Files
rustfs/.github/workflows/rustfs-heal-test.yml
T
hector b6c3108e53 fix(ci): keep functional workflow chain running after failures (#6926)
* fix(ci): isolate s3 compat temp file paths

* fix(ci): use rooted auto-testing s3 temp fix

* fix(ci): follow auto-testing main after temp-path merge

* fix(ci): stabilize tier mqtt bootstrap on shared runner

* feat(ci): publish functional reports and keep workflows non-blocking

* fix(ci): keep functional chain running after failures

* fix(ci): standardize functional workflow cleanup steps
2026-08-31 08:43:28 +08:00

156 lines
5.8 KiB
YAML

name: RustFS Heal Test
on:
workflow_dispatch:
inputs:
package_url:
description: 'Direct .deb URL (nightly/R2). Defaults to the latest nightly deb.'
required: false
type: string
stop_node_gb:
description: 'Stop the outage node when surviving nodes reach N GiB'
required: false
default: '15'
warp_stop_gb:
description: '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
permissions:
contents: read
# Only one test at a time: both this and the pool-expansion workflow mutate
# the same test environment, so they share one concurrency group.
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 }}
RUSTFS_NIGHTLY_PACKAGE_URL: ${{ vars.RUSTFS_NIGHTLY_PACKAGE_URL || 'https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb' }}
jobs:
heal-test:
runs-on: smoke-testing
timeout-minutes: 480
# Manual-only standalone run. Nightly chain already runs heal in
# rustfs-pool-expand-test.yml to avoid duplicate heal executions.
if: ${{ github.event_name == 'workflow_dispatch' }}
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
${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
'
done
- name: Install RustFS package & start cluster
run: |
ARGS=(--steps "1,2" -y --endpoint "${{ 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 "${ARGS[@]}"
- name: Run heal test (write -> outage -> heal -> verify)
run: |
./auto-testing/rustfs_heal_test.sh \
--steps "3,4,5,6,7" -y \
--endpoint "${{ env.RUSTFS_API_ENDPOINT }}" \
--stop-node-gb "${{ inputs.stop_node_gb }}" \
--warp-stop-gb "${{ inputs.warp_stop_gb }}" \
--log-file /tmp/rustfs-heal-test.log
- 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."