Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

modify ray_cluster master settings to accept and pass on runtime_env #420

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

modify ray_cluster master settings to accept and pass on runtime_env #420

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
315efde
modify _set_up_master to accept and pass on runtime_env
g-clef Jan 24, 2025
676d028
fix linting
g-clef Jan 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 13 additions & 5 deletions python/raydp/spark/ray_cluster.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,8 @@ def __init__(self,
executor_cores,
executor_memory,
enable_hive,
configs):
configs,
runtime_env=None):
super().__init__(None)
self._app_name = app_name
self._spark_master = None
Expand All @@ -49,24 +50,31 @@ def __init__(self,
self._enable_hive = enable_hive
self._configs = configs
self._prepare_spark_configs()
self._set_up_master(resources=self._get_master_resources(self._configs), kwargs=None)
self._set_up_master(resources=self._get_master_resources(self._configs),
runtime_env=runtime_env)
self._spark_session: SparkSession = None

def _set_up_master(self, resources: Dict[str, float], kwargs: Dict[Any, Any]):
def _set_up_master(self, resources: Dict[str, float], runtime_env: Dict[Any, Any]):
# TODO: specify the app master resource
spark_master_name = self._app_name + RAYDP_SPARK_MASTER_SUFFIX

if runtime_env is None:
runtime_env = {}

if resources:
num_cpu = 1
if "CPU" in resources:
num_cpu = resources["CPU"]
resources.pop("CPU", None)

self._spark_master_handle = RayDPSparkMaster.options(name=spark_master_name,
num_cpus=num_cpu,
resources=resources) \
resources=resources,
runtime_env=runtime_env) \
.remote(self._configs)
else:
self._spark_master_handle = RayDPSparkMaster.options(name=spark_master_name) \
self._spark_master_handle = RayDPSparkMaster.options(name=spark_master_name,
runtime_env=runtime_env) \
.remote(self._configs)

ray.get(self._spark_master_handle.start_up.remote())
Expand Down
Loading