7 What is a Cloud? It’s a cluster! It’s a supercomputer! It’s a datastore! It’s superman! None of the above All of the above Cloud = Lots of storage + compute cycles nearby

8 What is a Cloud? A single-site cloud (aka “Datacenter”) consists of –Compute nodes (split into racks) –Switches, connecting the racks –A network topology, e.g., hierarchical –Storage (backend) nodes connected to the network –Front-end for submitting jobs –Services: physical resource set, software services A geographically distributed cloud consists of –Multiple such sites –Each site perhaps with a different structure and services

9 A Sample Cloud Topology Top of the Rack Switch Core Switch Servers Rack If higher bandwidth link, then a “fat tree” topology

10 Scale of Industry Datacenters Microsoft [NYTimes, 2008] –150,000 machines –Growth rate of 10,000 per month –Largest datacenter: 48,000 machines –80,000 total running Bing Yahoo! [Hadoop Summit, 2009] –25,000 machines –Split into datacenters of 4000 machines each AWS EC2 (Oct 2009) –40,000 machines –8 cores/machine Google –(Rumored) several hundreds of thousands of machines

11 OK, they are massive. But it is still called a “cluster”! And that’s not a new concept!

Timesharing Companies & Data Processing Industry 2010 Grids Peer to peer systems Clusters The first datacenters! PCs (not distributed!) Clouds and datacenters “A Cloudy History of Time” © IG 2010

13 Timesharing Industry (1975): Market Share: Honeywell 34%, IBM 15%, Xerox 10%, CDC 10%, DEC 10%, UNIVAC 10% Honeywell 6000 & 635, IBM 370/168, Xerox 940 & Sigma 9, DEC PDP-10, UNIVAC 1108 Grids (1980s-2000s): GriPhyN (1970s-80s) Open Science Grid and Lambda Rail (2000s) Globus & other standards (1990s-2000s) First large datacenters: ENIAC, ORDVAC, ILLIAC Many used vacuum tubes and mechanical relays P2P Systems (90s-00s) Many Millions of users Many GB per day Data Processing Industry : $70 M. 1978: $3.15 Billion. Berkeley NOW Project Supercomputers Server Farms (e.g., Oceano) “A Cloudy History of Time” © IG 2010 Clouds

14 Why did all of this happen?

15 Trends: Technology Doubling Periods – storage: 12 mos, bandwidth: 9 mos, and (what law is this?) cpu capacity: 18 mos Then and Now Bandwidth –1985: mostly 56Kbps links nationwide –2004: 155 Mbps links widespread Disk capacity –Today’s PCs have 100GBs, same as a 1990 supercomputer

16 Trends: Users Then and Now Biologists: –1990: were running small single-molecule simulations –2004: want to calculate structures of complex macromolecules, want to screen thousands of drug candidates, sequence very complex genomes Physicists –2008 onwards: CERN’s Large Hadron Collider will produce 700 MB/s or 15 PB/year Trends in Technology and User Requirements: Independent or Symbiotic?

17 Prophecies In 1965, MIT's Fernando Corbató and the other designers of the Multics operating system envisioned a computer facility operating “like a power company or water company”. Plug your thin client into the computing Utility and Play your favorite Intensive Compute & Communicate Application –[Have today’s clouds brought us closer to this reality?]

18 So, clouds have been around for decades! But aside from massive scale what’s new about today’s cloud computing?!

19 What(’s new) in Today’s Clouds? Three major features: I.On-demand access: Pay-as-you-go, no upfront commitment. –Anyone can access it (e.g., Washington Post – Hillary Clinton example) II.Data-intensive Nature: What was MBs has now become TBs. –Daily logs, forensics, Web data, etc. –Do you know the size of Wikipedia dump? III.New Cloud Programming Paradigms: MapReduce/Hadoop, Pig Latin, DryadLinq, Swift, and many others. –High in accessibility and ease of programmability Combination of one or more of these gives rise to novel and unsolved distributed computing problems in cloud computing.

20 I. On-demand access: *aaS Classification On-demand: renting a cab vs (previously) renting a car, or buying one. E.g.: –AWS Elastic Compute Cloud (EC2): $0.086-$1.16 per CPU hour –AWS Simple Storage Service (S3): $0.055-$0.15 per GB-month HaaS: Hardware as a Service –You get access to barebones hardware machines, do whatever you want with them –Ex: Your own cluster, Emulab IaaS: Infrastructure as a Service –You get access to flexible computing and storage infrastructure. Virtualization is one way of achieving this. Often said to subsume HaaS. –Ex: Amazon Web Services (AWS: EC2 and S3), Eucalyptus, Rightscale. PaaS: Platform as a Service –You get access to flexible computing and storage infrastructure, coupled with a software platform (often tightly) –Ex: Google’s AppEngine SaaS: Software as a Service –You get access to software services, when you need them. Often said to subsume SOA (Service Oriented Architectures). –Ex: Microsoft’s LiveMesh, MS Office on demand

21 II. Data-intensive Computing Computation-Intensive Computing –Example areas: MPI-based, High-performance computing, Grids –Typically run on supercomputers (e.g., NCSA Blue Waters) Data-Intensive –Typically store data at datacenters –Use compute nodes nearby –Compute nodes run computation services In data-intensive computing, the focus shifts from computation to the data: CPU utilization no longer the most important resource metric Problem areas include –Distributed systems –Middleware –OS –Storage –Networking –Security –Others

22 III. New Cloud Programming Paradigms Dataflow programming frameworks Google: MapReduce and Sawzall Yahoo: Hadoop and Pig Latin Microsoft: DryadLINQ Facebook: Hive Amazon: Elastic MapReduce service (pay-as-you-go) Google (MapReduce) –Indexing: a chain of 24 MapReduce jobs –~200K jobs processing 50PB/month (in 2006) Yahoo! (Hadoop + Pig) –WebMap: a chain of 100 MapReduce jobs –280 TB of data, 2500 nodes, 73 hours Facebook (Hadoop + Hive) –~300TB total, adding 2TB/day (in 2008) –3K jobs processing 55TB/day Similar numbers from other companies, e.g., Yieldex, eharmony.com, etc.

23 This is all confusing. Can you give me some examples of clouds?

24 Two Categories of Clouds Industrial Clouds –Can be either a (i) public cloud, or (ii) private cloud –Private clouds are accessible only to company employees –Public clouds provide service to any paying customer: Amazon S3 (Simple Storage Service): store arbitrary datasets,pay per GB- onth stored Amazon EC2 (Elastic Compute Cloud): upload and run arbitrary images, pay per CPU hour used Google AppEngine: develop applications within their appengine framework, upload data which is then imported into their format, and run Academic Clouds –Allow researchers to innovate, deploy, and experiment –Google-IBM Cloud (U. Washington): run apps programmed atop Hadoop –Cloud Computing Testbed UIUC): first cloud testbed to support systems research. Runs: (i) apps programmed atop Hadoop and Pig, (ii) systems-level research on this first generation of cloud computing models (~HaaS), and (iii) Eucalyptus services (~AWS EC2). –OpenCirrus: first federated cloud testbed.

25 Academic Clouds CCT = Cloud Computing Testbed –NSF infrastructure –Used by 10+ NSF projects, including several non- UIUC projects –Housed within Siebel Center (4 th floor!) –Accessible to students of CS525! Almost half of SP09/SP10 course used CCT for their projects OpenCirrus = Federated Cloud Testbed –Contains CCT and other sites If you need a CCT account for your CS525 experiment, let me know asap! There are a limited number of these available for CS525

26 Cloud Computing Testbed (CCT)

compute nodes = TB & shared cores CCT Hardware in more Detail

28 Goal of CCT: Support both Systems Research and Applications Research in Data-intensive Distributed Computing

29 CCT Software Services Accessing and Using CCT: I.Systems Partition (64-8 nodes): –CentOS machines –Dedicated access to a subset of machines (~ Emulab), with sudo access –User accounts User requests # machines (<= 64) + storage quota (<= 30 TB) Machine allocation survives for 4 weeks, storage survives for 6 months (both extendible) II.Hadoop/Pig Partition and Service (64 nodes) III.Eucalyptus Partition (8 nodes)

30 Accessing and Using CCT: I.Systems Partition (64-8 nodes) II.Hadoop/Pig Partition and Service (64 nodes): –Looks like a regular shared Hadoop cluster service Users share 64 nodes. Individual nodes not directly reachable. 4 slots per machine Several users are reporting stable operation at 256 instances During Spring 09/10, 10+ projects running simultaneously –User accounts User requests account + storage quota (<= 30 TB) Storage survives for 6 months (extendible) III.Eucalyptus Partition (8 nodes) CCT Software Services

31 Accessing and Using CCT: I.Systems Partition (64-8 nodes) II.Hadoop/Pig Partition and Service (64 nodes): III.Eucalyptus Partition (8 nodes): Based on open-source version of Eucalyptus from UCSB (Rich Wolski) Exports same interface as AWS EC2 and S3. CCT Software Services

32 Some Services running inside CCT –ZFS: backend file system. –Zenoss: Systems Monitoring. Shared with department’s other computing clusters –Hadoop + HDFS –Ability to make datasets publicly available How do users request an account: two-stage process (go to ) 1.User account request – require background check 2.Allocation request CCT Software Services

33 Founding 6 sites Open Cirrus Federation

34 23 June 2015 HP UIUC Intel KIT (de) IDA (sg) Yahoo First open federated cloud testbed Shared: research, applications, infrastructure (9*1,000 cores), data sets Global services: sign on, monitoring, store, etc., Federated clouds, meaning each is different CMU RAS ETRI MIMOS Grown to 9 sites, with more to come Open Cirrus Federation

35 OK, so that’s what a cloud looks like today. Now, suppose I want to start my own company, Devils Inc. Should I buy a cloud and own it, or should I outsource to a public cloud?

We’ll do that next week… For now, it’s important to start thinking of who’s on your project team… Projects Groups of 2 (need not be same as presentation groups). Could be 3. We’ll start detailed discussions “soon” (a few classes into the student-led presentations)

Entr. Tidbits: Selecting your Team Selecting your partner is important: select someone with a complementary personality to yours! –Apple: Wozniak loved being an engineer and hated interacting with people, Jobs loved making calls, doing sales and preferred engineering much less –Flickr: Stewart was improvisational, Fake was goal- driven –Levchin loved to program and break things, Thiel talked to VCs and did sales. –Hansson says that development of Ruby on Rails benefited from having a small team and a small budget that kept them focused – this is why the big giants could not beat them. The upshot is that you have to select a team with complementary characteristics 37

Next Week We will continue discussion of cloud computing –How MapReduce works –What is PlanetLab and Emulab –What is Grid computing Then we will start to discuss Basics of P2P systems Please read at least one paper from each session 38

39 Administrative Announcements Student-led paper presentations (see instructions on website) Start from February 10th Groups of up to 2 students present each class, responsible for a set of 3 “Main Papers” on a topic –45 minute presentations (total) followed by discussion –Set up appointment with me to show slides by 5 pm day prior to presentation –Select your topic by Jan 31st List of papers is up on the website Each of the other students (non-presenters) expected to read the papers before class and turn in a one to two page review of the any two of the main set of papers (summary, comments, criticisms and possible future directions) – review and bring in hardcopy before class –Reviews are not due until student presentations start –Submit reviews for any 15 sessions (from 2/10 to 4/28)