onnxruntime/tools/ci_build/get_docker_image.py

164 lines
5.2 KiB
Python
Raw Normal View History

#!/usr/bin/env python3
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
import argparse
import os
import shlex
import shutil
import sys
from pathlib import Path
from logger import get_logger
SCRIPT_DIR = os.path.dirname(os.path.realpath(__file__))
REPO_DIR = os.path.normpath(os.path.join(SCRIPT_DIR, "..", ".."))
sys.path.append(os.path.join(REPO_DIR, "tools", "python"))
from util import run # noqa: E402
log = get_logger("get_docker_image")
def parse_args():
parser = argparse.ArgumentParser(
description="Build a docker image and push it to a remote Azure Container Registry."
"The content in the remote registry can be used as a cache when we need to build the thing again."
"The user must be logged in to the container registry."
)
parser.add_argument("--dockerfile", default="Dockerfile", help="Path to the Dockerfile.")
parser.add_argument("--context", default=".", help="Path to the build context.")
parser.add_argument(
"--docker-build-args", default="", help="Arguments that will be passed to the 'docker build' command."
)
parser.add_argument(
"--container-registry",
help="The Azure container registry name. If not provided, no container registry will be used.",
)
parser.add_argument("--repository", required=True, help="The image repository name.")
parser.add_argument("--use_imagecache", action="store_true", help="use cached image in pipeline cache")
parser.add_argument("--docker-path", default="docker", help="Path to docker.")
parser.add_argument("--manylinux-src", default="manylinux", help="Path to manylinux src folder")
parser.add_argument(
"--multiple_repos",
action="store_true",
help="used in packaging pipeline, which couldn't use get-docker-images-steps.yml",
)
return parser.parse_args()
def main():
args = parse_args()
log.debug(
"Dockerfile: {}, context: {}, docker build args: '{}'".format(
args.dockerfile, args.context, args.docker_build_args
)
)
use_container_registry = args.container_registry is not None
if not use_container_registry:
log.info("No container registry will be used")
full_image_name = (
Adopt linrtunner as the linting tool - take 2 (#15085) ### Description `lintrunner` is a linter runner successfully used by pytorch, onnx and onnx-script. It provides a uniform experience running linters locally and in CI. It supports all major dev systems: Windows, Linux and MacOs. The checks are enforced by the `Python format` workflow. This PR adopts `lintrunner` to onnxruntime and fixed ~2000 flake8 errors in Python code. `lintrunner` now runs all required python lints including `ruff`(replacing `flake8`), `black` and `isort`. Future lints like `clang-format` can be added. Most errors are auto-fixed by `ruff` and the fixes should be considered robust. Lints that are more complicated to fix are applied `# noqa` for now and should be fixed in follow up PRs. ### Notable changes 1. This PR **removed some suboptimal patterns**: - `not xxx in` -> `xxx not in` membership checks - bare excepts (`except:` -> `except Exception`) - unused imports The follow up PR will remove: - `import *` - mutable values as default in function definitions (`def func(a=[])`) - more unused imports - unused local variables 2. Use `ruff` to replace `flake8`. `ruff` is much (40x) faster than flake8 and is more robust. We are using it successfully in onnx and onnx-script. It also supports auto-fixing many flake8 errors. 3. Removed the legacy flake8 ci flow and updated docs. 4. The added workflow supports SARIF code scanning reports on github, example snapshot: ![image](https://user-images.githubusercontent.com/11205048/212598953-d60ce8a9-f242-4fa8-8674-8696b704604a.png) 5. Removed `onnxruntime-python-checks-ci-pipeline` as redundant ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Unified linting experience in CI and local. Replacing https://github.com/microsoft/onnxruntime/pull/14306 --------- Signed-off-by: Justin Chu <justinchu@microsoft.com>
2023-03-24 22:29:03 +00:00
f"{args.container_registry}.azurecr.io/{args.repository}:latest"
if use_container_registry
Adopt linrtunner as the linting tool - take 2 (#15085) ### Description `lintrunner` is a linter runner successfully used by pytorch, onnx and onnx-script. It provides a uniform experience running linters locally and in CI. It supports all major dev systems: Windows, Linux and MacOs. The checks are enforced by the `Python format` workflow. This PR adopts `lintrunner` to onnxruntime and fixed ~2000 flake8 errors in Python code. `lintrunner` now runs all required python lints including `ruff`(replacing `flake8`), `black` and `isort`. Future lints like `clang-format` can be added. Most errors are auto-fixed by `ruff` and the fixes should be considered robust. Lints that are more complicated to fix are applied `# noqa` for now and should be fixed in follow up PRs. ### Notable changes 1. This PR **removed some suboptimal patterns**: - `not xxx in` -> `xxx not in` membership checks - bare excepts (`except:` -> `except Exception`) - unused imports The follow up PR will remove: - `import *` - mutable values as default in function definitions (`def func(a=[])`) - more unused imports - unused local variables 2. Use `ruff` to replace `flake8`. `ruff` is much (40x) faster than flake8 and is more robust. We are using it successfully in onnx and onnx-script. It also supports auto-fixing many flake8 errors. 3. Removed the legacy flake8 ci flow and updated docs. 4. The added workflow supports SARIF code scanning reports on github, example snapshot: ![image](https://user-images.githubusercontent.com/11205048/212598953-d60ce8a9-f242-4fa8-8674-8696b704604a.png) 5. Removed `onnxruntime-python-checks-ci-pipeline` as redundant ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Unified linting experience in CI and local. Replacing https://github.com/microsoft/onnxruntime/pull/14306 --------- Signed-off-by: Justin Chu <justinchu@microsoft.com>
2023-03-24 22:29:03 +00:00
else f"{args.repository}:latest"
)
Adopt linrtunner as the linting tool - take 2 (#15085) ### Description `lintrunner` is a linter runner successfully used by pytorch, onnx and onnx-script. It provides a uniform experience running linters locally and in CI. It supports all major dev systems: Windows, Linux and MacOs. The checks are enforced by the `Python format` workflow. This PR adopts `lintrunner` to onnxruntime and fixed ~2000 flake8 errors in Python code. `lintrunner` now runs all required python lints including `ruff`(replacing `flake8`), `black` and `isort`. Future lints like `clang-format` can be added. Most errors are auto-fixed by `ruff` and the fixes should be considered robust. Lints that are more complicated to fix are applied `# noqa` for now and should be fixed in follow up PRs. ### Notable changes 1. This PR **removed some suboptimal patterns**: - `not xxx in` -> `xxx not in` membership checks - bare excepts (`except:` -> `except Exception`) - unused imports The follow up PR will remove: - `import *` - mutable values as default in function definitions (`def func(a=[])`) - more unused imports - unused local variables 2. Use `ruff` to replace `flake8`. `ruff` is much (40x) faster than flake8 and is more robust. We are using it successfully in onnx and onnx-script. It also supports auto-fixing many flake8 errors. 3. Removed the legacy flake8 ci flow and updated docs. 4. The added workflow supports SARIF code scanning reports on github, example snapshot: ![image](https://user-images.githubusercontent.com/11205048/212598953-d60ce8a9-f242-4fa8-8674-8696b704604a.png) 5. Removed `onnxruntime-python-checks-ci-pipeline` as redundant ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Unified linting experience in CI and local. Replacing https://github.com/microsoft/onnxruntime/pull/14306 --------- Signed-off-by: Justin Chu <justinchu@microsoft.com>
2023-03-24 22:29:03 +00:00
log.info(f"Image: {full_image_name}")
Improve dependency management (#13523) ## Description 1. Convert some git submodules to cmake external projects 2. Update nsync from [1.23.0](https://github.com/google/nsync/releases/tag/1.23.0) to [1.25.0](https://github.com/google/nsync/releases/tag/1.25.0) 3. Update re2 from 2021-06-01 to 2022-06-01 4. Update wil from an old commit to 1.0.220914.1 tag 5. Update gtest to a newer commit so that it can optionally leverage absl/re2 for parsing command line flags. The following git submodules are deleted: 1. FP16 2. safeint 3. XNNPACK 4. cxxopts 5. dlpack 7. flatbuffers 8. googlebenchmark 9. json 10. mimalloc 11. mp11 12. pthreadpool More will come. ## Motivation and Context There are 3 ways of integrating 3rd party C/C++ libraries into ONNX Runtime: 1. Install them to a system location, then use cmake's find_package module to locate them. 2. Use git submodules 6. Use cmake's external projects(externalproject_add). At first when this project was just started, we considered both option 2 and option 3. We preferred option 2 because: 1. It's easier to handle authentication. At first this project was not open source, and it had some other non-public dependencies. If we use git submodule, ADO will handle authentication smoothly. Otherwise we need to manually pass tokens around and be very careful on not exposing them in build logs. 2. At that time, cmake fetched dependencies after "cmake" finished generating vcprojects/makefiles. So it was very difficult to make cflags consistent. Since cmake 3.11, it has a new command: FetchContent, which fetches dependencies when it generates vcprojects/makefiles just before add_subdirectories, so the parent project's variables/settings can be easily passed to the child projects. And when the project went on, we had some new concerns: 1. As we started to have more and more EPs and build configs, the number of submodules grew quickly. For more developers, most ORT submodules are not relevant to them. They shouldn't need to download all of them. 2. It is impossible to let two different build configs use two different versions of the same dependency. For example, right now we have protobuf 3.18.3 in the submodules. Then every EP must use the same version. Whenever we have a need to upgrade protobuf, we need to coordinate across the whole team and many external developers. I can't manage it anymore. 3. Some projects want to manage the dependencies in a different way, either because of their preference or because of compliance requirements. For example, some Microsoft teams want to use vcpkg, but we don't want to force every user of onnxruntime using vcpkg. 7. Someone wants to dynamically link to protobuf, but our build script only does static link. 8. Hard to handle security vulnerabilities. For example, whenever protobuf has a security patch, we have a lot of things to do. But if we allowed people to build ORT with a different version of protobuf without changing ORT"s source code, the customer who build ORT from source will be able to act on such things in a quicker way. They will not need to wait ORT having a patch release. 9. Every time we do a release, github will also publish a source file zip file and a source file tarball for us. But they are not usable, because they miss submodules. ### New features After this change, users will be able to: 1. Build the dependencies in the way they want, then install them to somewhere(for example, /usr or a temp folder). 2. Or download the dependencies by using cmake commands from these dependencies official website 3. Similar to the above, but use your private mirrors to migrate supply chain risks. 4. Use different versions of the dependencies, as long as our source code is compatible with them. For example, you may use you can't use protobuf 3.20.x as they need code changes in ONNX Runtime. 6. Only download the things the current build needs. 10. Avoid building external dependencies again and again in every build. ### Breaking change The onnxruntime_PREFER_SYSTEM_LIB build option is removed you could think from now it is default ON. If you don't like the new behavior, you can set FETCHCONTENT_TRY_FIND_PACKAGE_MODE to NEVER. Besides, for who relied on the onnxruntime_PREFER_SYSTEM_LIB build option, please be aware that this PR will change find_package calls from Module mode to Config mode. For example, in the past if you have installed protobuf from apt-get from ubuntu 20.04's official repo, find_package can find it and use it. But after this PR, it won't. This is because that protobuf version provided by Ubuntu 20.04 is too old to support the "config mode". It can be resolved by getting a newer version of protobuf from somewhere.
2022-12-01 17:51:59 +00:00
dst_deps_file = Path(args.context) / "scripts" / "deps.txt"
# The docker file may provide a special deps.txt in its docker context dir and uses that one.
# Otherwise, copy a generic one from this repo's cmake dir.
if not dst_deps_file.exists():
log.info(f"Copy deps.txt to : {dst_deps_file}")
Improve dependency management (#13523) ## Description 1. Convert some git submodules to cmake external projects 2. Update nsync from [1.23.0](https://github.com/google/nsync/releases/tag/1.23.0) to [1.25.0](https://github.com/google/nsync/releases/tag/1.25.0) 3. Update re2 from 2021-06-01 to 2022-06-01 4. Update wil from an old commit to 1.0.220914.1 tag 5. Update gtest to a newer commit so that it can optionally leverage absl/re2 for parsing command line flags. The following git submodules are deleted: 1. FP16 2. safeint 3. XNNPACK 4. cxxopts 5. dlpack 7. flatbuffers 8. googlebenchmark 9. json 10. mimalloc 11. mp11 12. pthreadpool More will come. ## Motivation and Context There are 3 ways of integrating 3rd party C/C++ libraries into ONNX Runtime: 1. Install them to a system location, then use cmake's find_package module to locate them. 2. Use git submodules 6. Use cmake's external projects(externalproject_add). At first when this project was just started, we considered both option 2 and option 3. We preferred option 2 because: 1. It's easier to handle authentication. At first this project was not open source, and it had some other non-public dependencies. If we use git submodule, ADO will handle authentication smoothly. Otherwise we need to manually pass tokens around and be very careful on not exposing them in build logs. 2. At that time, cmake fetched dependencies after "cmake" finished generating vcprojects/makefiles. So it was very difficult to make cflags consistent. Since cmake 3.11, it has a new command: FetchContent, which fetches dependencies when it generates vcprojects/makefiles just before add_subdirectories, so the parent project's variables/settings can be easily passed to the child projects. And when the project went on, we had some new concerns: 1. As we started to have more and more EPs and build configs, the number of submodules grew quickly. For more developers, most ORT submodules are not relevant to them. They shouldn't need to download all of them. 2. It is impossible to let two different build configs use two different versions of the same dependency. For example, right now we have protobuf 3.18.3 in the submodules. Then every EP must use the same version. Whenever we have a need to upgrade protobuf, we need to coordinate across the whole team and many external developers. I can't manage it anymore. 3. Some projects want to manage the dependencies in a different way, either because of their preference or because of compliance requirements. For example, some Microsoft teams want to use vcpkg, but we don't want to force every user of onnxruntime using vcpkg. 7. Someone wants to dynamically link to protobuf, but our build script only does static link. 8. Hard to handle security vulnerabilities. For example, whenever protobuf has a security patch, we have a lot of things to do. But if we allowed people to build ORT with a different version of protobuf without changing ORT"s source code, the customer who build ORT from source will be able to act on such things in a quicker way. They will not need to wait ORT having a patch release. 9. Every time we do a release, github will also publish a source file zip file and a source file tarball for us. But they are not usable, because they miss submodules. ### New features After this change, users will be able to: 1. Build the dependencies in the way they want, then install them to somewhere(for example, /usr or a temp folder). 2. Or download the dependencies by using cmake commands from these dependencies official website 3. Similar to the above, but use your private mirrors to migrate supply chain risks. 4. Use different versions of the dependencies, as long as our source code is compatible with them. For example, you may use you can't use protobuf 3.20.x as they need code changes in ONNX Runtime. 6. Only download the things the current build needs. 10. Avoid building external dependencies again and again in every build. ### Breaking change The onnxruntime_PREFER_SYSTEM_LIB build option is removed you could think from now it is default ON. If you don't like the new behavior, you can set FETCHCONTENT_TRY_FIND_PACKAGE_MODE to NEVER. Besides, for who relied on the onnxruntime_PREFER_SYSTEM_LIB build option, please be aware that this PR will change find_package calls from Module mode to Config mode. For example, in the past if you have installed protobuf from apt-get from ubuntu 20.04's official repo, find_package can find it and use it. But after this PR, it won't. This is because that protobuf version provided by Ubuntu 20.04 is too old to support the "config mode". It can be resolved by getting a newer version of protobuf from somewhere.
2022-12-01 17:51:59 +00:00
shutil.copyfile(Path(REPO_DIR) / "cmake" / "deps.txt", str(dst_deps_file))
if "manylinux" in args.dockerfile and args.multiple_repos:
manylinux_build_scripts_folder = Path(args.manylinux_src) / "docker" / "build_scripts"
dest = Path(args.context) / "build_scripts"
if dest.exists():
log.info(f"Deleting: {dest!s}")
shutil.rmtree(str(dest))
shutil.copytree(str(manylinux_build_scripts_folder), str(dest))
src_entrypoint_file = str(Path(args.manylinux_src) / "docker" / "manylinux-entrypoint")
dst_entrypoint_file = str(Path(args.context) / "manylinux-entrypoint")
shutil.copyfile(src_entrypoint_file, dst_entrypoint_file)
shutil.copymode(src_entrypoint_file, dst_entrypoint_file)
run(
"patch",
"-p1",
"-i",
str((Path(SCRIPT_DIR) / "github" / "linux" / "docker" / "manylinux.patch").resolve()),
cwd=str(dest),
)
if use_container_registry:
run(
args.docker_path,
"--log-level",
"error",
"buildx",
"build",
"--push",
"--tag",
full_image_name,
"--cache-from",
full_image_name,
"--build-arg",
"BUILDKIT_INLINE_CACHE=1",
*shlex.split(args.docker_build_args),
"-f",
args.dockerfile,
args.context,
)
elif args.use_imagecache:
log.info("Building image with pipeline cache...")
run(
args.docker_path,
"--log-level",
"error",
"buildx",
"build",
"--tag",
full_image_name,
"--cache-from",
full_image_name,
"--build-arg",
"BUILDKIT_INLINE_CACHE=1",
*shlex.split(args.docker_build_args),
"-f",
args.dockerfile,
args.context,
)
else:
log.info("Building image...")
run(
args.docker_path,
"build",
"--pull",
*shlex.split(args.docker_build_args),
"--tag",
full_image_name,
"--file",
args.dockerfile,
args.context,
)
# tag so we can refer to the image by repository name
run(args.docker_path, "tag", full_image_name, args.repository)
return 0
if __name__ == "__main__":
sys.exit(main())