ASV Benchmarking Pull Request Workflow (#831)

* add workflow file, update asv config and enviroment.yml

* comment out broken benchmarks for now

.github/workflows/asv-benchmarking-pr.yml

@@ -0,0 +1,107 @@
+name: ASV Benchmarking (PR)
+
+on:
+  pull_request:
+    types: [opened, reopened, synchronize, labeled]
+  workflow_dispatch:
+
+jobs:
+  benchmark:
+    if: ${{ contains(github.event.pull_request.labels.*.name, 'run-benchmark') && github.event_name == 'pull_request' || github.event_name == 'workflow_dispatch' }}
+    name: Linux
+    runs-on: ubuntu-latest
+    env:
+      ASV_DIR: "./benchmarks"
+      CONDA_ENV_FILE: ci/environment.yml
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+
+      - name: Set up Conda environment
+        uses: mamba-org/setup-micromamba@v1
+        with:
+          environment-file: ${{env.CONDA_ENV_FILE}}
+          cache-environment: true
+          environment-name: uxarray_build
+          cache-environment-key: "${{runner.os}}-${{runner.arch}}-py${{env.PYTHON_VERSION}}-${{env.TODAY}}-${{hashFiles(env.CONDA_ENV_FILE)}}-benchmark"
+          create-args: >-
+            asv
+            build
+            mamba
+
+      - name: Run Benchmarks
+        shell: bash -l {0}
+        id: benchmark
+        run: |
+          set -x
+          # ID this runner
+          asv machine --yes
+          echo "Baseline:  ${{ github.event.pull_request.base.sha }} (${{ github.event.pull_request.base.label }})"
+          echo "Contender: ${GITHUB_SHA} (${{ github.event.pull_request.head.label }})"
+          # Run benchmarks for current commit against base
+          ASV_OPTIONS="--split --show-stderr"
+          asv continuous $ASV_OPTIONS ${{ github.event.pull_request.base.sha }} ${GITHUB_SHA}
+          # Save compare results
+          asv compare --split ${{ github.event.pull_request.base.sha }} ${GITHUB_SHA} > asv_compare_results.txt
+        working-directory: ${{ env.ASV_DIR }}
+
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: asv-benchmark-results-${{ runner.os }}
+          path: |
+            ${{ env.ASV_DIR }}/results
+            ${{ env.ASV_DIR }}/asv_compare_results.txt
+
+      - name: Post or update result comment
+        id: comment
+        uses: actions/github-script@v6
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const fs = require('fs');
+            const compareResults = fs.readFileSync('${{ env.ASV_DIR }}/asv_compare_results.txt', 'utf8');
+            const { owner, repo } = context.repo;
+            const issue_number = context.issue.number;
+
+            // Customize the comment content with your action results
+            const newComment = `
+            ## ASV Benchmarking
+
+            <details>
+              <summary>Benchmark Comparison Results</summary>
+
+              ${compareResults}
+            </details>
+            `;
+
+            // Fetch existing comments on the PR
+            const { data: comments } = await github.rest.issues.listComments({
+              owner,
+              repo,
+              issue_number,
+            });
+
+            // Find if there is an existing comment by this action
+            const botComment = comments.find(comment => comment.user.login === 'github-actions[bot]');
+
+            if (botComment) {
+              // Update the existing comment
+              await github.rest.issues.updateComment({
+                owner,
+                repo,
+                comment_id: botComment.id,
+                body: newComment,
+              });
+            } else {
+              // Create a new comment
+              await github.rest.issues.createComment({
+                owner,
+                repo,
+                issue_number,
+                body: newComment,
+              });
+            }

benchmarks/asv.conf.json

@@ -54,7 +54,8 @@
     // If missing or the empty string, the tool will be automatically
     // determined by looking for tools on the PATH environment
     // variable.
-    "environment_type": "conda",
+    "environment_type": "mamba",
+    "conda_channels": ["conda-forge"],
 
     // timeout in seconds for installing any dependencies in environment
     // defaults to 10 min
@@ -69,13 +70,6 @@
     // 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
@@ -96,10 +90,19 @@
     // new environments.  A value of ``null`` means that the variable
     // will not be set for the current combination.
     //
-    "matrix": {
-        "python": [""],
+     "matrix": {
+        "setuptools_scm": [""],
+        "xarray": [""],
+        "netcdf4": [""],
+        "pip+pyfma": [""]
     },
 
+
+    "build_command": [
+        "python -m build",
+        "python -mpip wheel --no-deps --no-build-isolation --no-index -w {build_cache_dir} {build_dir}"
+    ],
+
     // 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.

benchmarks/quad_hexagon.py

@@ -14,9 +14,9 @@ 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 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`"""
@@ -27,9 +27,9 @@ 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 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`"""

ci/environment.yml

@@ -1,22 +1,27 @@
 name: uxarray_build
 channels:
   - conda-forge
+  - nodefaults
 dependencies:
+  - antimeridian
   - cartopy
   - dask
   - datashader
   - gmpy2
+  - h5netcdf
+  - hdf5
   - holoviews
   - matplotlib-base
   - matplotlib-inline
   - netcdf4
   - numba
-  - numpy
+  - numpy<2
   - pandas<2.1.0
   - pathlib
   - pre_commit
   - pyarrow
   - pytest
+  - pip
   - pytest-cov
   - requests
   - scikit-learn
@@ -25,5 +30,4 @@ dependencies:
   - spatialpandas
   - xarray
   - pip:
-    - antimeridian
     - pyfma