Raylet task dispatch and throttling worker startup (#1912)

* separate task placement and task dispatch; throttle task dispatch with locally available resournces

* keep track of worker's being started/in flight and suppress starting extraneous workers

* cleanup comments

* remove early termination in task dispatch to support zero-resource actor tasks

* info -> debug

* add documentation

* linting

* mock the worker pool for testing

* some linting

* kill all workers in flight; clear the worker pool in dtor

* remove fixed todo

* lint
This commit is contained in:
Alexey Tumanov
2018-04-18 10:58:11 -07:00
committed by Stephanie Wang
parent 0728d4719b
commit 1c965fcfeb
8 changed files with 147 additions and 32 deletions
+1 -1
View File
@@ -306,7 +306,7 @@ def stop():
subprocess.call(
[
"killall global_scheduler plasma_store plasma_manager "
"local_scheduler raylet"
"local_scheduler raylet raylet_monitor"
],
shell=True)