This is an automated email from the ASF dual-hosted git repository. potiuk pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/airflow.git
The following commit(s) were added to refs/heads/main by this push: new ba28334621 Fix local k8s test venv installation to accomodate for local changes (#35191) ba28334621 is described below commit ba283346215278404912baca4854d78b64e1e7d2 Author: Jarek Potiuk <ja...@potiuk.com> AuthorDate: Thu Oct 26 11:05:01 2023 +0200 Fix local k8s test venv installation to accomodate for local changes (#35191) The #35099 switched installation of the local venv for Airflow to released packages, in order to accomodate for case from #34729 where we locally install a new provider that is preinstalled but has not yet been released. This however has the side-effect - some k8s tests are using K8S Pod operator to run the tests and if this operator has been changed, the local - modified - version of it is not going to be used for tests. Another side effect is that in case of a new installation, when the constraint installation does not work (for example constraints in main are conflicting with released airflow), `pip` starts to backtrack - and for conflicting requirements it produces strange results (for example it attempts to install airflow 1.10 and fails due to "slugify" dependency. The previous version of it had another problem - once installed, it had not changed, so in case someone used breeze to run k8s tests locally and iterated over changes in K8SPod Operator, only the version from the moment the k8s environment was installed was used. Both cases are now handled better: * INSTALL_PROVIDERS_FROM_SOURCES is used as env variable to make sure new providers (including preinstalled providers) are found in Airfow sources, not in PyPI * The "." is used back in order to install Airflow but also the -e (editable) installation is used for it - so that any changes to local version of k8s are used. We are not using constraints for installation. * Dry run and verbose mode of installing the venv are improved a bit - they show better what's going on (and dry_run does not interact with the installation in unexpected ways - deleting the installed venv without recreating it). We already handled a change that k8s test environment has been reinstalled after the requirements file changed and caching in CI includes the hash of the requirements file as content - so we do not need to handle reinstallation of the venv or caching in CI. The venv should be appropriately reinstalled as needed. --- .github/workflows/ci.yml | 2 +- .../src/airflow_breeze/utils/kubernetes_utils.py | 47 +++++++++++----------- scripts/ci/kubernetes/k8s_requirements.txt | 2 +- 3 files changed, 26 insertions(+), 25 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 3dd00e2094..28e0a41372 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -1683,7 +1683,7 @@ jobs: KUBERNETES_VERSIONS: ${{needs.build-info.outputs.kubernetes-versions-list-as-string}} EXECUTOR: ${{matrix.executor}} USE_STANDARD_NAMING: ${{matrix.use-standard-naming}} - VERBOSE: false + VERBOSE: true - name: Upload KinD logs on failure ${{needs.build-info.outputs.kubernetes-combos-list-as-string}} uses: actions/upload-artifact@v3 if: failure() || cancelled() diff --git a/dev/breeze/src/airflow_breeze/utils/kubernetes_utils.py b/dev/breeze/src/airflow_breeze/utils/kubernetes_utils.py index 3bed798c22..7c2e6a7230 100644 --- a/dev/breeze/src/airflow_breeze/utils/kubernetes_utils.py +++ b/dev/breeze/src/airflow_breeze/utils/kubernetes_utils.py @@ -32,13 +32,12 @@ from time import sleep from typing import Any, NamedTuple from urllib import request -from airflow_breeze.branch_defaults import DEFAULT_AIRFLOW_CONSTRAINTS_BRANCH from airflow_breeze.global_constants import ALLOWED_ARCHITECTURES, HELM_VERSION, KIND_VERSION, PIP_VERSION from airflow_breeze.utils.console import Output, get_console from airflow_breeze.utils.host_info_utils import Architecture, get_host_architecture, get_host_os from airflow_breeze.utils.path_utils import AIRFLOW_SOURCES_ROOT, BUILD_CACHE_DIR from airflow_breeze.utils.run_utils import RunCommandResult, run_command -from airflow_breeze.utils.shared_options import get_dry_run +from airflow_breeze.utils.shared_options import get_dry_run, get_verbose K8S_ENV_PATH = BUILD_CACHE_DIR / ".k8s-env" K8S_CLUSTERS_PATH = BUILD_CACHE_DIR / ".k8s-clusters" @@ -270,7 +269,7 @@ def make_sure_kubernetes_tools_are_installed(): def _requirements_changed() -> bool: if not CACHED_K8S_REQUIREMENTS.exists(): get_console().print( - f"\n[warning]The K8S venv in {K8S_ENV_PATH}. has never been created. Installing it.\n" + f"\n[warning]The K8S venv in {K8S_ENV_PATH} has never been created. Installing it.\n" ) return True requirements_file_content = K8S_REQUIREMENTS.read_text() @@ -284,7 +283,7 @@ def _requirements_changed() -> bool: return False -def _install_packages_in_k8s_virtualenv(with_constraints: bool): +def _install_packages_in_k8s_virtualenv(): install_command = [ str(PYTHON_BIN_PATH), "-m", @@ -293,20 +292,19 @@ def _install_packages_in_k8s_virtualenv(with_constraints: bool): "-r", str(K8S_REQUIREMENTS.resolve()), ] - if with_constraints: - install_command.extend( - [ - "--constraint", - f"https://raw.githubusercontent.com/apache/airflow/{DEFAULT_AIRFLOW_CONSTRAINTS_BRANCH}/" - f"constraints-{sys.version_info.major}.{sys.version_info.minor}.txt", - ] - ) - install_packages_result = run_command(install_command, check=False, capture_output=True, text=True) + env = os.environ.copy() + env["INSTALL_PROVIDERS_FROM_SOURCES"] = "true" + capture_output = True + if get_verbose(): + capture_output = False + install_packages_result = run_command( + install_command, check=False, capture_output=capture_output, text=True, env=env + ) if install_packages_result.returncode != 0: - get_console().print( - f"[error]Error when installing packages from : {K8S_REQUIREMENTS.resolve()}[/]\n" - f"{install_packages_result.stdout}\n{install_packages_result.stderr}" - ) + get_console().print(f"[error]Error when installing packages from : {K8S_REQUIREMENTS.resolve()}[/]\n") + if not get_verbose(): + get_console().print(install_packages_result.stdout) + get_console().print(install_packages_result.stderr) return install_packages_result @@ -328,7 +326,10 @@ def create_virtualenv(force_venv_setup: bool) -> RunCommandResult: get_console().print(f"[info]Forcing initializing K8S virtualenv in {K8S_ENV_PATH}") else: get_console().print(f"[info]Initializing K8S virtualenv in {K8S_ENV_PATH}") - shutil.rmtree(K8S_ENV_PATH, ignore_errors=True) + if get_dry_run(): + get_console().print(f"[info]Dry run - would be removing {K8S_ENV_PATH}") + else: + shutil.rmtree(K8S_ENV_PATH, ignore_errors=True) venv_command_result = run_command( [sys.executable, "-m", "venv", str(K8S_ENV_PATH)], check=False, @@ -354,12 +355,12 @@ def create_virtualenv(force_venv_setup: bool) -> RunCommandResult: return pip_reinstall_result get_console().print(f"[info]Installing necessary packages in {K8S_ENV_PATH}") - install_packages_result = _install_packages_in_k8s_virtualenv(with_constraints=True) - if install_packages_result.returncode != 0: - # if the first installation fails, attempt to install it without constraints - install_packages_result = _install_packages_in_k8s_virtualenv(with_constraints=False) + install_packages_result = _install_packages_in_k8s_virtualenv() if install_packages_result.returncode == 0: - CACHED_K8S_REQUIREMENTS.write_text(K8S_REQUIREMENTS.read_text()) + if get_dry_run(): + get_console().print(f"[info]Dry run - would be saving {K8S_REQUIREMENTS} to cache") + else: + CACHED_K8S_REQUIREMENTS.write_text(K8S_REQUIREMENTS.read_text()) return install_packages_result diff --git a/scripts/ci/kubernetes/k8s_requirements.txt b/scripts/ci/kubernetes/k8s_requirements.txt index 0922c62b2c..0f6cc2fd38 100644 --- a/scripts/ci/kubernetes/k8s_requirements.txt +++ b/scripts/ci/kubernetes/k8s_requirements.txt @@ -1,4 +1,4 @@ -apache-airflow[cncf.kubernetes] +-e .[kubernetes] pytest pytest-cov pytest-instafail