ray/python/setup.py

171 lines
5.8 KiB
Python
Raw Normal View History

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import re
import shutil
import subprocess
import sys
2016-02-22 17:35:03 -08:00
from setuptools import setup, find_packages, Distribution
import setuptools.command.build_ext as _build_ext
2016-02-07 15:50:02 -08:00
# Ideally, we could include these files by putting them in a
# MANIFEST.in or using the package_data argument to setup, but the
# MANIFEST.in gets applied at the very beginning when setup.py runs
# before these files have been created, so we have to move the files
# manually.
# NOTE: The lists below must be kept in sync with ray/CMakeLists.txt.
ray_files = [
"ray/core/src/ray/thirdparty/redis/src/redis-server",
"ray/core/src/ray/gcs/redis_module/libray_redis_module.so",
"ray/core/src/plasma/plasma_store_server",
"ray/core/src/ray/raylet/liblocal_scheduler_library_python.so",
2018-04-11 10:11:35 -07:00
"ray/core/src/ray/raylet/raylet_monitor", "ray/core/src/ray/raylet/raylet",
"ray/WebUI.ipynb"
]
# These are the directories where automatically generated Python flatbuffer
# bindings are created.
generated_python_directories = [
"ray/core/generated", "ray/core/generated/ray",
"ray/core/generated/ray/protocol"
]
optional_ray_files = []
ray_ui_files = [
"ray/core/src/catapult_files/index.html",
"ray/core/src/catapult_files/trace_viewer_full.html"
]
[autoscaler] GCP node provider (#2061) * Google Cloud Platform scaffolding * Add minimal gcp config example * Add googleapiclient discoveries, update gcp.config constants * Rename and update gcp.config key pair name function * Implement gcp.config._configure_project * Fix the create project get project flow * Implement gcp.config._configure_iam_role * Implement service account iam binding * Implement gcp.config._configure_key_pair * Implement rsa key pair generation * Implement gcp.config._configure_subnet * Save work-in-progress gcp.config._configure_firewall_rules. These are likely to be not needed at all. Saving them if we happen to need them later. * Remove unnecessary firewall configuration * Update example-minimal.yaml configuration * Add new wait_for_compute_operation, rename old wait_for_operation * Temporarily rename autoscaler tags due to gcp incompatibility * Implement initial gcp.node_provider.nodes * Still missing filter support * Implement initial gcp.node_provider.create_node * Implement another compute wait operation (wait_For_compute_zone_operation). TODO: figure out if we can remove the function. * Implement initial gcp.node_provider._node and node status functions * Implement initial gcp.node_provider.terminate_node * Implement node tagging and ip getter methods for nodes * Temporarily rename tags due to gcp incompatibility * Tiny tweaks for autoscaler.updater * Remove unused config from gcp node_provider * Add new example-full example to gcp, update load_gcp_example_config * Implement label filtering for gcp.node_provider.nodes * Revert unnecessary change in ssh command * Revert "Temporarily rename tags due to gcp incompatibility" This reverts commit e2fe634c5d11d705c0f5d3e76c80c37394bb23fb. * Revert "Temporarily rename autoscaler tags due to gcp incompatibility" This reverts commit c938ee435f4b75854a14e78242ad7f1d1ed8ad4b. * Refactor autoscaler tagging to support multiple tag specs * Remove missing cryptography imports * Update quote function import * Fix threading issue in gcp.config with the compute discovery object * Add gcs support for log_sync * Fix the labels/tags naming discrepancy * Add expanduser to file_mounts hashing * Fix gcp.node_provider.internal_ip * Add uuid to node name * Remove 'set -i' from updater ssh command * Also add TODO with the context and reason for the change. * Update ssh key creation in autoscaler.gcp.config * Fix wait_for_compute_zone_operation's threading issue Google discovery api's compute object is not thread safe, and thus needs to be recreated for each thread. This moves the `wait_for_compute_zone_operation` under `autoscaler.gcp.config`, and adds compute as its argument. * Address pr feedback from @ericl * Expand local file mount paths in NodeUpdater * Add ssh_user name to key names * Update updater ssh to attempt 'set -i' and fall back if that fails * Update gcp/example-full.yaml * Fix wait crm operation in gcp.config * Update gcp/example-minimal.yaml to match aws/example-minimal.yaml * Fix gcp/example-full.yaml comment indentation * Add gcp/example-full.yaml to setup files * Update example-full.yaml command * Revert "Refactor autoscaler tagging to support multiple tag specs" This reverts commit 9cf48409ca2e5b66f800153853072c706fa502f6. * Update tag spec to only use characters [0-9a-z_-] * Change the tag values to conform gcp spec * Add project_id in the ssh key name * Replace '_' with '-' in autoscaler tag names * Revert "Update updater ssh to attempt 'set -i' and fall back if that fails" This reverts commit 23a0066c5254449e49746bd5e43b94b66f32bfb4. * Revert "Remove 'set -i' from updater ssh command" This reverts commit 5fa034cdf79fa7f8903691518c0d75699c630172. * Add fallback to `set -i` in force_interactive command * Update autoscaler tests to match current implementation * Update GCPNodeProvider.create_node to include hash in instance name * Add support for creating multiple instance on one create_node call * Clean TODOs * Update styles * Replace single quotes with double quotes * Some minor indentation fixes etc. * Remove unnecessary comment. Fix indentation. * Yapfify files that fail flake8 test * Yapfify more files * Update project_id handling in gcp node provider * temporary yapf mod * Revert "temporary yapf mod" This reverts commit b6744e4e15d4d936d1a14f4bf155ed1d3bb14126. * Fix autoscaler/updater.py lint error, remove unused variable
2018-05-31 09:00:03 -07:00
ray_autoscaler_files = [
"ray/autoscaler/aws/example-full.yaml",
"ray/autoscaler/gcp/example-full.yaml",
]
if "RAY_USE_NEW_GCS" in os.environ and os.environ["RAY_USE_NEW_GCS"] == "on":
2018-04-11 10:11:35 -07:00
ray_files += [
"ray/core/src/credis/build/src/libmember.so",
"ray/core/src/credis/build/src/libmaster.so",
"ray/core/src/credis/redis/src/redis-server"
]
# The UI files are mandatory if the INCLUDE_UI environment variable equals 1.
# Otherwise, they are optional.
if "INCLUDE_UI" in os.environ and os.environ["INCLUDE_UI"] == "1":
ray_files += ray_ui_files
else:
optional_ray_files += ray_ui_files
optional_ray_files += ray_autoscaler_files
extras = {"rllib": ["pyyaml", "gym[atari]", "opencv-python", "lz4", "scipy"]}
class build_ext(_build_ext.build_ext):
def run(self):
# Note: We are passing in sys.executable so that we use the same
# version of Python to build pyarrow inside the build.sh script. Note
# that certain flags will not be passed along such as --user or sudo.
# TODO(rkn): Fix this.
subprocess.check_call(["../build.sh", "-p", sys.executable])
# We also need to install pyarrow along with Ray, so make sure that the
# relevant non-Python pyarrow files get copied.
pyarrow_files = []
for (root, dirs, filenames) in os.walk("./ray/pyarrow_files/pyarrow"):
for name in filenames:
pyarrow_files.append(os.path.join(root, name))
files_to_include = ray_files + pyarrow_files
# Copy over the autogenerated flatbuffer Python bindings.
for directory in generated_python_directories:
for filename in os.listdir(directory):
if filename[-3:] == ".py":
files_to_include.append(os.path.join(directory, filename))
for filename in files_to_include:
self.move_file(filename)
# Try to copy over the optional files.
for filename in optional_ray_files:
try:
self.move_file(filename)
2018-10-24 16:30:00 -07:00
except Exception:
print("Failed to copy optional file {}. This is ok."
.format(filename))
def move_file(self, filename):
# TODO(rkn): This feels very brittle. It may not handle all cases. See
# https://github.com/apache/arrow/blob/master/python/setup.py for an
# example.
source = filename
destination = os.path.join(self.build_lib, filename)
# Create the target directory if it doesn't already exist.
parent_directory = os.path.dirname(destination)
if not os.path.exists(parent_directory):
os.makedirs(parent_directory)
print("Copying {} to {}.".format(source, destination))
shutil.copy(source, destination)
class BinaryDistribution(Distribution):
def has_ext_modules(self):
return True
def find_version(*filepath):
# Extract version information from filepath
here = os.path.abspath(os.path.dirname(__file__))
with open(os.path.join(here, *filepath)) as fp:
version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]",
fp.read(), re.M)
if version_match:
return version_match.group(1)
raise RuntimeError("Unable to find version string.")
2018-04-11 10:11:35 -07:00
setup(
name="ray",
version=find_version("ray", "__init__.py"),
description=("A system for parallel and distributed Python that unifies "
"the ML ecosystem."),
long_description=open("../README.rst").read(),
url="https://github.com/ray-project/ray",
keywords=("ray distributed parallel machine-learning "
"reinforcement-learning deep-learning python"),
2018-04-11 10:11:35 -07:00
packages=find_packages(),
cmdclass={"build_ext": build_ext},
# The BinaryDistribution argument triggers build_ext.
distclass=BinaryDistribution,
install_requires=[
"numpy",
"funcsigs",
"click",
"colorama",
"pytest",
"pyyaml",
"redis",
"faulthandler;python_version<'3'",
"setproctitle",
2018-04-11 10:11:35 -07:00
# The six module is required by pyarrow.
"six >= 1.0.0",
"flatbuffers"
],
setup_requires=["cython >= 0.27, < 0.28"],
2018-04-11 10:11:35 -07:00
extras_require=extras,
2018-07-12 19:12:04 +02:00
entry_points={
"console_scripts": [
"ray=ray.scripts.scripts:main",
"rllib=ray.rllib.scripts:cli [rllib]"
]
},
2018-04-11 10:11:35 -07:00
include_package_data=True,
zip_safe=False,
license="Apache 2.0")