From 871e270b3ef3fe56c80d7d7e2d51910ccd79280f Mon Sep 17 00:00:00 2001 From: Philip Chmielowiec <67855069+philipc2@users.noreply.github.com> Date: Mon, 12 Feb 2024 22:21:38 -0600 Subject: [PATCH] Setup ASV Benchmarking (#694) * initial asv setup * configure ruff to work to skip benchmarks dir * fix failing benchmark * fix failing benchmark * use underscore instead of dash * fix file path * fix file path * fix file path * fix file path * add docstrings to benchmarks * update asv-benchmarking.yml * update conda env path * fix typo * Delete .github/workflows/asv-benchmarking.yml * add asv to gitignore * add workflow for asv * Update quad_hexagon.py * Update asv-benchmarking.yml --- .github/workflows/asv-benchmarking.yml | 86 +++++++++++ .gitignore | 6 + .pre-commit-config.yaml | 2 - benchmarks/__init__.py | 0 benchmarks/asv.conf.json | 188 +++++++++++++++++++++++++ benchmarks/import.py | 5 + benchmarks/quad_hexagon.py | 36 +++++ ci/asv.yml | 31 ++++ ruff.toml | 3 + 9 files changed, 355 insertions(+), 2 deletions(-) create mode 100644 .github/workflows/asv-benchmarking.yml create mode 100644 benchmarks/__init__.py create mode 100644 benchmarks/asv.conf.json create mode 100644 benchmarks/import.py create mode 100644 benchmarks/quad_hexagon.py create mode 100644 ci/asv.yml create mode 100644 ruff.toml diff --git a/.github/workflows/asv-benchmarking.yml b/.github/workflows/asv-benchmarking.yml new file mode 100644 index 000000000..aa06f2441 --- /dev/null +++ b/.github/workflows/asv-benchmarking.yml @@ -0,0 +1,86 @@ +name: ASV Benchmarking + +on: + push: + branches: + - main + workflow_dispatch: + +jobs: + benchmark: + runs-on: ubuntu-latest + env: + CONDA_ENV_FILE: ./ci/asv.yml + ASV_DIR: ./benchmarks + + steps: + - name: Checkout uxarray + uses: actions/checkout@v4 + with: + repository: UXARRAY/uxarray + fetch-depth: 0 + - name: Checkout uxarray-asv + uses: actions/checkout@v4 + with: + repository: uxarray/uxarray-asv + persist-credentials: false + fetch-depth: 0 + ref: main + path: uxarray-asv + - name: Set environment variables + run: | + echo "TODAY=$(date +'%Y-%m-%d')" >> $GITHUB_ENV + + - name: Set up conda environment + id: env-setup + continue-on-error: true + uses: mamba-org/setup-micromamba@v1 + with: + environment-file: ./ci/asv.yml + cache-environment: true + cache-environment-key: "benchmark-${{runner.os}}-${{runner.arch}}-${{env.TODAY}}" + + - name: retry environment set up if failed + if: steps.env-setup.outcome == 'failure' + uses: mamba-org/setup-micromamba@v1 + with: + download-micromamba: false + environment-file: ./ci/asv.yml + cache-environment: true + cache-environment-key: "benchmark-${{runner.os}}-${{runner.arch}}-${{env.TODAY}}" + + - name: Copy existing results + run: | + if [ -d "uxarray-asv/results" ]; then + cp -r uxarray-asv/results benchmarks/ + fi + + - name: Run benchmarks + shell: bash -l {0} + id: benchmark + run: | + cd benchmarks + asv machine --machine GH-Actions --os ubuntu-latest --arch x64 --cpu "2-core unknown" --ram 7GB + asv run v2024.02.0..main --skip-existing --parallel || true + + - name: Commit and push benchmark results + run: | + if [ -d "uxarray-asv/results" ]; then + rm -r uxarray-asv/results + fi + cp -r benchmarks/results/ uxarray-asv/ + cd uxarray-asv + git config --local user.email "${{ secrets.UXARRAY_ASV_EMAIL }}" + git config --local user.name "${{ secrets.UXARRAY_ASV_USER_NAME }}" + git add results + git commit -m "[🤖] Update benchmark results" + + - name: Push to uxarray-asv + if: github.ref == 'refs/heads/main' && github.repository == 'UXARRAY/uxarray' + uses: ad-m/github-push-action@master + with: + github_token: ${{ secrets.UXARRAY_ASV_PAT }} + branch: main + force: true + repository: UXARRAY/uxarray-asv + directory: uxarray-asv diff --git a/.gitignore b/.gitignore index 2c41b5e38..af6b72791 100644 --- a/.gitignore +++ b/.gitignore @@ -152,3 +152,9 @@ test/write_* docs/user_api/_autosummary/ docs/notebook-examples.txt + + +# benchmarking +benchmarks/env +benchmarks/results +benchmarks/html diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 77ef1bad1..574548d3d 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -22,8 +22,6 @@ repos: # Run the linter. - id: ruff args: [ --fix ] - exclude: ".test" # Run the formatter. - id: ruff-format - exclude: ".test" diff --git a/benchmarks/__init__.py b/benchmarks/__init__.py new file mode 100644 index 000000000..e69de29bb diff --git a/benchmarks/asv.conf.json b/benchmarks/asv.conf.json new file mode 100644 index 000000000..e1dd0d8a9 --- /dev/null +++ b/benchmarks/asv.conf.json @@ -0,0 +1,188 @@ +{ + // The version of the config file format. Do not change, unless + // you know what you are doing. + "version": 1, + + // The name of the project being benchmarked + "project": "uxarray", + + // The project's homepage + "project_url": "https://github.com/UXARRAY/uxarray", + + // The URL or local path of the source code repository for the + // project being benchmarked + "repo": "..", + + // The Python project's subdirectory in your repo. If missing or + // the empty string, the project is assumed to be located at the root + // of the repository. + // "repo_subdir": "", + + // Customizable commands for building the project. + // See asv.conf.json documentation. + // To build the package using pyproject.toml (PEP518), uncomment the following lines + // "build_command": [ + // "python -m pip install build", + // "python -m build", + // "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}" + // ], + // To build the package using setuptools and a setup.py file, uncomment the following lines + // "build_command": [ + // "python setup.py build", + // "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}" + // ], + + // Customizable commands for installing and uninstalling the project. + // See asv.conf.json documentation. + // "install_command": ["in-dir={env_dir} python -mpip install {wheel_file}"], + // "uninstall_command": ["return-code=any python -mpip uninstall -y {project}"], + + // List of branches to benchmark. If not provided, defaults to "master" + // (for git) or "default" (for mercurial). + "branches": ["main"], // for git + // "branches": ["default"], // for mercurial + + // The DVCS being used. If not set, it will be automatically + // determined from "repo" by looking at the protocol in the URL + // (if remote), or by looking for special directories, such as + // ".git" (if local). + "dvcs": "git", + + // The tool to use to create environments. May be "conda", + // "virtualenv", "mamba" (above 3.8) + // or other value depending on the plugins in use. + // If missing or the empty string, the tool will be automatically + // determined by looking for tools on the PATH environment + // variable. + "environment_type": "conda", + + // timeout in seconds for installing any dependencies in environment + // defaults to 10 min + "install_timeout": 600, + + // the base URL to show a commit for the project. + "show_commit_url": "https://github.com/UXARRAY/uxarray/commit/", + + // The Pythons you'd like to test against. If not provided, defaults + // to the current version of Python used to run `asv`. + "pythons": ["3.11"], + + // The list of conda channel names to be searched for benchmark + // dependency packages in the specified order + "conda_channels": ["conda-forge"], + + // A conda environment file that is used for environment creation. + "conda_environment_file": "../ci/asv.yml", + + // The matrix of dependencies to test. Each key of the "req" + // requirements dictionary is the name of a package (in PyPI) and + // the values are version numbers. An empty list or empty string + // indicates to just test against the default (latest) + // version. null indicates that the package is to not be + // installed. If the package to be tested is only available from + // PyPi, and the 'environment_type' is conda, then you can preface + // the package name by 'pip+', and the package will be installed + // via pip (with all the conda available packages installed first, + // followed by the pip installed packages). + // + // The ``@env`` and ``@env_nobuild`` keys contain the matrix of + // environment variables to pass to build and benchmark commands. + // An environment will be created for every combination of the + // cartesian product of the "@env" variables in this matrix. + // Variables in "@env_nobuild" will be passed to every environment + // during the benchmark phase, but will not trigger creation of + // new environments. A value of ``null`` means that the variable + // will not be set for the current combination. + // + "matrix": { + "python": [""], + }, + + // Combinations of libraries/python versions can be excluded/included + // from the set to test. Each entry is a dictionary containing additional + // key-value pairs to include/exclude. + // + // An exclude entry excludes entries where all values match. The + // values are regexps that should match the whole string. + // + // An include entry adds an environment. Only the packages listed + // are installed. The 'python' key is required. The exclude rules + // do not apply to includes. + // + // In addition to package names, the following keys are available: + // + // - python + // Python version, as in the *pythons* variable above. + // - environment_type + // Environment type, as above. + // - sys_platform + // Platform, as in sys.platform. Possible values for the common + // cases: 'linux2', 'win32', 'cygwin', 'darwin'. + // - req + // Required packages + // - env + // Environment variables + // - env_nobuild + // Non-build environment variables + // + // "exclude": [ + // {"python": "3.2", "sys_platform": "win32"}, // skip py3.2 on windows + // {"environment_type": "conda", "req": {"six": null}}, // don't run without six on conda + // {"env": {"ENV_VAR_1": "val2"}}, // skip val2 for ENV_VAR_1 + // ], + // + // "include": [ + // // additional env for python2.7 + // {"python": "2.7", "req": {"numpy": "1.8"}, "env_nobuild": {"FOO": "123"}}, + // // additional env if run on windows+conda + // {"platform": "win32", "environment_type": "conda", "python": "2.7", "req": {"libpython": ""}}, + // ], + + // The directory (relative to the current directory) that benchmarks are + // stored in. If not provided, defaults to "benchmarks" + "benchmark_dir": ".", + + // The directory (relative to the current directory) to cache the Python + // environments in. If not provided, defaults to "env" + // "env_dir": "env", + + // The directory (relative to the current directory) that raw benchmark + // results are stored in. If not provided, defaults to "results". + // "results_dir": "results", + + // The directory (relative to the current directory) that the html tree + // should be written to. If not provided, defaults to "html". + // "html_dir": "html", + + // The number of characters to retain in the commit hashes. + // "hash_length": 8, + + // `asv` will cache results of the recent builds in each + // environment, making them faster to install next time. This is + // the number of builds to keep, per environment. + // "build_cache_size": 2, + + // The commits after which the regression search in `asv publish` + // should start looking for regressions. Dictionary whose keys are + // regexps matching to benchmark names, and values corresponding to + // the commit (exclusive) after which to start looking for + // regressions. The default is to start from the first commit + // with results. If the commit is `null`, regression detection is + // skipped for the matching benchmark. + // + // "regressions_first_commits": { + // "some_benchmark": "352cdf", // Consider regressions only after this commit + // "another_benchmark": null, // Skip regression detection altogether + // }, + + // The thresholds for relative change in results, after which `asv + // publish` starts reporting regressions. Dictionary of the same + // form as in ``regressions_first_commits``, with values + // indicating the thresholds. If multiple entries match, the + // maximum is taken. If no entry matches, the default is 5%. + // + // "regressions_thresholds": { + // "some_benchmark": 0.01, // Threshold of 1% + // "another_benchmark": 0.5, // Threshold of 50% + // }, +} diff --git a/benchmarks/import.py b/benchmarks/import.py new file mode 100644 index 000000000..e53515f2a --- /dev/null +++ b/benchmarks/import.py @@ -0,0 +1,5 @@ +class Imports: + """Benchmark importing uxarray.""" + + def timeraw_import_uxarray(self): + return "import uxarray" diff --git a/benchmarks/quad_hexagon.py b/benchmarks/quad_hexagon.py new file mode 100644 index 000000000..ee740d832 --- /dev/null +++ b/benchmarks/quad_hexagon.py @@ -0,0 +1,36 @@ +import os +from pathlib import Path + +import uxarray as ux + +current_path = Path(os.path.dirname(os.path.realpath(__file__))).parents[0] + +grid_path = current_path / "test" / "meshfiles" / "ugrid" / "quad-hexagon" / "grid.nc" +data_path = current_path / "test" / "meshfiles" / "ugrid" / "quad-hexagon" / "data.nc" + + +class QuadHexagon: + def time_open_grid(self): + """Time to open a `Grid`""" + ux.open_grid(grid_path) + + def mem_open_grid(self): + """Memory Occupied by a `Grid`""" + return ux.open_grid(grid_path) + + def peakmem_open_grid(self): + """Peak memory usage of a `Grid`""" + uxgrid = ux.open_grid(grid_path) + + + def time_open_dataset(self): + """Time to open a `UxDataset`""" + ux.open_dataset(grid_path, data_path) + + def mem_open_dataset(self): + """Memory occupied by a `UxDataset`""" + return ux.open_dataset(grid_path, data_path) + + def peakmem_open_dataset(self): + """Peak memory usage of a `UxDataset`""" + uxds = ux.open_dataset(grid_path, data_path) diff --git a/ci/asv.yml b/ci/asv.yml new file mode 100644 index 000000000..761a6ab5c --- /dev/null +++ b/ci/asv.yml @@ -0,0 +1,31 @@ +name: asv +channels: + - conda-forge +dependencies: + - python=3.11 + - cartopy + - dask + - datashader + - gmpy2 + - holoviews + - matplotlib-base + - netcdf4 + - numba + - numpy + - pandas<2.1.0 + - pathlib + - pre_commit + - pyarrow<13.0.0 # pin due to CI faliures on macOS & ubuntu + - pytest + - pytest-cov + - requests + - scikit-learn + - scipy + - shapely + - spatialpandas + - xarray + - pip: + - antimeridian + - pyfma + - asv + - -e ../ diff --git a/ruff.toml b/ruff.toml new file mode 100644 index 000000000..b13fa12c6 --- /dev/null +++ b/ruff.toml @@ -0,0 +1,3 @@ +extend-exclude = [ +"test", +"benchmarks"]