jrmccluskey commented on code in PR #33391: URL: https://github.com/apache/beam/pull/33391#discussion_r1887483537
########## .github/workflows/beam_CostBenchmark_Python_TF_MNIST_Classification_Dataflow.yml: ########## @@ -0,0 +1,91 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +name: Cost Benchmark Python TF MNIST Classification Dataflow + +on: + workflow_dispatch: + +#Setting explicit permissions for the action to avoid the default permissions which are `write-all` in case of pull_request_target event +permissions: + actions: write + pull-requests: read + checks: read + contents: read + deployments: read + id-token: none + issues: read + discussions: read + packages: read + pages: read + repository-projects: read + security-events: read + statuses: read + +# This allows a subsequently queued workflow run to interrupt previous runs +concurrency: + group: '${{ github.workflow }} @ ${{ github.event.issue.number || github.sha || github.head_ref || github.ref }}-${{ github.event.schedule || github.event.comment.id || github.event.sender.login }}' + cancel-in-progress: true + +env: + DEVELOCITY_ACCESS_KEY: ${{ secrets.GE_ACCESS_TOKEN }} + GRADLE_ENTERPRISE_CACHE_USERNAME: ${{ secrets.GE_CACHE_USERNAME }} + GRADLE_ENTERPRISE_CACHE_PASSWORD: ${{ secrets.GE_CACHE_PASSWORD }} + INFLUXDB_USER: ${{ secrets.INFLUXDB_USER }} + INFLUXDB_USER_PASSWORD: ${{ secrets.INFLUXDB_USER_PASSWORD }} + +jobs: + beam_Inference_Python_Benchmarks_Dataflow: + if: | + github.event_name == 'workflow_dispatch' + runs-on: [self-hosted, ubuntu-20.04, main] + timeout-minutes: 900 + name: ${{ matrix.job_name }} (${{ matrix.job_phrase }}) + strategy: + matrix: + job_name: ["beam_CostBenchmark_Python_TF_MNIST_Classification_Dataflow"] + job_phrase: ["Run TF MNIST Classification Cost Benchmark"] + steps: + - uses: actions/checkout@v4 + - name: Setup repository + uses: ./.github/actions/setup-action + with: + comment_phrase: ${{ matrix.job_phrase }} + github_token: ${{ secrets.GITHUB_TOKEN }} + github_job: ${{ matrix.job_name }} (${{ matrix.job_phrase }}) + - name: Setup Python environment + uses: ./.github/actions/setup-environment-action + with: + python-version: '3.10' + - name: Prepare test arguments + uses: ./.github/actions/test-arguments-action + with: + test-type: load + test-language: python + argument-file-paths: | + ${{ github.workspace }}/.github/workflows/cost-benchmarks-pipeline-options/python_tf_mnist_classification.txt + # The env variables are created and populated in the test-arguments-action as "<github.job>_test_arguments_<argument_file_paths_index>" + - name: get current time + run: echo "NOW_UTC=$(date '+%m%d%H%M%S' --utc)" >> $GITHUB_ENV + - name: run wordcount on Dataflow Python + uses: ./.github/actions/gradle-command-self-hosted-action + timeout-minutes: 30 + with: + gradle-command: :sdks:python:apache_beam:testing:load_tests:run + arguments: | + -PloadTest.mainClass=apache_beam.testing.benchmarks.inference.tensorflow_mnist_classification_cost_benchmark \ + -Prunner=DataflowRunner \ + -PpythonVersion=3.10 \ + '-PloadTest.args=${{ env.beam_Inference_Python_Benchmarks_Dataflow_test_arguments_1 }} --job_name=benchmark-tests-tf-mnist-classification-python-${{env.NOW_UTC}} --input_file=gs://apache-beam-ml/testing/inputs/it_mnist_data.csv --output_file=gs://temp-storage-for-end-to-end-tests/wordcount/result_tf_mnist-${{env.NOW_UTC}}.txt --model=gs://apache-beam-ml/models/tensorflow/mnist/' \ Review Comment: Eventually we can bundle them either by framework or put them all together in one workflow, this is largely just me building on the wordcount example benchmark by having a RunInference-specific instance (the most important distinction is the need to include a requirements file for Dataflow workers, but the pattern will largely hold for custom containers with CUDA deps too.) If we wanted to go ahead and choose one of those routes we could go ahead and do that now + set the workflow up for cron scheduling, I'm not opposed to that. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
