Merge pull request #19 from converged-computing/first-release

prepare for first release

.github/workflows/release.yaml

@@ -0,0 +1,142 @@
+name: metrics operator tag and release
+
+on:
+  workflow_dispatch:
+    inputs:
+      release_tag:
+        description: Custom release tag
+        type: string
+        required: true
+
+jobs:
+  build-arm:
+    runs-on: ubuntu-latest
+    name: make and build arm
+    steps:
+    - name: Checkout Repository
+      uses: actions/checkout@v3
+    - name: Set tag
+      run: |
+        echo "Tag for release is ${{ inputs.release_tag }}"
+        echo "tag=${{ inputs.release_tag }}" >> ${GITHUB_ENV}
+    - uses: actions/setup-go@v3
+      with:
+        go-version: ^1.20
+    - name: GHCR Login
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Add custom buildx ARM builder
+      run: |
+       docker buildx create --name armbuilder
+       docker buildx use armbuilder
+       docker buildx inspect --bootstrap
+
+    - name: Deploy Container
+      env:
+        tag: ${{ env.tag }}
+      run: make arm-deploy ARMIMG=ghcr.io/converged-computing/metrics-operator:${tag}-arm
+
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        command: [docker]
+    name: make and build ${{ matrix.command }}
+    steps:
+    - name: Checkout Repository
+      uses: actions/checkout@v3
+    - uses: actions/setup-go@v3
+      with:
+        go-version: ^1.20
+    - name: Set tag
+      run: |
+        echo "Tag for release is ${{ inputs.release_tag }}"
+        echo "tag=${{ inputs.release_tag }}" >> ${GITHUB_ENV}
+    - name: GHCR Login
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Build Container
+      env:
+        tag: ${{ env.tag }}
+      run: |
+        image=ghcr.io/converged-computing/metrics-operator-${{ matrix.command }}:v${tag}
+        img=ghcr.io/converged-computing/metrics-operator:v${tag}
+        make ${{ matrix.command }}-build BUNDLE_IMG=${image} IMG=${img} CATALOG_IMG=${image}
+
+    - name: Deploy Container
+      env:
+        tag: ${{ env.tag }}
+      run: |
+        image=ghcr.io/converged-computing/metrics-operator-${{ matrix.command }}:v${tag}
+        img=ghcr.io/converged-computing/metrics-operator:v${tag}
+        make ${{ matrix.command }}-push BUNDLE_IMG=${image} IMG=${img} CATALOG_IMG=${image}
+
+  release:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v3
+    - uses: actions/setup-go@v3
+      with:
+        go-version: ^1.20
+    - name: Set tag
+      run: |
+        echo "Tag for release is ${{ inputs.release_tag }}"
+        echo "tag=${{ inputs.release_tag }}" >> ${GITHUB_ENV}
+    - name: Install
+      run: conda create --quiet --name mo twine
+    - name: Install dependencies
+      run: |
+        export PATH="/usr/share/miniconda/bin:$PATH"
+        source activate mo
+        pip install setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USER }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASS }}
+        tag: ${{ env.tag }}
+      run: |
+        export PATH="/usr/share/miniconda/bin:$PATH"
+        source activate mo
+        cd sdk/python/v1alpha1/
+        pip install -e .
+        python setup.py sdist bdist_wheel
+        cd dist
+        wheelfile=$(ls metricsoperator-*.whl)
+        wheelfile=$(echo "$wheelfile" | sed "s/metricsoperator-//")
+        wheelfile=$(echo "$wheelfile" | sed "s/-py3-none-any.whl//")
+        echo "Release for Python is ${wheelfile}"
+        echo "Release for metrics operator is ${tag}"
+        cd ../
+        if [[ "${wheelfile}" == "${tag}" ]]; then
+            echo "Versions are correct, publishing."          
+            twine upload dist/*
+        else
+            echo "Versions are not correct, please fix and upload locally."          
+        fi
+
+    - name: Build release manifests
+      env:
+        tag: ${{ env.tag }}
+      run: |
+        make build-config-arm ARMIMG=ghcr.io/converged-computing/metrics-operator:${tag}-arm
+        make build-config IMG=ghcr.io/converged-computing/metrics-operator:v${tag}
+    - name: Release metrics Operator
+      uses: softprops/action-gh-release@v1
+      with:
+        name: Metrics Operator Release v${{ env.tag }}
+        tag_name: ${{ env.tag }}
+        generate_release_notes: true
+        files: |
+          examples/dist/metrics-operator-arm.yaml
+          examples/dist/metrics-operator.yaml
+      env:
+        GITHUB_REPOSITORY: converged-computing/metrics-operator

README.md

@@ -5,18 +5,17 @@
 Developing metrics and a catalog of applications to assess different kinds of Kubernetes performance.
 We likely will choose different metrics that are important for HPC.
 Note that I haven't started the operator yet because I'm [testing ideas for the design](hack/test).
+To learn more:
 
-View our ⭐️ [Documentation](https://converged-computing.github.io/metrics-operator/) ⭐️
+- ⭐️ [Documentation](https://converged-computing.github.io/metrics-operator/) ⭐️
+- 🐯️ [Python module](https://pypi.org/project/metricsoperator/0.0.0/) 🐯️
 
 ## Dinosaur TODO
 
 - Find better logging library for logging outside of controller
-- Python function to save entire spec to yaml (for MetricSet and JobSet)
-- When first metric ready for use with Python (storage) do first releases
-- We should have Python SDK with parsers for output (e.g., run metric, parse output meaningfully)
-- Need a strategy for storing metrics output / logs
+- For larger metric collections, we should have a log streaming mode (and not wait for Completed/Successful)
 - For services we are measuring, we likely need to be able to kill after N seconds (to complete job) or to specify the success policy on the metrics containers instead of the application
-- TBA
+- Python function to save entire spec to yaml (for MetricSet and JobSet)?
 - Metrics parsers to do (need to add separators, formatting, python parser):
   - perf-sysstat
   - netmark / osu-benchmark

docs/_static/data/metrics.json

@@ -1,11 +1,4 @@
 [
- {
-  "name": "network-osu-benchmark",
-  "description": "point to point MPI benchmarks",
-  "type": "standalone",
-  "image": "ghcr.io/converged-computing/metric-osu-benchmark:latest",
-  "url": "https://mvapich.cse.ohio-state.edu/benchmarks/"
- },
  {
   "name": "perf-sysstat",
   "description": "statistics for Linux tasks (processes) : I/O, CPU, memory, etc.",
@@ -26,5 +19,12 @@
   "type": "standalone",
   "image": "vanessa/netmark:latest",
   "url": ""
+ },
+ {
+  "name": "network-osu-benchmark",
+  "description": "point to point MPI benchmarks",
+  "type": "standalone",
+  "image": "ghcr.io/converged-computing/metric-osu-benchmark:latest",
+  "url": "https://mvapich.cse.ohio-state.edu/benchmarks/"
  }
 ]

docs/development/developer-guide.md

@@ -108,6 +108,13 @@ I run this before I push to a GitHub branch.
 $ make pre-push
 ```
 
+We also use pre-commit for Python formatting:
+
+```bash
+pip install -r .github/dev-requirements.txt
+pre-commit run --all-files
+```
+
 ## Writing Metric Containers
 
 This section will include instructions for how to write a metrics container.

docs/getting_started/user-guide.md

@@ -98,8 +98,7 @@ Let's first review how this works.
 3. The metric output is printed in pod logs with a standard packaging (e.g., sections and headers) to distinguish output sections.
 4. We provide a Python module [metricsoperator](https://pypi.org/project/metricsoperator/) that can help you run an experiment, applying the metrics.yaml and then retrieving and parsing logs.
 
-For the last step, this is important because every metric tool is a special snowflake, outputting some custom format that is hard to parse and then plot. We hope to provide
-an easy means to do this so you can go from data collection to results more quickly. Now let's review a suggested set of steps for you as a new user! You can:
+For the last step, this is important because every metric tool is a special snowflake, outputting some custom format that is hard to parse and then plot. By providing a parser paired with each metric, we hope to provide an easy means to do this so you can go from data collection to results more quickly. Now let's review a suggested set of steps for you as a new user! You can:
 
 1. First choose one or more [metrics](metrics.md), [request a metric be added](https://github.com/converged-computing/metrics-operator/issues), or start with a pre-created [examples](https://github.com/converged-computing/metrics-operator/tree/main/examples). Often if you want to measure an application or storage or "other" (e.g., networking) we already have a metrics.yaml and associated parser suited for your needs.
 2. Run the metric directly from the metrics.yaml, or use the Python module [metricsoperator](https://pypi.org/project/metricsoperator/) to run and collect output.
@@ -119,8 +118,8 @@ and experiments that you put together here for others to use.
 For all metric types, the following applies:
 
 1. You can create more than one pod (scale the metric) as you see fit.
-2. There is always a headless service provided for metrics within the JobSet to make use of
-3. The definition of metrics in your metrics.yaml file is consistent across types
+2. There is always a headless service provided for metrics within the JobSet to make use of.
+3. The definition of metrics in your metrics.yaml file is consistent across types.
 4. Each metric type in the list can take a rate, completions, and custom options.
 
 For another overview of these designs, please see the [developer docs](../development/index.md).

docs/index.md

@@ -7,12 +7,12 @@ that you can install to your cluster to easily measure different aspects of perf
 
  - I/O metrics to assess storage options
  - system performance metrics (memory, cpu, etc.)
- - timings
+ - network or other custom metrics / timings
 
-For this project, we aim to provide both of the following:
+For this project, we aim to provide the following:
 
 1. A catalog of pre-defined metrics and associated containers you can quickly use
-2. A number of containerized HPC applications to demonstrate using the operator.
+2. A number of containerized HPC applications and experiments to demonstrate using the operator.
 
 We wanted to create this operator because we didn't have a solid understanding
 of our application performance (typically from the high performance computing space)

sdk/python/v1alpha1/.gitignore

@@ -2,3 +2,4 @@ metricsoperator.egg-info
 build
 __pycache__
 .eggs
+dist

sdk/python/v1alpha1/CHANGELOG.md

@@ -0,0 +1,18 @@
+# CHANGELOG
+
+This is a manually generated log to track changes to the repository for each release.
+Each section should include general headers such as **Implemented enhancements**
+and **Merged pull requests**. Critical items to know are:
+
+ - renamed commands
+ - deprecated / removed commands
+ - changed defaults
+ - backward incompatible changes (recipe file format? image file format?)
+ - migration guidance (how to convert images?)
+ - changed behaviour (recipe sections work differently)
+
+The versions coincide with releases on pip. Only major versions will be released as tags on Github.
+
+## [0.0.x](https://github.com/converged-computing/metrics-operator/tree/main) (0.0.x)
+ - First release with support for parsing io-sysstat output (0.0.1)
+ - Skeleton release (0.0.0)

sdk/python/v1alpha1/README.md

@@ -1,3 +1,22 @@
 # Metrics Operator Python
 
 > Helpers for submitting CRD with Python and parsing logs.
+
+![https://raw.githubusercontent.com/converged-computing/metrics-operator/main/docs/images/metrics-operator-banner.png](https://raw.githubusercontent.com/converged-computing/metrics-operator/main/docs/images/metrics-operator-banner.png)
+
+Welcome to the Metrics Operator Python! You can learn more about the operator
+at the  ⭐️ [Documentation](https://converged-computing.github.io/metrics-operator/) ⭐️
+and see our [python examples](https://github.com/converged-computing/metrics-operator/tree/main/examples/python/) for examples of using this module.
+
+## License
+
+HPCIC DevTools is distributed under the terms of the MIT license.
+All new contributions must be made under this license.
+
+See [LICENSE](https://github.com/converged-computing/cloud-select/blob/main/LICENSE),
+[COPYRIGHT](https://github.com/converged-computing/cloud-select/blob/main/COPYRIGHT), and
+[NOTICE](https://github.com/converged-computing/cloud-select/blob/main/NOTICE) for details.
+
+SPDX-License-Identifier: (MIT)
+
+LLNL-CODE- 842614

sdk/python/v1alpha1/setup.py

@@ -30,7 +30,7 @@
 if __name__ == "__main__":
     setup(
         name="metricsoperator",
-        version="0.0.0",
+        version="0.0.1",
         author="Vanessasaurus",
         author_email="[email protected]",
         maintainer="Vanessasaurus",