Justin Santa Barbara
f9a6ac077e
Ubernetes Lite: Volumes can dictate zone scheduling
...
For AWS EBS, a volume can only be attached to a node in the same AZ.
The scheduler must therefore detect if a volume is being attached to a
pod, and ensure that the pod is scheduled on a node in the same AZ as
the volume.
So that the scheduler need not query the cloud provider every time, and
to support decoupled operation (e.g. bare metal) we tag the volume with
our placement labels. This is done automatically by means of an
admission controller on AWS when a PersistentVolume is created backed by
an EBS volume.
Support for tagging GCE PVs will follow.
Pods that specify a volume directly (i.e. without using a
PersistentVolumeClaim) will not currently be scheduled correctly (i.e.
they will be scheduled without zone-awareness).
2015-12-31 12:27:01 -05:00
mqliang
e58eae313e
move filter logic to list&watch client
2015-12-22 19:32:18 +08:00
David Oppenheimer
7851d24d04
Merge pull request #18466 from xiang90/pod_fits
...
scheduler: clean up PodFitsResources
2015-12-18 22:11:05 -08:00
Brendan Burns
0ee0e16bcd
Don't recreate the same map 3 times
2015-12-16 20:39:28 -08:00
Justin Santa Barbara
cd433c974f
Zone-scheduler: Fixes per code-review
2015-12-13 20:34:01 -05:00
Justin Santa Barbara
6aa16c744b
When scheduling, spread between zones if labeled
...
We already spread across nodes; we modify this spreading preference to
spread across zones when nodes are labeled with zone information.
2015-12-13 20:34:01 -05:00
Xiang Li
d8c6e6dc4e
scheduler: clean up PodFitsResources
2015-12-09 13:24:54 -08:00
jiangyaoguo
f4c5d00b0c
Implement a cachedNodeInfo in predicates
2015-11-27 21:49:14 +08:00
Ravi Gadde
cadc24e9fd
Scheduler extension
2015-11-25 08:19:27 -08:00
Aaron Crickenberger
fad1968023
Adjust V level for scheduler messages
...
The "Combined requested resources" message becomes excessive as
the cluster fills up, drop it down to V(2)
Put an explicit V(2) on the only other scheduler Infof call that didn't
have V specified already.
2015-11-19 15:12:13 -05:00
k8s-merge-robot
986dd3ea49
Merge pull request #15956 from rootfs/no-disk-conflict
...
Auto commit by PR queue bot
2015-11-12 01:27:39 -08:00
Huamin Chen
bcbdd44267
rbd NoDiskConflict predicate: review feedback
...
Signed-off-by: Huamin Chen <hchen@redhat.com>
2015-11-02 10:18:39 -05:00
Huamin Chen
1ec9829ddf
replace variable manifest to podSpec to make names unconfusing; update NoDiskConflicts comments
...
Signed-off-by: Huamin Chen <hchen@redhat.com>
2015-10-22 15:39:40 -04:00
Huamin Chen
bd10664851
rbd: support NoDiskConflicts scheduler predicates
...
Signed-off-by: Huamin Chen <hchen@redhat.com>
2015-10-20 14:33:45 -04:00
Daniel Smith
7372e18e02
NO BIG MESSAGES IN N^2 LOGGING
2015-10-19 15:00:41 -07:00
David Oppenheimer
b9cfab87e3
Merge pull request #14724 from HaiyangDING/PodFitsHostPorts
...
Replace PodFitsPorts with PodFitsHostPorts
2015-10-03 12:45:35 -07:00
HaiyangDING
6e11cd6028
Replace PodFitsPorts with PodFitsHostPorts
2015-09-30 15:14:59 +08:00
Piotr Szczesniak
659de4d7d0
Improved logging in scheduler
2015-09-29 15:46:22 +02:00
Wojciech Tyczynski
53ae56f205
Replace "minion" with "node" in bunch of places.
2015-09-14 11:07:11 +02:00
Kris Rousey
ae6c64d9bb
Moving everyone to unversioned client
2015-08-18 10:23:03 -07:00
Robert Bailey
5d58c2ca77
Merge pull request #12718 from HaiyangDING/ChangeLimitToRequest
...
Use request to deal with resource requirement in priority functions.
2015-08-17 13:52:28 -07:00
dinghaiyang
43c2bd72cb
Use resource request instead of resource limit to deal with resource
...
requirement in priority functions.
2015-08-14 17:25:48 +08:00
Jordan Liggitt
cf7a2cdfff
Re-add ServiceSpreadingPriority priority algorithm
2015-08-12 08:39:04 -04:00
dingh
472a66aee1
Update comments.
...
Change limit to request in the comments for CheckPodsExceedingFreeResources()
2015-08-12 17:30:09 +08:00
Kris Rousey
565189f5b8
Correcting all go vet errors
2015-08-11 13:55:37 -07:00
Marek Grabowski
e034712456
Merge pull request #11788 from HaiyangDING/ImproveClarityResource
...
Improve clarity around PodFitsResource(issue#11453)
2015-08-10 09:56:32 +02:00
Satnam Singh
bee48f4ce5
Merge pull request #12035 from AnanyaKumar/requests
...
Add support for request
2015-08-07 14:27:34 -07:00
Jerzy Szczepkowski
d6dab28b96
Revert "Move prioritizer function EqualPriority to package priorities"
2015-08-07 15:51:26 +02:00
dinghaiyang
dab7280ae4
Improve clarity around PodFitsResource by showing pods limits in kubectl describe node
2015-08-07 16:58:11 +08:00
dinghaiyang
ebbcd4a3ba
Move prioritizer function EqualPriority to package priorities
2015-08-07 09:56:54 +08:00
Ananya Kumar
ef1e576810
Add support for request
2015-08-05 19:00:19 -07:00
Mike Danese
17defc7383
run gofmt on everything we touched
2015-08-05 17:52:56 -07:00
Mike Danese
8e33cbfa28
rewrite go imports
2015-08-05 17:30:03 -07:00
gmarek
94eb52de33
Add spreading by controllers
2015-07-31 16:28:50 +02:00
Vish Kannan
c60238921f
Merge pull request #11051 from nak3/AWSElasticBlockStore
...
Update comment about NoDiskConflict predicate
2015-07-23 17:49:37 -07:00
Wojciech Tyczynski
d30704af87
Merge pull request #11682 from nak3/priorities-fix
...
Remove unused argument from fractionOfCapacity()
2015-07-23 12:57:22 +02:00
Kenjiro Nakayama
a176001aa1
Fix calculation comment for LeastRequestedPriority
2015-07-22 17:18:19 +09:00
Kenjiro Nakayama
5d3958ff64
Remove unused argument from fractionOfCapacity()
2015-07-22 15:43:50 +09:00
Kenjiro Nakayama
78a8d287e9
Comment update
2015-07-10 21:11:15 +09:00
gmarek
b25c97bca4
Add more logging to scheduler predicates to help debugging max_pods e2e test flakyness
2015-07-08 10:48:50 +02:00
David Oppenheimer
bdf22e3121
Increase zero-limit pod RAM for spreading to 200 MB to match cluster
...
addon pods and represent less trivial fraction of typical machine RAM
(e.g. n1-standard-1).
2015-07-07 13:48:57 -07:00
David Oppenheimer
2e3f2ea20b
gofmt
2015-07-05 21:31:54 -07:00
David Oppenheimer
9fbccb4ff7
Respond to review comments.
2015-07-05 15:41:52 -07:00
David Oppenheimer
4ea8b8a66d
Get rid of separate DumbSpreading function and just treat zero-limit
...
pods as having a constant non-zero memory and CPU limit.
2015-07-05 11:39:35 -07:00
David Oppenheimer
44ed229069
Foo.
2015-07-03 01:40:00 -07:00
David Oppenheimer
53518e37a6
Add a test for DumbSpreadingPriority.
2015-07-03 01:34:07 -07:00
David Oppenheimer
cb9d515004
Add DumbSpreadingPriority, which tries to spread pods across nodes.
2015-07-03 00:45:54 -07:00
Brendan Burns
97634c7fbf
Fix the scheduler to ignore terminated pods.
2015-06-10 14:38:08 -07:00
Daniel Smith
32caedd882
Demote log spam
...
These messages are only useful if you want to debug a particular
scheduler assigment, and they are extremely verbose-- they each print
out a line per host per assignment. Let's try to keep our log messages
linear in the number of assigments.
2015-06-04 14:08:11 -07:00
Jonathan Wills
882462ad87
Change isVolumeConflict so read-only gce persistent disks don't conflict with each other
2015-06-01 08:13:48 -04:00
