Patrick Ames
dc51b08c36
[autoscaler] Allow users to disable the cluster config cache ( #8117 )
...
* [autoscaler] Remove autoscaler config cache.
* [autoscaler] Add flag allowing users to explicitly disable the config cache.
2020-07-09 15:47:58 -07:00
Eric Liang
09b9b81ea4
[autoscaler] Move command runners into separate file and clean up interface. ( #9340 )
...
* cleanup
* wip
* fix imports
* fix lint
2020-07-09 15:40:56 -07:00
Zhuohan Li
8a76f4cbb5
[Core] put small objects in memory store ( #8972 )
...
* remove the put in memory store
* put small objects directly in memory store
* cast data type
* fix another place that uses Put to spill to plasma store
* fix multiple tests related to memory limits
* partially fix test_metrics
* remove not functioning codes
* fix core_worker_test
* refactor put to plasma codes
* add a flag for the new feature
* add flag to more places
* do a warmup round for the plasma store
* lint
* lint again
* fix warmup store
* Update _raylet.pyx
Co-authored-by: Eric Liang <ekhliang@gmail.com>
2020-07-09 15:39:40 -07:00
Alex Wu
34b85659d4
[Core] New scheduler fixes ( #9186 )
...
* .
* test_args passes
* .
* test_basic.py::test_many_fractional_resources causes ray to hang
* test_basic.py::test_many_fractional_resources causes ray to hang
* .
* .
* useful
* test_many_fractional_resources fails instead of hanging now :)
* Passes test_fractional_resources
* .
* .
* Some cleanup
* git is hard
* cleanup
* Fixed scheduling tests
* .
* .
2020-07-09 15:37:51 -07:00
Stephanie Wang
0389735d7a
[core] Pass owner address from the workers to the raylet ( #9299 )
...
* Add intended worker ID to GetObjectStatus, tests
* Remove TaskID owner_id
* lint
* Add owner address to task args
* Make TaskArg a virtual class, remove multi args
* Set owner address for task args
* merge
* Fix tests
* Add ObjectRefs to task dependency manager, pass from task spec args
* tmp
* tmp
* Fix
* Add ownership info for task arguments
* Convert WaitForDirectActorCallArgs
* lint
* build
* update
* build
* java
* Move code
* build
* Revert "Fix Google log directory again (#9063 )"
This reverts commit 275da2e400
2020-07-09 14:35:54 -07:00
fangfengbin
62fe403a57
Fix the bug that PollOwnerForActorOutOfScope's reply may be missing ( #9330 )
2020-07-09 17:33:52 +08:00
Kai Yang
fa1eadd61f
fix java worker log dir ( #9352 )
2020-07-09 10:11:03 +08:00
SangBin Cho
9f8ff2e3b1
[Core] GCS Actor Management Race Condition ( #9215 )
...
* GCS Actor management on by default.
* Fix travis config.
* Change condition.
* Finish the initial race condition fix.
* Lint.
* Refine the codebase.
* Finish the initial version
* Improve logic.
* Remove unnecessary log messages.
* Address code review.
* Add tests
* Revert the second race condition that doesn't happen anymore, handle some edge cases. add tests.
* Address the second race condition found.
* Addressed code review.
* Addressed code review.
* Run a new unit test only when gcs actor management is on.
2020-07-08 10:56:52 -07:00
Ian Rodney
9172f8c3a6
[core] Store Internal Config in GCS ( #8921 )
2020-07-08 11:22:08 -05:00
Sven Mika
4da0e542d5
[RLlib] DDPG and SAC eager support (preparation for tf2.x) ( #9204 )
2020-07-08 16:12:20 +02:00
Tao Wang
f395e48031
[GCS] Add integration test for actor info cleaning ( #8900 )
2020-07-08 10:25:08 +08:00
Max Fitton
ca54da66b6
Worker <> GPU Mapping Information in Dashboard ( #9163 )
2020-07-07 18:58:22 -05:00
yncxcw
4ba4110dec
[Core] Make worker_register_timeout_seconds configurable ( #9221 )
2020-07-07 18:27:15 -05:00
SangBin Cho
8f19f1eafb
[Core] Actor handle refactoring ( #8895 )
...
* Marking needed changes.
* Resolve basic dependencies.
* In progress.
* linting.
* In progress 2.
* Linting.
* Refactor done. Cleanup needed.
* Linting.
* Recover kill actor in core worker because it is used inside raylet
* Cleanup.
* Use unique pointer instead. Unit tests are broken now.
* Fix the upstream change.
* Addressed code review 1.
* Lint.
* Addressed code review 2.
* Fix weird github history.
* Lint.
* Linting using clang 7.0.
* Use a better check message.
* Revert cpp stuff.
* Fix weird linting errors.
* Manuall fix all lint issues.
* Update a newline.
* Refactor some interface.
* Addressed all code review.
* Addressed code review
2020-07-07 11:11:41 -07:00
Ian Rodney
f69d8b951e
[core] Disable flaky cancellation test ( #9325 )
2020-07-07 09:52:35 -07:00
Ian Rodney
a1e14380ce
[core] Switch Async Callback to C++ [WIP] ( #9228 )
...
Co-authored-by: simon-mo <simon.mo@hey.com>
2020-07-07 09:47:25 -07:00
Ian Rodney
079c1eaa5c
[autoscaler] Require keyword arguments ( #9256 )
2020-07-06 22:12:59 -07:00
Stephanie Wang
b42d6a1ddc
[core] Refactor task arguments and attach owner address ( #9152 )
...
* Add intended worker ID to GetObjectStatus, tests
* Remove TaskID owner_id
* lint
* Add owner address to task args
* Make TaskArg a virtual class, remove multi args
* Set owner address for task args
* merge
* Fix tests
* Fix
* build
* update
* build
* java
* Move code
* build
* Revert "Fix Google log directory again (#9063 )"
This reverts commit 275da2e400#9063 )""
This reverts commit 4a326fcb148ca09a35bc7de11d89df10edbb56e7.
* lint
2020-07-06 21:25:14 -07:00
Ian Rodney
6fecd3cfce
[autoscaler] Run initialization_commands without a persistent connection ( #9020 )
...
Co-authored-by: Richard Liaw <rliaw@berkeley.edu>
Co-authored-by: Edward Oakes <ed.nmi.oakes@gmail.com>
2020-07-06 16:34:59 -07:00
Richard Liaw
139d21e068
[tune] Docs for tune-sklearn ( #9129 )
...
Co-authored-by: krfricke <krfricke@users.noreply.github.com>
2020-07-06 15:35:10 -07:00
SangBin Cho
557da7044f
Fix flaky test that says ray.init is called twice. ( #9234 )
2020-07-06 15:19:00 -07:00
Ian Rodney
c79a49488c
[Doc] Fixing Wheel Build Command ( #8789 )
2020-07-06 11:17:59 -07:00
ChenZhilei
6f3d993681
GCS server use worker table to handle RegisterWorker instead of redis accessor ( #9168 )
2020-07-06 10:37:25 +08:00
Richard Liaw
b71c912da7
[tune] Fix up examples ( #9201 )
2020-07-05 01:16:20 -07:00
Tao Wang
f7ac495a68
[Core] Use map instead of list to represent resources in heartbeat message ( #9294 )
2020-07-05 10:59:25 +08:00
mehrdadn
28d18ec836
[windows] Improve GPU detection ( #9300 )
...
Co-authored-by: Mehrdad <noreply@github.com>
2020-07-04 13:20:23 -07:00
David Fidalgo
c0ba337fe0
[tune] Add np.bool8 and np.int to allowed HPARAMS types ( #9297 )
2020-07-03 18:34:45 -07:00
mehrdadn
7135cb2aec
Fix .exe file extensions ( #9197 )
...
Co-authored-by: Mehrdad <noreply@github.com>
2020-07-02 15:29:34 -05:00
Simon Mo
a25472c657
[Serve] Fix prometheus exporter label override ( #9227 )
2020-07-02 11:40:14 -07:00
Ian Rodney
f1173d55e0
[autoscaler] Fix cluster_shutdown using wrong args ( #9252 )
2020-07-02 09:34:50 -07:00
SangBin Cho
bfb8a28a3c
Revert "Support accessing underlying attributes in RayTaskErrors ( #9210 )" ( #9263 )
...
This reverts commit 21cad5250a
2020-07-02 08:35:10 -05:00
Sven Mika
c4ccbfdfa9
[RLlib] tf-eager support for ES and ARS (tf2.x preparation). ( #9207 )
2020-07-02 13:03:10 +02:00
fangfengbin
8fcfcc4100
GCS server error handling for actor creation ( #8899 )
2020-07-02 16:27:32 +08:00
Eric Liang
82a5ed3fb5
[autoscaler] Instance type assert fix for non-AWS node providers ( #9223 )
2020-07-01 17:54:20 -07:00
Andrija Djurisic
e0d8b58969
Fix Azure example-gpu.yml ( #9242 )
...
`imageSku` should be string ... otherwise this is the error it shows up:
```
msrestazure.azure_exceptions.CloudError: Azure Error: InvalidTemplate
Message: Deployment template validation failed: 'Template parameter JToken type is not valid. Expected 'String, Uri'. Actual 'Integer'. Please see https://aka.ms/resource-manager-parameter-files for usage details.'.
Additional Information:
Type: TemplateViolation
Info: {
"lineNumber": 1,
"linePosition": 673,
"path": "properties.template.parameters.imageSku"
}
```
2020-07-01 12:02:34 -07:00
Richard Liaw
d35f0e40d0
[tune] Use public methods for trainable ( #9184 )
2020-07-01 11:00:00 -07:00
Edward Oakes
21cad5250a
Support accessing underlying attributes in RayTaskErrors ( #9210 )
2020-07-01 10:49:38 -05:00
Sven Mika
b4c0b942fe
[RLlib] Remove requirement for dataclasses in rllib (not supported in py3.5) ( #9237 )
2020-07-01 17:31:44 +02:00
ChenZhilei
c11855728a
Remove raylet monitor after use GCS service ( #9179 )
2020-07-01 20:01:52 +08:00
Siyuan (Ryans) Zhuang
a1dfcfc893
Add test for Ray outputs ( #9231 )
2020-06-30 23:54:54 -07:00
Ian Rodney
4ce4be5c54
Show actual command in output ( #9224 )
2020-06-30 16:00:28 -07:00
Simon Mo
be647b69ab
[Serve] Performance: Use uvloop when possible ( #9216 )
2020-06-30 15:59:13 -07:00
Edward Oakes
681bae709a
[serve] Add backend config options to docstrings ( #9193 )
2020-06-30 10:53:17 -05:00
Sven Mika
43043ee4d5
[RLlib] Tf2x preparation; part 2 (upgrading try_import_tf()). ( #9136 )
...
* WIP.
* Fixes.
* LINT.
* WIP.
* WIP.
* Fixes.
* Fixes.
* Fixes.
* Fixes.
* WIP.
* Fixes.
* Test
* Fix.
* Fixes and LINT.
* Fixes and LINT.
* LINT.
2020-06-30 10:13:20 +02:00
Ian Rodney
fb074da7c3
[core] Return all GPUs for Local Mode ( #9108 )
2020-06-30 00:55:09 -07:00
mehrdadn
882f60012f
Fix WSL patch (it doesn't fall under "win32") ( #9195 )
2020-06-29 21:00:00 -05:00
krfricke
e0b6984dce
[tune] pytorch lightning template and walkthrough ( #9151 )
...
Co-authored-by: Kai Fricke <kai@anyscale.com>
2020-06-29 16:52:07 -07:00
SangBin Cho
7af6c69672
[Test] Cluster util fix ( #8929 )
2020-06-29 14:15:41 -05:00
Edward Oakes
87e47c4a53
Fix serve dependencies ( #9192 )
2020-06-29 12:44:04 -05:00
mehrdadn
bc140b69cc
Patch WSL psutil bug ( #6808 )
2020-06-29 10:55:43 -05:00
