95aec091e4
### What changes were proposed in this pull request? As part of the Stage level scheduling features, add the Python api's to set resource profiles. This also adds the functionality to properly apply the pyspark memory configuration when specified in the ResourceProfile. The pyspark memory configuration is being passed in the task local properties. This was an easy way to get it to the PythonRunner that needs it. I modeled this off how the barrier task scheduling is passing the addresses. As part of this I added in the JavaRDD api's because those are needed by python. ### Why are the changes needed? python api for this feature ### Does this PR introduce any user-facing change? Yes adds the java and python apis for user to specify a ResourceProfile to use stage level scheduling. ### How was this patch tested? unit tests and manually tested on yarn. Tests also run to verify it errors properly on standalone and local mode where its not yet supported. Closes #28085 from tgravescs/SPARK-29641-pr-base. Lead-authored-by: Thomas Graves <tgraves@nvidia.com> Co-authored-by: Thomas Graves <tgraves@apache.org> Signed-off-by: HyukjinKwon <gurwls223@apache.org>
73 lines
2.9 KiB
Python
73 lines
2.9 KiB
Python
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
# this work for additional information regarding copyright ownership.
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
# (the "License"); you may not use this file except in compliance with
|
|
# the License. You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
from pyspark.resource.taskrequests import TaskResourceRequest
|
|
from pyspark.resource.executorrequests import ExecutorResourceRequest
|
|
|
|
|
|
class ResourceProfile(object):
|
|
|
|
"""
|
|
.. note:: Evolving
|
|
|
|
Resource profile to associate with an RDD. A :class:`pyspark.resource.ResourceProfile`
|
|
allows the user to specify executor and task requirements for an RDD that will get
|
|
applied during a stage. This allows the user to change the resource requirements between
|
|
stages. This is meant to be immutable so user doesn't change it after building.
|
|
|
|
.. versionadded:: 3.1.0
|
|
"""
|
|
|
|
def __init__(self, _java_resource_profile=None, _exec_req={}, _task_req={}):
|
|
if _java_resource_profile is not None:
|
|
self._java_resource_profile = _java_resource_profile
|
|
else:
|
|
self._java_resource_profile = None
|
|
self._executor_resource_requests = _exec_req
|
|
self._task_resource_requests = _task_req
|
|
|
|
@property
|
|
def id(self):
|
|
if self._java_resource_profile is not None:
|
|
return self._java_resource_profile.id()
|
|
else:
|
|
raise RuntimeError("SparkContext must be created to get the id, get the id "
|
|
"after adding the ResourceProfile to an RDD")
|
|
|
|
@property
|
|
def taskResources(self):
|
|
if self._java_resource_profile is not None:
|
|
taskRes = self._java_resource_profile.taskResourcesJMap()
|
|
result = {}
|
|
for k, v in taskRes.items():
|
|
result[k] = TaskResourceRequest(v.resourceName(), v.amount())
|
|
return result
|
|
else:
|
|
return self._task_resource_requests
|
|
|
|
@property
|
|
def executorResources(self):
|
|
if self._java_resource_profile is not None:
|
|
execRes = self._java_resource_profile.executorResourcesJMap()
|
|
result = {}
|
|
for k, v in execRes.items():
|
|
result[k] = ExecutorResourceRequest(v.resourceName(), v.amount(),
|
|
v.discoveryScript(), v.vendor())
|
|
return result
|
|
else:
|
|
return self._executor_resource_requests
|