rustfs/.github/workflows/rustfs-pool-expand-test.yml

name: RustFS Pool Expansion / Heal Test

on:
  workflow_dispatch:
    inputs:
      rustfs_version:
        description: 'RustFS release tag to test (leave empty to use the latest nightly deb)'
        required: false
      package_url:
        description: 'Direct .deb URL (nightly/R2/dev). Overrides rustfs_version.'
        required: false
        type: string
      pools:
        description: 'Number of pools to expand to (2 = first rebalance only)'
        type: choice
        options:
          - '2'
          - '3'
        default: '3'
      storage_threshold:
        description: 'Stop writing when storage usage reaches N%'
        required: false
        default: '50'
      warp_duration:
        description: 'warp write duration (e.g. 5m, 10m)'
        required: false
        default: '10m'
      run_decommission:
        description: 'Run the pool decommission step (3-pool topology only)'
        type: boolean
        default: true
      stop_node_gb:
        description: 'Heal: stop the outage node when surviving nodes reach N GiB'
        required: false
        default: '15'
      warp_stop_gb:
        description: 'Heal: stop warp when surviving nodes reach N GiB'
        required: false
        default: '40'
      cleanup_before:
        description: 'Reset the nodes before the test (DESTROYS existing data/config)'
        type: boolean
        default: true
      cleanup_after:
        description: 'Reset the nodes after the test (DESTROYS test data/config)'
        type: boolean
        default: true
  workflow_run:
    # Strict shared-environment order: run after tier test completes.
    workflows: ["RustFS Tier Test"]
    types: [completed]

permissions:
  contents: read

# Only one test run at a time: every job mutates the same shared test
# environment (vm000/vm001/vm002), so concurrent runs must not clobber each
# other. Jobs inside a run are chained with needs to serialize them.
concurrency:
  group: rustfs-shared-functional-tests
  cancel-in-progress: false

defaults:
  run:
    shell: bash

env:
  RUSTFS_ACCESS_KEY: ${{ secrets.RUSTFS_ACCESS_KEY }}
  RUSTFS_SECRET_KEY: ${{ secrets.RUSTFS_SECRET_KEY }}
  RUSTFS_API_ENDPOINT: ${{ secrets.RUSTFS_API_ENDPOINT || vars.RUSTFS_API_ENDPOINT || vars.RUSTFS_RC_ENDPOINT }}
  RUSTFS_NODES: ${{ secrets.RUSTFS_NODES || vars.RUSTFS_NODES }}
  RUSTFS_SSH_USER: ${{ secrets.RUSTFS_SSH_USER || vars.RUSTFS_SSH_USER }}
  # Package used by the nightly run (workflow_dispatch inputs are empty for
  # workflow_run events), i.e. the latest nightly deb published by nightly-gnu.yml.
  RUSTFS_NIGHTLY_PACKAGE_URL: ${{ vars.RUSTFS_NIGHTLY_PACKAGE_URL || 'https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb' }}

jobs:
  heal-test:
    name: Heal test
    runs-on: smoke-testing
    timeout-minutes: 480
    if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run' }}
    steps:
      - name: Checkout auto-testing scripts
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
        with:
          repository: rustfs/auto-testing
          ref: main
          path: auto-testing
          persist-credentials: false
          token: ${{ secrets.PF_TESTING_GH_TOKEN }}

      - name: Show environment
        run: |
          uname -a
          jq --version
          openssl version
          df -h /data | tail -1

      - name: Cleanup environment (before)
        if: ${{ inputs.cleanup_before != 'false' }}
        run: |
          set -euo pipefail
          read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
          SSH_USER="${RUSTFS_SSH_USER:-azureuser}"
          for node in "${NODES[@]}"; do
            ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new "${SSH_USER}@${node}" '
              set -euo pipefail
              SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
              ${SUDO} systemctl stop rustfs 2>/dev/null || true
              if ${SUDO} dpkg -l rustfs 2>/dev/null | grep -q "^ii"; then
                ${SUDO} dpkg -P rustfs
              fi
              for i in 1 2 3 4; do ${SUDO} rm -rf /data/rustfs${i}/mnmd; done
              ${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
            '
          done

      - name: Install RustFS package & start cluster
        run: |
          ARGS=(--steps "1,2" -y --endpoint "${{ env.RUSTFS_API_ENDPOINT }}")
          if [ -n "${{ inputs.package_url }}" ]; then
            ARGS+=(--package-url "${{ inputs.package_url }}")
          else
            ARGS+=(--package-url "${{ env.RUSTFS_NIGHTLY_PACKAGE_URL }}")
          fi
          ./auto-testing/rustfs_heal_test.sh "${ARGS[@]}"

      - name: Preflight checks
        run: |
          ARGS=(--preflight --endpoint "${{ env.RUSTFS_API_ENDPOINT }}")
          if [ -n "${{ inputs.package_url }}" ]; then
            ARGS+=(--package-url "${{ inputs.package_url }}")
          else
            ARGS+=(--package-url "${{ env.RUSTFS_NIGHTLY_PACKAGE_URL }}")
          fi
          ./auto-testing/rustfs_heal_test.sh "${ARGS[@]}"

      - name: Run heal test (write -> outage -> heal -> verify)
        run: |
          ARGS=(--steps "3,4,5,6,7" -y \
            --endpoint "${{ env.RUSTFS_API_ENDPOINT }}" \
            --stop-node-gb "${{ inputs.stop_node_gb || '15' }}" \
            --warp-stop-gb "${{ inputs.warp_stop_gb || '40' }}" \
            --log-file /tmp/rustfs-heal-test.log)
          if [ -n "${{ inputs.package_url }}" ]; then
            ARGS+=(--package-url "${{ inputs.package_url }}")
          else
            ARGS+=(--package-url "${{ env.RUSTFS_NIGHTLY_PACKAGE_URL }}")
          fi
          ./auto-testing/rustfs_heal_test.sh "${ARGS[@]}"

      - name: Upload test logs
        if: always()
        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
        with:
          name: rustfs-heal-test-${{ github.run_id }}
          path: |
            /tmp/rustfs-heal-test.log
            /tmp/rustfs-warp.*.log
          if-no-files-found: warn

      - name: Cleanup environment (after)
        if: ${{ always() && inputs.cleanup_after != 'false' }}
        run: |
          set -euo pipefail
          read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
          SSH_USER="${RUSTFS_SSH_USER:-azureuser}"
          for node in "${NODES[@]}"; do
            ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new "${SSH_USER}@${node}" '
              set -euo pipefail
              SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
              ${SUDO} systemctl stop rustfs 2>/dev/null || true
              if ${SUDO} dpkg -l rustfs 2>/dev/null | grep -q "^ii"; then
                ${SUDO} dpkg -P rustfs
              fi
              for i in 1 2 3 4; do ${SUDO} rm -rf /data/rustfs${i}/mnmd; done
              ${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
            '
          done

      - name: Notify on failure
        if: failure()
        run: |
          echo "RustFS heal test failed"
          echo "Package source: ${{ inputs.package_url || 'nightly (R2 latest)' }}"
          echo "See the uploaded log artifact for details."

  # Pool expansion runs after heal regardless of heal outcome.
  pool-expansion-test:
    name: Pool expansion / decommission test
    runs-on: smoke-testing
    timeout-minutes: 360
    needs: heal-test
    if: ${{ always() && (github.event_name == 'workflow_dispatch' || github.event_name == 'workflow_run') }}
    steps:
      - name: Checkout auto-testing scripts
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
        with:
          repository: rustfs/auto-testing
          ref: main
          path: auto-testing
          persist-credentials: false
          token: ${{ secrets.PF_TESTING_GH_TOKEN }}

      - name: Show environment
        run: |
          uname -a
          jq --version
          openssl version
          warp --version || true
          df -h /data | tail -1

      - name: Cleanup environment (before)
        if: ${{ inputs.cleanup_before != 'false' }}
        run: |
          set -euo pipefail
          read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
          SSH_USER="${RUSTFS_SSH_USER:-azureuser}"
          for node in "${NODES[@]}"; do
            ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new "${SSH_USER}@${node}" '
              set -euo pipefail
              SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
              ${SUDO} systemctl stop rustfs 2>/dev/null || true
              if ${SUDO} dpkg -l rustfs 2>/dev/null | grep -q "^ii"; then
                ${SUDO} dpkg -P rustfs
              fi
              for i in 1 2 3 4; do ${SUDO} rm -rf /data/rustfs${i}/mnmd; done
              ${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
            '
          done

      - name: Install RustFS package & start cluster
        run: |
          ARGS=(--steps "1,2,3" -y --endpoint "${{ env.RUSTFS_API_ENDPOINT }}")
          if [ -n "${{ inputs.package_url }}" ]; then
            ARGS+=(--package-url "${{ inputs.package_url }}")
          elif [ -n "${{ inputs.rustfs_version }}" ]; then
            ARGS+=(--version "${{ inputs.rustfs_version }}")
          else
            ARGS+=(--package-url "${{ env.RUSTFS_NIGHTLY_PACKAGE_URL }}")
          fi
          ./auto-testing/rustfs_pool_expand.sh "${ARGS[@]}"

      - name: Preflight checks
        run: |
          ARGS=(--preflight --endpoint "${{ env.RUSTFS_API_ENDPOINT }}")
          if [ -n "${{ inputs.package_url }}" ]; then
            ARGS+=(--package-url "${{ inputs.package_url }}")
          elif [ -n "${{ inputs.rustfs_version }}" ]; then
            ARGS+=(--version "${{ inputs.rustfs_version }}")
          else
            ARGS+=(--package-url "${{ env.RUSTFS_NIGHTLY_PACKAGE_URL }}")
          fi
          ./auto-testing/rustfs_pool_expand.sh "${ARGS[@]}"

      - name: Run pool expansion & decommission test
        id: pool_test
        run: |
          set -o pipefail
          STEPS="4,5,6"
          if [ "${{ inputs.pools || '3' }}" = "3" ]; then
            STEPS="$STEPS,7,8"
            if [ "${{ inputs.run_decommission != 'false' }}" = "true" ]; then
              STEPS="$STEPS,9"
            fi
          fi
          ARGS=(--steps "$STEPS" --with-warp -y \
            --endpoint "${{ env.RUSTFS_API_ENDPOINT }}" \
            --storage-threshold "${{ inputs.storage_threshold || '50' }}" \
            --warp-duration "${{ inputs.warp_duration || '10m' }}" \
            --log-file /tmp/rustfs-pool-test.log)
          if [ -n "${{ inputs.package_url }}" ]; then
            ARGS+=(--package-url "${{ inputs.package_url }}")
          elif [ -n "${{ inputs.rustfs_version }}" ]; then
            ARGS+=(--version "${{ inputs.rustfs_version }}")
          else
            ARGS+=(--package-url "${{ env.RUSTFS_NIGHTLY_PACKAGE_URL }}")
          fi
          ./auto-testing/rustfs_pool_expand.sh "${ARGS[@]}"

      - name: Upload test logs
        if: always()
        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
        with:
          name: rustfs-pool-test-${{ github.run_id }}
          path: |
            /tmp/rustfs-pool-test*.log
            /tmp/rustfs-warp.*.log
          if-no-files-found: warn

      - name: Cleanup environment (after)
        if: ${{ always() && inputs.cleanup_after != 'false' }}
        run: |
          set -euo pipefail
          read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
          SSH_USER="${RUSTFS_SSH_USER:-azureuser}"
          for node in "${NODES[@]}"; do
            ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new "${SSH_USER}@${node}" '
              set -euo pipefail
              SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
              ${SUDO} systemctl stop rustfs 2>/dev/null || true
              if ${SUDO} dpkg -l rustfs 2>/dev/null | grep -q "^ii"; then
                ${SUDO} dpkg -P rustfs
              fi
              for i in 1 2 3 4; do ${SUDO} rm -rf /data/rustfs${i}/mnmd; done
              ${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
            '
          done

      - name: Notify on failure
        if: failure()
        run: |
          echo "RustFS pool expansion test failed"
          echo "Package source: ${{ inputs.package_url || inputs.rustfs_version || 'nightly (R2 latest)' }}"
          echo "See the uploaded log artifact for details."