Changes between Version 28 and Version 29 of ClusterDMtg070209


Ignore:
Timestamp:
07/28/09 17:34:32 (10 years ago)
Author:
hmussman@bbn.com
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • ClusterDMtg070209

    v28 v29  
    6666
    6767Progress against milestones
    68 - Planning to make ORCA a production capability for BEN; two issues:
    69   will the software work? and will there be sufficient documentation
    70   that people can use it?
    71 - Can ORCA be used to request connections to I2?  Yes, working with
    72   Chris Tracy.  More than one way to do it.  Could create an ORCA AM for
    73   I2.  Complicated by I2's work on their next-gen network
     68- Planning to make ORCA a production capability for BEN; two issues:  will the software work? and will there be sufficient documentation that people can use it?
     69- Can ORCA be used to request connections to I2?  Yes, working with Chris Tracy.  More than one way to do it.  Could create an ORCA AM for I2.  Complicated by I2's work on their next-gen network
    7470  architecture.  Working with John Volbrecht at I2
    75 - Experimenters in mind for spiral 1?  Mostly Keren Bergman, already share
    76   cluster & interests.  More detail later today.  Other experimenters
    77   will need patience and expertise.  Plan to take a cautious approach.
     71- Experimenters in mind for spiral 1?  Mostly Keren Bergman, already share cluster & interests.  More detail later today.  Other experimenters will need patience and expertise.  Plan to take a cautious approach.
    7872- Could move faster with more funding. 
    7973- Could GPO help with documentation?  Maybe a little but probably not.
     
    8175        11:00           DOME project [http://groups.geni.net/geni/wiki/DOME  wiki] [http://groups.geni.net/geni/attachment/wiki/ClusterDMtg070209/dome-spiral1.pptx  slides] (Brian Levine, Mark Corner, Brian Lynn)
    8276
     77Connection to Internet2
     78- In discussions with local OIT staff
     79- Will connect geni.cs.umass.edu to I2 directly via fiber from campus to Springfield to Boston, working in tandem with VISE team; requesting one VLAN ID, expecting little traffic; will have the capability to inject frames with VLAN tags
     80
     81Experiments by outsiders
     82- Have portal for job submission, one resource: wifi card, 900MHz radio coming next year; gets status; interfaces to ORCA
     83- Experiments on Buses. DTN tolerant downloading of experiments to buses; dynamic creation of VM sandbox to execute experiments, includes partitions, networking, devices; scheduling of experiments based on ORCA leases
     84- Instrumented measurements.  Half the core is about remote management and diagnostics.  Researcher data is uploaded automatically if
     85  certain file format is used.
     86
     87* Should compare DOME measurements to ORBIT
     88
     89* Should compare disconnected operation in DOME with ORBIT/WiMAX
     90
     91Plans for Spiral 2
     92
     93- Goal is to deploy on buses this summer.  5-6 out of 40 buses in field per
     94  day.
     95
     96- Will bring on undergrad projects in the fall from "Intro to
     97  Networking" class.  Imagine only 1 or 2 projects will get far enough
     98  to use the real system.  Have a PhD graduating this year heading to
     99  Arkansas who is expected do experiments.
     100
     101- Plan to allow experimenters to access XTend radios
     102
     103- Want 'true and open access to testbed by experimenters'
     104
     105- Tutorials on how to use?  May require some separate funding.  Keren
     106  very interested in such a tutorial. 
     107
     108  Concern about maintaining documents after publishing.  This is made
     109  more difficult since the prototypes are rapidly evolving.
     110
     111  Concern that supporting users will delay system development because
     112  of the need to have a stable system.  GPO thinks projects have
     113  latitude to define the level of stability and support that makes
     114  sense for them.  Currently, GENI is in the 'exploratory prototyping'
     115  phase, likely that composition and design will change over time.
     116
     117  Anish: We've found that tutorials are good as a way to train PIs
     118  grad students and colleagues.  There's a real cost to keeping it up
     119  but it is in general a good idea.  What events would be a good fit?
     120  Having a pull from users helps a lot. 
     121
     122  Chip: one approach is that folks want to use a remote system
     123  initially then make their own local copy.  Anish: yes, that's our
     124  experience but doing 'cross-experiments' has been quite hard.  Not
     125  clear what the benefit is to other users.
     126
     127  What are the GPO's incentives to get people to do experiments?  Not
     128  much.  The GPO doesn't sponsor research.  This is what NSF does.
     129  The GPO sponsor trial experiments to help shake down the system.
     130
    83131        11:30           ViSE project [http://groups.geni.net/geni/wiki/ViSE  wiki][http://groups.geni.net/geni/attachment/wiki/ClusterDMtg070209/vise.pptx  slides] (Prashant Shenoy, Michael Zink, David Irwin)
     132
     133Plans: Experiment Examples
     134
     135- Sensor-centric experiments.  E.g., comparing fidelity from Furuno, Raymarine, MA1 (students from Peurto Rico) to focus on ground truth verification and long-term data collection with the UMass trace repository.  Peurto Rico very interested in low-infrastructure radars due to its geography.  Have a PhD student going back to PR, might be a good GEC grant candidate.  Virtualization of these systems might be of great interest to engineering communities, not just networking.  PR is developing a student testbed with tight collaboration with UMass.
     136
     137- Long-distance wireless experiments such as looking at wireless BW over long-distance.  One REU and one UMass undergrad.  Doing experiments now, would like to migrate to GENI.
     138
     139- Longer term vision.  Connect sensed data to cloud-based storage and processing. Run complete experiments: sensing + storage + processing.  BEN is applying for some processing; has a state  project for micro-rain radar
    84140
    85141        12:00           Lunch
    86142
    87143        1:00            Kansei project  [http://groups.geni.net/geni/wiki/KanseiSensorNet  ] [http://groups.geni.net/geni/attachment/wiki/ClusterDMtg070209/KanseiGenie-Spiral1Status-Spiral2Plans%280.3%29.pptx?format=raw  slides](Anish Aurora, Rajiv Ramnath, Hongwei Zhang)
     144
     145Challenges
     146
     147* NSF doesn't have a way to pay for operations costs. Might want to have a workshop or other organized forum educate CISE on operations costs.
     148
     149
    88150
    89151        1:30            Measurement project  [http://groups.geni.net/geni/wiki/Embedded%20Real-Time%20Measurements  wiki] [http://groups.geni.net/geni/attachment/wiki/ClusterDMtg070209/ClusterD_ERM_final.ppt  slides] (Keren Bergman, Franz Fidler)