test(e2e): add distributed cluster regression coverage (#7158)

* test(e2e): add distributed 4x4 validation

* test(e2e): prove operations overlap data movement

---------

Co-authored-by: Zhengchao An <anzhengchao@gmail.com>
This commit is contained in:
RustFS
2026-09-06 10:12:06 +08:00
committed by GitHub
parent 6655272c90
commit 07833379b4
27 changed files with 4101 additions and 2 deletions
+199
View File
@@ -0,0 +1,199 @@
# Copyright 2024 RustFS Team
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# 4-node 4-disk distributed e2e lane.
#
# Each selected test starts a real localhost cluster via
# `RustFSTestClusterEnvironment` (4 processes; 4 drives per node unless the
# case is a two-site 4-node 1-drive pair or a 4-node upgrade). Membership is
# `[profile.e2e-distributed]` in `.config/nextest.toml`. Storage-sensitive PRs,
# nightly runs, and manual dispatches all execute the same fail-closed suite.
# Upgrade cases download the same pinned previous release as e2e-upgrade.yml.
name: e2e-distributed
on:
pull_request:
paths:
- "Cargo.lock"
- "Cargo.toml"
- ".config/nextest.toml"
- ".github/workflows/e2e-distributed.yml"
- "crates/audit/**"
- "crates/common/**"
- "crates/config/**"
- "crates/e2e_test/**"
- "crates/ecstore/**"
- "crates/filemeta/**"
- "crates/heal/**"
- "crates/iam/**"
- "crates/lock/**"
- "crates/madmin/**"
- "crates/notify/**"
- "crates/replication/**"
- "crates/s3-client/**"
- "crates/s3-ops/**"
- "crates/s3-types/**"
- "crates/scanner/**"
- "crates/storage-api/**"
- "crates/utils/**"
- "rustfs/**"
workflow_dispatch:
inputs:
filter:
description: "Optional nextest -E filter (default: the whole e2e-distributed profile)"
required: false
default: ""
schedule:
# 05:53 UTC nightly — clear of e2e-nightly (04:29) and ODM interop (05:23).
- cron: "53 5 * * *"
permissions:
contents: read
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: ${{ github.event_name != 'schedule' }}
jobs:
distributed:
name: Distributed 4-node 4-disk e2e
runs-on: sm-standard-4
timeout-minutes: 180
env:
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: "true"
NO_PROXY: 127.0.0.1,localhost
HTTP_PROXY: ""
HTTPS_PROXY: ""
# Pinned previous release used by distributed::upgrade_test (same pin as e2e-upgrade.yml).
UPGRADE_SOURCE_VERSION: 1.0.0-rc.2
UPGRADE_SOURCE_ASSET: rustfs-linux-x86_64-gnu-v1.0.0-rc.2.zip
UPGRADE_SOURCE_SHA256: 7c789386bf85278f865b8e0d359bf4edb84d5aa408cc3fa54a18c25ca74cd6e7
steps:
- name: Checkout repository
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
with:
persist-credentials: false
- name: Setup Rust environment
uses: ./.github/actions/setup
with:
rust-version: stable
cache-shared-key: ci-e2e-distributed
cache-save-if: ${{ github.ref == 'refs/heads/main' }}
install-build-packaging-tools: 'false'
- name: Prepare isolated filesystems for pool movement
run: |
set -euo pipefail
mount_base="${RUNNER_TEMP}/rustfs-e2e-pools"
mkdir -p "${mount_base}"
roots=()
for pool in 0 1 2 3; do
image="${mount_base}/pool-${pool}.img"
mountpoint="${mount_base}/pool-${pool}"
truncate -s 1G "${image}"
mkfs.ext4 -q -F "${image}"
mkdir -p "${mountpoint}"
sudo mount -o loop,nosuid,nodev "${image}" "${mountpoint}"
sudo chmod 1777 "${mountpoint}"
roots+=("${mountpoint}")
done
printf -v joined_roots '%s:' "${roots[@]}"
echo "RUSTFS_E2E_POOL_ROOTS=${joined_roots%:}" >> "${GITHUB_ENV}"
findmnt --noheadings --output TARGET,SOURCE,FSTYPE --target "${roots[0]}"
findmnt --noheadings --output TARGET,SOURCE,FSTYPE --target "${roots[1]}"
findmnt --noheadings --output TARGET,SOURCE,FSTYPE --target "${roots[2]}"
findmnt --noheadings --output TARGET,SOURCE,FSTYPE --target "${roots[3]}"
- name: Download pinned previous release
env:
SOURCE_DIR: ${{ runner.temp }}/rustfs-upgrade-source
run: |
set -euo pipefail
mkdir -p "$SOURCE_DIR"
archive="$SOURCE_DIR/$UPGRADE_SOURCE_ASSET"
curl --fail --location --retry 3 --output "$archive" \
"https://github.com/${GITHUB_REPOSITORY}/releases/download/${UPGRADE_SOURCE_VERSION}/${UPGRADE_SOURCE_ASSET}"
echo "$UPGRADE_SOURCE_SHA256 $archive" | sha256sum --check --strict
unzip -q "$archive" -d "$SOURCE_DIR"
chmod +x "$SOURCE_DIR/rustfs"
test -x "$SOURCE_DIR/rustfs"
echo "RUSTFS_UPGRADE_SOURCE_BINARY=$SOURCE_DIR/rustfs" >> "$GITHUB_ENV"
- name: Build rustfs binary
run: |
cargo build -p rustfs --bins
: > target/debug/rustfs.features
- name: Verify distributed e2e membership
env:
NEXTEST_LISTING: ${{ runner.temp }}/rustfs-e2e-distributed-list.json
run: |
cargo nextest list --profile e2e-distributed -p e2e_test --message-format json > "${NEXTEST_LISTING}"
python3 ./scripts/check_test_wiring.py --check-profile e2e-distributed "${NEXTEST_LISTING}"
- name: Run distributed 4-node e2e suite
env:
RUSTFS_E2E_LOG_DIR: ${{ runner.temp }}/rustfs-e2e-distributed-logs
FILTER: ${{ inputs.filter }}
run: |
set -euo pipefail
if [ -n "${FILTER}" ]; then
cargo nextest run --profile e2e-distributed -p e2e_test -E "${FILTER}"
else
cargo nextest run --profile e2e-distributed -p e2e_test --no-tests=fail
fi
- name: Upload distributed e2e diagnostics
if: always()
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
with:
name: e2e-distributed-${{ github.run_number }}
path: |
target/nextest/e2e-distributed/junit.xml
${{ runner.temp }}/rustfs-e2e-distributed-list.json
${{ runner.temp }}/rustfs-e2e-distributed-logs/
retention-days: 7
if-no-files-found: warn
- name: Unmount isolated pool filesystems
if: always()
run: |
set -euo pipefail
mount_base="${RUNNER_TEMP}/rustfs-e2e-pools"
for pool in 0 1 2 3; do
mountpoint="${mount_base}/pool-${pool}"
if mountpoint --quiet "${mountpoint}"; then
sudo umount "${mountpoint}"
fi
done
alert-on-failure:
name: Alert on scheduled failure
needs: [distributed]
if: always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure')
runs-on: ubuntu-latest
timeout-minutes: 10
permissions:
contents: read
issues: write
steps:
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
with:
persist-credentials: false
- name: Open or update failure-tracking issue
uses: ./.github/actions/schedule-failure-issue
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
@@ -22,6 +22,7 @@ on:
- "Continuous Integration"
- "coverage"
- "e2e-nightly"
- "e2e-distributed"
- "e2e-s3tests"
- "Fuzz"
- "mint"