mirror of
https://github.com/rustfs/rustfs.git
synced 2026-10-12 07:39:05 +00:00
hector
bdea44f332
The fault-tolerance suite now registers and runs scenario E (rustfs/auto-testing#100): --all covers A, B, C, C2, D, E with 38 + 6 = 44 expected cases. The chain-evidence assertion still hardcoded [A, B, C, C2, D] and 38 everywhere, which would fail every green FT run's evidence validation once E is registered. Bump the scenario list to include E and all count assertions from 38 to 44; step name updated to match. No other lanes reference 38.
394 lines
18 KiB
YAML
394 lines
18 KiB
YAML
# RustFS Fault-Tolerance (degradation) Test
|
|
#
|
|
# Scenario suite for the 2026-09 degradation report: verifies read/write
|
|
# behavior under drive and node loss against the erasure-coding contract and
|
|
# snapshots health-endpoint responses at every tier.
|
|
#
|
|
# A single-node 4 drives (SNMD): revoke access to 1/2/3 drives, restore
|
|
# B multi-node 4x1 (one drive per node): stop 1/2/3 nodes, restore
|
|
# C multi-node 4x4 (16 drives, EC:4): stop 1 node (read-quorum boundary),
|
|
# stop 2 nodes, restore
|
|
# C2 multi-node 4x4 with EC:8: 2 nodes down puts 8 drives online -- reads
|
|
# satisfy the EC read quorum while the lock majority is broken (the
|
|
# reported divergence window: reads 503 with lock_quorum_unavailable)
|
|
# D multi-node 4x1: stop 1/2 nodes, then restore
|
|
#
|
|
# Expectations come from product source (default_parity_count, erasure set
|
|
# sizing). By default a "reads refused although the read quorum is met"
|
|
# observation is reported as known-divergence without failing the suite; the
|
|
# strict input turns those into failures once the product behavior changes.
|
|
|
|
name: RustFS Fault-Tolerance Test
|
|
|
|
on:
|
|
workflow_call:
|
|
inputs:
|
|
chain_manifest:
|
|
description: Verified candidate and chain attempt from the chain driver
|
|
type: string
|
|
required: true
|
|
workflow_dispatch:
|
|
inputs:
|
|
package_url:
|
|
description: 'Direct .deb URL. Required unless the nightly default is wanted.'
|
|
required: false
|
|
type: string
|
|
auto_testing_ref:
|
|
description: 'auto-testing branch, tag, or SHA (defaults to main)'
|
|
required: false
|
|
default: main
|
|
type: string
|
|
strict:
|
|
description: 'Fail the suite when reads are refused despite a met read quorum'
|
|
type: boolean
|
|
default: false
|
|
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 replication suite finishes, ahead of
|
|
# the performance suite.
|
|
types: [rustfs-chain-fault-tolerance]
|
|
|
|
permissions:
|
|
contents: read
|
|
|
|
# The suite stops services and revokes drive access on the shared fleet; only one
|
|
# functional suite may touch the environment at a time.
|
|
concurrency:
|
|
group: rustfs-shared-functional-tests-v2
|
|
cancel-in-progress: false
|
|
|
|
defaults:
|
|
run:
|
|
shell: bash
|
|
|
|
env:
|
|
RUSTFS_ACCESS_KEY: ${{ secrets.RUSTFS_ACCESS_KEY }}
|
|
RUSTFS_SECRET_KEY: ${{ secrets.RUSTFS_SECRET_KEY }}
|
|
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 }}
|
|
RUSTFS_NIGHTLY_PACKAGE_URL: ${{ vars.RUSTFS_NIGHTLY_PACKAGE_URL || 'https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb' }}
|
|
|
|
jobs:
|
|
fault-tolerance-test:
|
|
runs-on: smoke-testing
|
|
timeout-minutes: 60
|
|
if: ${{ inputs.chain_manifest != '' || github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
|
|
steps:
|
|
- name: Checkout repository (for report parser)
|
|
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
|
|
with:
|
|
persist-credentials: false
|
|
|
|
- name: Initialize functional evidence
|
|
id: evidence
|
|
run: |
|
|
set -euo pipefail
|
|
umask 077
|
|
FUNCTIONAL_ARTIFACTS_DIR="${RUNNER_TEMP}/rustfs-fault-tolerance-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
|
|
mkdir -- "${FUNCTIONAL_ARTIFACTS_DIR}" "${FUNCTIONAL_ARTIFACTS_DIR}-scratch" "${FUNCTIONAL_ARTIFACTS_DIR}/evidence"
|
|
{
|
|
printf 'FUNCTIONAL_ARTIFACTS_DIR=%s\n' "${FUNCTIONAL_ARTIFACTS_DIR}"
|
|
printf 'LOG_FILE=%s/suite.log\n' "${FUNCTIONAL_ARTIFACTS_DIR}"
|
|
printf 'REPORT_FILE=%s/report.md\n' "${FUNCTIONAL_ARTIFACTS_DIR}"
|
|
printf 'RESULTS_FILE=%s/results.json\n' "${FUNCTIONAL_ARTIFACTS_DIR}"
|
|
printf 'EVIDENCE_DIR=%s/evidence\n' "${FUNCTIONAL_ARTIFACTS_DIR}"
|
|
printf 'TMPDIR=%s-scratch\n' "${FUNCTIONAL_ARTIFACTS_DIR}"
|
|
} >> "${GITHUB_ENV}"
|
|
|
|
# Pin the private suite checkout when the chain supplies a candidate.
|
|
- name: Bind functional candidate
|
|
id: chain
|
|
if: ${{ inputs.chain_manifest != '' }}
|
|
env:
|
|
CHAIN_MANIFEST: ${{ inputs.chain_manifest }}
|
|
run: python3 scripts/functional_chain_evidence.py consume
|
|
|
|
- name: Checkout auto-testing scripts
|
|
timeout-minutes: 5
|
|
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
|
|
with:
|
|
repository: rustfs/auto-testing
|
|
ref: ${{ steps.chain.outputs.testing_sha || inputs.auto_testing_ref || 'main' }}
|
|
token: ${{ secrets.PF_TESTING_GH_TOKEN }}
|
|
path: auto-testing
|
|
persist-credentials: false
|
|
|
|
- name: Record auto-testing revision
|
|
run: |
|
|
set -euo pipefail
|
|
AUTO_TESTING_SHA="$(git -C auto-testing rev-parse HEAD)"
|
|
printf 'AUTO_TESTING_SHA=%s\n' "${AUTO_TESTING_SHA}" >> "${GITHUB_ENV}"
|
|
echo "auto-testing revision: ${AUTO_TESTING_SHA}"
|
|
|
|
- name: Show environment
|
|
run: |
|
|
uname -a
|
|
jq --version
|
|
aws --version
|
|
echo "auto-testing: ${AUTO_TESTING_SHA}"
|
|
df -h /data | tail -1
|
|
|
|
- name: Cleanup environment (before)
|
|
timeout-minutes: 5
|
|
if: ${{ inputs.cleanup_before != 'false' }}
|
|
run: |
|
|
./auto-testing/rustfs-fault-tolerance-test.sh --cleanup -y --log-file "${LOG_FILE}"
|
|
|
|
- name: Stage verified candidate package
|
|
id: chain_package
|
|
if: ${{ inputs.chain_manifest != '' }}
|
|
env:
|
|
CHAIN_MANIFEST: ${{ inputs.chain_manifest }}
|
|
run: python3 scripts/prepare_functional_package.py prepare
|
|
|
|
- name: Run fault-tolerance scenarios (A, B, C, C2, D, E)
|
|
timeout-minutes: 45
|
|
id: test
|
|
# Standalone case failures are reported by the backlog manager.
|
|
# Chain evidence separately requires complete passing cases.
|
|
continue-on-error: true
|
|
run: |
|
|
ARGS=(--all -y --package-url "${{ steps.chain_package.outputs.package_url || inputs.package_url || env.RUSTFS_NIGHTLY_PACKAGE_URL }}" --log-file "${LOG_FILE}" --results-file "${RESULTS_FILE}")
|
|
if [ "${{ inputs.strict }}" = "true" ]; then
|
|
ARGS+=(--strict)
|
|
fi
|
|
./auto-testing/rustfs-fault-tolerance-test.sh "${ARGS[@]}"
|
|
|
|
- name: Generate report
|
|
timeout-minutes: 2
|
|
id: chain_report
|
|
if: ${{ always() && steps.evidence.outcome == 'success' }}
|
|
run: |
|
|
set -euo pipefail
|
|
{
|
|
echo "# RustFS fault-tolerance test report"
|
|
echo ""
|
|
echo "- Run: ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
|
|
echo "- Package: ${{ inputs.package_url || 'nightly (R2 latest)' }}"
|
|
echo "- auto-testing: \`${AUTO_TESTING_SHA}\`"
|
|
echo "- Strict mode: ${{ inputs.strict || 'false' }}"
|
|
echo ""
|
|
echo "## Per-probe results"
|
|
echo ""
|
|
echo '```'
|
|
grep -E '^FT-(CASE|COMPLETE|SUMMARY|REPORT)' "${LOG_FILE}" || echo "(no FT-CASE lines found)"
|
|
echo '```'
|
|
echo ""
|
|
echo "## Health snapshots"
|
|
echo ""
|
|
for f in "${FUNCTIONAL_ARTIFACTS_DIR}"/evidence/*.code; do
|
|
[ -e "${f}" ] || continue
|
|
printf '%s -> %s\n' "$(basename "${f}" .code)" "$(cat "${f}")"
|
|
done
|
|
} > "${REPORT_FILE}"
|
|
cat "${REPORT_FILE}" >> "${GITHUB_STEP_SUMMARY}"
|
|
printf 'complete=false\n' >> "${GITHUB_OUTPUT}"
|
|
jq -e --arg testing_sha "${AUTO_TESTING_SHA}" '
|
|
.schema_version == 1 and
|
|
.auto_testing_sha == $testing_sha and
|
|
.selected_scenarios == ["A", "B", "C", "C2", "D", "E"] and
|
|
.complete == true and
|
|
.counts.expected == 44 and
|
|
.counts.seen == 44 and
|
|
.counts.harness_errors == 0 and
|
|
(.expected_cases | length) == 44 and
|
|
(.expected_cases | unique | length) == 44 and
|
|
(.seen_cases | length) == 44 and
|
|
(.seen_cases | unique | length) == 44 and
|
|
(.seen_cases | sort) == (.expected_cases | sort) and
|
|
(.missing_cases | length) == 0 and
|
|
(.harness_errors | length) == 0 and
|
|
(.cases | length) == 44 and
|
|
([.cases[].case_id] | sort) == (.expected_cases | sort) and
|
|
([.cases[].case_id] | unique | length) == 44 and
|
|
all(.cases[]; .verdict == "pass" or .verdict == "known-divergence" or .verdict == "UNEXPECTED") and
|
|
.counts.unexpected == ([.cases[] | select(.verdict == "UNEXPECTED")] | length) and
|
|
.counts.known_divergence == ([.cases[] | select(.verdict == "known-divergence")] | length)
|
|
' "${RESULTS_FILE}" >/dev/null
|
|
printf 'complete=true\n' >> "${GITHUB_OUTPUT}"
|
|
|
|
- name: Manage backlog issues (dedup / label / auto-close)
|
|
timeout-minutes: 2
|
|
# Signal-based lifecycle: dedups against open issues by label
|
|
# (fault-tolerance + FT case), labels new issues (functional-test,
|
|
# category, case IDs, env), and closes fixed issues after a fully
|
|
# green run. Never acts on cancelled runs. Logic lives in
|
|
# auto-testing/scripts/issue_manager.py, which parses the
|
|
# FT-CASE verdict lines from the suite log.
|
|
if: ${{ always() && steps.evidence.outcome == 'success' && steps.chain_report.outputs.complete == 'true' }}
|
|
continue-on-error: true
|
|
env:
|
|
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
|
|
SUITE: 'fault-tolerance'
|
|
SUITE_LABEL: 'Fault-Tolerance'
|
|
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
|
|
run: |
|
|
set -euo pipefail
|
|
if [ -z "${GH_TOKEN:-}" ]; then
|
|
echo "PF_TESTING_GH_TOKEN is not configured; skipping backlog issue management"
|
|
exit 0
|
|
fi
|
|
if [ ! -f auto-testing/scripts/issue_manager.py ]; then
|
|
echo "issue_manager.py not found in auto-testing checkout; skipping"
|
|
exit 0
|
|
fi
|
|
PACKAGE_URL='${{ inputs.package_url }}'
|
|
PACKAGE_SOURCE=""
|
|
if [ -n "${PACKAGE_URL}" ]; then
|
|
PACKAGE_SOURCE="${PACKAGE_URL}"
|
|
else
|
|
PACKAGE_SOURCE="${RUSTFS_NIGHTLY_PACKAGE_URL}"
|
|
fi
|
|
python3 auto-testing/scripts/issue_manager.py handle \
|
|
--repo rustfs/backlog \
|
|
--suite "${SUITE}" --category "${SUITE}" --suite-label "${SUITE_LABEL}" \
|
|
--outcome "${{ steps.test.outcome }}" \
|
|
--report-file "${REPORT_FILE}" \
|
|
--log "${LOG_FILE}" \
|
|
--run-url "${RUN_URL}/attempts/${GITHUB_RUN_ATTEMPT}#summary" \
|
|
--run-id "${GITHUB_RUN_ID}" \
|
|
--attempt "${GITHUB_RUN_ATTEMPT}" \
|
|
--commit "${GITHUB_SHA}" \
|
|
--trigger "${{ github.event_name }}" \
|
|
--package-source "${PACKAGE_SOURCE}" \
|
|
--date "$(date -u +%Y-%m-%d)"
|
|
|
|
- name: Upload functional report to dashboard
|
|
timeout-minutes: 2
|
|
if: ${{ always() && steps.evidence.outcome == 'success' }}
|
|
continue-on-error: true
|
|
env:
|
|
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
|
|
REPORT_FILE: ${{ env.REPORT_FILE }}
|
|
SUITE: fault-tolerance
|
|
run: |
|
|
set -euo pipefail
|
|
if [ -z "${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}/${DATE}.md"
|
|
B64_FILE="$(mktemp)"
|
|
python3 -c 'import base64,sys;print(base64.b64encode(open(sys.argv[1],"rb").read()).decode())' "${REPORT_FILE}" > "${B64_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}): ${DATE}" --rawfile content "${B64_FILE}" --arg sha "${SHA}" \
|
|
'{message:$msg, content:($content|rtrimstr("\n")), sha:$sha}' \
|
|
| gh api --method PUT "repos/rustfs/dashboard/contents/${REPORT_PATH}" --input - >/dev/null
|
|
else
|
|
jq -n --arg msg "report(${SUITE}): ${DATE}" --rawfile content "${B64_FILE}" \
|
|
'{message:$msg, content:($content|rtrimstr("\n"))}' \
|
|
| gh api --method PUT "repos/rustfs/dashboard/contents/${REPORT_PATH}" --input - >/dev/null
|
|
fi
|
|
echo "dashboard updated: ${REPORT_PATH}"
|
|
|
|
- name: Upload test logs & evidence
|
|
timeout-minutes: 2
|
|
if: ${{ always() && steps.evidence.outcome == 'success' }}
|
|
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
|
|
with:
|
|
name: rustfs-fault-tolerance-${{ github.run_id }}-${{ github.run_attempt }}
|
|
path: |
|
|
${{ env.FUNCTIONAL_ARTIFACTS_DIR }}/report.md
|
|
${{ env.FUNCTIONAL_ARTIFACTS_DIR }}/results.json
|
|
${{ env.FUNCTIONAL_ARTIFACTS_DIR }}/suite.log
|
|
${{ env.FUNCTIONAL_ARTIFACTS_DIR }}/evidence/
|
|
if-no-files-found: warn
|
|
|
|
- name: Cleanup environment (after)
|
|
timeout-minutes: 5
|
|
if: ${{ always() && inputs.cleanup_after != 'false' }}
|
|
run: |
|
|
./auto-testing/rustfs-fault-tolerance-test.sh --cleanup -y --log-file "${LOG_FILE}" || true
|
|
|
|
- name: "Continue functional chain (next: Performance)"
|
|
# Only chain-triggered runs forward to the next suite; standalone
|
|
# workflow_dispatch runs stop after their own cleanup. A failed
|
|
# handoff retries, then files an alert issue in rustfs/backlog.
|
|
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-performance' \
|
|
-F 'client_payload[from_suite]=fault-tolerance'; then
|
|
echo "dispatched next suite Performance (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 Performance after 3 attempts" >&2
|
|
TITLE="[functional][chain] stalled after fault-tolerance (run ${GITHUB_RUN_ID})"
|
|
BODY_FILE="$(mktemp)"
|
|
{
|
|
echo "The functional chain could not hand off from **fault-tolerance** to **Performance** after 3 attempts."
|
|
echo ""
|
|
echo "- Failed suite job: ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
|
|
echo "- Expected next event: 'rustfs-chain-performance'"
|
|
echo "- Likely cause: PF_TESTING_GH_TOKEN lacks contents:write on rustfs/rustfs, or the GitHub API was unavailable."
|
|
echo "- Recovery: re-dispatch manually with"
|
|
FENCE="$(printf "\x60\x60\x60")"; echo " ${FENCE}"
|
|
echo " gh api --method POST repos/rustfs/rustfs/dispatches -f event_type='rustfs-chain-performance'"
|
|
FENCE="$(printf "\x60\x60\x60")"; echo " ${FENCE}"
|
|
} > "${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 fault-tolerance test failed"
|
|
echo "Package source: ${{ inputs.package_url || 'nightly (R2 latest)' }}"
|
|
echo "See the uploaded log artifact and FT-CASE lines for details."
|
|
|
|
- name: Remove verified candidate package
|
|
if: ${{ always() && inputs.chain_manifest != '' && steps.chain.outcome == 'success' }}
|
|
env:
|
|
CHAIN_MANIFEST: ${{ inputs.chain_manifest }}
|
|
run: python3 scripts/prepare_functional_package.py cleanup
|
|
|
|
- name: Record chain evidence
|
|
id: chain_record
|
|
if: ${{ always() && inputs.chain_manifest != '' && steps.evidence.outcome == 'success' }}
|
|
env:
|
|
CHAIN_MANIFEST: ${{ inputs.chain_manifest }}
|
|
CHAIN_JOB_STATUS: ${{ job.status }}
|
|
CHAIN_TEST_OUTCOME: ${{ steps.test.outcome }}
|
|
CHAIN_REPORT_OUTCOME: ${{ steps.chain_report.outcome }}
|
|
run: >-
|
|
python3 scripts/functional_chain_evidence.py record --suite fault-tolerance
|
|
--report "${FUNCTIONAL_ARTIFACTS_DIR}/suite.log"
|
|
--output "${RUNNER_TEMP}/chain-fault-tolerance-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}/fault-tolerance.json"
|
|
|
|
- name: Upload chain evidence
|
|
if: ${{ always() && steps.chain_record.outputs.written == 'true' }}
|
|
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
|
|
with:
|
|
name: functional-chain-fault-tolerance-${{ github.run_id }}-${{ github.run_attempt }}
|
|
path: ${{ runner.temp }}/chain-fault-tolerance-${{ github.run_id }}-${{ github.run_attempt }}/fault-tolerance.json
|
|
if-no-files-found: error
|