Oxicloud/.github/workflows/load-nightly.yml

name: Load Nightly

# Nightly regression gate. Runs every k6 scenario, diffs against
# baseline/load.json, opens an issue if any metric regresses.
#
# IMPORTANT: shared GitHub-hosted runners produce noisy timings —
# regression signal is unreliable until this workflow is moved to a
# pinned self-hosted runner with consistent hardware. The cron run is
# informational until then; treat opened issues as "investigate" not
# "broken main."

on:
  schedule:
    # 03:00 UTC daily — outside US/EU working hours, low contention.
    - cron: '0 3 * * *'
  workflow_dispatch:

env:
  CARGO_TERM_COLOR: always

jobs:
  load:
    name: k6 load suite + baseline diff
    # Skip the scheduled run on forks — nightly is only meaningful against the
    # canonical baseline.json on the upstream repo. Forks can still hit it
    # manually via `workflow_dispatch` if they want, and the guard is bypassed
    # for that path (event != schedule). Additional fork repositories are
    # opted-in explicitly below.
    if: github.event_name != 'schedule' || github.repository == 'AtalayaLabs/OxiCloud' || github.repository == 'EdouardVanbelle/OxiCloud'
    # tunning on Ed's nuc to ensure stable environment
    # treating regressions here as merge-blocking. ubuntu-latest is too noisy
    # for trustworthy p95/p99 deltas.
    runs-on: [self-hosted, nuc-loadtest]
    timeout-minutes: 45
    steps:
      - uses: actions/checkout@v4
        with:
          # The self-hosted runner bind-mounts target/ as a persistent volume
          # for fast incremental rebuilds. actions/checkout's default cleanup
          # tries to rmdir it and hits EBUSY on the mount point. Git still
          # syncs the working tree to the target SHA — only non-git files
          # (target/, tests/load/results/) persist, which is what we want.
          clean: false

      - uses: dtolnay/rust-toolchain@stable

      - uses: Swatinem/rust-cache@v2
        with:
          shared-key: load

      - name: Install Node 20
        # The self-hosted runner image ships Node 12, which can't parse the
        # ES-module `.mjs` helpers (compare.mjs / merge-summaries.mjs /
        # bake-baseline.mjs). Pin to a current LTS for both runners.
        uses: actions/setup-node@v4
        with:
          node-version: '20'

      - name: Install k6
        uses: grafana/setup-k6-action@v1

      - name: Build OxiCloud + load-seed (release)
        # Single cargo invocation: load_seed_bin is an empty marker feature
        # that gates the load-seed bin without changing oxicloud's dep
        # graph, so cargo compiles oxicloud exactly once.
        run: cargo build --release --features load_seed_bin --bin oxicloud --bin load-seed

      - name: Run full load suite
        id: load
        run: bash tests/load/run.sh
        env:
          BUILD_TARGET: release
        continue-on-error: true

      - name: Upload raw k6 summaries
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: load-results-${{ github.run_id }}
          path: tests/load/results/*.json
          retention-days: 30

      - name: Prepare regression report
        if: steps.load.outcome == 'failure'
        run: |
          {
            echo "## Load nightly regression"
            echo ""
            echo "Run: \`${{ github.run_id }}\`  ·  Commit: \`${{ github.sha }}\`"
            echo "Runner: \`${{ runner.name }}\` (\`${{ runner.os }}/${{ runner.arch }}\`)"
            echo ""
            echo "Compare exited non-zero — see uploaded artifact \`load-results-${{ github.run_id }}\` for raw summaries."
            echo ""
            echo "Baseline is anchored to the runner that produced it; cross-runner"
            echo "comparisons (e.g. an artifact baked on different hardware) will"
            echo "show large \"regressions\" that are really hardware deltas."
          } > regression-issue.md

      - name: Open issue on regression
        # Skip on forks where Issues are disabled — the regression report is
        # already in the artifact, and the workflow's exit code marks the run
        # as failed regardless. Forks that want issue notifications can enable
        # issues on their repo and remove this condition.
        if: steps.load.outcome == 'failure' && github.repository == 'AtalayaLabs/OxiCloud'
        uses: peter-evans/create-issue-from-file@v5
        with:
          title: "Load nightly: regression on ${{ github.sha }}"
          content-filepath: regression-issue.md
          labels: |
            load-test
            regression