mirror of
https://github.com/rustfs/rustfs.git
synced 2026-10-12 07:39:05 +00:00
hector
9c30cc8851
Adds rustfs-fault-tolerance-matrix.yml, a manually dispatched workflow that runs the --matrix topology x EC outage sweep from rustfs/auto-testing (38 combinations, 320 cases). The scenario suite hardcodes --all and a 60-minute budget, so the exhaustive sweep had no CI entry point.
222 lines
9.6 KiB
YAML
222 lines
9.6 KiB
YAML
# RustFS Fault-Tolerance (degradation) Matrix Sweep
|
|
#
|
|
# Exhaustive topology x EC outage sweep, complementary to the scenario suite
|
|
# (rustfs-fault-tolerance-test.yml). For each topology (nodes x drives per
|
|
# node) and each EC level P in 1..N*drives/2 the runner installs that exact
|
|
# cluster shape and drives progressive node outages plus recovery:
|
|
#
|
|
# M-<topo>EC<P>-full full-capacity reads/writes must succeed
|
|
# M-<topo>EC<P>-n<k> with k nodes online: reads succeed iff the online
|
|
# drives cover the read quorum (N-P), writes iff they
|
|
# cover the write quorum (N-P+1); probes below quorum
|
|
# assert the expected outage
|
|
# M-<topo>EC<P>-rec after restoring every node, reads/writes succeed
|
|
#
|
|
# 10 topologies x EC levels = 38 combinations, 320 cases. The full sweep runs
|
|
# 3-5 hours and is dispatched on demand (e.g. after a nightly chain goes
|
|
# green), not nightly. Case ids and expectations come from product source
|
|
# (default_parity_count, erasure set sizing) via rustfs/auto-testing.
|
|
|
|
name: RustFS Fault-Tolerance Matrix
|
|
|
|
on:
|
|
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
|
|
matrix_topo:
|
|
description: 'Topology filter like 4x2; empty sweeps all ten topologies'
|
|
required: false
|
|
default: ''
|
|
type: string
|
|
matrix_ec:
|
|
description: 'EC/parity filter; empty sweeps every EC level'
|
|
required: false
|
|
default: ''
|
|
type: string
|
|
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
|
|
|
|
# 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: ${{ vars.RUSTFS_NIGHTLY_PACKAGE_URL || 'https://dl.rustfs.com/artifacts/rustfs/packages/nightly/rustfs-nightly-latest.deb' }}
|
|
|
|
jobs:
|
|
fault-tolerance-matrix:
|
|
runs-on: smoke-testing
|
|
# The full 38-combination sweep takes 3-5h; 360 is the runner job ceiling.
|
|
timeout-minutes: 360
|
|
steps:
|
|
- name: Initialize functional evidence
|
|
id: evidence
|
|
run: |
|
|
set -euo pipefail
|
|
umask 077
|
|
FUNCTIONAL_ARTIFACTS_DIR="${RUNNER_TEMP}/rustfs-fault-tolerance-matrix-${GITHUB_RUN_ID}-${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}"
|
|
|
|
- name: Checkout auto-testing scripts
|
|
timeout-minutes: 5
|
|
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
|
|
with:
|
|
repository: rustfs/auto-testing
|
|
ref: ${{ inputs.auto_testing_ref }}
|
|
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: Run matrix sweep (topology x EC outage combinations)
|
|
timeout-minutes: 350
|
|
id: test
|
|
# No continue-on-error: an UNEXPECTED verdict (a probe that should
|
|
# fail by quorum math but passes, or vice versa) is the finding this
|
|
# sweep exists to surface, and the red run is the signal until matrix
|
|
# runs get backlog integration like the scenario suite has.
|
|
env:
|
|
MATRIX_EC: ${{ inputs.matrix_ec }}
|
|
run: |
|
|
set -euo pipefail
|
|
ARGS=(--matrix -y --package-url "${{ inputs.package_url || env.RUSTFS_NIGHTLY_PACKAGE_URL }}" --log-file "${LOG_FILE}" --results-file "${RESULTS_FILE}")
|
|
if [ -n "${{ inputs.matrix_topo }}" ]; then
|
|
# Trailing value form: consumed as `--matrix-topo <topo> [ec]`.
|
|
ARGS+=(--matrix-topo "${{ inputs.matrix_topo }}")
|
|
if [ -n "${MATRIX_EC}" ]; then
|
|
ARGS+=("${MATRIX_EC}")
|
|
fi
|
|
fi
|
|
./auto-testing/rustfs-fault-tolerance-test.sh "${ARGS[@]}"
|
|
|
|
- name: Generate report
|
|
timeout-minutes: 2
|
|
if: ${{ always() && steps.evidence.outcome == 'success' }}
|
|
run: |
|
|
set -euo pipefail
|
|
{
|
|
echo "# RustFS fault-tolerance matrix 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 "- Topology filter: ${{ inputs.matrix_topo || 'all (10 topologies)' }}"
|
|
echo "- EC filter: ${{ inputs.matrix_ec || 'all levels' }}"
|
|
echo ""
|
|
echo "## Per-probe results"
|
|
echo ""
|
|
echo '```'
|
|
grep -E '^FT-(CASE|COMPLETE|SUMMARY|REPORT)' "${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}" >> "${GITHUB_STEP_SUMMARY}"
|
|
|
|
# An unfiltered sweep must land exactly 320 cases (38 topology x EC
|
|
# combinations at 2*(nodes+1) cases each); filtered sweeps are held
|
|
# to internal consistency. Missing/harness-error rows always fail.
|
|
EXPECTED_TOTAL=""
|
|
if [ -z "${{ inputs.matrix_topo }}" ] && [ -z "${MATRIX_EC}" ]; then
|
|
EXPECTED_TOTAL=320
|
|
fi
|
|
jq -e --arg testing_sha "${AUTO_TESTING_SHA}" --argjson expected_total "${EXPECTED_TOTAL:-null}" '
|
|
.schema_version == 1 and
|
|
.auto_testing_sha == $testing_sha and
|
|
.complete == true and
|
|
.counts.expected == ($expected_total // .counts.expected) and
|
|
.counts.expected == .counts.seen and
|
|
.counts.harness_errors == 0 and
|
|
(.expected_cases | length) == .counts.expected and
|
|
(.expected_cases | unique | length) == .counts.expected and
|
|
(.seen_cases | length) == .counts.seen and
|
|
(.missing_cases | length) == 0 and
|
|
(.harness_errors | length) == 0 and
|
|
(.cases | length) == .counts.seen and
|
|
([.cases[].case_id] | unique | length) == .counts.seen and
|
|
([.cases[].case_id] | sort) == (.expected_cases | sort) and
|
|
all(.cases[]; (.case_id | startswith("M-")) and (.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
|
|
|
|
- name: Upload test logs & evidence
|
|
timeout-minutes: 2
|
|
if: ${{ always() && steps.evidence.outcome == 'success' }}
|
|
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
|
|
with:
|
|
name: rustfs-fault-tolerance-matrix-${{ 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
|