1 / 11

An Opening in the Clouds: Open Source Platform Cloud Computing at UCSB

An Opening in the Clouds: Open Source Platform Cloud Computing at UCSB. Chandra Krintz Chris Bunch and Navraj (Raj) Chohan Computer Science Dept. Univ. of California, Santa Barbara UC Cloud Summit April 2011. cloud computing. Infrastructure: Amazon Web Services (EC2, S3, EBS)

dom
Download Presentation

An Opening in the Clouds: Open Source Platform Cloud Computing at UCSB

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. An Opening in the Clouds: Open Source Platform Cloud Computing at UCSB Chandra Krintz Chris Bunch and Navraj (Raj) Chohan Computer Science Dept. Univ. of California, Santa Barbara UC Cloud Summit April 2011

  2. cloud computing • Infrastructure: Amazon Web Services (EC2, S3, EBS) • Virtualized, isolated (CPU, Network, Storage) systems on which users execute entire runtime stacks • Fully customer self-service • Open APIs (IaaS standard), scalable services • Platform: Google App Engine, Microsoft Azure • Scalable program-level abstractions via well-defined interfaces • Enable construction of network-accessible applications • Process-level (sandbox) isolation, complete software stack • Software: Salesforce.com • Applications provided to thin clients over a network • Customizable

  3. an opening in the clouds • Goal: Bring popular cloud fabrics “on-premise” or to alternative public cloud systems that are easy to use and are transparent • By emulating key cloud layers from the commercial sector • Engender user community, access to real applications/users • “Standard” APIs -- we target Google App Engine (GAE) • Leverage extant open source software technologies • Inspired by Eucalyptus -- yet, we target the platform layer • To facilitate investigation of • Next-generation distributed / cloud computing software • Simplifying application development and deployment • Services, underlying device technology, support technologies • Customization (availability, performance, application behavior) • Hybrid cloud solutions (public and on-premise)

  4. an opening in the clouds • Goal: Bring popular cloud fabrics “on-premise” or to alternative public cloud systems that are easy to use and are transparent • By emulating key cloud layers from the commercial sector • Leverage extant open source software technologies • PaaS: • Open-source platform as a service (PaaS) • API-compatible with Google App Engine (GAE) • GAE applications execute without modification • Test-drive GAE • Test/debug applications and workloads • Monitor GAE application behavior and performance • Help developers form a mental model of cloud application

  5. google app engine (GAE) private, enterprise data, Google apps SDC Google App Engine (GAE) MyApp.appspot.com GAE Application (Python, Java) Protobuf Data APIs Users Images URL Fetch Blob store Administrator Console IM Services Cron Data Store Tasks Memcache Mail

  6. from gae to appscale • APIs • Pluggable using open-source distributed database technologies HBase, Hypertable, Cassandra, Voldemort, MongoDB, MemcacheDB, MySQL • MemcacheD library (Python and Java) • From console or as background thread (automatically) • Interface to Hadoop (MapReduce) • Multi-language support: Python, Java, Ruby, Perl, X10 • Interface to Yahoo! S4 (distributed stream computing) • Translator to Linux Cron job, similar to Tasks • Pluggable: built-in cloud-wide authentication via Rails, support for Eucalyptus and EC2 credentials • Automatic configuration and deployment of all subsystems Data store Mem Cache Tasks Cron Users

  7. appscale deployment • Available as • A virtual machine image (KVM, XEN) • An EC2 AMI • Open source (automated AppScalle image installation) • Tool set for command-line cloud deployment • Inspired by AWS tools and Eucatools for instance management • Run, describe, terminate • Upload app, remove app • Automates deployment & configuration of all components • Web interface • Status, performance monitor time series • Cloud management (VM control) • Application control

  8. appscale • Open-source platform as a service (PaaS) • API-compatible with Google App Engine (GAE) • Ease resource constraints, limitations • Additional APIs to facilitate HPC and HTC • For large-scale data analytics • MapReduce (hadoop) • Pig query support • Yahoo! S4 distributed stream computing, graph-oriented systems • For compute-intensive applications • New cloud configuration language: Neptune • MPI X10 • MapReduce Erlang • Unified Parallel C (UPC) IaaS Cloud control • Extension & specialization: Biochemical simulation (Monte Carlo)

  9. appscale use, research, & potential • Open-source platform as a service (PaaS) • API-compatible with Google App Engine (GAE) • Additional APIs to facilitate HPC and HTC • Simplifies use of distributed resources & cloud app deployment • Support for a wide range of applications and app domains • Easing the way for a diversity of users to employ cloud resources • Pluggable services & features • Instrumentation, monitoring, performance visualization • Language/program, components, VM, system • Placement Distributed transactions • Elasticity (inter/intra VM) Fault tolerance • Executes over virtualization or IaaS layer: AWS, Eucalyptus • Hybrid cloud platform: GAE, AWS, Eucalyptus

  10. appscale as a hybrid cloud • Goal: “Write-once, Run anywhere” for the cloud • GAE, AWS, Eucalyptus • Simple storage (ala S3), block storage (ala EBS) • VM control and management • API export (via AppScale APIs and REST) • IaaS/PaaS services (e.g. authentication, datastore/databases) • Encourage public cloud cost and service competition • New applications & solutions • Disaster recovery, interruption tolerance, offline analytics • Cross-cloud elasticity • With open source, user, and cloud community: Identify APIs • AppScale implementation using disparate cloud fabrics

  11. thanks! • Students and Visitors! • Maciej Baranski, Chris Bunch, Jovan Chohan, Navraj Chohan, Nupur Garg, Shashank Hedge, Matt Hubert, Jonathan Kupferman, Puneet Lakhina, Yiming Li, Nagy Mostafa, Yoshihide Nomura (Fujitsu), Kowshik Prakasam, Raviprakash Ramanujam, Sujay Sundaram, Bing Wei, Michal Weigel • Support • Google, IBM Research, National Science Foundation http://www.cs.ucsb.edu/~racelab http://appscale.cs.ucsb.edu/

More Related