Milestone MAX: Extend DRAGON/GRMS
Extend DRAGON/GRMS as an aggregate manager to include optical and edge
compute resources (completed by month 6)
- Initially work to support such functionality end-to-end over VLANs
- Explore the impacts of layer 2 VLAN handoffs from national backbones like
Internet2 to the MAX network infrastructure and how they can lead to
supporting exploration at layer 1 optical level
work completed:
Multiple Aggregate Manager Integration (PlanetLab AM with DRAGON AM):
- use PLCAPI XMLRPC to instantiate a planetlab slice across several nodes
- adjusted polling interval on node manager:
- create tagged VLAN interfaces on these planetlab nodes
- provision a circuit (DRAGON slice) between HOUS/LOSA node and the "big" planetlab5 node at MAX
- demonstrates:
- dynamic circuits slice provisioning
- integration of non-planetlab and planetlab prototype aggregation managers
- inter-domain circuit creation over the wide-area network with a SONET-switched network
- demonstrates:
- transfer data using nuttscp (as fast as possible)
- run md5sum to show that data is valid
- provision circuits between planetlab nodes to distribute the data:
- src planetlab5, dst planetlab2
- src planetlab5, dst planetlab3
- src planetlab5, dst planetlab4
- transfer data between these pairs of nodes
- run md5sum to show that data is valid
Note: See
TracRoadmap for help on using
the roadmap.