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
This commit is contained in:
hector
2026-08-31 08:43:28 +08:00
committed by GitHub
parent 8ecd8f2520
commit b6c3108e53
5 changed files with 722 additions and 96 deletions
+148 -87
View File
@@ -46,7 +46,7 @@ on:
type: boolean
default: true
workflow_run:
# Strict shared-environment order: run after tier test succeeds.
# Strict shared-environment order: run after tier test completes.
workflows: ["RustFS Tier Test"]
types: [completed]
@@ -75,11 +75,124 @@ env:
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
if: ${{ github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success' }}
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
@@ -98,13 +211,26 @@ jobs:
warp --version || true
df -h /data | tail -1
- name: Reset test environment (before)
- name: Cleanup environment (before)
if: ${{ inputs.cleanup_before != 'false' }}
run: |
chmod +x auto-testing/rustfs_pool_expand.sh
./auto-testing/rustfs_pool_expand.sh --reset -y
set -euo pipefail
read -r -a NODES <<< "${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
${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
'
done
- name: Install RustFS package & start first pool
- name: Install RustFS package & start cluster
run: |
ARGS=(--steps "1,2,3" -y --endpoint "${{ env.RUSTFS_API_ENDPOINT }}")
if [ -n "${{ inputs.package_url }}" ]; then
@@ -163,10 +289,24 @@ jobs:
/tmp/rustfs-warp.*.log
if-no-files-found: warn
- name: Reset test environment (after)
- name: Cleanup environment (after)
if: ${{ always() && inputs.cleanup_after != 'false' }}
run: |
./auto-testing/rustfs_pool_expand.sh --reset -y
set -euo pipefail
read -r -a NODES <<< "${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()
@@ -174,82 +314,3 @@ jobs:
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."
# Heal regression runs after the pool test regardless of its outcome: a pool
# failure must be reported (it makes the run red) but must not block heal.
heal-test:
name: Heal test (after pool test)
runs-on: smoke-testing
timeout-minutes: 480
needs: pool-expansion-test
if: ${{ always() && (github.event_name == 'workflow_dispatch' || github.event.workflow_run.conclusion == 'success') }}
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: Reset test environment (before)
if: ${{ inputs.cleanup_before != 'false' }}
run: |
chmod +x auto-testing/rustfs_heal_test.sh
./auto-testing/rustfs_heal_test.sh --reset -y
- name: Install RustFS package & start cluster
run: |
ARGS=(--steps "1,2" -y --endpoint "${{ 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: Reset test environment (after)
if: ${{ always() && inputs.cleanup_after != 'false' }}
run: |
./auto-testing/rustfs_heal_test.sh --reset -y
- name: Notify on failure
if: failure()
run: |
echo "RustFS heal test failed"
echo "See the uploaded log artifact for details."