Changes between Version 1 and Version 2 of DICLOUD
- Timestamp:
- 10/26/09 09:56:19 (14 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
DICLOUD
v1 v2 48 48 == Scope == 49 49 50 This project augments the [wiki:ORCABEN ORCA/BEN project] which was started at the beginning of Spiral 1, and which provides the code for the ORCA control framework.50 This project will develop a complete environment for researchers to conduct data-intensive experiments in GENI from start (the data collection point) to finish (processing and archiving). [[BR]] 51 51 52 This project will augment the features of the current ORCA Control Framework prototype and integrate work from other relevant GENI projects to substantially increase the capabilities of the framework in the areas of: 53 (1) unified measurement and experimenter tools, particularly physical layer measurement [[BR]] 54 (2) identity and trust management based on Shibboleth and SAML [[BR]] 55 (3) cloud computing substrates[[BR]] 56 (4) resource description and allocation mechanisms, policies and algorithms [[BR]] 52 To do so, this project will extend the GENI/ViSE sensor network (sensornet) testbed at UMass-Amherst and augment GENI Cluster D’s Orca control framework with capabilities for researchers to 53 (i) obtain data-centric slices that span core sensornet nodes, data center nodes, and, importantly, storage volumes “in the cloud,” (ii) deploy popular cloud computing programming paradigms to enable simple, but powerful, distributed data processing, and 54 (iii) execute experiment workflows to explicitly control experiment data flow and resource allocation across a network of components/aggregates. [[BR]] 57 55 58 As the capabilities of ORCA are increased, they will be made available to the associated projects in Cluster D.[[BR]]56 The project will build on existing software artifacts in the GENI “ecosystem” and tailor them to the distinct requirements of data-intensive experiments. While the enhanced software artifacts will generalize to any high-bandwidth data-intensive experiments, the GENI/ViSE sensornet testbed, which collects high-bandwidth data from multiple high-power (virtualized) sensor/actuators, will be the initial data source. [[BR]] 59 57 60 In particular, it will assist in the integration of the Integrated Measurement Framework (IMF) and related tools being developed in a separate project, to enable advanced cross-layer experiments in the BEN regional optical network. [[BR]]58 Our goal by year one is to incorporate commercial cloud computing services, including storage services, as GENI substrates available for researchers. [[BR]] 61 59 62 It will integrate Shibboleth identity providers (IdPs) and SAML security assertions into ORCA to support: IdP-endorsed credential attributes; the use of attributes for authorization; and proxy authentication, which would enable users to delegate credentials to software entities acting on their behalf.[[BR]]60 Our goal by year two is to enhance GENI’s usefulness by testing and hardening the capability for researchers to request (or load) distributed software platforms on commercial clouds. We will demonstrate the capability using both an MPI stack and Apache’s Hadoop framework, an open-source version of MapReduce and Google File System (GFS).[[BR]] 63 61 64 It will add Orca interfaces (handler and driver plugins) for edge cluster substrates managed by Eucalyptus, a popular virtual/cloud computing systems, and integrate it into ORCA. Eucalyptus is an open-source Xen-based virtual cloud manager designed to resemble Amazon’s Elastic Compute Cloud (EC2) and cloud storage services. [[BR]] 65 66 In cooperation with the ORBIT project, it will extend the Network Description Language (NDL), an OWL-based ontology schema, by developing common ontology specifications and a common set of tools, to better describe all resources being integrated into ORCA and ORBIT. And, it will enable dynamic resource discovery, including the ability to query a broker about resources available.[[BR]] 62 Our goal by year three is to complete the integration of Gush to discover resources and deploy experiment workflows across data-centric slices in the Orca CF.[[BR]] 67 63 68 64