Merge branch 'main' into test/distributed-e2e-hardening

This commit is contained in:
Zhengchao An
2026-09-05 22:21:31 +08:00
committed by GitHub
190 changed files with 23423 additions and 3611 deletions
+6 -88
View File
@@ -12,24 +12,10 @@
# See the License for the specific language governing permissions and
# limitations under the License.
# Companion to ci.yml for required status checks.
#
# ci.yml skips docs-only pull requests via paths-ignore, but the branch ruleset
# requires a check named "Test and Lint" — without this workflow a docs-only PR
# would wait on it forever. This workflow triggers on exactly the paths ci.yml
# ignores and reports success under the same job name. Mixed PRs trigger both
# workflows and the real check still gates: a required check with any failing
# run blocks the merge.
# https://docs.github.com/en/repositories/configuring-branches-and-merges-in-your-repository/defining-the-mergeability-of-pull-requests/troubleshooting-required-status-checks#handling-skipped-but-required-checks
#
# "Quick Checks" is mirrored here ahead of the ruleset change that will make it
# required too (rustfs/backlog#1599). Until that change lands this job is
# inert; mirroring it first is what lets the ruleset change happen without
# stranding docs-only PRs on a check nobody reports.
#
# Keep the paths list below in sync with the pull_request paths-ignore list
# in ci.yml, and keep the quick-checks steps below byte-identical to the
# quick-checks job in ci.yml.
# Reports the existing required checks for paths excluded by ci.yml.
# Mixed PRs can trigger both workflows; their Quick Checks jobs use one shared
# action to keep validation coverage aligned. Keep this paths list in sync with
# ci.yml's pull_request.paths-ignore via scripts/check_ci_paths_sync.sh.
name: Continuous Integration (docs only)
@@ -59,19 +45,6 @@ permissions:
contents: read
jobs:
# Deliberately NOT a bare `echo`. Once "Quick Checks" becomes a required
# check, ci.yml gates every expensive job behind it, so a mixed PR reports
# two check runs with this name: the real one (45-51s) and this companion.
# GitHub has no written contract for how it picks between same-named
# required check runs ("latest wins" vs "any failure blocks"), so instead of
# relying on ordering we make both runs execute the same commands against
# the same merge ref — their conclusions are then necessarily identical and
# the choice does not matter. Keep these steps byte-identical to the
# quick-checks job in ci.yml (a guard script that asserts this, and the paths
# sync below, is tracked in rustfs/backlog#1603).
#
# For a genuinely docs-only PR this adds no strictness (no code changed, so
# fmt and the guards always pass) and costs ~50s of ubuntu-latest.
quick-checks:
name: Quick Checks
runs-on: ubuntu-latest
@@ -82,63 +55,8 @@ jobs:
with:
persist-credentials: false
- name: Install ripgrep
uses: taiki-e/install-action@bffeee26d4db9be238a4ea78d8826604ebcb594d # v2
with:
tool: ripgrep@15.2.0
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8 # stable
with:
components: rustfmt
- name: Check code formatting
run: cargo fmt --all --check
- name: Check unsafe code allowances
run: ./scripts/check_unsafe_code_allowances.sh
- name: Check layered dependencies
run: ./scripts/check_layer_dependencies.sh
- name: Check architecture migration rules
run: ./scripts/check_architecture_migration_rules.sh
- name: Check logging guardrails
run: ./scripts/check_logging_guardrails.sh
- name: Check tokio io-uring feature guard
run: ./scripts/check_no_tokio_io_uring.sh
- name: Check extension schema boundaries
run: ./scripts/check_extension_schema_boundaries.sh
- name: Check body-cache whitelist guard
run: ./scripts/check_body_cache_whitelist.sh
- name: Check s3s footprint ratchet
run: ./scripts/check_s3s_footprint.sh
- name: Check cryptographic capability wording
run: ./scripts/check_fips_wording.sh
- name: Check no embedded secret material
run: ./scripts/check_embedded_secrets.sh
- name: Check test wiring
run: |
python3 ./scripts/check_test_wiring.py --self-test
python3 ./scripts/check_scheduled_validation_freshness.py --self-test
python3 ./scripts/check_test_wiring.py
- name: Check no planning docs committed
run: ./scripts/check_no_planning_docs.sh
- name: Check CI paths stay in sync
run: ./scripts/check_ci_paths_sync.sh
- name: Check io_uring lane --lib precondition
run: ./scripts/check_uring_lane_lib_only.sh
- name: Run shared quick checks
uses: ./.github/actions/quick-checks
test-and-lint:
name: Test and Lint
+10 -66
View File
@@ -100,12 +100,7 @@ jobs:
- name: Typos check with custom config file
uses: crate-ci/typos@37bb98842b0d8c4ffebdb75301a13db0267cef89 # master
# Fast, compile-free checks that fail early so contributors get feedback in
# ~1 minute instead of waiting for the full test job.
#
# These steps are mirrored byte-for-byte in ci-docs-only.yml so that a mixed
# PR, which reports two check runs named "Quick Checks", cannot get one red
# and one green. Edit both jobs together.
# Fail early with compile-free checks shared with docs-only CI.
quick-checks:
name: Quick Checks
if: github.event_name != 'pull_request' || github.event.action != 'closed'
@@ -117,66 +112,8 @@ jobs:
with:
persist-credentials: false
- name: Install ripgrep
uses: taiki-e/install-action@bffeee26d4db9be238a4ea78d8826604ebcb594d # v2
with:
tool: ripgrep@15.2.0
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@29eef336d9b2848a0b548edc03f92a220660cdb8 # stable
with:
components: rustfmt
- name: Check code formatting
run: cargo fmt --all --check
- name: Check unsafe code allowances
run: ./scripts/check_unsafe_code_allowances.sh
- name: Check layered dependencies
run: ./scripts/check_layer_dependencies.sh
- name: Check architecture migration rules
run: ./scripts/check_architecture_migration_rules.sh
- name: Check logging guardrails
run: ./scripts/check_logging_guardrails.sh
- name: Check error other(format!) ratchet
run: ./scripts/check_error_other_format_ratchet.sh
- name: Check tokio io-uring feature guard
run: ./scripts/check_no_tokio_io_uring.sh
- name: Check extension schema boundaries
run: ./scripts/check_extension_schema_boundaries.sh
- name: Check body-cache whitelist guard
run: ./scripts/check_body_cache_whitelist.sh
- name: Check s3s footprint ratchet
run: ./scripts/check_s3s_footprint.sh
- name: Check cryptographic capability wording
run: ./scripts/check_fips_wording.sh
- name: Check no embedded secret material
run: ./scripts/check_embedded_secrets.sh
- name: Check test wiring
run: |
python3 ./scripts/check_test_wiring.py --self-test
python3 ./scripts/check_scheduled_validation_freshness.py --self-test
python3 ./scripts/check_test_wiring.py
- name: Check no planning docs committed
run: ./scripts/check_no_planning_docs.sh
- name: Check CI paths stay in sync
run: ./scripts/check_ci_paths_sync.sh
- name: Check io_uring lane --lib precondition
run: ./scripts/check_uring_lane_lib_only.sh
- name: Run shared quick checks
uses: ./.github/actions/quick-checks
test-and-lint:
name: Test and Lint
@@ -269,6 +206,7 @@ jobs:
CARGO_BUILD_JOBS: ${{ (github.event_name == 'push' || github.event_name == 'workflow_dispatch') && '3' || '2' }}
run: |
mkdir -p artifacts/test-and-lint
rm -f target/nextest/ci/junit.xml
./scripts/ci/resource_sampler.sh start nextest
trap './scripts/ci/resource_sampler.sh stop' EXIT
set +e
@@ -277,6 +215,12 @@ jobs:
--status-level all --final-status-level all \
2>&1 | tee artifacts/test-and-lint/nextest.log
status=${PIPESTATUS[0]}
if [[ "${status}" -eq 0 ]]; then
cargo nextest list --profile ci --all --exclude e2e_test --message-format json \
> artifacts/test-and-lint/core-test-listing.json \
&& python3 scripts/check_test_wiring.py --check-core artifacts/test-and-lint/core-test-listing.json \
&& test -s target/nextest/ci/junit.xml || status=$?
fi
{
echo "command=cargo nextest run --profile ci --all --exclude e2e_test"
echo "exit_status=${status}"
-3
View File
@@ -54,9 +54,6 @@ env:
jobs:
heal-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: 480
# Standalone manual run, or one link of the nightly functional chain
# (storage -> heal -> pool). Pool expansion no longer re-runs heal.
-2
View File
@@ -49,7 +49,6 @@ env:
jobs:
kms-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 420
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -109,7 +108,6 @@ jobs:
- name: Run KMS suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-kms.log
run: |
@@ -84,9 +84,6 @@ env:
jobs:
performance-test:
runs-on: pf-testing
# Requirement: a failing benchmark must not fail the workflow;
# failures are filed to rustfs/backlog.
continue-on-error: true
timeout-minutes: 900
# Run on manual dispatch, or when the nightly build completed successfully.
# Skipped when nightly failed.
@@ -76,9 +76,6 @@ jobs:
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:
@@ -62,9 +62,6 @@ env:
jobs:
replication-test:
runs-on: smoke-testing
# A failed replication run must not break the chain or the workflow: the
# failure is reported to rustfs/backlog instead (see the issue step).
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -116,7 +113,6 @@ jobs:
- name: Run replication suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-replication.log
run: |
@@ -37,7 +37,6 @@ env:
jobs:
s3-compat-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -88,7 +87,6 @@ jobs:
- name: Run S3 compatibility suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-s3-compat.log
run: |
+55 -28
View File
@@ -74,10 +74,23 @@ env:
jobs:
security-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
- name: Checkout repository (for the OIDC live gate script)
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
with:
persist-credentials: false
- name: Initialize security evidence
id: evidence
run: |
set -euo pipefail
umask 077
SECURITY_ARTIFACTS_DIR="${RUNNER_TEMP}/rustfs-security-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}"
mkdir -- "${SECURITY_ARTIFACTS_DIR}"
printf 'SECURITY_ARTIFACTS_DIR=%s\n' "${SECURITY_ARTIFACTS_DIR}" >> "${GITHUB_ENV}"
# 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)
@@ -98,11 +111,6 @@ jobs:
echo "ERROR: unable to clone rustfs/auto-testing after 5 attempts" >&2
exit 1
- name: Checkout repository (for the OIDC live gate script)
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
with:
persist-credentials: false
- name: Show environment
run: |
uname -a
@@ -135,7 +143,8 @@ jobs:
id: test
continue-on-error: true
env:
REPORT_FILE: /tmp/rustfs-security-report.md
REPORT_FILE: ${{ env.SECURITY_ARTIFACTS_DIR }}/suite-report.md
TMPDIR: ${{ env.SECURITY_ARTIFACTS_DIR }}
RUSTFS_SECURITY_OIDC_LIVE_SCRIPT: ${{ github.workspace }}/scripts/test/oidc_keycloak_live.sh
run: |
set -euo pipefail
@@ -159,29 +168,48 @@ jobs:
else
ARGS+=(--package-url "${RUSTFS_NIGHTLY_PACKAGE_URL}")
fi
./auto-testing/rustfs-security-test.sh "${ARGS[@]}"
GITHUB_STEP_SUMMARY=/dev/null ./auto-testing/rustfs-security-test.sh "${ARGS[@]}"
- name: Generate report
if: always()
id: report
if: ${{ always() && steps.evidence.outcome == 'success' }}
env:
TEST_OUTCOME: ${{ steps.test.outcome }}
run: |
set -euo pipefail
if [ ! -f /tmp/rustfs-security-report.md ]; then
{
echo "# RustFS security test report"
echo ""
echo "- Run: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
echo "- Trigger: ${{ github.event_name }}"
echo "- Test Step Outcome: failure (suite did not produce a report)"
} > /tmp/rustfs-security-report.md
RESULT=failure
if [ "${TEST_OUTCOME}" = "success" ] && [ -s "${SECURITY_ARTIFACTS_DIR}/suite-report.md" ]; then
RESULT=success
fi
cat /tmp/rustfs-security-report.md >> "${GITHUB_STEP_SUMMARY}"
{
echo "# RustFS security test report"
echo ""
echo "- Run: ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"
echo "- Attempt: ${GITHUB_RUN_ATTEMPT}"
echo "- Workflow Commit: ${GITHUB_SHA}"
echo "- Trigger: ${GITHUB_EVENT_NAME}"
echo "- Test Step Outcome: ${RESULT}"
echo "- Suite Step Outcome: ${TEST_OUTCOME}"
echo ""
# The dashboard prioritizes case rows over the step outcome.
# Keep partial case results in the artifact when the suite fails.
if [ "${RESULT}" = "success" ]; then
cat "${SECURITY_ARTIFACTS_DIR}/suite-report.md"
elif [ -s "${SECURITY_ARTIFACTS_DIR}/suite-report.md" ]; then
echo "The suite did not complete successfully. See suite-report.md in this run's artifact for diagnostics."
else
echo "The suite did not produce a non-empty report."
fi
} > "${SECURITY_ARTIFACTS_DIR}/report.md"
cat "${SECURITY_ARTIFACTS_DIR}/report.md" >> "${GITHUB_STEP_SUMMARY}"
[ "${RESULT}" = "success" ]
- name: Upload functional report to dashboard
if: always()
if: ${{ always() && steps.evidence.outcome == 'success' }}
continue-on-error: true
env:
GH_TOKEN: ${{ env.PF_TESTING_GH_TOKEN }}
REPORT_FILE: /tmp/rustfs-security-report.md
REPORT_FILE: ${{ env.SECURITY_ARTIFACTS_DIR }}/report.md
SUITE: security
run: |
set -euo pipefail
@@ -210,8 +238,9 @@ jobs:
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
SUITE: 'security'
SUITE_LABEL: 'Security'
EVIDENCE_OUTCOME: ${{ steps.evidence.outcome }}
RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
REPORT_FILE: '/tmp/rustfs-security-report.md'
REPORT_FILE: ${{ env.SECURITY_ARTIFACTS_DIR }}/report.md
LOG_FILE: ''
run: |
set -euo pipefail
@@ -245,7 +274,7 @@ jobs:
echo ""
echo "## Report (errors and symptoms)"
echo ""
if [ -s "${REPORT_FILE}" ]; then
if [ "${EVIDENCE_OUTCOME}" = "success" ] && [ -s "${REPORT_FILE}" ]; then
redact < "${REPORT_FILE}"
elif [ -s "${LOG_FILE:-}" ]; then
echo "(report file missing; log tail below)"
@@ -263,14 +292,12 @@ jobs:
echo "filed backlog issue for suite ${SUITE}"
- name: Upload report and logs
if: always()
if: ${{ always() && steps.evidence.outcome == 'success' }}
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
with:
name: rustfs-security-test-${{ github.run_id }}
path: |
/tmp/rustfs-security-report.md
/tmp/rustfs-security.*/*
if-no-files-found: ignore
name: rustfs-security-test-${{ github.run_id }}-${{ github.run_attempt }}
path: ${{ env.SECURITY_ARTIFACTS_DIR }}/
if-no-files-found: error
retention-days: 3
- name: Cleanup environment (after)
@@ -46,7 +46,6 @@ env:
jobs:
storage-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 360
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -97,7 +96,6 @@ jobs:
- name: Run storage engine suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-storage.log
run: |
-3
View File
@@ -61,9 +61,6 @@ env:
jobs:
tier-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: 420
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
+26 -4
View File
@@ -18,7 +18,7 @@ on:
workflow_dispatch:
inputs:
from_version:
description: 'OLD RustFS release tag (must ship a .deb asset, e.g. 1.0.0-rc.3)'
description: 'OLD RustFS release tag, e.g. 1.0.0-rc.3 (its release must ship a .deb asset). Leave empty for the default.'
required: false
default: '1.0.0-rc.3'
from_url:
@@ -26,7 +26,7 @@ on:
required: false
type: string
to_version:
description: 'NEW RustFS release tag (leave empty for latest nightly)'
description: 'NEW RustFS release tag, e.g. 1.0.0-rc.5 (any version with a .deb asset). Leave empty for latest nightly.'
required: false
to_url:
description: 'NEW .deb URL. Overrides to_version / nightly default.'
@@ -79,7 +79,6 @@ env:
jobs:
upgrade-test:
runs-on: smoke-testing
continue-on-error: true
timeout-minutes: 420
if: ${{ github.event_name == 'workflow_dispatch' || github.event_name == 'repository_dispatch' }}
steps:
@@ -142,9 +141,9 @@ jobs:
- name: Run upgrade compatibility suite
id: test
continue-on-error: true
env:
LOG_FILE: /tmp/rustfs-upgrade.log
GH_TOKEN: ${{ secrets.PF_TESTING_GH_TOKEN }}
run: |
set -euo pipefail
chmod +x auto-testing/rustfs-upgrade-test.sh
@@ -175,6 +174,29 @@ jobs:
else
ARGS+=(--to-url "${RUSTFS_NIGHTLY_PACKAGE_URL}")
fi
# Fail fast with a clear message when a requested release tag has
# no .deb asset (e.g. 1.0.0-rc.4 ships only zips), instead of
# letting the suite die mid-run on a 404.
check_release_asset() {
local version="$1" tag asset url
[ -n "${version}" ] && [ "${version}" != "null" ] || return 0
tag="${version#v}"
asset="rustfs_${tag//-/.}_amd64.deb"
url="https://github.com/rustfs/rustfs/releases/download/${tag}/${asset}"
if ! gh api "repos/rustfs/rustfs/releases/tags/${tag}" --jq '.assets[].name' 2>/dev/null | grep -qxF "${asset}"; then
echo "ERROR: release ${tag} has no downloadable asset ${asset}:" >&2
echo " ${url}" >&2
echo "Pick a tag whose release ships a .deb (check its release assets)." >&2
exit 1
fi
echo "resolved ${tag} -> ${url}"
}
if [ -z "${FROM_URL}" ]; then
check_release_asset "${FROM_VERSION}"
fi
if [ -z "${TO_URL}" ]; then
check_release_asset "${TO_VERSION}"
fi
./auto-testing/rustfs-upgrade-test.sh "${ARGS[@]}"
- name: Generate report
@@ -42,6 +42,7 @@ jobs:
- name: Check latest scheduled runs
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
RUSTFS_DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
run: |
set +e
python3 scripts/check_scheduled_validation_freshness.py \