github/kubernetes
4
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
83,135 Commits 1 Branch 31 Tags 1,019 MiB
89cb15b5de
Commit Graph

142 Commits

Author SHA1 Message Date
Ted Yu
89a70fa407 Handle pod addition / removal errors 2019-09-06 16:25:11 -07:00
Guoliang Wang
d84a75c140 Fix filter plugins are not been called during preemption 2019-09-06 09:59:01 +08:00
Kubernetes Prow Robot
b33968972b
Merge pull request #82034 from alculquicondor/feat/unschedulable_unresolvable 
[Framework] Add UnschedulableAndUnresolvable status code
 2019-08-30 11:20:57 -07:00
Aldo Culquicondor
3c1f8a8c4e [Framework] Add UnschedulableAndUnresolvable status code 
The status can be used by (Pre)Filter plugins to indicate that
preemption wouldn't change the decision of the filter.

Signed-off-by: Aldo Culquicondor <acondor@google.com>
 2019-08-28 10:10:47 -04:00
Kubernetes Prow Robot
e57bee7332
Merge pull request #81840 from draveness/feature/move-node-info-snapshot-to-framework 
feat(scheduler): move node info snapshot out of internal package
 2019-08-26 16:42:54 -07:00
Kubernetes Prow Robot
4680ec8fde
Merge pull request #81346 from mrkm4ntr/fits-on-node-fast-path 
Add fast path to podFitsOnNode
 2019-08-23 15:48:26 -07:00
draveness
ffef11f768 feat(scheduler): move node info snapshot out of internal package 2019-08-23 22:32:16 +08:00
draveness
f3816fb757 feat: use PreFilter instead of Prefilter in the scheduling framework 2019-08-23 02:09:00 +08:00
Shintaro Murakami
acd82613ef Add fast path to podFitsOnNode 
Add test
 2019-08-22 17:21:00 +09:00
Kubernetes Prow Robot
90df64b75b
Merge pull request #81614 from liu-cong/score-refactor 
Move RunNormalizeScorePlugins and ApplyScoreWeights into RunScorePlugins; Also add unit tests for RunScorePlugins.
 2019-08-21 10:37:29 -07:00
Cong Liu
e50a24d64c Move RunNormalizeScorePlugins and ApplyScoreWeights into RunScorePlugins; Also add unit tests for RunScorePlugins. 2019-08-20 13:18:32 -04:00
Wei Huang
8f559ea53b
Optimize internal data structure of EvenPodsSpread 
- Rename 'topologyPairsPodSpreadMap' to 'podSpreadCache'
- New struct `criticalPaths criticalPaths`
- Add unified method `*criticalPaths.update()` for:
    - regular update
    - addPod in preemption case
    - remotePod in preemption case
 2019-08-20 09:26:41 -07:00
Kubernetes Prow Robot
1906650d92
Merge pull request #80901 from draveness/feature/use-map-instead-of-array 
feat: use named array instead of array in normalizing score
 2019-08-14 03:28:25 -07:00
Shintaro Murakami
11f043c784 Remove algorithm.NodeLister from scheduler interface 
Will fixup
 2019-08-13 10:30:30 +09:00
draveness
aa5f9fda52 feat: use named array instead of score array in normalizing score 2019-08-08 08:19:49 +08:00
Joe Betz
46a04d50af Replace string concatination with trace fields 2019-08-05 12:18:57 -07:00
draveness
feb64858aa feat: implement "post-filter" extension point for scheduling framework 2019-08-02 10:12:54 +08:00
Kubernetes Prow Robot
aaad4c4afa
Merge pull request #80533 from alculquicondor/refactor/find_nodes 
Query nodes in Schedule only when there are no predicates
 2019-08-01 13:38:28 -07:00
Kubernetes Prow Robot
ac1cde5577
Merge pull request #78009 from hainesc/develop 
Use reservoir sampling to select one host from priority list
 2019-08-01 00:52:15 -07:00
Cong Liu
34373662d3 Add NormalizeScore extension point for scheduler framework. 2019-07-30 20:02:13 -04:00
Aldo Culquicondor
e703226522 Optimize Schedule by querying nodes only when needed. 
Signed-off-by: Aldo Culquicondor <acondor@google.com>
 2019-07-25 08:24:05 -04:00
Kubernetes Prow Robot
cbae6ed036
Merge pull request #80220 from alculquicondor/refactor/scheduler-cache 
Use scheduler cache in affinity priority functions
 2019-07-24 13:50:06 -07:00
Aldo Culquicondor
f58abdf966 Use scheduler cache in affinity priority functions 
Make the cache implement NodeLister and expose it to the priority
functions. This way, the priority functions make use of a single cache,
the scheduler's, instead of mixing it with the lister's caches.

Signed-off-by: Aldo Culquicondor <acondor@google.com>
 2019-07-23 22:10:49 -04:00
Youbing Li
7f9dd949e0 The implementation of Filter extension for the new framework 2019-07-17 03:28:30 -04:00
Abdullah Gharaibeh
c54c4d1962 Score plugin for the scheduling framework. 2019-07-16 09:38:37 -04:00
Jianfei Bai
95bd52cfe9 Trace step should be at the end of calls rather than the begin. 2019-07-08 16:54:04 +08:00
Abdullah Gharaibeh
a61a437ef2 prefilter extension point implementation. 2019-06-10 17:01:50 -04:00
ahg-g
ece3e3cdba
Revert "Faster scheduler" 2019-06-06 22:34:18 -04:00
wangqingcan
52f3380ef3 change preempting to PreemptionPolicy 2019-05-31 12:42:05 +08:00
wangqingcan
5c9438c691 non-preempting-priorityclass 
Co-authored-by: Vallery Lancey <vallery@zeitgeistlabs.io>
Co-authored-by: Tan shanshan <tan.shanshan@zte.com.cn>
 2019-05-31 12:37:07 +08:00
Haines Chan
f977863f70 Use reservoir sampling to select one host from priority list 2019-05-27 22:25:58 +08:00
Abdullah Gharaibeh
e660e84459 Faster scheduler. 2019-05-08 09:49:01 -04:00
Bobby (Babak) Salamat
404dc1ed79 Update scheduler framework plugins to align with the latest changes to the framework design 2019-04-29 16:40:56 -07:00
Jun Gong
49832cf887 Save pod priority to avoid repeated calculation 2019-04-11 11:09:47 +08:00
Kubernetes Prow Robot
fdeedf4431
Merge pull request #75911 from marsno1/fix-forloop-in-preemption 
Improve for-loop in nodesWherePreemptionMightHelp function
 2019-04-09 11:21:01 -07:00
madianjun
d84a8c563e Improve for-loop in nodesWherePreemptionMightHelp function 2019-04-09 15:24:50 +08:00
Kubernetes Prow Robot
1ac4cc7980
Merge pull request #75703 from tedyu/master 
Simplify the loop for latest start time in pickOneNodeForPreemption
 2019-04-01 13:18:58 -07:00
Jun Gong
042b83ba73 Pick pods for preemption based on StartTime of pods when priorities are equal 2019-03-26 09:04:50 +08:00
Ted Yu
dbdc782412 Simplify the loop for latest start time in pickOneNodeForPreemption 2019-03-25 15:53:03 -07:00
Kubernetes Prow Robot
057ad6d4ce
Merge pull request #75571 from Huang-Wei/shorten-alias 
shorten scheduler package alias for better readability
 2019-03-22 02:34:17 -07:00
Wei Huang
49346c1e04
shorten scheduler package alias for better readability 
- schedulerinternalcache -> internalcache
 2019-03-21 18:14:19 -07:00
Jun Gong
2755373470 Avoid unnecessary sort for some cases in selectVictimsOnNode 2019-03-20 17:52:37 +08:00
Kubernetes Prow Robot
8592098e60
Merge pull request #74974 from goodluckbot/pick-node-preempt-start-time 
Pick node for preemption based on start time of pods
 2019-03-19 21:26:49 -07:00
goodluckbot
8d991e6ee2 Pick node for preemption based on start time of pods 2019-03-12 12:30:15 +08:00
Bobby (Babak) Salamat
a1b8777d42 Revert "Merge pull request #73934 from bsalamat/num_cpu" 
This reverts commit cfe4ca8012, reversing
changes made to f16035600a.
 2019-03-04 13:14:25 -08:00
Kubernetes Prow Robot
cfe4ca8012
Merge pull request #73934 from bsalamat/num_cpu 
Use runtime.NumCPU() instead of a fixed value for parallel scheduler threads
 2019-03-01 23:04:17 -08:00
danielqsj
f7b437cae0 convert latency in mertics name to duration 2019-02-22 21:40:13 +08:00
Bobby (Babak) Salamat
e0ad271891 Optimize scheduler cache snapshotting using an MRU structure. 2019-02-20 13:38:37 -08:00
Bobby (Babak) Salamat
d0ebeefbc4 Use runtime.NumCPU() instead of a fixed value for parallel scheduler threads. 2019-02-11 13:37:30 -08:00
Andrew Kim
93b086f6ea replace k8s.io/apiserver/pkg/util/trace with k8s.io/utils/trace 2019-01-24 15:34:21 -05:00