Changes between Initial Version and Version 1 of Gec5ClusterEAgenda


Ignore:
Timestamp:
07/24/09 16:18:36 (15 years ago)
Author:
Vic Thomas
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • Gec5ClusterEAgenda

    v1 v1  
     1The ORBIT Cluster met at the GEC on Monday July 20 and Tuesday July
     221.  At the July 20 meeting Max Ott and Ray Raychaudhuri gave an
     3overview of the ORBIT testbed and discussed the integration of WiMax
     4base stations into the cluster.  An initial deployment at Rutgers is
     5complete and baseline performance measurements have been collected.
     6The July 21 meeting was less structured and included dicussions of
     7topics and issues raised by the meeting participants.
     8
     9Topics discussed at the ORBIT CF meetings:
     10   * ORBIT is not and does not claim to be a full-fledged control
     11   framework.  It is best viewed as a GENI aggregate.  The ORBIT team
     12   would like guidance from the GPO on which cluster they should work
     13   with.  They do not want to be developing and maintaining software
     14   needed to talk to all other control frameworks.  Integration with
     15   the ORCA control framework is their next step.
     16  * ORBIT OMF might be able to serve as a GENI aggregate manager.
     17  * The ORBIT experiment controller can be used to control
     18    experiments on PlanetLab.  An ORBIT experiment can now include
     19    PlanetLab nodes.
     20  * There was some discussion around integration of the Clemson
     21    testbed.  This testbed includes embedded wireless platforms with
     22    802.16 radios but not operating at WiMAX frequencies.  The Clemson
     23    testbed includes mobile nodes that can travel a high speeds on a
     24    BMW test track.
     25  * ORBIT OMF is being extended to handle mobility.
     26  * Concerns specific to wireless testbed such as ORBIT: scheduling
     27    and slicing of testbed resources so experiments don't interfere;
     28    conforming to rules by the FCC and other similar regulatory
     29    bodies; protecting measurement devices from badly behaved
     30    experiments.
     31  * Issues with using !OpenFlow in a testbed where flows are not
     32    persistent.  For example, when vehicles more in and out of range
     33    of a base station.
     34  * ORBIT can be used to do experiments based on DTN (Disruption
     35    Tolerant Networking) technologies since every node as processing
     36    and storage resources.
     37  * MIT is interested in using ORBIT for network coding
     38    experiments.  They want to push networking coding as close to the
     39    physical layer as possible.  They will work with Rutgers to
     40    determine the feasibility of such experimentation.
     41
     42Max Ott's summary of the WG meetings, presented at the Cluster Outbriefs on Wed July 22, is available at