1 / 5

Experiences with the ProtoGENI Control Framework

Experiences with the ProtoGENI Control Framework. Guilherme Fernandes fernande@cis.udel.edu. RSpec / “Reflection”. Using extensions is a good way to annotate nodes with experiment/system specific information How to access this information from the nodes? Only owner has access to manifest

Download Presentation

Experiences with the ProtoGENI Control Framework

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Experiences with the ProtoGENI Control Framework Guilherme Fernandes fernande@cis.udel.edu

  2. RSpec / “Reflection” • Using extensions is a good way to annotate nodes with experiment/system specific information • How to access this information from the nodes? • Only owner has access to manifest • Simpler yet, how can a node ask “which slice am I a part of?”, or “who is the owner of this slice?”

  3. AA • How to handle the case of automated services (i.e. there’s no user certificate)? • If other services only accept authenticated users, service-to-service communication also needs certificates • If certificates are created, they need to be pushed.. how? • In our case, services should be slice ‘restrained’.. • urn:…+emulab.net+services+lamp@lampdemo

  4. Callbacks? • With global services that work with all slices, it would be good to have callbacks for events on the slice/sliver

  5. Dedicated Dev. Environment • 7 VirtualBox VMs: CH, boss, ops, 4 nodes • Nodes really only limited by memory/disk/cpu • BUT Emulab busy waits (100% cpu) • Virtual switching by Open vSwitch (Linux) • Kind of hacked right now because of issues like Emulab only accepting port numbers (OVS uses UUIDs/port names) or OVS not having a VLAN table to store names • Some issues with Vbox PXE booting and kernel drivers on MFS images, but isn’t too hard to setup

More Related