Files
rustfs/.github/workflows/rustfs-pool-expand-test.yml
hector bba934723a ci(functional): retry chain handoffs and alert on stall (#7023)
The repository_dispatch handoff step was continue-on-error with a single
attempt: if the call failed (token lacking contents:write, transient API
error), the chain stalled silently while every job stayed green.

Each handoff now retries 3x and, if all attempts fail, files an alert
issue in rustfs/backlog with the exact recovery command before exiting 1
(still continue-on-error, so suite workflows themselves never fail).
2026-09-01 23:11:25 +08:00

652 lines
30 KiB
YAML

name: RustFS Pool Expansion 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'
warp_concurrent:
description: 'Pool fill: concurrent warp operations'
required: false
default: '32'
run_decommission:
description: 'Run the pool decommission step (3-pool topology only)'
type: boolean
default: true
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
repository_dispatch:
# Chain handoff: dispatched when the heal suite finishes.
types: [rustfs-chain-pool]
permissions:
contents: read
# Only one test run at a time: the job mutates the same shared test
# environment (vm000/vm001/vm002), so concurrent runs must not clobber each
# other.
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 }}
PF_TESTING_GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
# 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:
# Pool expansion: dispatched by the heal suite's chain handoff. Heal
# itself lives in rustfs-heal-test.yml and runs exactly once per chain.
pool-expansion-test:
name: Pool expansion / decommission test
runs-on: smoke-testing
# Requirement: a failing suite must not fail the workflow; failures
# are filed to rustfs/backlog and the chain continues.
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
env:
RUSTFS_POOL_ADMIN_ENDPOINT: ${{ secrets.RUSTFS_POOL_ADMIN_ENDPOINT || vars.RUSTFS_POOL_ADMIN_ENDPOINT || 'http://rustfs-node1:9000' }}
RUSTFS_POOL_PROXY_ENDPOINT: http://127.0.0.1:19000
RUSTFS_POOL_WARP_ENDPOINT: http://127.0.0.1:19000
RUSTFS_SHARED_PROXY_ENDPOINT: ${{ secrets.RUSTFS_API_ENDPOINT || vars.RUSTFS_API_ENDPOINT || vars.RUSTFS_RC_ENDPOINT }}
RUSTFS_POOL_NODE_ENDPOINTS: ${{ secrets.RUSTFS_POOL_NODE_ENDPOINTS || vars.RUSTFS_POOL_NODE_ENDPOINTS || 'http://rustfs-node1:9000 http://rustfs-node2:9000 http://rustfs-node3:9000' }}
steps:
# auto-testing is private: clone it with the dedicated PF token (not
# GITHUB_TOKEN) and retry transient GitHub/network failures.
- name: Checkout auto-testing scripts (with retry)
env:
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
run: |
set -euo pipefail
rm -rf auto-testing
for attempt in 1 2 3 4 5; do
if gh repo clone rustfs/auto-testing auto-testing -- --depth 1 --quiet; then
echo "auto-testing cloned (attempt ${attempt})"
exit 0
fi
rm -rf auto-testing
echo "clone attempt ${attempt} failed; retrying in $((attempt * 15))s" >&2
sleep $((attempt * 15))
done
echo "ERROR: unable to clone rustfs/auto-testing after 5 attempts" >&2
exit 1
- name: Initialize pool test artifacts
run: |
set -euo pipefail
ARTIFACT_DIR="${RUNNER_TEMP}/rustfs-pool-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
mkdir -p "${ARTIFACT_DIR}"
echo "POOL_ARTIFACT_DIR=${ARTIFACT_DIR}" >> "${GITHUB_ENV}"
- 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
${SUDO} rm -rf /var/log/rustfs /var/lib/rustfs/kms /var/lib/rustfs/kms-backup
'
done
- name: Install RustFS package & start cluster
run: |
ARGS=(--steps "1,2,3" -y \
--admin-endpoint "${RUSTFS_POOL_ADMIN_ENDPOINT}" \
--warp-endpoint "${RUSTFS_POOL_WARP_ENDPOINT}" \
--node-endpoints "${RUSTFS_POOL_NODE_ENDPOINTS}" \
--log-file "${POOL_ARTIFACT_DIR}/pool-test.log")
if [ -n "${{ 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 "${ARGS[@]}"
- name: Preflight checks
run: |
ARGS=(--preflight \
--admin-endpoint "${RUSTFS_POOL_ADMIN_ENDPOINT}" \
--warp-endpoint "${RUSTFS_POOL_WARP_ENDPOINT}" \
--node-endpoints "${RUSTFS_POOL_NODE_ENDPOINTS}" \
--log-file "${POOL_ARTIFACT_DIR}/pool-test.log")
if [ -n "${{ 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 "${ARGS[@]}"
- name: Reset dedicated pool proxy
run: |
set -euo pipefail
RUSTFS_POOL_NGINX_CONFIG_PATH=/etc/nginx/conf.d/rustfs-pool-test.conf \
RUSTFS_POOL_NGINX_LISTEN="${RUSTFS_POOL_PROXY_ENDPOINT#http://}" \
RUSTFS_POOL_NGINX_ACCESS_LOG=/var/log/nginx/rustfs-pool-test-access.log \
RUSTFS_POOL_NGINX_ERROR_LOG=/var/log/nginx/rustfs-pool-test-error.log \
./auto-testing/rustfs_pool_nginx_stage.sh cleanup
- name: Capture pool test baseline
run: |
set -uo pipefail
BASELINE_FILE="${POOL_ARTIFACT_DIR}/pool-baseline.log"
read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
read -r -a DIRECT_ENDPOINTS <<< "${RUSTFS_POOL_NODE_ENDPOINTS}"
SSH_USER="${RUSTFS_SSH_USER:-azureuser}"
failed=0
: > "${BASELINE_FILE}"
if [ "${#DIRECT_ENDPOINTS[@]}" -lt "${#NODES[@]}" ]; then
echo "not enough direct endpoints for the configured nodes" | tee -a "${BASELINE_FILE}" >&2
exit 1
fi
for index in "${!NODES[@]}"; do
node="${NODES[$index]}"
endpoint="${DIRECT_ENDPOINTS[$index]}"
body_file="${POOL_ARTIFACT_DIR}/ready-baseline-$((index + 1)).body"
{
echo "--- node=${node} endpoint=${endpoint} ---"
if ! ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new \
"${SSH_USER}@${node}" '
set -euo pipefail
SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
echo "--- rustfs version ---"
rustfs --version
echo "--- systemd state ---"
${SUDO} systemctl show rustfs --no-pager \
--property=ActiveState,SubState,Result,ExecMainPID,ExecMainStartTimestamp,NRestarts
'; then
echo "baseline collection failed for ${node}"
failed=1
fi
curl -sS --connect-timeout 5 --max-time 15 -o "${body_file}" \
-w "baseline_ready=${endpoint} http=%{http_code} connect=%{time_connect} ttfb=%{time_starttransfer} total=%{time_total}\n" \
"${endpoint%/}/health/ready" || true
echo "--- readiness body ---"
cat "${body_file}" 2>/dev/null || true
echo
} >> "${BASELINE_FILE}" 2>&1
done
[ "${failed}" -eq 0 ] || exit 1
- name: Run pool expansion & decommission test
id: pool_test
run: |
set -o pipefail
STEPS="4,5,6"
if [ "${{ 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 \
--admin-endpoint "${RUSTFS_POOL_ADMIN_ENDPOINT}" \
--warp-endpoint "${RUSTFS_POOL_WARP_ENDPOINT}" \
--node-endpoints "${RUSTFS_POOL_NODE_ENDPOINTS}" \
--storage-threshold "${{ inputs.storage_threshold || '50' }}" \
--warp-duration "${{ inputs.warp_duration || '10m' }}" \
--warp-concurrent "${{ inputs.warp_concurrent || '32' }}" \
--log-file "${POOL_ARTIFACT_DIR}/pool-test.log")
if [ -n "${RUSTFS_POOL_PROXY_ENDPOINT}" ]; then
ARGS+=(--proxy-endpoint "${RUSTFS_POOL_PROXY_ENDPOINT}")
fi
if [ -n "${{ 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
RUSTFS_WARP_LOG_FILE="${POOL_ARTIFACT_DIR}/warp.log" \
RUSTFS_PROXY_STAGE_HOOK=./auto-testing/rustfs_pool_nginx_stage.sh \
RUSTFS_POOL_NGINX_CONFIG_PATH=/etc/nginx/conf.d/rustfs-pool-test.conf \
RUSTFS_POOL_NGINX_LISTEN="${RUSTFS_POOL_PROXY_ENDPOINT#http://}" \
RUSTFS_POOL_NGINX_ACCESS_LOG=/var/log/nginx/rustfs-pool-test-access.log \
RUSTFS_POOL_NGINX_ERROR_LOG=/var/log/nginx/rustfs-pool-test-error.log \
./auto-testing/rustfs_pool_expand.sh "${ARGS[@]}"
- name: Collect pool test diagnostics
if: always()
run: |
set -uo pipefail
ARTIFACT_DIR="${POOL_ARTIFACT_DIR:-${RUNNER_TEMP}/rustfs-pool-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}}"
mkdir -p "${ARTIFACT_DIR}"
echo "POOL_ARTIFACT_DIR=${ARTIFACT_DIR}" >> "${GITHUB_ENV}"
redact() {
sed -E \
-e 's/(RUSTFS_(ACCESS_KEY|SECRET_KEY)=).*/\1[REDACTED]/Ig' \
-e 's/(Authorization:).*/\1 [REDACTED]/Ig' \
-e 's/(X-Amz-Signature=)[^&[:space:]]+/\1[REDACTED]/Ig' \
-e 's/(proxy_set_header[[:space:]]+Authorization[[:space:]]+).*/\1[REDACTED];/Ig' \
-e 's/^.*(password|secret|token).*/[REDACTED SENSITIVE LINE]/Ig'
}
if [ "$(id -u)" -eq 0 ]; then
SUDO=()
else
SUDO=(sudo -n)
fi
{
echo "captured_at=$(date -u +%Y-%m-%dT%H:%M:%SZ)"
echo "run_id=${GITHUB_RUN_ID}"
echo "run_attempt=${GITHUB_RUN_ATTEMPT}"
if command -v nginx >/dev/null 2>&1; then
"${SUDO[@]}" nginx -T 2>&1 || echo "nginx -T failed"
else
echo "nginx is not installed on the runner"
fi
} | redact > "${ARTIFACT_DIR}/nginx-config-redacted.txt"
for log_path in \
/var/log/nginx/access.log \
/var/log/nginx/error.log \
/var/log/nginx/rustfs-pool-test-access.log \
/var/log/nginx/rustfs-pool-test-error.log; do
log_name="$(basename "${log_path}")"
if "${SUDO[@]}" test -r "${log_path}" 2>/dev/null; then
"${SUDO[@]}" cat "${log_path}" 2>&1 | redact \
> "${ARTIFACT_DIR}/nginx-${log_name%.log}-redacted.log"
else
echo "unavailable: ${log_path}" > "${ARTIFACT_DIR}/nginx-${log_name%.log}-redacted.log"
fi
done
"${SUDO[@]}" journalctl -u nginx --no-pager -n 5000 2>&1 | redact \
> "${ARTIFACT_DIR}/nginx-journal-redacted.log" || true
read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
SSH_USER="${RUSTFS_SSH_USER:-azureuser}"
for node in "${NODES[@]}"; do
safe_node="${node//[^A-Za-z0-9_.-]/_}"
{
if ! ssh -o BatchMode=yes -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new \
"${SSH_USER}@${node}" '
SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo -n"
echo "--- rustfs version ---"
rustfs --version 2>&1 || true
echo "--- systemd state ---"
${SUDO} systemctl show rustfs --no-pager \
--property=ActiveState,SubState,Result,ExecMainPID,ExecMainStartTimestamp,NRestarts 2>&1 || true
echo "--- rustfs journal ---"
${SUDO} journalctl -u rustfs --no-pager -n 10000 2>&1 || true
echo "--- rustfs file logs ---"
if ${SUDO} test -d /var/log/rustfs; then
${SUDO} find /var/log/rustfs -maxdepth 2 -type f -print 2>/dev/null | while IFS= read -r file; do
echo "--- ${file} (last 5000 lines) ---"
${SUDO} tail -n 5000 "${file}" 2>&1 || true
done
else
echo "/var/log/rustfs is unavailable"
fi
'; then
echo "SSH diagnostics failed for ${node}"
fi
} 2>&1 | redact > "${ARTIFACT_DIR}/${safe_node}-rustfs-redacted.log"
done
: > "${ARTIFACT_DIR}/endpoint-ready-probes.log"
read -r -a DIRECT_ENDPOINTS <<< "${RUSTFS_POOL_NODE_ENDPOINTS}"
probe_index=0
for endpoint in "${DIRECT_ENDPOINTS[@]}"; do
probe_index=$((probe_index + 1))
curl -sS --connect-timeout 5 --max-time 15 -o "${ARTIFACT_DIR}/ready-direct-${probe_index}.body" \
-w "direct[${probe_index}]=${endpoint} http=%{http_code} connect=%{time_connect} ttfb=%{time_starttransfer} total=%{time_total}\n" \
"${endpoint%/}/health/ready" >> "${ARTIFACT_DIR}/endpoint-ready-probes.log" 2>&1 || true
done
if [ -n "${RUSTFS_POOL_PROXY_ENDPOINT}" ]; then
curl -sS --connect-timeout 5 --max-time 15 -o "${ARTIFACT_DIR}/ready-proxy.body" \
-w "proxy=${RUSTFS_POOL_PROXY_ENDPOINT} http=%{http_code} connect=%{time_connect} ttfb=%{time_starttransfer} total=%{time_total}\n" \
"${RUSTFS_POOL_PROXY_ENDPOINT%/}/health/ready" >> "${ARTIFACT_DIR}/endpoint-ready-probes.log" 2>&1 || true
fi
if [ -n "${RUSTFS_SHARED_PROXY_ENDPOINT}" ]; then
curl -sS --connect-timeout 5 --max-time 15 -o "${ARTIFACT_DIR}/ready-shared-proxy.body" \
-w "shared_proxy=${RUSTFS_SHARED_PROXY_ENDPOINT} http=%{http_code} connect=%{time_connect} ttfb=%{time_starttransfer} total=%{time_total}\n" \
"${RUSTFS_SHARED_PROXY_ENDPOINT%/}/health/ready" >> "${ARTIFACT_DIR}/endpoint-ready-probes.log" 2>&1 || true
fi
- name: Generate report
if: always()
run: |
set -euo pipefail
LOG_FILE="${POOL_ARTIFACT_DIR}/pool-test.log"
REPORT_FILE="${POOL_ARTIFACT_DIR}/pool-report.md"
PACKAGE_URL='${{ inputs.package_url }}'
RUSTFS_VERSION='${{ inputs.rustfs_version }}'
if [ -n "${PACKAGE_URL}" ]; then
PACKAGE_SOURCE="${PACKAGE_URL}"
elif [ -n "${RUSTFS_VERSION}" ]; then
PACKAGE_SOURCE="version ${RUSTFS_VERSION}"
else
PACKAGE_SOURCE="${RUSTFS_NIGHTLY_PACKAGE_URL}"
fi
{
echo "# RustFS pool expansion test report"
echo ""
echo "- Run: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
echo "- Trigger: ${{ github.event_name }}"
echo "- Package: ${PACKAGE_SOURCE}"
echo "- Warp concurrent: ${{ inputs.warp_concurrent || '32' }}"
echo "- Test Step Outcome: ${{ steps.pool_test.outcome }}"
echo ""
echo "## Log tail"
echo '```text'
tail -n 200 "${LOG_FILE}" || true
echo '```'
} | tee "${REPORT_FILE}"
cat "${REPORT_FILE}" >> "${GITHUB_STEP_SUMMARY}"
- name: Validate pool diagnostic completeness
if: always()
run: |
set -euo pipefail
failed=0
require_nonempty() {
if [ ! -s "$1" ]; then
echo "required diagnostic is missing or empty: $1" >&2
failed=1
fi
}
require_available() {
if [ ! -e "$1" ]; then
echo "required diagnostic is missing: $1" >&2
failed=1
elif grep -Fq 'unavailable:' "$1" 2>/dev/null; then
echo "required diagnostic could not be collected: $1" >&2
failed=1
fi
}
require_nonempty "${POOL_ARTIFACT_DIR}/pool-test.log"
require_nonempty "${POOL_ARTIFACT_DIR}/warp.log"
require_nonempty "${POOL_ARTIFACT_DIR}/pool-report.md"
require_nonempty "${POOL_ARTIFACT_DIR}/pool-baseline.log"
require_nonempty "${POOL_ARTIFACT_DIR}/nginx-config-redacted.txt"
require_nonempty "${POOL_ARTIFACT_DIR}/nginx-rustfs-pool-test-access-redacted.log"
require_available "${POOL_ARTIFACT_DIR}/nginx-rustfs-pool-test-access-redacted.log"
require_available "${POOL_ARTIFACT_DIR}/nginx-rustfs-pool-test-error-redacted.log"
require_nonempty "${POOL_ARTIFACT_DIR}/endpoint-ready-probes.log"
read -r -a NODES <<< "${RUSTFS_NODES:-vm000 vm001 vm002}"
if grep -Fq 'baseline collection failed' "${POOL_ARTIFACT_DIR}/pool-baseline.log" 2>/dev/null; then
echo "one or more node baselines could not be collected" >&2
failed=1
fi
for node in "${NODES[@]}"; do
safe_node="${node//[^A-Za-z0-9_.-]/_}"
node_log="${POOL_ARTIFACT_DIR}/${safe_node}-rustfs-redacted.log"
require_nonempty "${node_log}"
if grep -Fq "SSH diagnostics failed for ${node}" "${node_log}" 2>/dev/null; then
echo "node diagnostics failed: ${node_log}" >&2
failed=1
fi
if ! grep -Eq '^rustfs @' "${node_log}" 2>/dev/null \
|| ! grep -Eq '^NRestarts=[0-9]+$' "${node_log}" 2>/dev/null; then
echo "node version or restart evidence is incomplete: ${node_log}" >&2
failed=1
elif grep -Eq '^NRestarts=[1-9][0-9]*$' "${node_log}"; then
echo "RustFS restarted unexpectedly during the run: ${node_log}" >&2
failed=1
fi
done
if ! grep -Fq "upstream_status=\"\$upstream_status\"" \
"${POOL_ARTIFACT_DIR}/nginx-config-redacted.txt"; then
echo "Nginx config does not expose upstream status fields" >&2
failed=1
fi
if ! grep -Eq '^proxy=.* http=200([[:space:]]|$)' "${POOL_ARTIFACT_DIR}/endpoint-ready-probes.log"; then
echo "dedicated proxy readiness probe did not return HTTP 200" >&2
failed=1
fi
if grep -Eq 'status=50(2|4)|upstream_status="[^"]*50(2|4)' \
"${POOL_ARTIFACT_DIR}/nginx-rustfs-pool-test-access-redacted.log"; then
echo "dedicated proxy access log contains a 502/504 response" >&2
failed=1
fi
if grep -Eiq 'upstream prematurely closed connection|upstream timed out|(connect\(\)|recv\(\)|send\(\)) failed.*upstream|connection reset by peer.*upstream' \
"${POOL_ARTIFACT_DIR}/nginx-rustfs-pool-test-error-redacted.log"; then
echo "dedicated proxy error log contains an upstream timeout or connection failure" >&2
failed=1
fi
[ "${failed}" -eq 0 ] || exit 1
- name: Upload functional report to dashboard
if: always()
continue-on-error: true
env:
GH_TOKEN: ${{ env.PF_TESTING_GH_TOKEN }}
SUITE: pool
run: |
set -euo pipefail
REPORT_FILE="${POOL_ARTIFACT_DIR}/pool-report.md"
if [ -z "${GH_TOKEN:-}" ]; then
echo "PF_TESTING_GH_TOKEN is not configured; skipping dashboard upload"
exit 0
fi
DATE="$(date -u +%Y-%m-%d)"
REPORT_PATH="functional-reports/${SUITE}/${DATE}.md"
CONTENT="$(python3 -c 'import base64,sys;print(base64.b64encode(open(sys.argv[1],"rb").read()).decode())' "${REPORT_FILE}")"
SHA="$(gh api "repos/rustfs/dashboard/contents/${REPORT_PATH}" -q '.sha' 2>/dev/null || true)"
if [ -n "${SHA}" ]; then
jq -n --arg msg "report(${SUITE}): ${DATE}" --arg content "${CONTENT}" --arg sha "${SHA}" \
'{message:$msg, content:$content, sha:$sha}' \
| gh api --method PUT "repos/rustfs/dashboard/contents/${REPORT_PATH}" --input - >/dev/null
else
jq -n --arg msg "report(${SUITE}): ${DATE}" --arg content "${CONTENT}" \
'{message:$msg, content:$content}' \
| gh api --method PUT "repos/rustfs/dashboard/contents/${REPORT_PATH}" --input - >/dev/null
fi
- name: File failure issue in rustfs/backlog
if: ${{ always() && (failure() || steps.pool_test.outcome == 'failure' || steps.pool_test.outcome == 'cancelled') }}
continue-on-error: true
env:
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
SUITE: 'pool'
SUITE_LABEL: 'Pool expansion'
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
REPORT_FILE: '${{ env.POOL_ARTIFACT_DIR }}/pool-report.md'
LOG_FILE: '${{ env.POOL_ARTIFACT_DIR }}/pool-test.log'
run: |
set -euo pipefail
if [ -z "${GH_TOKEN:-}" ]; then
echo "PF_TESTING_GH_TOKEN is not configured; skipping backlog issue"
exit 0
fi
TITLE="[functional][${SUITE}] ${SUITE_LABEL} suite failed (run ${GITHUB_RUN_ID})"
EXISTING="$(gh issue list -R rustfs/backlog --state all \
--search "in:title \"run ${GITHUB_RUN_ID}\"" \
--json number --jq '.[].number' || true)"
if [ -n "${EXISTING}" ]; then
echo "backlog issue already exists for run ${GITHUB_RUN_ID}; skipping"
exit 0
fi
redact() {
sed -E \
-e 's/(RUSTFS_(ACCESS_KEY|SECRET_KEY)[=: ]+)[^[:space:]]+/\1[REDACTED]/Ig' \
-e 's/(Authorization:).*/\1 [REDACTED]/Ig' \
-e 's/(X-Amz-Signature=)[^&[:space:]]+/\1[REDACTED]/Ig' \
-e 's/^.*(password|secret|token)[=: ].*/[REDACTED SENSITIVE LINE]/Ig'
}
BODY_FILE="$(mktemp)"
{
echo "The **${SUITE_LABEL}** functional suite failed."
echo ""
echo "- Suite: \`${SUITE}\`"
echo "- Run: ${RUN_URL}"
echo "- Trigger: ${GITHUB_EVENT_NAME}"
echo "- Date: $(date -u +%Y-%m-%d)"
echo ""
echo "## Report (errors and symptoms)"
echo ""
if [ -s "${REPORT_FILE}" ]; then
redact < "${REPORT_FILE}"
elif [ -s "${LOG_FILE:-}" ]; then
echo "(report file missing; log tail below)"
echo ""
tail -n 200 "${LOG_FILE}" | redact
else
echo "(no report or log file was produced)"
fi
} | head -c 55000 > "${BODY_FILE}"
gh label create functional-test -R rustfs/backlog --color d73a4a 2>/dev/null || true
if ! gh issue create -R rustfs/backlog --title "${TITLE}" \
--body-file "${BODY_FILE}" --label functional-test; then
gh issue create -R rustfs/backlog --title "${TITLE}" --body-file "${BODY_FILE}"
fi
echo "filed backlog issue for suite ${SUITE}"
- name: Upload test logs
if: always()
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
with:
name: rustfs-pool-test-${{ github.run_id }}-${{ github.run_attempt }}
path: ${{ runner.temp }}/rustfs-pool-${{ github.run_id }}-${{ github.run_attempt }}
if-no-files-found: warn
- name: Restore dedicated pool proxy
if: always()
run: |
set -euo pipefail
RUSTFS_POOL_NGINX_CONFIG_PATH=/etc/nginx/conf.d/rustfs-pool-test.conf \
RUSTFS_POOL_NGINX_LISTEN="${RUSTFS_POOL_PROXY_ENDPOINT#http://}" \
RUSTFS_POOL_NGINX_ACCESS_LOG=/var/log/nginx/rustfs-pool-test-access.log \
RUSTFS_POOL_NGINX_ERROR_LOG=/var/log/nginx/rustfs-pool-test-error.log \
./auto-testing/rustfs_pool_nginx_stage.sh cleanup
- 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: "Continue functional chain (next: Security)"
# Only chain-triggered runs forward to the next suite; standalone
# workflow_dispatch runs stop after their own cleanup. A failed
# handoff must never pass silently: it retries, then files an alert
# issue in rustfs/backlog so a stalled chain is visible.
if: ${{ always() && github.event_name == 'repository_dispatch' }}
continue-on-error: true
env:
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
run: |
set -uo pipefail
if [ -z "${{GH_TOKEN:-}}" ]; then
echo "PF_TESTING_GH_TOKEN is not configured; cannot dispatch the next suite" >&2
exit 1
fi
DISPATCHED=0
for attempt in 1 2 3; do
if gh api --method POST repos/rustfs/rustfs/dispatches \
-f event_type='rustfs-chain-security' \
-F 'client_payload[from_suite]=pool'; then
echo "dispatched next suite Security (attempt ${{attempt}})"
DISPATCHED=1
break
fi
echo "dispatch attempt ${{attempt}} failed; retrying in ${{attempt}}0s" >&2
sleep "${{attempt}}0"
done
if [ "${{DISPATCHED:-0}}" -ne 1 ]; then
echo "ERROR: functional chain stalled: could not dispatch Security after 3 attempts" >&2
TITLE="[functional][chain] stalled after pool (run ${{GITHUB_RUN_ID}})"
BODY_FILE="$(mktemp)"
{
echo "The functional chain could not hand off from **pool** to **Security** after 3 attempts."
echo ""
echo "- Failed suite job: ${{GITHUB_SERVER_URL}}/${{GITHUB_REPOSITORY}}/actions/runs/${{GITHUB_RUN_ID}}"
echo "- Expected next event: `rustfs-chain-security`"
echo "- Likely cause: PF_TESTING_GH_TOKEN lacks contents:write on rustfs/rustfs, or the GitHub API was unavailable."
echo "- Recovery: re-dispatch manually with"
echo " ```"
echo " gh api --method POST repos/rustfs/rustfs/dispatches -f event_type='rustfs-chain-security'"
echo " ```"
} > "${{BODY_FILE}}"
gh issue create -R rustfs/backlog --title "${{TITLE}}" \
--body-file "${{BODY_FILE}}" --label functional-test \
|| gh issue create -R rustfs/backlog --title "${{TITLE}}" --body-file "${{BODY_FILE}}" \
|| echo "could not file the stall alert issue either; check the token" >&2
exit 1
fi
- 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."