Changes between Version 1 and Version 2 of MAX-GENI-Stitching-Status-Report-GEC14


Ignore:
Timestamp:
07/31/12 23:30:59 (12 years ago)
Author:
Tom Lehman
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • MAX-GENI-Stitching-Status-Report-GEC14

    v1 v2  
    1010   * Demonstrate stitching between GENI resources at MAX and CRON using the prototype GENI stitching AMs for MAX, CRON and Internet2. Demonstrate GENI slices using stitched layer2 connections between MAX and CRON over Internet2. We anticipate that MAX will use the DYNES rack that should be installed in MAX before this demo, and that CRON will use traditional ION services provided by their LONI regional connection to Internet2, which will use appropriate services to interconnect them.
    1111
    12    * Evaluate modifications required to PerfSonar Topology Service to build a GENI Topology Service. Share design on GENI wiki and review at a GENI teleconference. Assumptions: This is design work; no implementation is expected. However design will be to the level of detail where implementation could begin.
     12   * Evaluate modifications required to !PerfSonar Topology Service to build a GENI Topology Service. Share design on GENI wiki and review at a GENI teleconference. Assumptions: This is design work; no implementation is expected. However design will be to the level of detail where implementation could begin.
    1313
    1414
    … …  
    1818This functionality was demonstrated in the context of the larger multi-aggregate stitching architecture and implementation work underway. The OMNI Client was used to submit requests to the four aggregates (CRON AM, LONI AM, ION AM, MAX AM).   We demonstrated the cases where the Dynamic Circuit Network (DCN) networks in between the GENI Aggregates all have a GENI Aggregate Manager "covering" them, and the case where some (or all) of the DCN networks do not have a GENI AM API.
    1919
    20 A GENI Rack at MAX was not available, so we utilized PlanetLab Resources at MAX for the host resources in that aggregate.
     20A GENI Rack at MAX was not available, so we utilized !PlanetLab Resources at MAX for the host resources in that aggregate.
    2121
    2222More detailed descriptions of this demonstration, including example RSpecs and demo scripts are located here:
    … …  
    8181Based on already completed design, implementation, testing, and demonstrations, the indications are that we will be able to implement a GENI multi-aggregate stitching capability which will satisfy the needs of the initial GENI Rack deployments as well as other sites which will have GENI Aggregate Managers.  Now that the GENI AM API v3 has been finalized, we will need to update the current design for item ii (stitching w/ negotiation).  These updates are primarily message type and format in nature, and do not change the planned architecture or design.
    8282
    83 This initial capability set will likely be based on items i and iii (with basic stitching workflow).  This capability will allow GENI experimenters to utilize the initially deployed infrastructure to instantiate slices which span multiple aggregates.  Parallel to this initial stitching deployment, work will continue on items ii (stitching w/negotiation), and iv-v to prepare for larger scale deployments.
     83This initial capability set will likely be based on items i and iii (with basic stitching !workflow).  This capability will allow GENI experimenters to utilize the initially deployed infrastructure to instantiate slices which span multiple aggregates.  Parallel to this initial stitching deployment, work will continue on items ii (stitching w/negotiation), and iv-v to prepare for larger scale deployments.
    8484
    8585