From 8664fad9bacebe002c8e939fd17d99b423f38aa1 Mon Sep 17 00:00:00 2001
From: Mike Sarahan <msarahan@nvidia.com>
Date: Fri, 15 Nov 2024 14:54:05 -0600
Subject: [PATCH] add telemetry setup to test (#16924)

This is a prototype implementation of https://github.com/rapidsai/build-infra/issues/139

The work that this builds on:
* https://github.com/rapidsai/gha-tools/pull/118, which adds a shell wrapper that automatically creates spans for the commands that it wraps. It also uses the `opentelemetry-instrument` command to set up monkeypatching for supported Python libraries, if the command is python-based
* https://github.com/rapidsai/shared-workflows/tree/add-telemetry, which installs the gha-tools work from above and sets necessary environment variables. This is only done for the conda-cpp-build.yaml shared workflow at the time of submitting this PR.

The goal of this PR is to observe telemetry data sent from a GitHub Actions build triggered by this PR as a proof of concept. Once it all works, the remaining work is:

* merge https://github.com/rapidsai/gha-tools/pull/118
* Move the opentelemetry-related install stuff in https://github.com/rapidsai/shared-workflows/compare/add-telemetry?expand=1#diff-ca6188672785b5d214aaac2bf77ce0528a48481b2a16b35aeb78ea877b2567bcR118-R125 into https://github.com/rapidsai/ci-imgs, and rebuild ci-imgs
* expand coverage to other shared workflows
* Incorporate the changes from this PR to other jobs and to other repos

Authors:
  - Mike Sarahan (https://github.com/msarahan)

Approvers:
  - Bradley Dice (https://github.com/bdice)

URL: https://github.com/rapidsai/cudf/pull/16924
---
 .github/workflows/pr.yaml | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/.github/workflows/pr.yaml b/.github/workflows/pr.yaml
index 694b11dbe1d..a8f5023ef76 100644
--- a/.github/workflows/pr.yaml
+++ b/.github/workflows/pr.yaml
@@ -10,6 +10,7 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  # Please keep pr-builder as the top job here
   pr-builder:
     needs:
       - changed-files
@@ -37,13 +38,23 @@ jobs:
       - unit-tests-cudf-pandas
       - pandas-tests
       - pandas-tests-diff
+      - telemetry-setup
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/pr-builder.yaml@branch-24.12
     if: always()
     with:
       needs: ${{ toJSON(needs) }}
+  telemetry-setup:
+    continue-on-error: true
+    runs-on: ubuntu-latest
+    env:
+      OTEL_SERVICE_NAME: 'pr-cudf'
+    steps:
+      - name: Telemetry setup
+        uses: rapidsai/shared-actions/telemetry-dispatch-stash-base-env-vars@main
   changed-files:
     secrets: inherit
+    needs: telemetry-setup
     uses: rapidsai/shared-workflows/.github/workflows/changed-files.yaml@branch-24.12
     with:
       files_yaml: |
@@ -91,9 +102,11 @@ jobs:
           - '!notebooks/**'
   checks:
     secrets: inherit
+    needs: telemetry-setup
     uses: rapidsai/shared-workflows/.github/workflows/checks.yaml@branch-24.12
     with:
       enable_check_generated_files: false
+      ignored_pr_jobs: "telemetry-summarize"
   conda-cpp-build:
     needs: checks
     secrets: inherit
@@ -260,6 +273,7 @@ jobs:
   devcontainer:
     secrets: inherit
     uses: rapidsai/shared-workflows/.github/workflows/build-in-devcontainer.yaml@branch-24.12
+    needs: telemetry-setup
     with:
       arch: '["amd64"]'
       cuda: '["12.5"]'
@@ -298,3 +312,18 @@ jobs:
         node_type: cpu4
         build_type: pull-request
         run_script: "ci/cudf_pandas_scripts/pandas-tests/diff.sh"
+
+  telemetry-summarize:
+    runs-on: ubuntu-latest
+    needs: pr-builder
+    if: always()
+    continue-on-error: true
+    steps:
+      - name: Load stashed telemetry env vars
+        uses: rapidsai/shared-actions/telemetry-dispatch-load-base-env-vars@main
+        with:
+            load_service_name: true
+      - name: Telemetry summarize
+        uses: rapidsai/shared-actions/telemetry-dispatch-write-summary@main
+        with:
+          cert_concat: "${{ secrets.OTEL_EXPORTER_OTLP_CA_CERTIFICATE }};${{ secrets.OTEL_EXPORTER_OTLP_CLIENT_CERTIFICATE }};${{ secrets.OTEL_EXPORTER_OTLP_CLIENT_KEY }}"