Open Cirrus is an open cloud-computing research testbed designed to support research into design, provisioning, and management of services at a global, multi-datacenter scale.
The open nature of the testbed is designed to encourage research into all aspects of service and datacenter management. In addition, they hope to foster a collaborative community around the testbed, providing ways to share tools, lessons and best practices, and ways to benchmark and compare alternative approaches to service management at datacenter scale.
There are a number of important and useful testbeds, such as PlanetLab, EmuLab, IBM/Google cluster, and Amazon EC2/S3, that enable researchers to study different aspects of distrubuted computing. However, no single testbed supports research spanning systems, applications, services, open-source development, and datacenters. Towards this end, we have developed Open Cirrus, a cloud computing testbed for the research community that federates heterogeneous distributed data centers. Open Cirrus offers a cloud stack consisting of physical and virtual machines, and global services such as sign-on, monitoring, storage, and job submission. By developing the testbed and making it available to the research community, we hope to help spur innovation in cloud computing and catalyze the development of an open source stack for the cloud.
The Open Cirrus testbed is a collection of federated datacenters for open-source systems and services research. The testbed is composed of nine sites in North America, Europe, and Asia. Each site consists of a cluster with at least 1000 cores and associated storage. Authorized users can access any Open Cirrus site using the same login credentials.
The Open Cirrus project aims to provide systems researchers with a testbed of distributed data centers they can use for systems-level (as well as applications and services) cloud computing research. Open Cirrus aims to achieve the following goals:
- Foster system-level Research in Cloud Computing
- Encourage New Cloud Computing Applications and Applications-Level Research
- Collection of Experimental Datasets
- Develop Open-Source Stacks and APIs for the Cloud
Open Cirrus is a trademark of Yahoo Inc and the project is a joint initiative sponsored by HP, Intel, and Yahoo, in collaboration with NSF, the University of Illinois (UIUC), Karlsruhe Institute of Technology, the Infocomm Development Authority (IDA) of Singapore, the Electronics and Telecommunications Research Institute (ETRI ), the Malaysian Institute for Microelectronic Systems (MIMOS ), and the Institute for System Programming at the Russian Academy of Sciences (ISPRAS).
Additional Open Cirrus site members are expected to join.
Testbed Sites
Open Cirrus is a collaboration of several organizations:
For more information on The Open Cirrus Cloud Computing Testbed, please visit www.opencirrus.org.
Site Updates
- HP Open Cirrus Site Update
Dejan Milojicic, Sr Research Manager at HP Labs
June 2009 - January 2010
- Intel Research Pittsburgh Update
Michael Kozuch, Principal Research Scientist
June 2009 - January 2010
- Yahoo Open Cirrus Update
Thomas Kwan, Director of Research Operations
June 2009 - January 2010
- UIUC Open Cirrus Site Update
Indy Gupta, Assistant Professor, Department of Computer Sciences
June 2009 - January 2010
- CMU Open Cirrus Site Update
January 2010
- KIT Open Cirrus Site Update
Marcel Kunze, Technical Lead for Open Cirrus Cloud, Steinbuch Centre for Computing (SCC)
June 2009 - January 2010
- IDA Singapore COE Open Cirrus Site Update
June 2009 - January 2010
- ETRI Open Cirrus Site Update
Han Namgoong, Director at ETRI
June 2009 - January 2010
- MIMOS Open Cirrus Site Update
Kwang Ming NG, Sr Manager of Grid Computing Labs
June 2009 - January 2010
- Russian Center of Excellence (RCE) Open Cirrus Site Update
Arutyun Avetisyan – Deputy Director, ISP RAS
June 2009 - January 2010
Resources
- Paper: Open Cirrus TM Cloud Computing Testbed
 Federated Data Centers for Open Source Systems and Service Research – June 2009
This paper is an overview of the Open Cirrus Cloud Computing Testbed, a federated testbed of distributed clusters for systems and applications research. Open Cirrus offers unique opportunities for conducting research that none of the previous or current testbeds have offered (federation of heterogeneous sites, systems and applications research, and datasets). In addition, it offers an open stack with non-proprietary APIs for Cloud Computing. Through shared innovation it offers an economical model for an increased impact on communities around the globe.
Authors:
HP Labs: Kevin Lai, Martha Lyons, Dejan Milojicic; IDA: Hing Yan Lee, Yeng Chai Soh; Intel Research: Michael Kozuch, David O'Hallaron; KIT: Marcel Kunze; UIUC: Roy Campbell, Indranil Gupta, Mike Heath, Steve Ko; Yahoo: Thomas Kwan.
- Video: Hadoop Scheduling in the Open Cirrus Cloud Testbed - July 2009
Thomas Sandholm and Dejan Milojicic from HP Labs describe Hadoop Scheduling in the Open Cirrus Cloud Testbed.
Presentations from The Open Cirrus Summit
- Presentation: Scalable Storage and Deliverable Service - January 2010
Miles Libbey, Product Manager, Cloud Computing Group, Yahoo
- Presentation: Cloud and the Sustainable IT Ecosystem - January 2010
Chandrakant Patel, HP Fellow and Director, Sustainable IT Ecosystem Lab, HP Labs
- Presentation: Disk Reduce - January 2010
G Gibson, Professor, CMU
- Presentation: Hadoop Debugging and Visualization - January 2010
Priya Narasimhan, Professor, CMU
- Presentation: Cloud at Illinois - January 2010
Roy Campbell, Sohaib and Sara Abbasi, Professor, University of Illinois
- Presentation: Global Store in Open Cirrus - January 2010
Young Kyun Kim, ETRI
- Presentation: Federation Between Planet Lab and Open Cirrus - January 2010
Rick McGeer, HP Labs
- Presentation: CloneCloud: Elastic Smartphone Applications Through Cloud Clone Execution - January 2010
Byung-gon Chun, Intel Research
- Presentation: Cloud Sustainability Dashboard - January 2010
Priya Mahadevan and Yuan Chen, HP Labs
- Presentation: Data-Intensive Scalable Computing: The Prospects and the Challenges - January 2010
Randy Bryant, University Professor and Dean, School of Computer Science, Carnegie Mellon University
- Presentation: Managing Utility Clouds - Monalytics Approach - January 2010
Karsten Schwan, Professor and Director, Center for Experimental Research in Computer Systems, Georgia Tech
- Presentation: Macro-Reading the Web - January 2010
Tom Mitchell, E Fredkin University Professor and Chair, Machine Learning Department, Carnegie Mellon University
- Presentation: Large-Scale Graph Algorithms - January 2010
Christos Faloutsos, Professor, CMU
- Presentation: Computational Sustainability - January 2010
Bart Selman, Professor, Cornell
- Presentation: Hadoop Online - January 2010
Joe Hellerstein, Professor, UC Berkeley
- Presentation: Programming Hadoop Dataflows with Pig - January 2010
Chris Olston, Yahoo Research
- Presentation: Zookeeper Coordination Service - January 2010
Ben Reed, Yahoo Research
- Presentation: PNUTS: Building and Running a Cloud Database System - January 2010
Brian Cooper, Yahoo Research
- Presentation: Cloud Computing Research in Intel Labs - January 2010
Anthony Joseph, Director, Intel Berkeley Research
- Presentation: RDE: Organization of Cloud Services Based on Distributed Resources - January 2010
Arutyun Avetisyan, Deputy Director, Institute for System Programming of the Russian Academy of Sciences
- Presentation: Cloud Computing: Local User Expectation - January 2010
Fairus Khalid, MIMOS, Malaysia
- Presentation: SPAIN: COTS Data-Center Ethernet for Multipathing Over Arbitrary Topologies - January 2010
Praveen Yalagandula, HP Labs
|
|
|