Changes between Version 2 and Version 3 of Internal/Xen


Ignore:
Timestamp:
Oct 16, 2006, 4:31:39 AM (18 years ago)
Author:
anonymous
Comment:

—

Legend:

Unmodified
Added
Removed
Modified

  • Internal/Xen

    v2 v3  
    1 All these ideas are young and rough (9/28/2006).
     1= What is Xen? =
    22
    3 http://www.xensource.com
     3Please see http://www.xensource.com
     4
     5= Xen Hardware Support =
     6
     7Xen won't run on the VIA processors in the present (10/2006) implementation of ORBIT.
    48
    59= Potential Uses in Scheduling ORBIT =
    … …  
    1721Simultaneous experiments, or host preparations for the next experiment during the current experiment, mean experiments may no longer run in real time.  Granted, there is no hard real time scheduling in the operating systems running on the current nodes, but so long as the nodes are relatively unloaded they will probably run experiments fast enough so that you'll see similar performance as in the sandbox.  Delays from the ORBIT scheduler may become intolerable.
    1822
    19 There is no clear complete inventory of resources which need to be virtualized.  For example, ESSID?
     23We will always want to support a class of experiments at the physical layer of the network, which by definition may not be virtualized.
    2024
    21 There are broader issues with scheduling ORBIT experiments.  There is no way to detect when a particular experiment has failed.  Often an experiment that runs on two nodes in a sandbox has significant problems when it hits the grid, and the experimenter needs interactive access.
     25There are broader issues with scheduling ORBIT experiments.  There is no way to detect when a particular experiment has failed.  Often an experiment that runs on two nodes in a sandbox has significant problems when it hits the grid, and the experimenter needs interactive access for the first few full-grid sessions.