Changes between Version 4 and Version 5 of Gec5ClusterEAgenda
- Timestamp:
- 07/30/09 12:29:04 (15 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Gec5ClusterEAgenda
v4 v5 1 1 The ORBIT Cluster met at the GEC on Monday July 20 and Tuesday July 2 21. At the July 20 meeting Max Ott and Ray Raychaudhuri gave an 2 21. [[BR]] 3 4 At the July 20 meeting Max Ott and Ray Raychaudhuri gave an 3 5 overview of the ORBIT testbed and discussed the integration of !WiMax 4 6 base stations into the cluster. An initial deployment at Rutgers is 5 complete and baseline performance measurements have been collected. 7 complete and baseline performance measurements have been collected. [[BR]] 8 6 9 The July 21 meeting was less structured and included dicussions of 7 topics and issues raised by the meeting participants. 10 topics and issues raised by the meeting participants. [[BR]] 8 11 9 Topics discussed at the ORBIT CF meetings include: 12 Topics discussed at the ORBIT CF meetings include: [[BR]] 10 13 * ORBIT is not and does not claim to be a full-fledged control 11 14 framework. It is best viewed as a GENI aggregate. The ORBIT team … … 13 16 with. They do not want to be developing and maintaining software 14 17 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. 18 the ORCA control framework is their next step. [[BR]] 19 * ORBIT OMF might be able to serve as a GENI aggregate manager. [[BR]] 17 20 * The ORBIT experiment controller can be used to control 18 21 experiments on PlanetLab. An ORBIT experiment can now include 19 PlanetLab nodes. 22 PlanetLab nodes. [[BR]] 20 23 * There was some discussion around integration of the Clemson 21 24 testbed. This testbed includes embedded wireless platforms with 22 25 802.16 radios but not operating at WiMAX frequencies. The Clemson 23 26 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. 27 BMW test track. [[BR]] 28 * ORBIT OMF is being extended to handle mobility. [[BR]] 26 29 * Concerns specific to wireless testbed such as ORBIT: scheduling 27 30 and slicing of testbed resources so experiments don't interfere; 28 31 conforming to rules by the FCC and other similar regulatory 29 32 bodies; protecting measurement devices from badly behaved 30 experiments. 33 experiments. [[BR]] 31 34 * Issues with using !OpenFlow in a testbed where flows are not 32 35 persistent. For example, when vehicles more in and out of range 33 of a base station. 36 of a base station. [[BR]] 34 37 * ORBIT can be used to do experiments based on DTN (Disruption 35 38 Tolerant Networking) technologies since every node as processing 36 and storage resources. 39 and storage resources. [[BR]] 37 40 * MIT is interested in using ORBIT for network coding 38 41 experiments. They want to push networking coding as close to the 39 42 physical layer as possible. They will work with Rutgers to 40 determine the feasibility of such experimentation. 43 determine the feasibility of such experimentation. [[BR]] 41 44 42 45 Max Ott's summary of the WG meetings, presented at the Cluster Outbriefs on Wed July 22, is available [http://groups.geni.net/geni/attachment/wiki/Gec5Agenda/GEC5%20Day%203%20-%20cluster%20E%20update%20-%20Ott.pdf here]. 46 [[BR]] 47 48 Submitted by Vic Thomas, GOP System Engineer