Consodiate CI Python tests and fix bug about multiple ray.init (#4195)

.travis.yml

@@ -158,12 +158,8 @@ script:
 
   # ray tune tests
   - python python/ray/tune/test/dependency_test.py
-  - python -m pytest -v --durations=10 python/ray/tune/test/trial_runner_test.py
-  - python -m pytest -v --durations=10 python/ray/tune/test/trial_scheduler_test.py
-  - python -m pytest -v --durations=10 python/ray/tune/test/experiment_test.py
-  - python -m pytest -v --durations=10 python/ray/tune/test/tune_server_test.py
-  - python -m pytest -v --durations=10 python/ray/tune/test/ray_trial_executor_test.py
-  - python -m pytest -v --durations=10 python/ray/tune/test/automl_searcher_test.py
+  # `cluster_tests.py` runs on Jenkins, not Travis.
+  - python -m pytest -v --durations=30 --ignore=python/ray/tune/cluster_tests.py python/ray/tune/test
 
   # ray rllib tests
   - python python/ray/rllib/test/test_catalog.py
@@ -171,53 +167,10 @@ script:
   - python python/ray/rllib/test/test_optimizers.py
   - python python/ray/rllib/test/test_evaluators.py
 
-  # streaming library tests
-  - python -m pytest -v --durations=10 python/ray/tests/test_batched_queue.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_logical_graph.py
-
+  # ray tests
   # Python3.5+ only. Otherwise we will get `SyntaxError` regardless of how we set the tester.
   - python -c 'import sys;exit(sys.version_info>=(3,5))' || python -m pytest -v --durations=10 python/ray/experimental/test/async_test.py
-
-  # ray tests
-  # TODO(williamma12): We cannot use pytests built-in test discovery because
-  # it causes a lot of the tests to fail on travis' apple builds even though
-  # it runs without issue on an apple build locally.
-  - python -m pytest -v --durations=10 python/ray/tests/test_global_state.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_queue.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_ray_init.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_mini.py
-
-  - python -m pytest -v --durations=10 python/ray/tests/test_basic.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_array.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_actor.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_autoscaler.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_tensorflow.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_failure.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_microbenchmarks.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_stress.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_component_failures.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_multi_node.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_multi_node_2.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_recursion.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_monitors.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_cython.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_credis.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_node_manager.py
-  - python -m pytest -v --durations=10 python/ray/tests/test_signal.py
-  # TODO(yuhguo): object_manager_test.py requires a lot of CPU/memory, and
-  # better be put in Jenkins. However, it fails frequently in Jenkins, but
-  # works well in Travis. We should consider moving it back to Jenkins once
-  # we figure out the reason.
-  - python -m pytest -v --durations=10 python/ray/tests/test_object_manager.py
-
-  # ray temp file tests
-  - python -m pytest -v --durations=10 python/ray/tests/test_tempfile.py
-
-  # ray debug tools tests
-  - python -m pytest -v --durations=10 python/ray/tests/test_debug_tools.py
-
-  # modin test files
-  - python -m pytest -v --durations=10 python/ray/tests/test_modin.py
+  - python -m pytest -v --durations=30 python/ray/tests
 deploy:
   - provider: s3
     access_key_id: AKIAJ2L7XDUSZVTXI5QA

python/ray/remote_function.py

@@ -57,9 +57,11 @@ class RemoteFunction(object):
         self._function_signature = ray.signature.extract_signature(
             self._function)
 
-        # # Export the function.
+        # Export the function.
         worker = ray.worker.get_global_worker()
         worker.function_actor_manager.export(self)
+        # In which session this function was exported last time.
+        self._last_export_session = worker._session_index
 
     def __call__(self, *args, **kwargs):
         raise Exception("Remote functions cannot be called directly. Instead "
@@ -97,6 +99,13 @@ class RemoteFunction(object):
         """An experimental alternate way to submit remote functions."""
         worker = ray.worker.get_global_worker()
         worker.check_connected()
+
+        if self._last_export_session < worker._session_index:
+            # If this function was exported in a previous session, we need to
+            # export this function again, because current GCS doesn't have it.
+            self._last_export_session = worker._session_index
+            worker.function_actor_manager.export(self)
+
         kwargs = {} if kwargs is None else kwargs
         args = ray.signature.extend_args(self._function_signature, args,
                                          kwargs)

python/ray/tests/test_object_manager.py

@@ -13,6 +13,11 @@ import warnings
 import ray
 from ray.tests.cluster_utils import Cluster
 
+# TODO(yuhguo): This test file requires a lot of CPU/memory, and
+# better be put in Jenkins. However, it fails frequently in Jenkins, but
+# works well in Travis. We should consider moving it back to Jenkins once
+# we figure out the reason.
+
 if (multiprocessing.cpu_count() < 40
         or ray.utils.get_system_memory() < 50 * 10**9):
     warnings.warn("This test must be run on large machines.")

python/ray/worker.py

@@ -161,6 +161,9 @@ class Worker(object):
         # This event is checked regularly by all of the threads so that they
         # know when to exit.
         self.threads_stopped = threading.Event()
+        # Index of the current session. This number will
+        # increment every time when `ray.shutdown` is called.
+        self._session_index = 0
 
     @property
     def task_context(self):
@@ -2064,6 +2067,7 @@ def disconnect():
         if hasattr(worker, "logger_thread"):
             worker.logger_thread.join()
         worker.threads_stopped.clear()
+        worker._session_index += 1
 
     worker.connected = False
     worker.cached_functions_to_run = []