gsadmin/rustfs
1
0
Fork 0
mirror of https://github.com/rustfs/rustfs.git synced 2026-10-13 08:02:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

ci: reuse workspace test builds for serial ILM checks (#8465)

Browse Source
This commit is contained in:
Chris
2026-10-10 22:55:48 -07:00
committed by GitHub
parent da42266bfb
commit ba2047b184
5 changed files with 126 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/cache-warm.yml
+1 -1
View File
@@ -99,7 +99,7 @@ env:
RUST_BACKTRACE: 1
jobs:
# Readers: test-and-lint, test-ilm-integration-serial, build-rustfs-debug-binary,
# Readers: test-and-lint (workspace and ILM), build-rustfs-debug-binary,
# e2e-tests, e2e-full.
warm-ci-dev:
name: Warm ci-dev
.github/workflows/ci.yml
+46 -82
View File
@@ -168,13 +168,10 @@ jobs:
echo "started_at=$(date --utc --iso-8601=seconds)"
} > artifacts/test-and-lint/run-metadata.txt
# Clippy runs before the test pass: lint failures are the most common
# CI-only breakage and should surface in minutes, not after 20+ minutes
# of tests.
# Sampled too: clippy is the natural control arm for any CARGO_BUILD_JOBS
# experiment, since --all-targets is check-only for workspace members and
# never links the ~100 test binaries the limit exists to throttle.
# Keep full Clippy validation on main, merge groups, and scheduled/manual
# runs. PRs retain the complete default test suite and compile-free checks.
- name: Run clippy lints
if: github.event_name != 'pull_request'
run: |
./scripts/ci/resource_sampler.sh start clippy
trap './scripts/ci/resource_sampler.sh stop' EXIT
@@ -283,6 +280,49 @@ jobs:
- name: Verify rebalance/decommission migration proofs
run: ./scripts/check_migration_gate_count.sh evidence artifacts/test-and-lint/core-test-listing.json target/nextest/ci/junit.xml
# The workspace already compiled these ignored tests. Keep the same Cargo
# package selection to reuse their binaries, then run them serially in
# separate processes because they share fixed ports and global state.
# test_transition_and_restore_flows was re-enabled by rustfs/backlog#1303:
# its "missing xl.meta on disk2" was a test-util bug (open_disk hardcoded
# disk_index 0), not an EC metadata-distribution issue.
# restore_object_usecase_reports_ongoing_conflict_and_completion was
# re-enabled by backlog#1304 (restore accepts serialize on a short CAS
# guard; the copy-back no longer holds the #4877 whole-copy-back lock,
# so the mid-restore ongoing read and fast 409 rejection it asserts are
# the implemented contract).
- name: Run ignored ILM integration tests serially
if: needs.classify-changes.outputs.mode == 'full'
env:
# Match the preceding workspace build and reuse its feature graph.
CARGO_BUILD_JOBS: ${{ (github.event_name == 'push' || github.event_name == 'workflow_dispatch') && '3' || '2' }}
run: |
mkdir -p artifacts/ilm-integration
set +e
NEXTEST_HIDE_PROGRESS_BAR=1 timeout --verbose --signal=TERM --kill-after=30s 80m \
cargo nextest run --profile default -j1 --run-ignored ignored-only \
--all --exclude e2e_test \
-E 'binary(lifecycle_integration_test) or (package(rustfs) and test(lifecycle_transition_api_test))' \
--status-level all --final-status-level all \
2>&1 | tee artifacts/ilm-integration/nextest.log
status=${PIPESTATUS[0]}
{
echo "exit_status=${status}"
echo "finished_at=$(date --utc --iso-8601=seconds)"
echo
echo "Remaining test-related processes:"
pgrep -af 'cargo|nextest|target/.*/deps/' || true
} > artifacts/ilm-integration/diagnostics.txt
exit "${status}"
- name: Upload ILM test diagnostics
if: always() && needs.classify-changes.outputs.mode == 'full'
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: ilm-integration-${{ github.run_number }}-${{ github.run_attempt }}
path: artifacts/ilm-integration
retention-days: 3
# This gate builds into a fresh target directory to isolate the E2E root.
# Give its cold build a separate budget from workspace tests and migration proofs.
offline-enrollment-e2e:
@@ -314,80 +354,6 @@ jobs:
- name: Check offline enrollment E2E root boundary
run: ./scripts/check_offline_enrollment_e2e.sh
# Dedicated serial lane for the ILM / lifecycle integration tests. These tests
# drive the object layer through process-global singletons (the GLOBAL_ENV
# ECStore, the global tier-config manager, background-expiry workers) and bind
# fixed ports (9002 for the scanner suite, 9003 for the app suite), so they are
# marked #[ignore] to keep them out of the default parallel `cargo nextest run
# --all` pass. Run them here explicitly with `--run-ignored ignored-only` and
# `-j1` so no two of them share global state or race for a port at once.
# serial_test's #[serial] does NOT serialize across nextest's process-per-test
# boundary (see .config/nextest.toml); `-j1` is what actually serializes them.
# See rustfs/backlog#1148 (ilm-1) and #1155.
test-ilm-integration-serial:
name: ILM Integration (serial)
if: needs.classify-changes.outputs.mode == 'full' && (github.event_name != 'pull_request' || github.event.action != 'closed')
needs: [ quick-checks, classify-changes ]
runs-on: sm-standard-4
timeout-minutes: 90
env:
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
steps:
- name: Checkout repository
uses: actions/checkout@f548e57e544e1ff5a4c46bf1e1b8685f8e4a348a # v7
with:
persist-credentials: false
- name: Setup Rust environment
uses: ./.github/actions/setup
with:
rust-version: stable
cache-shared-key: ci-dev
cache-save-if: 'false'
install-build-packaging-tools: 'false'
# test_transition_and_restore_flows was re-enabled by rustfs/backlog#1303:
# its "missing xl.meta on disk2" was a test-util bug (open_disk hardcoded
# disk_index 0), not an EC metadata-distribution issue.
# restore_object_usecase_reports_ongoing_conflict_and_completion was
# re-enabled by backlog#1304 (restore accepts serialize on a short CAS
# guard; the copy-back no longer holds the #4877 whole-copy-back lock,
# so the mid-restore ongoing read and fast 409 rejection it asserts are
# the implemented contract).
- name: Run ignored ILM integration tests serially
env:
# Match the measured Test and Lint link budget. The default exposed
# all 14 pod CPUs and a cold cache spent the full 80m compiling
# without starting one ILM test (main run 32982910990).
CARGO_BUILD_JOBS: ${{ (github.event_name == 'push' || github.event_name == 'workflow_dispatch') && '3' || '2' }}
run: |
mkdir -p artifacts/ilm-integration
set +e
NEXTEST_HIDE_PROGRESS_BAR=1 timeout --verbose --signal=TERM --kill-after=30s 80m \
cargo nextest run -j1 --run-ignored ignored-only \
-p rustfs-scanner -p rustfs \
-E 'binary(lifecycle_integration_test) or (package(rustfs) and test(lifecycle_transition_api_test))' \
--status-level all --final-status-level all \
2>&1 | tee artifacts/ilm-integration/nextest.log
status=${PIPESTATUS[0]}
{
echo "exit_status=${status}"
echo "finished_at=$(date --utc --iso-8601=seconds)"
echo
echo "Remaining test-related processes:"
pgrep -af 'cargo|nextest|target/.*/deps/' || true
} > artifacts/ilm-integration/diagnostics.txt
exit "${status}"
- name: Upload ILM test diagnostics
if: always()
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: ilm-integration-${{ github.run_number }}-${{ github.run_attempt }}
path: |
artifacts/ilm-integration
target/nextest/ci/junit.xml
test-and-lint-rio-v2:
name: Test and Lint (rio-v2)
# Alternate feature configurations run on main, merge groups, and scheduled
@@ -1266,7 +1232,6 @@ jobs:
- quick-checks
- test-and-lint
- offline-enrollment-e2e
- test-ilm-integration-serial
- test-and-lint-rio-v2
- connect-short-credential-boundary
- test-and-lint-protocols
@@ -1300,7 +1265,6 @@ jobs:
- quick-checks
- test-and-lint
- offline-enrollment-e2e
- test-ilm-integration-serial
- test-and-lint-rio-v2
- test-and-lint-protocols
- build-rustfs-debug-binary