Changes between Version 11 and Version 12 of GEC19Agenda/CodingSprintTutoring


Ignore:
Timestamp:
06/20/14 10:50:20 (10 years ago)
Author:
griff@netlab.uky.edu
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • GEC19Agenda/CodingSprintTutoring

    v11 v12  
    127127     - The SCS requires a patch before it can handle this
    128128    - Currently, you cannot make such a LAN stitched later - you must request the stitched circuit at the same time, so that the VLAN tag comes from the pool of stitched VLAN tags.
     129 * '''Topic: Swapping Slices Out'''
     130  - Emulab had a facility to "swap and experiment out" so that its resources could be reused by other experiments
     131   - Running applications/service in the experiment would be lost.
     132   - However, the experiment could be swapped back in at a later date.
     133   - After swapping in, all the resources and files would be restored to their pre-swap status.
     134   - You were not guaranteed to get the same resources again.
     135  - A similar facility would be nice for GENI slices
     136   - Swapping in/out is nice if the user is not working in their slice continually
     137    - Setting up an experiment is often time consuming.  Being able to restore the state of a swapped experiment can save a lot of setup time.
     138   - GENI users are often frustrated (and surprised) by the fact that their slice expired and deleted all their resources (and files)
     139  - Issues: (While everyone saw the value of such a service, several issues were raised).
     140   - What entity is resposible for swapping the slice out?  What entity is responsible for swapping a slice in?
     141   - Where will the state be stored while it is swapped out.
     142   - Many experiments require specific resources (or resources from specific aggregates).  What happens if those resources are not available at swap in time?
     143   - How does the swap in process know how/where to restore state?
     144   - We can't restart processes that were running, can we?
     145   - To prevent a user from loosing state when their slice is about to expire, should the system automatically swap it out for them?
     146  - Alternatives:
     147   - Can the user just save their state away?  Because running processes/services do not survive swap out/in, a GENI swap mechanism would only be saving the state which the user can do themselves.
     148   - Can we write scripts that save user state away for users?
     149   - Instead of swapping a user's experiment before it expires, why not just extend the expiration time?  (This defeats the purpose of an expiration time).
     150  - No conclusions were reached and the topic was tabled for now.
     151