uc berkeley above the clouds a berkeley view of cloud computing 1 uc berkeley rad lab

Click here to load reader

Post on 31-Mar-2015




2 download

Embed Size (px)


  • Slide 1

UC Berkeley Above the Clouds A Berkeley View of Cloud Computing 1 UC Berkeley RAD Lab Slide 2 Outline What is it? Why now? Cloud killer apps Economics for users Economics for providers Challenges and opportunities Implications 2 Slide 3 What is Cloud Computing? Old idea: Software as a Service (SaaS) Def: delivering applications over the Internet Recently: [Hardware, Infrastrucuture, Platform] as a service Poorly defined so we avoid all X as a service Utility Computing: pay-as-you-go computing Illusion of infinite resources No up-front cost Fine-grained billing (e.g. hourly) 3 Slide 4 Why Now? Experience with very large datacenters Unprecedented economies of scale Other factors Pervasive broadband Internet Fast x86 virtualization Pay-as-you-go billing model Standard software stack 4 Slide 5 Spectrum of Clouds Instruction Set VM (Amazon EC2, 3Tera) Bytecode VM (Microsoft Azure) Framework VM Google AppEngine, Force.com EC2AzureAppEngineForce.com Lower-level, Less management Higher-level, More management 5 Slide 6 Cloud Killer Apps Mobile and web applications Extensions of desktop software Matlab, Mathematica Batch processing / MapReduce Oracle at Harvard, Hadoop at NY Times 6 Slide 7 Unused resources Economics of Cloud Users Pay by use instead of provisioning for peak Static data centerData center in the cloud Demand Capacity Time Resources Demand Capacity Time Resources 7 Slide 8 Unused resources Economics of Cloud Users Risk of over-provisioning: underutilization Static data center Demand Capacity Time Resources 8 Slide 9 Economics of Cloud Users Heavy penalty for under-provisioning Lost revenue Lost users Resources Demand Capacity Time (days) 1 23 Resources Demand Capacity Time (days) 1 23 Resources Demand Capacity Time (days) 1 23 9 Slide 10 Economics of Cloud Providers 5-7x economies of scale [Hamilton 2008] Extra benefits Amazon: utilize off-peak capacity Microsoft: sell.NET tools Google: reuse existing infrastructure Resource Cost in Medium DC Cost in Very Large DC Ratio Network$95 / Mbps / month$13 / Mbps / month7.1x Storage$2.20 / GB / month$0.40 / GB / month5.7x Administration140 servers/admin>1000 servers/admin7.1x 10 Slide 11 Adoption Challenges ChallengeOpportunity AvailabilityMultiple providers & DCs Data lock-inStandardization Data Condentiality and Auditability Encryption, VLANs, Firewalls; Geographical Data Storage 11 Slide 12 Growth Challenges ChallengeOpportunity Data transfer bottlenecks FedEx-ing disks, Data Backup/Archival Performance unpredictability Improved VM support, flash memory, scheduling VMs Scalable storageInvent scalable store Bugs in large distributed systems Invent Debugger that relies on Distributed VMs Scaling quicklyInvent Auto-Scaler that relies on ML; Snapshots 12 Slide 13 Policy and Business Challenges ChallengeOpportunity Reputation Fate SharingOffer reputation-guarding services like those for email Software LicensingPay-for-use licenses; Bulk use sales 13 Slide 14 Short Term Implications Startups and prototyping One-off tasks Washington post, NY Times Cost associativity for scientific applications Research at scale 14 Slide 15 Long Term Implications Application software: Cloud & client parts, disconnection tolerance Infrastructure software: Resource accounting, VM awareness Hardware systems: Containers, energy proportionality 15