Files
seaweedfs/.github/workflows/s3-tables-tests.yml
T
Chris Lu caadd6ca79 ci(s3tables): stop Lakekeeper flaking on Docker Hub pull timeouts (#9920)
* ci(s3tables): drop docker pre-pull from Lakekeeper job

The lakekeeper repro is pure Go against the local weed binary; the job
kept failing on Docker Hub timeouts pulling python:3 and localstack
images the test never runs. Also drop the stale python-in-docker
comments left from the old harness.

* ci(s3tables): serve python:3 from GHA cache in the STS job

Retried pulls still die when both mirror.gcr.io and registry-1.docker.io
are unreachable from the runner. Cache the saved image tarball under a
weekly key: an exact hit skips the registry entirely, a miss pulls fresh
and refreshes the cache, and a stale tarball from a previous week is the
fallback when Docker Hub is down.

* ci(spark): pre-pull the spark tag the test actually runs

The workflow warmed apache/spark:3.5.8 with retries while the
testcontainers setup runs apache/spark:3.5.1, so the real image was
pulled at test time with no retry at all.
2026-06-10 13:26:30 -07:00

944 lines
27 KiB
YAML

name: "S3 Tables Integration Tests"
on:
pull_request:
permissions:
contents: read
jobs:
s3-tables-tests:
name: S3 Tables Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run S3 Tables Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/table-buckets
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 Tables Tests ==="
# Run S3 Tables integration tests
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "S3 Tables integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/table-buckets
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-tables-test-logs
path: test/s3tables/table-buckets/test-output.log
retention-days: 3
iceberg-catalog-tests:
name: Iceberg Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Run go mod tidy
run: go mod tidy
- name: Run Iceberg Catalog Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/catalog
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Iceberg Catalog Tests ==="
# Run Iceberg catalog integration tests using Makefile (handles build)
make test 2>&1 | tee test-output.log || {
echo "Iceberg catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/catalog
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: iceberg-catalog-test-logs
path: test/s3tables/catalog/test-output.log
retention-days: 3
trino-iceberg-catalog-tests:
name: Trino Iceberg Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull Trino image
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull trinodb/trino:479
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run Trino Iceberg Catalog Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/catalog_trino
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Trino Iceberg Catalog Tests ==="
# Run Trino + Iceberg catalog integration tests
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "Trino Iceberg catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/catalog_trino
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: trino-iceberg-catalog-test-logs
path: test/s3tables/catalog_trino/test-output.log
retention-days: 3
dremio-iceberg-catalog-tests:
name: Dremio Iceberg Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull images
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull dremio/dremio-oss:25.2.0
pull python:3.11-slim
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run Dremio Iceberg Catalog Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/catalog_dremio
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
docker info
echo "=== Starting Dremio Iceberg Catalog Tests ==="
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "Dremio Iceberg catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/catalog_dremio
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker|dremio)" || true
echo "=== Dremio containers ==="
docker ps -a --filter "name=seaweed-dremio" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: dremio-iceberg-catalog-test-logs
path: test/s3tables/catalog_dremio/test-output.log
retention-days: 3
doris-iceberg-catalog-tests:
name: Doris Iceberg Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 35
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull images
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull apache/doris:doris-all-in-one-2.1.0
pull python:3.11-slim
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run Doris Iceberg Catalog Integration Tests
timeout-minutes: 30
working-directory: test/s3tables/catalog_doris
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
docker info
echo "=== Starting Doris Iceberg Catalog Tests ==="
go test -v -timeout 25m . 2>&1 | tee test-output.log || {
echo "Doris Iceberg catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/catalog_doris
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker|doris)" || true
echo "=== Doris containers ==="
docker ps -a --filter "name=seaweed-doris" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: doris-iceberg-catalog-test-logs
path: test/s3tables/catalog_doris/test-output.log
retention-days: 3
polaris-integration-tests:
name: Polaris Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull Polaris image
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull apache/polaris:latest
- name: Run Polaris Integration Tests
timeout-minutes: 25
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Polaris Tests ==="
go test -v -timeout 20m ./test/s3tables/polaris 2>&1 | tee test/s3tables/polaris/test-output.log || {
echo "Polaris integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/polaris
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: polaris-test-logs
path: test/s3tables/polaris/test-output.log
retention-days: 3
spark-iceberg-catalog-tests:
name: Spark Iceberg Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull Spark image
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull apache/spark:3.5.1
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run Spark Iceberg Catalog Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/catalog_spark
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Spark Iceberg Catalog Tests ==="
# Run Spark + Iceberg catalog integration tests
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "Spark Iceberg catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/catalog_spark
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: spark-iceberg-catalog-test-logs
path: test/s3tables/catalog_spark/test-output.log
retention-days: 3
risingwave-catalog-tests:
name: RisingWave Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull RisingWave image
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull risingwavelabs/risingwave:v2.5.0
pull postgres:16-alpine
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run RisingWave Catalog Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/catalog_risingwave
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting RisingWave Catalog Tests ==="
# Run RisingWave catalog integration tests
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "RisingWave catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/catalog_risingwave
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: risingwave-catalog-test-logs
path: test/s3tables/catalog_risingwave/test-output.log
retention-days: 3
sts-integration-tests:
name: STS Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Week stamp for image cache key
id: week
run: echo "week=$(date -u +%G-%V)" >> "$GITHUB_OUTPUT"
- name: Restore python:3 image cache
id: python-image
uses: actions/cache@v5
with:
path: /tmp/python3-image.tar
key: python3-image-${{ steps.week.outputs.week }}
restore-keys: |
python3-image-
- name: Load or pull python:3
run: |
if [ "${{ steps.python-image.outputs.cache-hit }}" = "true" ]; then
docker load -i /tmp/python3-image.tar
exit 0
fi
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
if pull python:3; then
docker save -o /tmp/python3-image.tar python:3
elif [ -f /tmp/python3-image.tar ]; then
# Docker Hub unreachable; fall back to last week's cached image
docker load -i /tmp/python3-image.tar
else
exit 1
fi
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run STS Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/sts_integration
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting STS Integration Tests ==="
# Run STS integration tests
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "STS integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/sts_integration
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: sts-integration-test-logs
path: test/s3tables/sts_integration/test-output.log
retention-days: 3
lakekeeper-integration-tests:
name: Lakekeeper Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run Lakekeeper Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/lakekeeper
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Lakekeeper Integration Tests ==="
# Run Lakekeeper integration tests
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "Lakekeeper integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/lakekeeper
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: lakekeeper-integration-test-logs
path: test/s3tables/lakekeeper/test-output.log
retention-days: 3
unity-catalog-integration-tests:
name: Unity Catalog Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Pre-pull images
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull unitycatalog/unitycatalog:v0.4.0
pull python:3.11-slim
- name: Run go mod tidy
run: go mod tidy
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Run Unity Catalog Integration Tests
timeout-minutes: 25
working-directory: test/s3tables/unity_catalog
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
docker info
echo "=== Starting Unity Catalog Tests ==="
go test -v -timeout 20m . 2>&1 | tee test-output.log || {
echo "Unity Catalog integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3tables/unity_catalog
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker|unitycatalog)" || true
echo "=== Unity Catalog containers ==="
docker ps -a --filter "name=seaweed-unity-catalog" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: unity-catalog-integration-test-logs
path: test/s3tables/unity_catalog/test-output.log
retention-days: 3
s3-tables-build-verification:
name: S3 Tables Build Verification
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Verify S3 Tables Package Builds
run: |
set -x
echo "=== Building S3 Tables package ==="
go build ./weed/s3api/s3tables || {
echo "S3 Tables package build failed"
exit 1
}
echo "S3 Tables package built successfully"
- name: Verify S3 API Integration Builds
run: |
set -x
echo "=== Building S3 API with S3 Tables integration ==="
go build ./weed/s3api || {
echo "S3 API build with S3 Tables failed"
exit 1
}
echo "S3 API with S3 Tables integration built successfully"
- name: Run Go Tests for S3 Tables Package
run: |
set -x
echo "=== Running Go unit tests for S3 Tables ==="
go test -v -race -timeout 5m ./weed/s3api/s3tables/... || {
echo "S3 Tables unit tests failed"
exit 1
}
echo "S3 Tables unit tests passed"
- name: Verify Iceberg Package Builds
run: |
set -x
echo "=== Building Iceberg package ==="
go build ./weed/s3api/iceberg || {
echo "Iceberg package build failed"
exit 1
}
echo "Iceberg package built successfully"
- name: Run Go Tests for Iceberg Package
run: |
set -x
echo "=== Running Go unit tests for Iceberg ==="
go test -v -race -timeout 5m ./weed/s3api/iceberg/... || {
echo "Iceberg unit tests failed"
exit 1
}
echo "Iceberg unit tests passed"
s3-tables-fmt-check:
name: S3 Tables Format Check
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Check Go Format
run: |
set -x
echo "=== Checking S3 Tables Go format ==="
unformatted=$(gofmt -l ./weed/s3api/s3tables)
if [ -n "$unformatted" ]; then
echo "Go format check failed - files need formatting"
echo "$unformatted"
exit 1
fi
echo "All S3 Tables files are properly formatted"
- name: Check S3 Tables Test Format
run: |
set -x
echo "=== Checking S3 Tables test format ==="
unformatted=$(gofmt -l ./test/s3tables)
if [ -n "$unformatted" ]; then
echo "Go format check failed for tests"
echo "$unformatted"
exit 1
fi
echo "All S3 Tables test files are properly formatted"
- name: Check Iceberg Format
run: |
set -x
echo "=== Checking Iceberg Go format ==="
unformatted=$(gofmt -l ./weed/s3api/iceberg)
if [ -n "$unformatted" ]; then
echo "Go format check failed for Iceberg - files need formatting"
echo "$unformatted"
exit 1
fi
echo "All Iceberg files are properly formatted"
s3-tables-vet:
name: S3 Tables Go Vet Check
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Run Go Vet
run: |
set -x
echo "=== Running go vet on S3 Tables package ==="
go vet ./weed/s3api/s3tables/... || {
echo "go vet check failed"
exit 1
}
echo "go vet checks passed"
- name: Run Go Vet on Tests
run: |
set -x
echo "=== Running go vet on S3 Tables tests ==="
go vet ./test/s3tables/... || {
echo "go vet check failed for tests"
exit 1
}
echo "go vet checks passed for tests"
- name: Run Go Vet on Iceberg
run: |
set -x
echo "=== Running go vet on Iceberg package ==="
go vet ./weed/s3api/iceberg/... || {
echo "go vet check failed for Iceberg"
exit 1
}
echo "go vet checks passed for Iceberg"