fee4ccf154
Prevent side effect modification of select options when preferred nodes are set
2018-01-31 09:56:53 -06:00
031c566ada
Reschedule previous allocs and track their reschedule attempts
2018-01-31 09:56:53 -06:00
52e9946da9
Implemented SetPrefferingNodes in stack
2016-08-30 16:17:50 -07:00
5018f5dd1e
Only interpret vars wrapped in braces
2016-02-04 17:26:46 -08:00
0d55fb2bdd
Add benchmark
2016-01-26 15:16:43 -08:00
2b7d42bf9b
FeasibilityWrapper uses computed node class eligibility to call feasibility checks minimally
2016-01-26 15:16:43 -08:00
5f0c30b926
Skip unreliable time measurement assertions on Windows.
2015-12-09 14:55:57 -05:00
d9b78ffdfe
Remove base nodes from stack constructors
2015-10-16 17:05:23 -07:00
494244ed06
System scheduler and system stack
2015-10-14 18:39:44 -07:00
b213462cb4
Change CPU from float64 to int
2015-09-23 11:14:32 -07:00
4333b7370b
scheduler: recompute scan limit on SetNodes
2015-09-11 12:03:41 -07:00
4a348cc0da
scheduler: allow updating the base nodes
2015-09-07 11:30:13 -07:00
96cb220ff4
Update references to "os" to use "kernel.name"
...
This brings test code and mocks up to date with the fingerprinter. This was a slightly larger change than I anticipated, but I think it's good for two reasons:
1. More semanitcally correct. `os.name` is something like "Windows 10 Pro" or "Ubuntu", while `kernel.name` is "windows" or "linux". `os.version` and `kernel.version` match these semantics.
2. `kernel.name` is much easier to grep for than `os`, which is helpful because oracle can't help us with strings.
2015-08-28 01:30:47 -07:00
0b1d096f87
scheduler: adding minor specialization for batch
2015-08-13 22:35:48 -07:00
e3f769f0ad
scheduler: test all the metrics
2015-08-13 21:58:55 -07:00
b290aac24f
scheduler: testing service stack
2015-08-13 21:55:37 -07:00
be4cd4d8a4
scheduler: adding tests
2015-08-13 18:51:08 -07:00
Preetha Appan