Project

General

Profile

Statistics
| Revision:

root / branches / 1.1 / src / haizea / core / scheduler @ 826

Name Size Revision Age Author Comment
  preparation_schedulers 826 almost 14 years Borja Sotomayor Not sure why this was commented out (maybe a st...
__init__.py 3.78 KB 726 over 14 years Borja Sotomayor Plugging a few more potential memory leaks (exp...
lease_scheduler.py 42 KB 825 almost 14 years Borja Sotomayor Extra logging
mapper.py 26 KB 788 over 14 years Borja Sotomayor Pushing a bunch of minor changes.
policy.py 13.3 KB 818 almost 14 years Borja Sotomayor - Modified LWF generator so it won't have an em...
resourcepool.py 16.7 KB 807 almost 14 years Borja Sotomayor Minor fixes
slottable.py 58.2 KB 824 almost 14 years Borja Sotomayor Not entirely sure what's the root of this, but ...
vm_scheduler.py 76.2 KB 818 almost 14 years Borja Sotomayor - Modified LWF generator so it won't have an em...

Latest revisions

# Date Author Comment
826 07/09/2010 05:07 PM Borja Sotomayor

Not sure why this was commented out (maybe a stopgap measure?) but it shouldn't be commented out.
825 07/09/2010 05:06 PM Borja Sotomayor

Extra logging
824 07/09/2010 04:32 PM Borja Sotomayor

Not entirely sure what's the root of this, but when using image transfers the availability window doesn't seem to get properly cached. This fix seems to shave ~30% off the time it takes to run the simulations that involve image transfers.
823 07/08/2010 04:55 PM Borja Sotomayor

Preparation scheduling for AR leases was broken. THere were cases when it would schedule an image transfer that was actually infeasible.
822 07/08/2010 04:55 PM Borja Sotomayor

Preparation scheduling for AR leases was broken. THere were cases when it would schedule an image transfer that was actually infeasible.
821 07/08/2010 04:54 PM Borja Sotomayor

Since preparation scheduling can result in an infeasible lease, preemptions should be done after the preparation has been scheduled.
818 07/04/2010 11:37 AM Borja Sotomayor

- Modified LWF generator so it won't have an empty ramp-up period.
- Minor fixes here and there.
817 06/28/2010 07:40 PM Borja Sotomayor

Fixed bug when determining the "first start" of a VMRR. Shouldn't include the migration RRs.
816 06/25/2010 07:28 PM Borja Sotomayor

Fix bug in availability window optimization
815 06/25/2010 06:06 PM Borja Sotomayor

Fixed some bugs in optimization. Added a flag to turn it off (albeit in a kludgy way), because otherwise the slottable unit tests get confused.

View revisions

Also available in: Atom