From a5d9bb40380c598bf7d03cb16623026892844ed4 Mon Sep 17 00:00:00 2001
From: "L. R. Couto" <57910428+lrcouto@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:57:40 -0300
Subject: [PATCH] Add Github Actions workflow to trigger pipeline performance
 test (#4231)

* Add Github Actions workflow to trigger pipeline performance test

Signed-off-by: Laura Couto <laurarccouto@gmail.com>

* Lint

Signed-off-by: Laura Couto <laurarccouto@gmail.com>

* Lint

Signed-off-by: Laura Couto <laurarccouto@gmail.com>

* Change trigger to PR label

Signed-off-by: Laura Couto <laurarccouto@gmail.com>

* Run workflow on kedro repo

Signed-off-by: Laura Couto <laurarccouto@gmail.com>

* Change setup-python version to 5

Signed-off-by: L. R. Couto <57910428+lrcouto@users.noreply.github.com>

---------

Signed-off-by: Laura Couto <laurarccouto@gmail.com>
Signed-off-by: L. R. Couto <57910428+lrcouto@users.noreply.github.com>
---
 .../workflows/pipeline-performance-test.yml   | 79 +++++++++++++++++++
 1 file changed, 79 insertions(+)
 create mode 100644 .github/workflows/pipeline-performance-test.yml

diff --git a/.github/workflows/pipeline-performance-test.yml b/.github/workflows/pipeline-performance-test.yml
new file mode 100644
index 0000000000..58fb582213
--- /dev/null
+++ b/.github/workflows/pipeline-performance-test.yml
@@ -0,0 +1,79 @@
+name: Trigger and Run Pipeline Performance Test
+
+on:
+  pull_request:
+    types: [labeled]
+
+jobs:
+  performance-test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Check if 'performance' label was added
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: echo "Performance label detected. Running performance test."
+
+    - name: Clone test repo
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: |
+        git clone https://x-access-token:${{ secrets.GH_TAGGING_TOKEN }}@github.com/kedro-org/pipeline-performance-test.git
+
+    - name: Set up Python 3.11
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.11'
+
+    - name: Install dependencies
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: |
+        pip install kedro
+        pip install uv
+        cd pipeline-performance-test/performance-test
+        pip install -r requirements.txt
+
+    - name: Run performance test and capture time for latest Kedro release
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: |
+        cd pipeline-performance-test/performance-test
+        total_time_release=0.0
+        for i in {1..10}; do
+          { time kedro run; } 2> release_time_output.txt
+          real_time_release=$(grep real release_time_output.txt | awk '{print $2}' | sed 's/[^0-9.]//g')
+          total_time_release=$(echo "$total_time_release + $real_time_release" | bc)
+        done
+        average_time_release=$(echo "scale=3; $total_time_release / 10" | bc)
+        echo "average_time_release=${average_time_release}" >> $GITHUB_ENV
+
+    - name: Pull specific branch from Kedro and install it
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: |
+        git clone --branch ${{ github.event.pull_request.head.ref }} https://github.com/kedro-org/kedro.git
+        cd kedro
+        make install
+
+    - name: Run performance test and capture time for specific Kedro branch
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: |
+        cd pipeline-performance-test/performance-test
+        total_time_branch=0.0
+        for i in {1..10}; do
+          { time kedro run --params=hook_delay=0,dataset_load_delay=0,file_save_delay=0; } 2> branch_time_output.txt
+          real_time_branch=$(grep real branch_time_output.txt | awk '{print $2}' | sed 's/[^0-9.]//g')
+          total_time_branch=$(echo "$total_time_branch + $real_time_branch" | bc)
+        done
+        average_time_branch=$(echo "scale=3; $total_time_branch / 10" | bc)
+        echo "average_time_branch=${average_time_branch}" >> $GITHUB_ENV
+
+    - name: Extract and format real time from release version
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: echo "Average elapsed time for Kedro release version test was ${average_time_release} seconds"
+
+    - name: Extract and format real time from specific branch
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: echo "Average elapsed time for specific branch test was ${average_time_branch} seconds"
+
+    - name: Clean up time output files
+      if: github.event.action == 'labeled' && contains(github.event.label.name, 'performance')
+      run: |
+        rm pipeline-performance-test/performance-test/release_time_output.txt pipeline-performance-test/performance-test/branch_time_output.txt