Compare commits

..
Author SHA1 Message Date
Chris Lu aff9aa7fa5 fmt 2025-12-01 10:34:10 -08:00
Chris Lu 2f007425c0 http: disable HTTP/2 to enable parallel connections
This fixes the mount read throughput issue where HTTP GET requests to the
same volume server were being serialized even with high -concurrentReaders.

The issue was that:
1. HTTP/2 multiplexes all requests over a single TCP connection
2. Even with HTTP/1.1, ForceAttemptHTTP2 defaults to true in Go

Changes:
- Set ForceAttemptHTTP2: false on http.Transport to disable HTTP/2
- Set MaxConnsPerHost: 0 (unlimited) to allow parallel connections per host
- For HTTPS, set NextProtos to only 'http/1.1' to prevent HTTP/2 negotiation

This allows multiple goroutines to use separate TCP connections to the same
volume server, enabling true parallel chunk fetching and better network
bandwidth utilization.

Relates to: #7504
2025-12-01 09:52:18 -08:00
1860 changed files with 40044 additions and 300560 deletions
+1 -5
View File
@@ -5,6 +5,7 @@
# How are we solving the problem?
# How is the PR tested?
@@ -12,8 +13,3 @@
# Checks
- [ ] I have added unit tests if possible.
- [ ] I will add related wiki document changes and link to this PR after merging.
- [ ] All AI code review comments have been addressed. No more comments to fix if reviewed again. Reviewer may request additional gemini and copilot reviews.
# Checks for AI generated PRs
- [ ] I have reviewed every line of code.
- [ ] The PR is kept as minimum as possible. Large PRs would not be accepted.
+6 -6
View File
@@ -38,13 +38,13 @@ jobs:
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Set BUILD_TIME env
run: echo BUILD_TIME=$(date -u +%Y%m%d-%H%M) >> ${GITHUB_ENV}
- name: Go Release Binaries Large Disk
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -60,7 +60,7 @@ jobs:
asset_name: "weed-large-disk-${{ env.BUILD_TIME }}-${{ matrix.goos }}-${{ matrix.goarch }}"
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -87,13 +87,13 @@ jobs:
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Set BUILD_TIME env
run: echo BUILD_TIME=$(date -u +%Y%m%d-%H%M) >> ${GITHUB_ENV}
- name: Go Release Binaries Large Disk
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -109,7 +109,7 @@ jobs:
asset_name: "weed-large-disk-${{ env.BUILD_TIME }}-${{ matrix.goos }}-${{ matrix.goarch }}"
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+3 -3
View File
@@ -28,9 +28,9 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -44,7 +44,7 @@ jobs:
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+3 -3
View File
@@ -28,9 +28,9 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -44,7 +44,7 @@ jobs:
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+3 -3
View File
@@ -28,9 +28,9 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -44,7 +44,7 @@ jobs:
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+3 -3
View File
@@ -28,9 +28,9 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -44,7 +44,7 @@ jobs:
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+3 -3
View File
@@ -28,9 +28,9 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -45,7 +45,7 @@ jobs:
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}_full"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+3 -3
View File
@@ -28,9 +28,9 @@ jobs:
# Steps represent a sequence of tasks that will be executed as part of the job
steps:
# Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -44,7 +44,7 @@ jobs:
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@481a2c1a0f1be199722e3e9b74d7199acafc30a8 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
+1 -1
View File
@@ -18,7 +18,7 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
+8 -7
View File
@@ -3,6 +3,7 @@ name: "docker: build dev containers"
on:
push:
branches: [ master ]
workflow_dispatch: {}
permissions:
contents: read
@@ -15,11 +16,11 @@ jobs:
steps:
-
name: Checkout
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@030e881283bb7a6894de51c315a6bfe6a94e05cf # v3
uses: docker/metadata-action@318604b99e75e41977312d83839a89be02ca4893 # v3
with:
images: |
chrislusf/seaweedfs
@@ -32,7 +33,7 @@ jobs:
org.opencontainers.image.vendor=Chris Lu
-
name: Set up QEMU
uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v1
uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v1
-
name: Create BuildKit config
run: |
@@ -42,28 +43,28 @@ jobs:
EOF
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v1
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v1
with:
buildkitd-flags: "--debug"
buildkitd-config: /tmp/buildkitd.toml
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v1
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Login to GHCR
if: github.event_name != 'pull_request'
uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v1
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v1
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
-
name: Build
uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
@@ -126,14 +126,14 @@ jobs:
echo "seaweedfs_ref=$seaweed" >> "$GITHUB_OUTPUT"
- name: Set up QEMU
uses: docker/setup-qemu-action@v4
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
@@ -150,7 +150,7 @@ jobs:
fi
- name: Build and push image
uses: docker/build-push-action@v7
uses: docker/build-push-action@v6
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
+46 -239
View File
@@ -4,73 +4,29 @@ on:
push:
tags:
- '*'
workflow_dispatch:
inputs:
source_ref:
description: 'Git ref to build (branch, tag, or commit SHA)'
required: true
default: 'master'
image_tag:
description: 'Docker tag to publish (without variant suffix)'
required: true
default: 'latest'
variant:
description: 'Variant to build manually'
required: true
type: choice
default: all
options:
- all
- standard
- large_disk
publish:
description: 'Publish images and manifests'
required: true
type: boolean
default: false
workflow_dispatch: {}
permissions:
contents: read
security-events: write
jobs:
setup:
runs-on: ubuntu-latest
outputs:
variants: ${{ steps.set-variants.outputs.variants }}
publish: ${{ steps.set-publish.outputs.publish }}
steps:
- name: Select variants for this run
id: set-variants
run: |
if [ "${{ github.event_name }}" = "workflow_dispatch" ] && [ "${{ github.event.inputs.variant }}" != "all" ]; then
variants="[\"${{ github.event.inputs.variant }}\"]"
else
variants='["standard","large_disk"]'
fi
echo "variants=$variants" >> "$GITHUB_OUTPUT"
- name: Select publish mode
id: set-publish
run: |
if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
echo "publish=${{ github.event.inputs.publish }}" >> "$GITHUB_OUTPUT"
else
echo "publish=true" >> "$GITHUB_OUTPUT"
fi
build:
needs: [setup]
runs-on: ubuntu-latest
strategy:
matrix:
platform: [amd64, arm64, arm, 386]
variant: ${{ fromJSON(needs.setup.outputs.variants) }}
include:
- platform: amd64
qemu: false
- platform: arm64
qemu: true
- platform: arm
qemu: true
- platform: 386
qemu: true
steps:
- name: Checkout
uses: actions/checkout@v6
with:
ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
uses: actions/checkout@v4
- name: Free Disk Space
run: |
echo "Available disk space before cleanup:"
@@ -87,33 +43,21 @@ jobs:
[ -d /go/pkg ] && rm -rf /go/pkg || true
echo "Available disk space after cleanup:"
df -h
- name: Configure variant
id: config
run: |
if [ "${{ matrix.variant }}" == "large_disk" ]; then
echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
echo "build_args=TAGS=5BytesOffset" >> $GITHUB_OUTPUT
else
echo "tag_suffix=" >> $GITHUB_OUTPUT
echo "build_args=" >> $GITHUB_OUTPUT
fi
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@v5
with:
images: |
chrislusf/seaweedfs
ghcr.io/chrislusf/seaweedfs
tags: type=raw,value=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }},suffix=${{ steps.config.outputs.tag_suffix }}
tags: type=raw,value=latest
labels: |
org.opencontainers.image.title=seaweedfs
org.opencontainers.image.description=SeaweedFS is a distributed storage system for blobs, objects, files, and data lake, to store and serve billions of files fast!
org.opencontainers.image.vendor=Chris Lu
- name: Set up QEMU
if: matrix.platform != 'amd64'
uses: docker/setup-qemu-action@v4
if: matrix.qemu
uses: docker/setup-qemu-action@v3
- name: Create BuildKit config
run: |
cat > /tmp/buildkitd.toml <<EOF
@@ -121,41 +65,40 @@ jobs:
mirrors = ["https://mirror.gcr.io"]
EOF
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
with:
buildkitd-flags: "--debug"
buildkitd-config: /tmp/buildkitd.toml
- name: Login to Docker Hub
if: needs.setup.outputs.publish == 'true'
uses: docker/login-action@v4
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
if: needs.setup.outputs.publish == 'true'
uses: docker/login-action@v4
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Build ${{ matrix.platform }} ${{ matrix.variant }}
uses: docker/build-push-action@v7
- name: Build ${{ matrix.platform }}
uses: docker/build-push-action@v5
env:
DOCKER_BUILDKIT: 1
with:
context: ./docker
push: ${{ needs.setup.outputs.publish == 'true' }}
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
platforms: linux/${{ matrix.platform }}
# Push to GHCR only during build to avoid Docker Hub rate limits
tags: ghcr.io/chrislusf/seaweedfs:${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}${{ steps.config.outputs.tag_suffix }}-${{ matrix.platform }}
tags: ghcr.io/chrislusf/seaweedfs:latest-${{ matrix.platform }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha,scope=${{ matrix.variant }}-${{ matrix.platform }}
cache-to: type=gha,mode=max,scope=${{ matrix.variant }}-${{ matrix.platform }}
cache-from: type=gha
cache-to: type=gha,mode=max
build-args: |
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.sha }}
${{ steps.config.outputs.build_args }}
BRANCH=${{ github.sha }}
- name: Clean up build artifacts
if: always()
run: |
@@ -164,161 +107,28 @@ jobs:
# Remove Go build cache
sudo rm -rf /tmp/go-build*
trivy-scan:
runs-on: ubuntu-latest
needs: [setup, build]
strategy:
matrix:
variant: ${{ fromJSON(needs.setup.outputs.variants) }}
steps:
- name: Configure variant
id: config
run: |
if [ "${{ matrix.variant }}" == "large_disk" ]; then
echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
else
echo "tag_suffix=" >> $GITHUB_OUTPUT
fi
- name: Login to GHCR
if: needs.setup.outputs.publish == 'true'
uses: docker/login-action@v4
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Checkout for local scan build
if: needs.setup.outputs.publish != 'true'
uses: actions/checkout@v6
with:
ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
- name: Create BuildKit config for local scan build
if: needs.setup.outputs.publish != 'true'
run: |
cat > /tmp/buildkitd.toml <<EOF
[registry."docker.io"]
mirrors = ["https://mirror.gcr.io"]
EOF
- name: Set up Docker Buildx for local scan build
if: needs.setup.outputs.publish != 'true'
uses: docker/setup-buildx-action@v4
with:
buildkitd-flags: "--debug"
buildkitd-config: /tmp/buildkitd.toml
- name: Build local scan image tarball
if: needs.setup.outputs.publish != 'true'
uses: docker/build-push-action@v7
env:
DOCKER_BUILDKIT: 1
with:
context: ./docker
file: ./docker/Dockerfile.go_build
platforms: linux/amd64
outputs: type=docker,dest=/tmp/seaweedfs${{ steps.config.outputs.tag_suffix }}-amd64.tar
build-args: |
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.sha }}
${{ matrix.variant == 'large_disk' && 'TAGS=5BytesOffset' || '' }}
- name: Trivy report (published image)
if: needs.setup.outputs.publish == 'true'
# Pin to SHA - mutable tags were compromised (GHSA-69fq-xp46-6x23)
uses: aquasecurity/trivy-action@57a97c7e7821a5776cebc9bb87c984fa69cba8f1 # v0.35.0
with:
scan-type: image
# Scan amd64 only - OS packages are identical across architectures
# since they all use the same alpine base, so a single-arch scan
# provides sufficient coverage without multiplying CI time.
image-ref: ghcr.io/chrislusf/seaweedfs:${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}${{ steps.config.outputs.tag_suffix }}-amd64
scanners: vuln
vuln-type: os,library
severity: HIGH,CRITICAL
ignore-unfixed: true
limit-severities-for-sarif: true
format: sarif
output: trivy-results.sarif
exit-code: '0'
- name: Trivy report (local tarball)
if: needs.setup.outputs.publish != 'true'
uses: aquasecurity/trivy-action@57a97c7e7821a5776cebc9bb87c984fa69cba8f1 # v0.35.0
with:
input: /tmp/seaweedfs${{ steps.config.outputs.tag_suffix }}-amd64.tar
scanners: vuln
vuln-type: os,library
severity: HIGH,CRITICAL
ignore-unfixed: true
limit-severities-for-sarif: true
format: sarif
output: trivy-results.sarif
exit-code: '0'
- name: Upload Trivy scan results to GitHub Security
uses: github/codeql-action/upload-sarif@v4
if: always()
with:
sarif_file: trivy-results.sarif
- name: Trivy gate (published image)
if: needs.setup.outputs.publish == 'true'
# Gate only on fixable high/critical vulnerabilities. Non-fixable
# findings are still visible in the SARIF upload above.
uses: aquasecurity/trivy-action@57a97c7e7821a5776cebc9bb87c984fa69cba8f1 # v0.35.0
with:
scan-type: image
image-ref: ghcr.io/chrislusf/seaweedfs:${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}${{ steps.config.outputs.tag_suffix }}-amd64
scanners: vuln
vuln-type: os,library
severity: HIGH,CRITICAL
ignore-unfixed: true
format: table
exit-code: '1'
skip-setup-trivy: true
- name: Trivy gate (local tarball)
if: needs.setup.outputs.publish != 'true'
uses: aquasecurity/trivy-action@57a97c7e7821a5776cebc9bb87c984fa69cba8f1 # v0.35.0
with:
input: /tmp/seaweedfs${{ steps.config.outputs.tag_suffix }}-amd64.tar
scanners: vuln
vuln-type: os,library
severity: HIGH,CRITICAL
ignore-unfixed: true
format: table
exit-code: '1'
skip-setup-trivy: true
create-manifest:
runs-on: ubuntu-latest
needs: [setup, build, trivy-scan]
if: needs.setup.outputs.publish == 'true' && github.event_name != 'pull_request'
strategy:
matrix:
variant: ${{ fromJSON(needs.setup.outputs.variants) }}
needs: [build]
if: github.event_name != 'pull_request'
steps:
- name: Checkout
uses: actions/checkout@v6
with:
ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
- name: Configure variant
id: config
run: |
if [ "${{ matrix.variant }}" == "large_disk" ]; then
echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
else
echo "tag_suffix=" >> $GITHUB_OUTPUT
fi
uses: actions/checkout@v4
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@v5
with:
images: |
chrislusf/seaweedfs
ghcr.io/chrislusf/seaweedfs
tags: type=raw,value=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }},suffix=${{ steps.config.outputs.tag_suffix }}
tags: type=raw,value=latest
- name: Login to Docker Hub
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
@@ -332,16 +142,13 @@ jobs:
crane version
- name: Create and push manifest
run: |
SUFFIX="${{ steps.config.outputs.tag_suffix }}"
BASE_TAG="${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}"
# Create manifest on GHCR first (no rate limits)
echo "Creating GHCR manifest (no rate limits)..."
docker buildx imagetools create -t ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-amd64 \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm64 \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-386
docker buildx imagetools create -t ghcr.io/chrislusf/seaweedfs:latest \
ghcr.io/chrislusf/seaweedfs:latest-amd64 \
ghcr.io/chrislusf/seaweedfs:latest-arm64 \
ghcr.io/chrislusf/seaweedfs:latest-arm \
ghcr.io/chrislusf/seaweedfs:latest-386
# Copy the complete multi-arch image from GHCR to Docker Hub
# This only requires one pull from GHCR (no rate limit) and one push to Docker Hub
@@ -377,16 +184,16 @@ jobs:
# Use crane or skopeo to copy, fallback to docker if not available
if command -v crane &> /dev/null; then
echo "Using crane to copy..."
retry_with_backoff crane copy ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}
retry_with_backoff crane copy ghcr.io/chrislusf/seaweedfs:latest chrislusf/seaweedfs:latest
elif command -v skopeo &> /dev/null; then
echo "Using skopeo to copy..."
retry_with_backoff skopeo copy --all docker://ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} docker://chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}
retry_with_backoff skopeo copy --all docker://ghcr.io/chrislusf/seaweedfs:latest docker://chrislusf/seaweedfs:latest
else
echo "Using docker buildx imagetools (pulling 4 images from Docker Hub)..."
# Fallback: create manifest directly on Docker Hub (pulls from Docker Hub - rate limited)
retry_with_backoff docker buildx imagetools create -t chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-amd64 \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm64 \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-arm \
ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}-386
retry_with_backoff docker buildx imagetools create -t chrislusf/seaweedfs:latest \
ghcr.io/chrislusf/seaweedfs:latest-amd64 \
ghcr.io/chrislusf/seaweedfs:latest-arm64 \
ghcr.io/chrislusf/seaweedfs:latest-arm \
ghcr.io/chrislusf/seaweedfs:latest-386
fi
+152
View File
@@ -0,0 +1,152 @@
name: "docker: build release containers for normal volume"
# DISABLED: Merged into container_release_unified.yml
on:
workflow_dispatch:
inputs:
force_run:
description: 'This workflow is disabled. Use container_release_unified.yml instead'
required: true
default: 'disabled'
permissions:
contents: read
jobs:
build:
runs-on: ubuntu-latest
strategy:
matrix:
platform: [amd64, arm64, arm, 386]
include:
- platform: amd64
qemu: false
- platform: arm64
qemu: true
- platform: arm
qemu: true
- platform: 386
qemu: true
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Free Disk Space
run: |
echo "Available disk space before cleanup:"
df -h
# Remove pre-installed tools
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
# Clean package managers
sudo apt-get clean
sudo rm -rf /var/lib/apt/lists/*
# Clean Docker aggressively
sudo docker system prune -af --volumes
# Clean Go cache if it exists
[ -d ~/.cache/go-build ] && rm -rf ~/.cache/go-build || true
[ -d /go/pkg ] && rm -rf /go/pkg || true
echo "Available disk space after cleanup:"
df -h
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: chrislusf/seaweedfs
tags: type=ref,event=tag
flavor: latest=false
- name: Set up QEMU
if: matrix.qemu
uses: docker/setup-qemu-action@v3
- name: Create BuildKit config
run: |
cat > /tmp/buildkitd.toml <<EOF
[registry."docker.io"]
mirrors = ["https://mirror.gcr.io"]
EOF
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
with:
buildkitd-config: /tmp/buildkitd.toml
- name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Build ${{ matrix.platform }}
uses: docker/build-push-action@v5
env:
DOCKER_BUILDKIT: 1
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
platforms: linux/${{ matrix.platform }}
tags: ${{ steps.docker_meta.outputs.tags }}-${{ matrix.platform }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
build-args: |
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.sha }}
- name: Clean up build artifacts
if: always()
run: |
# Clean up Docker build cache and temporary files
sudo docker system prune -f
# Remove Go build cache
sudo rm -rf /tmp/go-build*
create-manifest:
runs-on: ubuntu-latest
needs: [build]
if: github.event_name != 'pull_request'
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: chrislusf/seaweedfs
tags: type=ref,event=tag
flavor: latest=false
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Create and push manifest
run: |
# Function to retry command with exponential backoff
retry_with_backoff() {
local max_attempts=5
local timeout=1
local attempt=1
local exit_code=0
while [ $attempt -le $max_attempts ]; do
if "$@"; then
return 0
else
exit_code=$?
fi
if [ $attempt -lt $max_attempts ]; then
echo "Attempt $attempt failed. Retrying in ${timeout}s..." >&2
sleep $timeout
timeout=$((timeout * 2))
fi
attempt=$((attempt + 1))
done
echo "Command failed after $max_attempts attempts" >&2
return $exit_code
}
# Create manifest with retry
retry_with_backoff docker buildx imagetools create -t ${{ steps.docker_meta.outputs.tags }} \
${{ steps.docker_meta.outputs.tags }}-amd64 \
${{ steps.docker_meta.outputs.tags }}-arm64 \
${{ steps.docker_meta.outputs.tags }}-arm \
${{ steps.docker_meta.outputs.tags }}-386
+153
View File
@@ -0,0 +1,153 @@
name: "docker: build release containers for large volume"
# DISABLED: Merged into container_release_unified.yml
on:
workflow_dispatch:
inputs:
force_run:
description: 'This workflow is disabled. Use container_release_unified.yml instead'
required: true
default: 'disabled'
permissions:
contents: read
jobs:
build:
runs-on: ubuntu-latest
strategy:
matrix:
platform: [amd64, arm64, arm, 386]
include:
- platform: amd64
qemu: false
- platform: arm64
qemu: true
- platform: arm
qemu: true
- platform: 386
qemu: true
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Free Disk Space
run: |
echo "Available disk space before cleanup:"
df -h
# Remove pre-installed tools
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
# Clean package managers
sudo apt-get clean
sudo rm -rf /var/lib/apt/lists/*
# Clean Docker aggressively
sudo docker system prune -af --volumes
# Clean Go cache if it exists
[ -d ~/.cache/go-build ] && rm -rf ~/.cache/go-build || true
[ -d /go/pkg ] && rm -rf /go/pkg || true
echo "Available disk space after cleanup:"
df -h
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: chrislusf/seaweedfs
tags: type=ref,event=tag,suffix=_large_disk
flavor: latest=false
- name: Set up QEMU
if: matrix.qemu
uses: docker/setup-qemu-action@v3
- name: Create BuildKit config
run: |
cat > /tmp/buildkitd.toml <<EOF
[registry."docker.io"]
mirrors = ["https://mirror.gcr.io"]
EOF
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
with:
buildkitd-config: /tmp/buildkitd.toml
- name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Build ${{ matrix.platform }}
uses: docker/build-push-action@v5
env:
DOCKER_BUILDKIT: 1
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
build-args: |
TAGS=5BytesOffset
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.sha }}
platforms: linux/${{ matrix.platform }}
tags: ${{ steps.docker_meta.outputs.tags }}-${{ matrix.platform }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Clean up build artifacts
if: always()
run: |
# Clean up Docker build cache and temporary files
sudo docker system prune -f
# Remove Go build cache
sudo rm -rf /tmp/go-build*
create-manifest:
runs-on: ubuntu-latest
needs: [build]
if: github.event_name != 'pull_request'
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: chrislusf/seaweedfs
tags: type=ref,event=tag,suffix=_large_disk
flavor: latest=false
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Create and push manifest
run: |
# Function to retry command with exponential backoff
retry_with_backoff() {
local max_attempts=5
local timeout=1
local attempt=1
local exit_code=0
while [ $attempt -le $max_attempts ]; do
if "$@"; then
return 0
else
exit_code=$?
fi
if [ $attempt -lt $max_attempts ]; then
echo "Attempt $attempt failed. Retrying in ${timeout}s..." >&2
sleep $timeout
timeout=$((timeout * 2))
fi
attempt=$((attempt + 1))
done
echo "Command failed after $max_attempts attempts" >&2
return $exit_code
}
# Create manifest with retry
retry_with_backoff docker buildx imagetools create -t ${{ steps.docker_meta.outputs.tags }} \
${{ steps.docker_meta.outputs.tags }}-amd64 \
${{ steps.docker_meta.outputs.tags }}-arm64 \
${{ steps.docker_meta.outputs.tags }}-arm \
${{ steps.docker_meta.outputs.tags }}-386
+73
View File
@@ -0,0 +1,73 @@
name: "docker: build release containers for rocksdb"
# DISABLED: Merged into container_release_unified.yml
on:
workflow_dispatch:
inputs:
force_run:
description: 'This workflow is disabled. Use container_release_unified.yml instead'
required: true
default: 'disabled'
permissions:
contents: read
jobs:
build-large-release-container_rocksdb:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@v4
-
name: Free Disk Space
run: |
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc
sudo docker system prune -af
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: chrislusf/seaweedfs
tags: type=ref,event=tag,suffix=_large_disk_rocksdb
flavor: latest=false
labels: |
org.opencontainers.image.title=seaweedfs
org.opencontainers.image.description=SeaweedFS is a distributed storage system for blobs, objects, files, and data lake, to store and serve billions of files fast!
org.opencontainers.image.vendor=Chris Lu
-
name: Create BuildKit config
run: |
cat > /tmp/buildkitd.toml <<EOF
[registry."docker.io"]
mirrors = ["https://mirror.gcr.io"]
EOF
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
with:
buildkitd-config: /tmp/buildkitd.toml
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@v5
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.rocksdb_large
build-args: |
BRANCH=${{ github.sha }}
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
+72
View File
@@ -0,0 +1,72 @@
name: "docker: build release containers for all tags"
# DISABLED: Merged into container_release_unified.yml
on:
workflow_dispatch:
inputs:
force_run:
description: 'This workflow is disabled. Use container_release_unified.yml instead'
required: true
default: 'disabled'
permissions:
contents: read
jobs:
build-default-release-container:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@v4
-
name: Free Disk Space
run: |
echo "Before cleanup:"
df -h
sudo rm -rf /usr/share/dotnet
sudo rm -rf /usr/local/lib/android
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo docker system prune -af
echo "After cleanup:"
df -h
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: |
chrislusf/seaweedfs
tags: |
type=ref,event=tag,suffix=_full
flavor: |
latest=false
labels: |
org.opencontainers.image.title=seaweedfs
org.opencontainers.image.description=SeaweedFS is a distributed storage system for blobs, objects, files, and data lake, to store and serve billions of files fast!
org.opencontainers.image.vendor=Chris Lu
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@v5
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
build-args: TAGS=elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
+62
View File
@@ -0,0 +1,62 @@
name: "docker: build release containers for all tags and large volume"
# DISABLED: Merged into container_release_unified.yml
on:
workflow_dispatch:
inputs:
force_run:
description: 'This workflow is disabled. Use container_release_unified.yml instead'
required: true
default: 'disabled'
permissions:
contents: read
jobs:
build-default-release-container:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@v4
-
name: Free Disk Space
run: |
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc
sudo docker system prune -af
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v5
with:
images: chrislusf/seaweedfs
tags: type=ref,event=tag,suffix=_large_disk_full
flavor: latest=false
labels: |
org.opencontainers.image.title=seaweedfs
org.opencontainers.image.description=SeaweedFS is a distributed storage system for blobs, objects, files, and data lake, to store and serve billions of files fast!
org.opencontainers.image.vendor=Chris Lu
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@v5
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
build-args: TAGS=5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha
cache-to: type=gha,mode=max
@@ -21,7 +21,7 @@ jobs:
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@v5
with:
images: |
chrislusf/seaweedfs
@@ -35,14 +35,14 @@ jobs:
org.opencontainers.image.vendor=Chris Lu
-
name: Set up QEMU
uses: docker/setup-qemu-action@v4
uses: docker/setup-qemu-action@v3
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
@@ -57,7 +57,7 @@ jobs:
fi
-
name: Build
uses: docker/build-push-action@v7
uses: docker/build-push-action@v6
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
+23 -75
View File
@@ -4,35 +4,11 @@ on:
push:
tags:
- '*'
workflow_dispatch:
inputs:
variant:
description: 'Variant to build manually'
required: true
type: choice
default: all
options:
- all
- normal
- large_disk
- full
- large_disk_full
- rocksdb
release_tag:
description: 'Release tag to publish (e.g. 3.93)'
required: true
default: ''
rocksdb_version:
description: 'RocksDB git tag to use when variant=rocksdb'
required: false
default: 'v10.10.1'
workflow_dispatch: {}
permissions:
contents: read
env:
RELEASE_TAG: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.release_tag || github.ref_name }}
# Limit concurrent builds to avoid rate limits
concurrency:
group: release-${{ github.ref }}
@@ -60,16 +36,16 @@ jobs:
build_args: TAGS=5BytesOffset
tag_suffix: _large_disk
# Full tags - multi-arch
# Full tags - amd64 only
- variant: full
platforms: linux/amd64,linux/arm64
platforms: linux/amd64
dockerfile: ./docker/Dockerfile.go_build
build_args: TAGS=elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
tag_suffix: _full
# Large disk + full tags - multi-arch
# Large disk + full tags - amd64 only
- variant: large_disk_full
platforms: linux/amd64,linux/arm64
platforms: linux/amd64
dockerfile: ./docker/Dockerfile.go_build
build_args: TAGS=5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
tag_suffix: _large_disk_full
@@ -83,11 +59,9 @@ jobs:
steps:
- name: Checkout
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: actions/checkout@v6
uses: actions/checkout@v4
- name: Free Disk Space
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
echo "Available disk space before cleanup:"
df -h
@@ -101,14 +75,13 @@ jobs:
df -h
- name: Docker meta
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
id: docker_meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@v5
with:
images: |
chrislusf/seaweedfs
ghcr.io/chrislusf/seaweedfs
tags: type=raw,value=${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
tags: type=ref,event=tag,suffix=${{ matrix.tag_suffix }}
flavor: latest=false
labels: |
org.opencontainers.image.title=seaweedfs
@@ -116,11 +89,10 @@ jobs:
org.opencontainers.image.vendor=Chris Lu
- name: Set up QEMU
if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && contains(matrix.platforms, 'arm')
uses: docker/setup-qemu-action@v4
if: contains(matrix.platforms, 'arm')
uses: docker/setup-qemu-action@v3
- name: Create BuildKit config
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
cat > /tmp/buildkitd.toml <<EOF
[registry."docker.io"]
@@ -128,29 +100,27 @@ jobs:
EOF
- name: Set up Docker Buildx
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
with:
buildkitd-config: /tmp/buildkitd.toml
- name: Login to Docker Hub
if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && github.event_name != 'pull_request'
uses: docker/login-action@v4
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && github.event_name != 'pull_request'
uses: docker/login-action@v4
if: github.event_name != 'pull_request'
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Build and push ${{ matrix.variant }}
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: docker/build-push-action@v7
uses: docker/build-push-action@v5
env:
DOCKER_BUILDKIT: 1
with:
@@ -160,7 +130,7 @@ jobs:
platforms: ${{ matrix.platforms }}
# Push to GHCR to avoid Docker Hub rate limits on pulls
tags: |
ghcr.io/chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
ghcr.io/chrislusf/seaweedfs:${{ github.ref_name }}${{ matrix.tag_suffix }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha,scope=${{ matrix.variant }}
cache-to: type=gha,mode=max,scope=${{ matrix.variant }}
@@ -168,10 +138,9 @@ jobs:
${{ matrix.build_args }}
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.sha }}
${{ matrix.variant == 'rocksdb' && format('ROCKSDB_VERSION={0}', github.event.inputs.rocksdb_version || 'v10.10.1') || '' }}
- name: Clean up build artifacts
if: always() && (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant)
if: always()
run: |
sudo docker system prune -f
sudo rm -rf /tmp/go-build*
@@ -197,22 +166,19 @@ jobs:
steps:
- name: Login to Docker Hub
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: docker/login-action@v4
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Install crane
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
cd $(mktemp -d)
curl -sL "https://github.com/google/go-containerregistry/releases/latest/download/go-containerregistry_Linux_x86_64.tar.gz" | tar xz
@@ -220,7 +186,6 @@ jobs:
crane version
- name: Copy ${{ matrix.variant }} from GHCR to Docker Hub
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
# Function to retry with exponential backoff
retry_with_backoff() {
@@ -253,25 +218,8 @@ jobs:
# This is much more efficient than pulling/pushing individual arch images
echo "Copying ${{ matrix.variant }} from GHCR to Docker Hub..."
retry_with_backoff crane copy \
ghcr.io/chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }} \
chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
ghcr.io/chrislusf/seaweedfs:${{ github.ref_name }}${{ matrix.tag_suffix }} \
chrislusf/seaweedfs:${{ github.ref_name }}${{ matrix.tag_suffix }}
echo "✓ Successfully copied ${{ matrix.variant }} to Docker Hub"
helm-release:
runs-on: ubuntu-latest
needs: [copy-to-dockerhub]
if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
permissions:
contents: write
pages: write
steps:
- uses: actions/checkout@v6
- name: Publish Helm charts
uses: stefanprodan/helm-gh-pages@v1.7.0
with:
token: ${{ secrets.GITHUB_TOKEN }}
charts_dir: k8s/charts
target_dir: helm
branch: gh-pages
helm_version: "3.18.4"
@@ -4,9 +4,9 @@ on:
workflow_dispatch:
inputs:
rocksdb_version:
description: 'RocksDB git tag or branch to build (e.g. v10.10.1)'
description: 'RocksDB git tag or branch to build (e.g. v10.5.1)'
required: true
default: 'v10.10.1'
default: 'v10.5.1'
seaweedfs_ref:
description: 'SeaweedFS git tag, branch, or commit to build'
required: true
@@ -25,7 +25,7 @@ jobs:
steps:
- name: Checkout
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v2
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Prepare Docker tag
id: tag
@@ -82,19 +82,19 @@ jobs:
echo "seaweedfs_ref=$seaweed" >> "$GITHUB_OUTPUT"
- name: Set up QEMU
uses: docker/setup-qemu-action@ce360397dd3f832beb865e1373c09c0e9f86d70a # v1
uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v1
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v1
uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v1
- name: Login to Docker Hub
uses: docker/login-action@b45d80f862d83dbcd57f89517bcf500b2ab88fb2 # v1
uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Build and push image
uses: docker/build-push-action@d08e5c354a6adb9ed34480a06d141179aa583294 # v2
uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v2
with:
context: ./docker
push: true
+1 -1
View File
@@ -26,7 +26,7 @@ jobs:
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
go-version: '1.24'
- name: Build Telemetry Server
if: github.event_name == 'workflow_dispatch' && inputs.deploy
+2 -2
View File
@@ -9,6 +9,6 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: 'Checkout Repository'
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3
- name: 'Dependency Review'
uses: actions/dependency-review-action@2031cfc080254a8a887f58cffee85186f0e49e48
uses: actions/dependency-review-action@3c4e3dcb1aa7874d2c16be7d79418e9b7efd6261
+10 -10
View File
@@ -23,19 +23,20 @@ jobs:
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
- name: Set up Go 1.x
uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # v2
with:
go-version-file: 'go.mod'
go-version: ^1.13
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
- name: Cache Docker layers
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-e2e-${{ github.sha }}
@@ -45,7 +46,6 @@ jobs:
- name: Install dependencies
run: |
# Use faster mirrors and install with timeout
sudo rm -f /etc/apt/sources.list.d/azure-cli.list /etc/apt/sources.list.d/microsoft-prod.list
echo "deb http://azure.archive.ubuntu.com/ubuntu/ $(lsb_release -cs) main restricted universe multiverse" | sudo tee /etc/apt/sources.list
echo "deb http://azure.archive.ubuntu.com/ubuntu/ $(lsb_release -cs)-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list
@@ -134,7 +134,7 @@ jobs:
- name: Archive logs
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: output-logs
path: docker/output.log
@@ -1,61 +0,0 @@
name: "EC Integration Tests"
on:
push:
branches: [ master ]
pull_request:
branches: [ master ]
permissions:
contents: read
jobs:
ec-integration-tests:
name: EC Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Build weed binary
run: |
cd weed && go build -o weed .
- name: Run EC Integration Tests
working-directory: test/erasure_coding
run: |
go test -v
- name: Collect server logs on failure
if: failure()
run: |
echo "Collecting server logs from temp directories..."
mkdir -p /tmp/ec-test-logs
# Find all temp directories created by the tests (they persist on failure with t.TempDir())
find /tmp -maxdepth 1 -type d \( -name "TestEC*" -o -name "TestDisk*" -o -name "TestCross*" -o -name "TestEvacuation*" \) 2>/dev/null | while read dir; do
if [ -d "$dir" ]; then
echo "Found test directory: $dir"
# Copy the entire directory structure to preserve organization
cp -r "$dir" /tmp/ec-test-logs/ 2>/dev/null || true
fi
done
# List what we collected
echo "Collected logs:"
find /tmp/ec-test-logs -type f -name "*.log" 2>/dev/null || echo "No logs found"
- name: Archive logs
if: failure()
uses: actions/upload-artifact@v7
with:
name: ec-integration-test-logs
path: |
/tmp/ec-test-logs/
test/erasure_coding/
if-no-files-found: warn
-49
View File
@@ -1,49 +0,0 @@
name: EC Integration Tests
on:
push:
branches: [ master ]
paths:
- 'weed/admin/**'
- 'weed/worker/**'
- 'test/erasure_coding/admin_dockertest/**'
- '.github/workflows/ec-integration.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/admin/**'
- 'weed/worker/**'
- 'test/erasure_coding/admin_dockertest/**'
- '.github/workflows/ec-integration.yml'
jobs:
ec-integration-test:
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Build weed binary
run: |
cd weed
go build -o ../weed_bin
- name: Run EC integration tests
run: |
cd test/erasure_coding/admin_dockertest
go test -v -timeout 15m ec_integration_test.go
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: ec-test-logs
path: test/erasure_coding/admin_dockertest/tmp/logs/
retention-days: 7
+184 -31
View File
@@ -21,61 +21,214 @@ concurrency:
permissions:
contents: read
env:
GO_VERSION: '1.24'
TEST_TIMEOUT: '45m'
jobs:
fuse-integration:
name: FUSE Integration Testing
runs-on: ubuntu-22.04
timeout-minutes: 50
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
- name: Set up Go ${{ env.GO_VERSION }}
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
go-version: ${{ env.GO_VERSION }}
- name: Install FUSE and dependencies
run: |
sudo apt-get update
# fuse3 is pre-installed on ubuntu-22.04 runners and conflicts
# with the legacy fuse package, so only install the dev headers.
sudo apt-get install -y libfuse3-dev
# Allow non-root FUSE mounts with allow_other
echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
sudo chmod 644 /etc/fuse.conf
sudo apt-get install -y fuse libfuse-dev
# Verify FUSE installation
fusermount3 --version || fusermount --version || true
ls -la /dev/fuse
fusermount --version || true
ls -la /dev/fuse || true
- name: Build SeaweedFS
run: |
cd weed
go build -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -o weed .
go build -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v .
chmod +x weed
# Verify binary
./weed version
# Make weed binary available in PATH for the test framework
sudo cp weed /usr/local/bin/weed
- name: Install test dependencies
- name: Prepare FUSE Integration Tests
run: |
cd test/fuse_integration
go mod download
# Create isolated test directory to avoid Go module conflicts
mkdir -p /tmp/seaweedfs-fuse-tests
# Copy only the working test files to avoid Go module conflicts
# These are the files we've verified work without package name issues
cp test/fuse_integration/simple_test.go /tmp/seaweedfs-fuse-tests/ 2>/dev/null || echo "⚠️ simple_test.go not found"
cp test/fuse_integration/working_demo_test.go /tmp/seaweedfs-fuse-tests/ 2>/dev/null || echo "⚠️ working_demo_test.go not found"
# Note: Other test files (framework.go, basic_operations_test.go, etc.)
# have Go module conflicts and are skipped until resolved
echo "📁 Working test files copied:"
ls -la /tmp/seaweedfs-fuse-tests/*.go 2>/dev/null || echo "ℹ️ No test files found"
# Initialize Go module in isolated directory
cd /tmp/seaweedfs-fuse-tests
go mod init seaweedfs-fuse-tests
go mod tidy
# Verify setup
echo "✅ FUSE integration test environment prepared"
ls -la /tmp/seaweedfs-fuse-tests/
echo ""
echo "ℹ️ Current Status: Running working subset of FUSE tests"
echo " • simple_test.go: Package structure verification"
echo " • working_demo_test.go: Framework capability demonstration"
echo " • Full framework: Available in test/fuse_integration/ (module conflicts pending resolution)"
- name: Run FUSE Integration Tests
run: |
set -o pipefail
cd test/fuse_integration
echo "Running full FUSE integration test suite..."
go test -v -count=1 -timeout=45m ./... 2>&1 | tee /tmp/fuse-test-output.log
- name: Upload Test Logs
cd /tmp/seaweedfs-fuse-tests
echo "🧪 Running FUSE integration tests..."
echo "============================================"
# Run available working test files
TESTS_RUN=0
if [ -f "simple_test.go" ]; then
echo "📋 Running simple_test.go..."
go test -v -timeout=${{ env.TEST_TIMEOUT }} simple_test.go
TESTS_RUN=$((TESTS_RUN + 1))
fi
if [ -f "working_demo_test.go" ]; then
echo "📋 Running working_demo_test.go..."
go test -v -timeout=${{ env.TEST_TIMEOUT }} working_demo_test.go
TESTS_RUN=$((TESTS_RUN + 1))
fi
# Run combined test if multiple files exist
if [ -f "simple_test.go" ] && [ -f "working_demo_test.go" ]; then
echo "📋 Running combined tests..."
go test -v -timeout=${{ env.TEST_TIMEOUT }} simple_test.go working_demo_test.go
fi
if [ $TESTS_RUN -eq 0 ]; then
echo "⚠️ No working test files found, running module verification only"
go version
go mod verify
else
echo "✅ Successfully ran $TESTS_RUN test file(s)"
fi
echo "============================================"
echo "✅ FUSE integration tests completed"
- name: Run Extended Framework Validation
run: |
cd /tmp/seaweedfs-fuse-tests
echo "🔍 Running extended framework validation..."
echo "============================================"
# Test individual components (only run tests that exist)
if [ -f "simple_test.go" ]; then
echo "Testing simple verification..."
go test -v simple_test.go
fi
if [ -f "working_demo_test.go" ]; then
echo "Testing framework demo..."
go test -v working_demo_test.go
fi
# Test combined execution if both files exist
if [ -f "simple_test.go" ] && [ -f "working_demo_test.go" ]; then
echo "Testing combined execution..."
go test -v simple_test.go working_demo_test.go
elif [ -f "simple_test.go" ] || [ -f "working_demo_test.go" ]; then
echo "✅ Individual tests already validated above"
else
echo "⚠️ No working test files found for combined testing"
fi
echo "============================================"
echo "✅ Extended validation completed"
- name: Generate Test Coverage Report
run: |
cd /tmp/seaweedfs-fuse-tests
echo "📊 Generating test coverage report..."
go test -v -coverprofile=coverage.out .
go tool cover -html=coverage.out -o coverage.html
echo "Coverage report generated: coverage.html"
- name: Verify SeaweedFS Binary Integration
run: |
# Test that SeaweedFS binary is accessible from test environment
WEED_BINARY=$(pwd)/weed/weed
if [ -f "$WEED_BINARY" ]; then
echo "✅ SeaweedFS binary found at: $WEED_BINARY"
$WEED_BINARY version
echo "Binary is ready for full integration testing"
else
echo "❌ SeaweedFS binary not found"
exit 1
fi
- name: Upload Test Artifacts
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: fuse-integration-test-results
path: |
/tmp/fuse-test-output.log
/tmp/seaweedfs-fuse-logs/
/tmp/seaweedfs-fuse-tests/coverage.out
/tmp/seaweedfs-fuse-tests/coverage.html
/tmp/seaweedfs-fuse-tests/*.log
retention-days: 7
- name: Test Summary
if: always()
run: |
echo "## 🚀 FUSE Integration Test Summary" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Framework Status" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Framework Design**: Complete and validated" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Working Tests**: Core framework demonstration functional" >> $GITHUB_STEP_SUMMARY
echo "- ⚠️ **Full Framework**: Available but requires Go module resolution" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **CI/CD Integration**: Automated testing pipeline established" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Test Capabilities" >> $GITHUB_STEP_SUMMARY
echo "- 📁 **File Operations**: Create, read, write, delete, permissions" >> $GITHUB_STEP_SUMMARY
echo "- 📂 **Directory Operations**: Create, list, delete, nested structures" >> $GITHUB_STEP_SUMMARY
echo "- 📊 **Large Files**: Multi-megabyte file handling" >> $GITHUB_STEP_SUMMARY
echo "- 🔄 **Concurrent Operations**: Multi-threaded stress testing" >> $GITHUB_STEP_SUMMARY
echo "- ⚠️ **Error Scenarios**: Comprehensive error handling validation" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Comparison with Current Tests" >> $GITHUB_STEP_SUMMARY
echo "| Aspect | Current (FIO) | This Framework |" >> $GITHUB_STEP_SUMMARY
echo "|--------|---------------|----------------|" >> $GITHUB_STEP_SUMMARY
echo "| **Scope** | Performance only | Functional + Performance |" >> $GITHUB_STEP_SUMMARY
echo "| **Operations** | Read/Write only | All FUSE operations |" >> $GITHUB_STEP_SUMMARY
echo "| **Concurrency** | Single-threaded | Multi-threaded stress tests |" >> $GITHUB_STEP_SUMMARY
echo "| **Automation** | Manual setup | Fully automated |" >> $GITHUB_STEP_SUMMARY
echo "| **Validation** | Speed metrics | Correctness + Performance |" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Current Working Tests" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Framework Structure**: Package and module verification" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Configuration Management**: Test config validation" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **File Operations Demo**: Basic file create/read/write simulation" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Large File Handling**: 1MB+ file processing demonstration" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Concurrency Simulation**: Multi-file operation testing" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Next Steps" >> $GITHUB_STEP_SUMMARY
echo "1. **Module Resolution**: Fix Go package conflicts for full framework" >> $GITHUB_STEP_SUMMARY
echo "2. **SeaweedFS Integration**: Connect with real cluster for end-to-end testing" >> $GITHUB_STEP_SUMMARY
echo "3. **Performance Benchmarks**: Add performance regression testing" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "📈 **Total Framework Size**: ~1,500 lines of comprehensive testing infrastructure" >> $GITHUB_STEP_SUMMARY
+13 -37
View File
@@ -15,50 +15,26 @@ permissions:
jobs:
vet:
name: Go Vet
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Get dependencies
run: |
cd weed; go get -v -t -d ./...
- name: Go Vet (excluding protobuf lock copying)
run: |
cd weed
# Run go vet and filter out known protobuf MessageState lock copying warnings
# These are expected in generated protobuf code with embedded sync.Mutex and are safe in practice
go vet -v ./... 2>&1 | grep -v "MessageState contains sync.Mutex" | grep -v "IdentityAccessManagement contains sync.RWMutex" | tee vet-output.txt
# Fail only if there are actual vet errors (not counting the filtered lock warnings)
if grep -q "vet:" vet-output.txt; then exit 1; fi
build:
name: Build
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
- name: Set up Go 1.x
uses: actions/setup-go@4dc6199c7b1a012772edbd06daecab0f50c9053c # v2
with:
go-version-file: 'go.mod'
go-version: ^1.13
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3 # v2
- name: Get dependencies
run: |
cd weed; go get -v -t -d ./...
- name: Build
run: cd weed; go build -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v .
test:
name: Test
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Test
run: cd weed; go test -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v ./...
+23
View File
@@ -0,0 +1,23 @@
name: "helm: publish charts"
on:
push:
tags:
- '*'
permissions:
contents: write
pages: write
jobs:
release:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3
- name: Publish Helm charts
uses: stefanprodan/helm-gh-pages@v1.7.0
with:
token: ${{ secrets.GITHUB_TOKEN }}
charts_dir: k8s/charts
target_dir: helm
branch: gh-pages
helm_version: "3.18.4"
+4 -179
View File
@@ -16,18 +16,18 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
uses: actions/checkout@1af3b93b6815bc44a9784bd300feb67ff0d1eeb3
with:
fetch-depth: 0
- name: Set up Helm
uses: azure/setup-helm@v5
uses: azure/setup-helm@v4
with:
version: v3.18.4
- uses: actions/setup-python@v6
with:
python-version: '3.10'
python-version: '3.9'
check-latest: true
- name: Set up chart-testing
@@ -44,183 +44,8 @@ jobs:
- name: Run chart-testing (lint)
run: ct lint --target-branch ${{ github.event.repository.default_branch }} --all --validate-maintainers=false --chart-dirs k8s/charts
- name: Verify template rendering
run: |
set -e
CHART_DIR="k8s/charts/seaweedfs"
echo "=== Testing default configuration ==="
helm template test $CHART_DIR > /tmp/default.yaml
echo "✓ Default configuration renders successfully"
echo "=== Testing with S3 enabled ==="
helm template test $CHART_DIR --set s3.enabled=true > /tmp/s3.yaml
grep -q "kind: Deployment" /tmp/s3.yaml && grep -q "seaweedfs-s3" /tmp/s3.yaml
echo "✓ S3 deployment renders correctly"
echo "=== Testing with all-in-one mode ==="
helm template test $CHART_DIR --set allInOne.enabled=true > /tmp/allinone.yaml
grep -q "seaweedfs-all-in-one" /tmp/allinone.yaml
echo "✓ All-in-one deployment renders correctly"
echo "=== Testing with security enabled ==="
helm template test $CHART_DIR --set global.seaweedfs.enableSecurity=true > /tmp/security.yaml
grep -q "security-config" /tmp/security.yaml
echo "✓ Security configuration renders correctly"
echo "=== Testing with monitoring enabled ==="
helm template test $CHART_DIR \
--set global.seaweedfs.monitoring.enabled=true \
--set global.seaweedfs.monitoring.gatewayHost=prometheus \
--set global.seaweedfs.monitoring.gatewayPort=9091 > /tmp/monitoring.yaml
echo "✓ Monitoring configuration renders correctly"
echo "=== Testing with PVC storage ==="
helm template test $CHART_DIR \
--set master.data.type=persistentVolumeClaim \
--set master.data.size=10Gi \
--set master.data.storageClass=standard > /tmp/pvc.yaml
grep -q "PersistentVolumeClaim" /tmp/pvc.yaml
echo "✓ PVC configuration renders correctly"
echo "=== Testing with custom replicas ==="
helm template test $CHART_DIR \
--set master.replicas=3 \
--set filer.replicas=2 \
--set volume.replicas=3 > /tmp/replicas.yaml
echo "✓ Custom replicas configuration renders correctly"
echo "=== Testing filer with S3 gateway ==="
helm template test $CHART_DIR \
--set filer.s3.enabled=true \
--set filer.s3.enableAuth=true > /tmp/filer-s3.yaml
echo "✓ Filer S3 gateway renders correctly"
echo "=== Testing SFTP enabled ==="
helm template test $CHART_DIR --set sftp.enabled=true > /tmp/sftp.yaml
grep -q "seaweedfs-sftp" /tmp/sftp.yaml
echo "✓ SFTP deployment renders correctly"
echo "=== Testing ingress configurations ==="
helm template test $CHART_DIR \
--set master.ingress.enabled=true \
--set filer.ingress.enabled=true \
--set s3.enabled=true \
--set s3.ingress.enabled=true > /tmp/ingress.yaml
grep -q "kind: Ingress" /tmp/ingress.yaml
echo "✓ Ingress configurations render correctly"
echo "=== Testing COSI driver ==="
helm template test $CHART_DIR --set cosi.enabled=true > /tmp/cosi.yaml
grep -q "seaweedfs-cosi" /tmp/cosi.yaml
echo "✓ COSI driver renders correctly"
echo ""
echo "=== Testing long release name: service names match DNS references ==="
# Use a release name that, combined with chart name "seaweedfs", exceeds 63 chars.
# fullname = "my-very-long-release-name-that-will-cause-truncation-seaweedfs" (65 chars before trunc)
LONG_RELEASE="my-very-long-release-name-that-will-cause-truncation"
# --- Normal mode: master + filer-client services vs helper-produced addresses ---
helm template "$LONG_RELEASE" $CHART_DIR \
--set s3.enabled=true \
--set global.seaweedfs.createBuckets[0].name=test > /tmp/longname.yaml
# Extract Service names from metadata
MASTER_SVC=$(awk '/kind: Service/{found=1} found && /^ *name:/{print $2; found=0}' /tmp/longname.yaml \
| grep -- '-master$')
FILER_CLIENT_SVC=$(awk '/kind: Service/{found=1} found && /^ *name:/{print $2; found=0}' /tmp/longname.yaml \
| grep -- '-filer-client$')
# Extract the hostname from WEED_CLUSTER_SW_MASTER in post-install-bucket-hook
MASTER_ADDR=$(grep 'WEED_CLUSTER_SW_MASTER' -A1 /tmp/longname.yaml \
| grep 'value:' | head -1 | sed 's/.*value: *"\{0,1\}\([^":]*\).*/\1/')
FILER_ADDR=$(grep 'WEED_CLUSTER_SW_FILER' -A1 /tmp/longname.yaml \
| grep 'value:' | head -1 | sed 's/.*value: *"\{0,1\}\([^":]*\).*/\1/')
# Extract the hostname from S3 deployment -filer= argument
S3_FILER_HOST=$(grep '\-filer=' /tmp/longname.yaml \
| head -1 | sed 's/.*-filer=\([^:]*\).*/\1/')
# The address helpers produce "<svc>.<namespace>:<port>"; extract just the svc name
MASTER_ADDR_SVC=$(echo "$MASTER_ADDR" | cut -d. -f1)
FILER_ADDR_SVC=$(echo "$FILER_ADDR" | cut -d. -f1)
S3_FILER_SVC=$(echo "$S3_FILER_HOST" | cut -d. -f1)
echo " master Service.name: $MASTER_SVC"
echo " cluster.masterAddress svc: $MASTER_ADDR_SVC"
echo " filer-client Service.name: $FILER_CLIENT_SVC"
echo " cluster.filerAddress svc: $FILER_ADDR_SVC"
echo " S3 -filer= svc: $S3_FILER_SVC"
[ "$MASTER_SVC" = "$MASTER_ADDR_SVC" ] || { echo "FAIL: master service name mismatch"; exit 1; }
[ "$FILER_CLIENT_SVC" = "$FILER_ADDR_SVC" ] || { echo "FAIL: filer-client service name mismatch"; exit 1; }
[ "$FILER_CLIENT_SVC" = "$S3_FILER_SVC" ] || { echo "FAIL: S3 -filer= does not match filer-client service"; exit 1; }
echo "✓ Normal mode: service names match DNS references with long release name"
# --- All-in-one mode: all-in-one service vs both helper addresses ---
helm template "$LONG_RELEASE" $CHART_DIR \
--set allInOne.enabled=true \
--set global.seaweedfs.createBuckets[0].name=test > /tmp/longname-aio.yaml
AIO_SVC=$(awk '/kind: Service/{found=1} found && /^ *name:/{print $2; found=0}' /tmp/longname-aio.yaml \
| grep -- '-all-in-one$')
AIO_MASTER_ADDR_SVC=$(grep 'WEED_CLUSTER_SW_MASTER' -A1 /tmp/longname-aio.yaml \
| grep 'value:' | head -1 | sed 's/.*value: *"\{0,1\}\([^":]*\).*/\1/' | cut -d. -f1)
AIO_FILER_ADDR_SVC=$(grep 'WEED_CLUSTER_SW_FILER' -A1 /tmp/longname-aio.yaml \
| grep 'value:' | head -1 | sed 's/.*value: *"\{0,1\}\([^":]*\).*/\1/' | cut -d. -f1)
echo " all-in-one Service.name: $AIO_SVC"
echo " cluster.masterAddress svc: $AIO_MASTER_ADDR_SVC"
echo " cluster.filerAddress svc: $AIO_FILER_ADDR_SVC"
[ "$AIO_SVC" = "$AIO_MASTER_ADDR_SVC" ] || { echo "FAIL: all-in-one master address mismatch"; exit 1; }
[ "$AIO_SVC" = "$AIO_FILER_ADDR_SVC" ] || { echo "FAIL: all-in-one filer address mismatch"; exit 1; }
echo "✓ All-in-one mode: service names match DNS references with long release name"
echo ""
echo "=== Testing security+S3: no blank lines in shell command blocks ==="
# Render the three manifests that include seaweedfs.s3.tlsArgs:
# filer-statefulset, s3-deployment, all-in-one-deployment
helm template test $CHART_DIR \
--set global.seaweedfs.enableSecurity=true \
--set filer.s3.enabled=true \
--set s3.enabled=true > /tmp/security-s3.yaml
helm template test $CHART_DIR \
--set global.seaweedfs.enableSecurity=true \
--set allInOne.enabled=true \
--set allInOne.s3.enabled=true > /tmp/security-aio.yaml
pip install pyyaml -q
python3 - /tmp/security-s3.yaml /tmp/security-aio.yaml <<'PYEOF'
import yaml, sys
errors = []
for path in sys.argv[1:]:
with open(path) as f:
docs = list(yaml.safe_load_all(f))
for doc in docs:
if not doc or doc.get("kind") not in ("Deployment", "StatefulSet"):
continue
name = doc["metadata"]["name"]
for c in doc["spec"]["template"]["spec"].get("containers", []):
cmd = c.get("command", [])
if len(cmd) >= 3 and cmd[0] == "/bin/sh" and cmd[1] == "-ec":
script = cmd[2]
for i, line in enumerate(script.splitlines(), 1):
if line.strip() == "":
errors.append(f"{path}: {name}/{c['name']} has blank line at script line {i}")
if errors:
for e in errors:
print(f"FAIL: {e}", file=sys.stderr)
print("Rendered with: global.seaweedfs.enableSecurity=true, filer.s3.enabled=true, s3.enabled=true, allInOne.enabled=true", file=sys.stderr)
sys.exit(1)
print("✓ No blank lines in security+S3 command blocks")
PYEOF
echo "✅ All template rendering tests passed!"
- name: Create kind cluster
uses: helm/kind-action@v1.14.0
uses: helm/kind-action@v1.13.0
- name: Run chart-testing (install)
run: ct install --target-branch ${{ github.event.repository.default_branch }} --all --chart-dirs k8s/charts
-38
View File
@@ -1,38 +0,0 @@
name: "helm: manual release"
on:
workflow_dispatch:
permissions:
contents: write
pages: write
packages: write
jobs:
helm-release:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v6
with:
fetch-depth: 0
- name: Publish Helm charts to github pages
uses: stefanprodan/helm-gh-pages@v1.7.0
with:
token: ${{ secrets.GITHUB_TOKEN }}
charts_dir: k8s/charts
target_dir: helm
branch: gh-pages
helm_version: "3.18.4"
- name: Publish Helm charts to github container registry (ghcr.io)
uses: bitdeps/helm-oci-charts-releaser@v0.1.5
with:
charts_dir: k8s/charts
github_token: ${{ secrets.GITHUB_TOKEN }}
oci_registry: ghcr.io/${{ github.repository_owner }}
oci_username: github-actions
oci_password: ${{ secrets.GITHUB_TOKEN }}
skip_dependencies: true
skip_helm_install: true
skip_gh_release: true
@@ -53,7 +53,6 @@ jobs:
mkdir -p "$WEED_DATA_DIR"
# Start SeaweedFS with optimized settings for CI
# Include S3 API for s3copier integration tests
weed server -dir="$WEED_DATA_DIR" \
-master.raftHashicorp \
-master.electionTimeout=1s \
@@ -62,9 +61,6 @@ jobs:
-volume.preStopSeconds=1 \
-master.peers=none \
-filer -filer.maxMB=64 \
-s3 -s3.port=8333 \
-s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" \
-s3.allowDeleteBucketNotEmpty=true \
-master.port=9333 \
-volume.port=8080 \
-filer.port=8888 \
@@ -109,16 +105,6 @@ jobs:
sleep 2
done
# Wait for S3 API
for i in {1..30}; do
if curl -s http://localhost:8333/healthz > /dev/null 2>&1; then
echo "✓ S3 API is ready"
break
fi
echo "Waiting for S3 API... ($i/30)"
sleep 2
done
echo "✓ All SeaweedFS components are ready!"
# Display cluster status
@@ -147,20 +133,6 @@ jobs:
run: |
mvn test -Dtest=SeaweedFileSystemConfigTest -Dmaven.javadoc.skip=true -Dgpg.skip=true
- name: Run S3 ETag Validation Tests (Issue #7768)
working-directory: other/java/s3copier
env:
S3_ENDPOINT: http://127.0.0.1:8333
S3_ACCESS_KEY: some_access_key1
S3_SECRET_KEY: some_secret_key1
run: |
echo "Running S3 ETag validation tests against $S3_ENDPOINT"
mvn test -Dtest=ETagValidationTest \
-DS3_ENDPOINT=$S3_ENDPOINT \
-DS3_ACCESS_KEY=$S3_ACCESS_KEY \
-DS3_SECRET_KEY=$S3_SECRET_KEY \
-Dmaven.javadoc.skip=true -Dgpg.skip=true
- name: Display logs on failure
if: failure()
run: |
+1 -1
View File
@@ -49,7 +49,7 @@ jobs:
- name: Upload Test Reports
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: test-reports-java-${{ matrix.java }}
path: |
+2 -2
View File
@@ -26,14 +26,14 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
cache-dependency-path: |
**/go.sum
id: go
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
- name: Install dependencies
run: |
+7 -14
View File
@@ -37,7 +37,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
id: go
- name: Check out code
@@ -52,7 +52,6 @@ jobs:
run: |
cd test/kafka
go mod download
go mod tidy
- name: Run Kafka Gateway Unit Tests
run: |
@@ -82,7 +81,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
id: go
- name: Check out code
@@ -97,7 +96,6 @@ jobs:
run: |
cd test/kafka
go mod download
go mod tidy
- name: Run Integration Tests
run: |
@@ -132,7 +130,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
cache-dependency-path: |
**/go.sum
@@ -156,7 +154,6 @@ jobs:
cd test/kafka
# Use go mod download with timeout to prevent hanging
timeout 90s go mod download || echo "Warning: Dependency download timed out, continuing with cached modules"
go mod tidy
- name: Build and start SeaweedFS MQ
run: |
@@ -311,7 +308,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
cache-dependency-path: |
**/go.sum
@@ -335,7 +332,6 @@ jobs:
cd test/kafka
# Use go mod download with timeout to prevent hanging
timeout 90s go mod download || echo "Warning: Dependency download timed out, continuing with cached modules"
go mod tidy
- name: Build and start SeaweedFS MQ
run: |
@@ -473,7 +469,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
cache-dependency-path: |
**/go.sum
@@ -496,7 +492,6 @@ jobs:
run: |
cd test/kafka
timeout 90s go mod download || echo "Warning: Dependency download timed out, continuing with cached modules"
go mod tidy
- name: Build and start SeaweedFS MQ
run: |
@@ -631,7 +626,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
cache-dependency-path: |
**/go.sum
@@ -654,7 +649,6 @@ jobs:
run: |
cd test/kafka
timeout 90s go mod download || echo "Warning: Dependency download timed out, continuing with cached modules"
go mod tidy
- name: Build and start SeaweedFS MQ
run: |
@@ -789,7 +783,7 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
id: go
- name: Check out code
@@ -809,7 +803,6 @@ jobs:
run: |
cd test/kafka
go mod download
go mod tidy
- name: Run Protocol Tests
run: |
-140
View File
@@ -1,140 +0,0 @@
name: "KMS Tests"
on:
pull_request:
paths:
- 'weed/kms/**'
- 'weed/s3api/s3_sse_*.go'
- 'weed/s3api/s3api_object_handlers.go'
- 'weed/s3api/s3api_object_handlers_put.go'
- 'test/kms/**'
- '.github/workflows/kms-tests.yml'
push:
branches: [ master, main ]
paths:
- 'weed/kms/**'
- 'weed/s3api/s3_sse_*.go'
- 'weed/s3api/s3api_object_handlers.go'
- 'weed/s3api/s3api_object_handlers_put.go'
- 'test/kms/**'
concurrency:
group: ${{ github.head_ref || github.ref }}-kms-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
kms-provider-tests:
name: KMS Provider Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run KMS provider integration tests
timeout-minutes: 15
working-directory: test/kms
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
docker --version
make test-provider-ci
- name: Show OpenBao logs on failure
if: failure()
run: |
echo "=== OpenBao Container Logs ==="
docker logs openbao-ci 2>&1 | tail -50 || echo "No OpenBao container found"
echo "=== Setup Logs ==="
cat /tmp/openbao-ci-setup.log 2>/dev/null || echo "No setup log found"
- name: Cleanup
if: always()
working-directory: test/kms
run: |
make stop-openbao-ci || true
s3-kms-e2e-tests:
name: S3 KMS End-to-End Tests
runs-on: ubuntu-22.04
timeout-minutes: 25
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 KMS end-to-end tests
timeout-minutes: 20
working-directory: test/kms
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
docker --version
aws --version
make test-s3-kms-ci
- name: Show logs on failure
if: failure()
working-directory: test/kms
run: |
echo "=== OpenBao Container Logs ==="
cat /tmp/openbao-ci-container.log 2>/dev/null || docker logs openbao-ci 2>&1 | tail -50 || echo "No OpenBao logs found"
echo "=== SeaweedFS Server Logs ==="
tail -100 /tmp/seaweedfs-kms-mini.log 2>/dev/null || echo "No server log found"
echo "=== Setup Logs ==="
cat /tmp/weed-kms-ci-setup.log 2>/dev/null || echo "No weed setup log"
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-kms-e2e-logs
path: |
/tmp/seaweedfs-kms-mini.log
/tmp/openbao-ci-container.log
/tmp/weed-kms-ci-setup.log
retention-days: 3
- name: Cleanup
if: always()
working-directory: test/kms
run: |
make stop-seaweedfs-ci || true
make stop-openbao-ci || true
make clean-ci || true
@@ -1,91 +0,0 @@
name: "Metadata Subscribe Integration Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/filer/**'
- 'weed/pb/filer_pb/**'
- 'weed/util/log_buffer/**'
- 'weed/server/filer_grpc_server_sub_meta.go'
- 'weed/command/filer_backup.go'
- 'test/metadata_subscribe/**'
- '.github/workflows/metadata-subscribe-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/filer/**'
- 'weed/pb/filer_pb/**'
- 'weed/util/log_buffer/**'
- 'weed/server/filer_grpc_server_sub_meta.go'
- 'weed/command/filer_backup.go'
- 'test/metadata_subscribe/**'
- '.github/workflows/metadata-subscribe-tests.yml'
concurrency:
group: ${{ github.head_ref }}/metadata-subscribe-tests
cancel-in-progress: true
permissions:
contents: read
env:
TEST_TIMEOUT: '10m'
jobs:
metadata-subscribe-integration:
name: Metadata Subscribe Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Build SeaweedFS
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
- name: Run Metadata Subscribe Integration Tests
run: |
cd test/metadata_subscribe
echo "Running Metadata Subscribe integration tests..."
echo "============================================"
# Run tests with verbose output
go test -v -timeout=${{ env.TEST_TIMEOUT }} ./...
echo "============================================"
echo "Metadata Subscribe integration tests completed"
- name: Archive logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: metadata-subscribe-test-logs
path: |
/tmp/seaweedfs_*
retention-days: 7
- name: Test Summary
if: always()
run: |
echo "## Metadata Subscribe Integration Test Summary" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Test Coverage" >> $GITHUB_STEP_SUMMARY
echo "- **Basic Subscription**: Subscribe to metadata changes and receive events" >> $GITHUB_STEP_SUMMARY
echo "- **Single-Filer No Stall**: Regression test for issue #4977" >> $GITHUB_STEP_SUMMARY
echo "- **Resume from Disk**: Verify subscription can resume from persisted logs" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Related Issues" >> $GITHUB_STEP_SUMMARY
echo "- [#4977](https://github.com/seaweedfs/seaweedfs/issues/4977): filer.backup synchronisation stall" >> $GITHUB_STEP_SUMMARY
-39
View File
@@ -1,39 +0,0 @@
name: "Plugin Worker Integration Tests"
on:
push:
branches: [ master ]
pull_request:
branches: [ master ]
permissions:
contents: read
jobs:
plugin-worker:
name: "Plugin Worker: ${{ matrix.worker }}"
runs-on: ubuntu-22.04
timeout-minutes: 10
strategy:
fail-fast: false
matrix:
include:
- worker: erasure_coding
path: test/plugin_workers/erasure_coding
- worker: vacuum
path: test/plugin_workers/vacuum
- worker: volume_balance
path: test/plugin_workers/volume_balance
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.26
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Run plugin worker tests
run: go test -v ./${{ matrix.path }}
+4 -4
View File
@@ -25,17 +25,17 @@ jobs:
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
id: go
- name: Check out code
uses: actions/checkout@v6
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
uses: docker/setup-buildx-action@v3
- name: Cache Docker layers
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-postgres-${{ github.sha }}
@@ -62,7 +62,7 @@ jobs:
- name: Archive logs
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: postgres-logs
path: test/postgres/postgres-output.log
@@ -1,242 +0,0 @@
name: "Rust Volume Server Tests"
on:
pull_request:
branches: [ master ]
paths:
- 'seaweed-volume/**'
- 'test/volume_server/**'
- 'weed/pb/volume_server.proto'
- 'weed/pb/volume_server_pb/**'
- '.github/workflows/rust-volume-server-tests.yml'
push:
branches: [ master, main ]
paths:
- 'seaweed-volume/**'
- 'test/volume_server/**'
- 'weed/pb/volume_server.proto'
- 'weed/pb/volume_server_pb/**'
- '.github/workflows/rust-volume-server-tests.yml'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
cancel-in-progress: true
permissions:
contents: read
jobs:
rust-unit-tests:
name: Rust Unit Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Install protobuf compiler
run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-
- name: Build Rust volume server
run: cd seaweed-volume && cargo build --release
- name: Run Rust unit tests
run: cd seaweed-volume && cargo test
rust-integration-tests:
name: Rust Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Install protobuf compiler
run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-
- name: Build Go weed binary
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
- name: Build Rust volume binary
run: cd seaweed-volume && cargo build --release
- name: Run integration tests
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
RUST_VOLUME_BINARY: ${{ github.workspace }}/seaweed-volume/target/release/weed-volume
run: |
echo "Running Rust volume server integration tests..."
go test -v -count=1 -timeout=15m ./test/volume_server/rust/...
- name: Collect logs on failure
if: failure()
run: |
mkdir -p /tmp/rust-volume-server-it-logs
find /tmp -maxdepth 1 -type d -name "seaweedfs_volume_server_it_*" -print -exec cp -r {} /tmp/rust-volume-server-it-logs/ \; || true
- name: Archive logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: rust-volume-server-integration-test-logs
path: /tmp/rust-volume-server-it-logs/
if-no-files-found: warn
retention-days: 7
- name: Test summary
if: always()
run: |
echo "## Rust Volume Server Integration Test Summary" >> "$GITHUB_STEP_SUMMARY"
echo "- Suite: test/volume_server/rust" >> "$GITHUB_STEP_SUMMARY"
echo "- Command: go test -v -count=1 -timeout=15m ./test/volume_server/rust/..." >> "$GITHUB_STEP_SUMMARY"
rust-volume-go-tests:
name: Go Tests with Rust Volume (${{ matrix.test-type }} - Shard ${{ matrix.shard }})
runs-on: ubuntu-22.04
timeout-minutes: 45
strategy:
fail-fast: false
matrix:
test-type: [grpc, http]
shard: [1, 2, 3]
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Install protobuf compiler
run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-
- name: Build Go weed binary
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
- name: Build Rust volume binary
run: cd seaweed-volume && cargo build --release
- name: Run volume server integration tests with Rust volume
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
RUST_VOLUME_BINARY: ${{ github.workspace }}/seaweed-volume/target/release/weed-volume
VOLUME_SERVER_IMPL: rust
run: |
if [ "${{ matrix.test-type }}" == "grpc" ]; then
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-H]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[I-S]"
else
TEST_PATTERN="^Test[T-Z]"
fi
else
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-G]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[H-R]"
else
TEST_PATTERN="^Test[S-Z]"
fi
fi
echo "Running Go volume server tests with Rust volume for ${{ matrix.test-type }} (Shard ${{ matrix.shard }}, pattern: ${TEST_PATTERN})..."
go test -v -count=1 -tags 5BytesOffset -timeout=30m ./test/volume_server/${{ matrix.test-type }}/... -run "${TEST_PATTERN}"
- name: Collect logs on failure
if: failure()
run: |
mkdir -p /tmp/rust-volume-go-test-logs
find /tmp -maxdepth 1 -type d -name "seaweedfs_volume_server_it_*" -print -exec cp -r {} /tmp/rust-volume-go-test-logs/ \; || true
- name: Archive logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: rust-volume-go-test-logs-${{ matrix.test-type }}-shard${{ matrix.shard }}
path: /tmp/rust-volume-go-test-logs/
if-no-files-found: warn
retention-days: 7
- name: Test summary
if: always()
run: |
if [ "${{ matrix.test-type }}" == "grpc" ]; then
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-H]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[I-S]"
else
TEST_PATTERN="^Test[T-Z]"
fi
else
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-G]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[H-R]"
else
TEST_PATTERN="^Test[S-Z]"
fi
fi
echo "## Rust Volume - Go Test Summary (${{ matrix.test-type }} - Shard ${{ matrix.shard }})" >> "$GITHUB_STEP_SUMMARY"
echo "- Suite: test/volume_server/${{ matrix.test-type }} (Pattern: ${TEST_PATTERN})" >> "$GITHUB_STEP_SUMMARY"
echo "- Volume server: Rust (VOLUME_SERVER_IMPL=rust)" >> "$GITHUB_STEP_SUMMARY"
-165
View File
@@ -1,165 +0,0 @@
name: "rust: build dev volume server binaries"
on:
push:
branches: [ master ]
paths:
- 'seaweed-volume/**'
- '.github/workflows/rust_binaries_dev.yml'
permissions:
contents: read
jobs:
cleanup:
permissions:
contents: write
runs-on: ubuntu-latest
steps:
- name: Delete old Rust volume dev assets
uses: mknejp/delete-release-assets@v1
with:
token: ${{ github.token }}
tag: dev
fail-if-no-assets: false
assets: |
weed-volume-*
build-rust-volume-dev-linux:
permissions:
contents: write
needs: cleanup
runs-on: ubuntu-22.04
strategy:
matrix:
include:
- target: x86_64-unknown-linux-gnu
asset_suffix: linux-amd64
steps:
- uses: actions/checkout@v6
- name: Install protobuf compiler
run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-dev-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-dev-${{ matrix.target }}-
- name: Set BUILD_TIME
run: echo BUILD_TIME=$(date -u +%Y%m%d-%H%M) >> "$GITHUB_ENV"
- name: Build Rust volume server (large disk)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: cd seaweed-volume && cargo build --release
- name: Package large disk binary
run: |
cp seaweed-volume/target/release/weed-volume weed-volume-large-disk
tar czf "weed-volume-large-disk-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz" weed-volume-large-disk
rm weed-volume-large-disk
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: cd seaweed-volume && cargo build --release --no-default-features
- name: Package normal binary
run: |
cp seaweed-volume/target/release/weed-volume weed-volume-normal
tar czf "weed-volume-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz" weed-volume-normal
rm weed-volume-normal
- name: Upload dev release assets
uses: softprops/action-gh-release@v2
with:
tag_name: dev
prerelease: true
files: |
weed-volume-large-disk-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz
weed-volume-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
build-rust-volume-dev-darwin:
permissions:
contents: write
needs: build-rust-volume-dev-linux
runs-on: macos-latest
strategy:
matrix:
include:
- target: aarch64-apple-darwin
asset_suffix: darwin-arm64
- target: x86_64-apple-darwin
asset_suffix: darwin-amd64
steps:
- uses: actions/checkout@v6
- name: Install protobuf compiler
run: brew install protobuf
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-dev-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-dev-${{ matrix.target }}-
- name: Set BUILD_TIME
run: echo BUILD_TIME=$(date -u +%Y%m%d-%H%M) >> "$GITHUB_ENV"
- name: Build Rust volume server (large disk)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: cd seaweed-volume && cargo build --release --target ${{ matrix.target }}
- name: Package large disk binary
run: |
cp seaweed-volume/target/${{ matrix.target }}/release/weed-volume weed-volume-large-disk
tar czf "weed-volume-large-disk-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz" weed-volume-large-disk
rm weed-volume-large-disk
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: cd seaweed-volume && cargo build --release --target ${{ matrix.target }} --no-default-features
- name: Package normal binary
run: |
cp seaweed-volume/target/${{ matrix.target }}/release/weed-volume weed-volume-normal
tar czf "weed-volume-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz" weed-volume-normal
rm weed-volume-normal
- name: Upload dev release assets
uses: softprops/action-gh-release@v2
with:
tag_name: dev
prerelease: true
files: |
weed-volume-large-disk-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz
weed-volume-${{ env.BUILD_TIME }}-${{ matrix.asset_suffix }}.tar.gz
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-253
View File
@@ -1,253 +0,0 @@
name: "rust: build versioned volume server binaries"
on:
push:
tags:
- '*'
workflow_dispatch:
permissions:
contents: read
jobs:
build-rust-volume-linux:
permissions:
contents: write
runs-on: ubuntu-22.04
strategy:
matrix:
include:
- target: x86_64-unknown-linux-gnu
asset_suffix: linux_amd64
- target: aarch64-unknown-linux-gnu
asset_suffix: linux_arm64
cross: true
steps:
- uses: actions/checkout@v6
- name: Install protobuf compiler
run: sudo apt-get update && sudo apt-get install -y protobuf-compiler
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Install cross-compilation tools
if: matrix.cross
run: |
sudo dpkg --add-architecture arm64
sudo sed -i 's/^deb /deb [arch=amd64] /' /etc/apt/sources.list
echo "deb [arch=arm64] http://ports.ubuntu.com/ jammy main restricted universe multiverse" | sudo tee /etc/apt/sources.list.d/arm64.list
echo "deb [arch=arm64] http://ports.ubuntu.com/ jammy-updates main restricted universe multiverse" | sudo tee -a /etc/apt/sources.list.d/arm64.list
sudo apt-get update
sudo apt-get install -y gcc-aarch64-linux-gnu libssl-dev:arm64
echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
echo "OPENSSL_DIR=/usr" >> "$GITHUB_ENV"
echo "OPENSSL_INCLUDE_DIR=/usr/include" >> "$GITHUB_ENV"
echo "OPENSSL_LIB_DIR=/usr/lib/aarch64-linux-gnu" >> "$GITHUB_ENV"
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-release-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-release-${{ matrix.target }}-
- name: Build Rust volume server (large disk)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }}
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features
- name: Package binaries
run: |
# Large disk (default, 5bytes feature)
cp seaweed-volume/target/${{ matrix.target }}/release/weed-volume weed-volume-large-disk
tar czf weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz weed-volume-large-disk
rm weed-volume-large-disk
# Normal volume size
cp seaweed-volume/target/${{ matrix.target }}/release/weed-volume weed-volume-normal
tar czf weed-volume_${{ matrix.asset_suffix }}.tar.gz weed-volume-normal
rm weed-volume-normal
- name: Upload release assets
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v2
with:
files: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload artifacts
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
uses: actions/upload-artifact@v4
with:
name: rust-volume-${{ matrix.asset_suffix }}
path: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz
build-rust-volume-darwin:
permissions:
contents: write
runs-on: macos-latest
strategy:
matrix:
include:
- target: x86_64-apple-darwin
asset_suffix: darwin_amd64
- target: aarch64-apple-darwin
asset_suffix: darwin_arm64
steps:
- uses: actions/checkout@v6
- name: Install protobuf compiler
run: brew install protobuf
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-release-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-release-${{ matrix.target }}-
- name: Build Rust volume server (large disk)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }}
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features
- name: Package binaries
run: |
cp seaweed-volume/target/${{ matrix.target }}/release/weed-volume weed-volume-large-disk
tar czf weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz weed-volume-large-disk
rm weed-volume-large-disk
cp seaweed-volume/target/${{ matrix.target }}/release/weed-volume weed-volume-normal
tar czf weed-volume_${{ matrix.asset_suffix }}.tar.gz weed-volume-normal
rm weed-volume-normal
- name: Upload release assets
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v2
with:
files: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload artifacts
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
uses: actions/upload-artifact@v4
with:
name: rust-volume-${{ matrix.asset_suffix }}
path: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz
build-rust-volume-windows:
permissions:
contents: write
runs-on: windows-latest
steps:
- uses: actions/checkout@v6
- name: Install protobuf compiler
run: choco install protoc -y
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v5
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-release-windows-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-release-windows-
- name: Build Rust volume server (large disk)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --no-default-features
- name: Package binaries
shell: bash
run: |
cp seaweed-volume/target/release/weed-volume.exe weed-volume-large-disk.exe
7z a weed-volume_large_disk_windows_amd64.zip weed-volume-large-disk.exe
rm weed-volume-large-disk.exe
cp seaweed-volume/target/release/weed-volume.exe weed-volume-normal.exe
7z a weed-volume_windows_amd64.zip weed-volume-normal.exe
rm weed-volume-normal.exe
- name: Upload release assets
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v2
with:
files: |
weed-volume_large_disk_windows_amd64.zip
weed-volume_windows_amd64.zip
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload artifacts
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
uses: actions/upload-artifact@v4
with:
name: rust-volume-windows_amd64
path: |
weed-volume_large_disk_windows_amd64.zip
weed-volume_windows_amd64.zip
@@ -1,72 +0,0 @@
name: "S3 Authenticated Integration Tests"
on:
pull_request:
concurrency:
group: ${{ github.head_ref }}/s3-integration-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
tests:
name: S3 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: Build SeaweedFS
run: |
cd weed
go build -o weed -buildvcs=false
- name: Run S3 Integration Tests
timeout-minutes: 15
working-directory: test/s3/normal
run: |
set -x
echo "=== Running S3 Integration Tests ==="
go test -v -timeout=60s -run TestS3Integration ./...
- name: Run S3 DeleteBucketNotEmpty Tests
timeout-minutes: 15
working-directory: test/s3/normal
run: |
set -x
echo "=== Running S3 DeleteBucketNotEmpty Tests ==="
go test -v -timeout=60s -run TestS3DeleteBucketNotEmpty ./...
- name: Run S3 Empty Directory Marker Tests
timeout-minutes: 15
working-directory: test/s3/normal
run: |
set -x
echo "=== Running S3 Empty Directory Marker Tests ==="
go test -v -timeout=180s -run TestS3ListObjectsEmptyDirectoryMarkers ./...
- name: Run IAM Integration Tests
timeout-minutes: 15
working-directory: test/s3/normal
run: |
set -x
echo "=== Running IAM Integration Tests ==="
go test -v -timeout=60s -run TestIAMOperations ./...
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: integration-test-logs
path: test/s3/normal/*.log
retention-days: 3
@@ -1,86 +0,0 @@
name: "S3 Filer Group Tests"
on:
pull_request:
concurrency:
group: ${{ github.head_ref }}/s3-filer-group-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
s3-filer-group-tests:
name: S3 Filer Group Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Filer Group Tests
timeout-minutes: 15
working-directory: test/s3/filer_group
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Filer Group Tests ==="
# Run tests with automatic server management
# The test-with-server target handles server startup/shutdown automatically
# Server is started with -filer.group=testgroup
make test-with-server || {
echo "❌ Filer group tests failed, checking logs..."
if [ -f weed-test.log ]; then
echo "=== Server logs ==="
tail -100 weed-test.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test)" || true
exit 1
}
- name: Show server logs on failure
if: failure()
working-directory: test/s3/filer_group
run: |
echo "=== Server Logs ==="
if [ -f weed-test.log ]; then
echo "Last 100 lines of server logs:"
tail -100 weed-test.log
else
echo "No server log file found"
fi
echo "=== Test Environment ==="
ps aux | grep -E "(weed|test)" || true
netstat -tlnp | grep -E "(8333|9333|8080)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-filer-group-test-logs
path: test/s3/filer_group/weed-test*.log
retention-days: 3
+9 -137
View File
@@ -76,7 +76,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-versioning-test-logs-${{ matrix.test-type }}
path: test/s3/versioning/weed-test*.log
@@ -124,7 +124,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-versioning-compatibility-logs
path: test/s3/versioning/weed-test*.log
@@ -172,7 +172,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-cors-compatibility-logs
path: test/s3/cors/weed-test*.log
@@ -239,7 +239,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-retention-test-logs-${{ matrix.test-type }}
path: test/s3/retention/weed-test*.log
@@ -306,7 +306,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-cors-test-logs-${{ matrix.test-type }}
path: test/s3/cors/weed-test*.log
@@ -355,7 +355,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-retention-worm-logs
path: test/s3/retention/weed-test*.log
@@ -365,6 +365,8 @@ jobs:
name: S3 Versioning Stress Test
runs-on: ubuntu-22.04
timeout-minutes: 35
# Only run stress tests on master branch pushes to avoid overloading PR testing
if: github.event_name == 'push' && github.ref == 'refs/heads/master'
steps:
- name: Check out code
@@ -389,9 +391,6 @@ jobs:
uname -a
free -h
# Start server for stress tests
make start-server
# Run stress tests (concurrent operations)
make test-versioning-stress || {
echo "❌ Stress test failed, checking logs..."
@@ -399,144 +398,17 @@ jobs:
echo "=== Server logs ==="
tail -200 weed-test.log
fi
make stop-server
make clean
exit 1
}
# Run pagination stress tests (>1000 versions)
echo "=== Running pagination stress tests ==="
make test-versioning-pagination-stress || {
echo "❌ Pagination stress test failed, checking logs..."
if [ -f weed-test.log ]; then
echo "=== Server logs ==="
tail -200 weed-test.log
fi
make stop-server
make clean
exit 1
}
make stop-server
make clean
- name: Upload stress test logs
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-versioning-stress-logs
path: test/s3/versioning/weed-test*.log
retention-days: 7
s3-tagging-tests:
# CI job for S3 object tagging tests
name: S3 Tagging Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Tagging Tests
timeout-minutes: 15
working-directory: test/s3/tagging
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Set environment variables for the test
export S3_ENDPOINT="http://localhost:8006"
export S3_ACCESS_KEY="0555b35654ad1656d804"
export S3_SECRET_KEY="h7GhxuBLTrlhVUyxSPUKUV8r/2EI4ngqJxD7iBdBYLhwluN30JaT3Q=="
export AWS_ACCESS_KEY_ID="$S3_ACCESS_KEY"
export AWS_SECRET_ACCESS_KEY="$S3_SECRET_KEY"
# Run the specific test that is equivalent to AWS S3 tagging behavior
make test-with-server || {
echo "❌ Test failed, checking logs..."
if [ -f weed-test.log ]; then
echo "=== Server logs ==="
tail -100 weed-test.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test)" || true
exit 1
}
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-tagging-test-logs
path: test/s3/tagging/weed-test*.log
retention-days: 3
s3-remote-cache-tests:
name: S3 Remote Cache Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Remote Cache Tests
timeout-minutes: 15
working-directory: test/s3/remote_cache
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run the remote cache integration tests
# Tests singleflight deduplication for caching remote objects
make test-with-server || {
echo "❌ Test failed, checking logs..."
if [ -f primary-weed.log ]; then
echo "=== Primary server logs ==="
tail -100 primary-weed.log
fi
if [ -f remote-weed.log ]; then
echo "=== Remote server logs ==="
tail -100 remote-weed.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test)" || true
exit 1
}
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-remote-cache-test-logs
path: |
test/s3/remote_cache/primary-weed.log
test/s3/remote_cache/remote-weed.log
retention-days: 3
# Removed SSE-C integration tests and compatibility job
+6 -15
View File
@@ -5,8 +5,6 @@ on:
paths:
- 'weed/iam/**'
- 'weed/s3api/**'
- 'weed/credential/**'
- 'weed/pb/**'
- 'test/s3/iam/**'
- '.github/workflows/s3-iam-tests.yml'
push:
@@ -14,8 +12,6 @@ on:
paths:
- 'weed/iam/**'
- 'weed/s3api/**'
- 'weed/credential/**'
- 'weed/pb/**'
- 'test/s3/iam/**'
- '.github/workflows/s3-iam-tests.yml'
@@ -69,7 +65,7 @@ jobs:
- name: Upload test results on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: iam-unit-test-results
path: |
@@ -84,7 +80,7 @@ jobs:
timeout-minutes: 25
strategy:
matrix:
test-type: ["basic", "advanced", "policy-enforcement", "group"]
test-type: ["basic", "advanced", "policy-enforcement"]
steps:
- name: Check out code
@@ -121,7 +117,7 @@ jobs:
"basic")
echo "Running basic IAM functionality tests..."
make clean setup start-services wait-for-services
go test -v -timeout 15m -run "TestS3IAMAuthentication|TestS3IAMBasicWorkflow|TestS3IAMTokenValidation|TestIAMUserManagement|TestIAMAccessKeyManagement|TestIAMPolicyManagement" ./...
go test -v -timeout 15m -run "TestS3IAMAuthentication|TestS3IAMBasicWorkflow|TestS3IAMTokenValidation" ./...
;;
"advanced")
echo "Running advanced IAM feature tests..."
@@ -133,11 +129,6 @@ jobs:
make clean setup start-services wait-for-services
go test -v -timeout 15m -run "TestS3IAMPolicyEnforcement|TestS3IAMBucketPolicy|TestS3IAMContextual" ./...
;;
"group")
echo "Running IAM group management tests..."
make clean setup start-services wait-for-services
go test -v -timeout 15m -run "TestIAMGroup" ./...
;;
*)
echo "Unknown test type: ${{ matrix.test-type }}"
exit 1
@@ -171,7 +162,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-iam-integration-logs-${{ matrix.test-type }}
path: test/s3/iam/weed-*.log
@@ -231,7 +222,7 @@ jobs:
- name: Upload distributed test logs
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-iam-distributed-logs
path: test/s3/iam/weed-*.log
@@ -283,7 +274,7 @@ jobs:
- name: Upload performance test results
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-iam-performance-results
path: |
+2 -2
View File
@@ -97,7 +97,7 @@ jobs:
# Verify service accessibility
echo "=== Verifying Service Accessibility ==="
curl -f http://localhost:8080/realms/master
curl -s http://localhost:8333/healthz
curl -s http://localhost:8333
echo "✅ SeaweedFS S3 API is responding (IAM-protected endpoint)"
# Run Keycloak-specific tests
@@ -152,7 +152,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-keycloak-test-logs
path: |
@@ -1,133 +0,0 @@
name: "S3 Mutation Regression Tests"
on:
pull_request:
paths:
- 'weed/s3api/**'
- 'test/s3/delete/**'
- 'test/s3/distributed_lock/**'
- 'test/s3/versioning/**'
- 'test/volume_server/framework/**'
- 'docker/compose/s3.json'
- '.github/workflows/s3-mutation-regression-tests.yml'
concurrency:
group: ${{ github.head_ref }}/s3-mutation-regression-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
s3-versioning-regressions:
name: S3 Versioning Regression Tests
runs-on: ubuntu-22.04
timeout-minutes: 25
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Run S3 versioning regression tests
timeout-minutes: 20
working-directory: test/s3/versioning
run: |
set -x
make test-with-server TEST_PATTERN="TestVersioningCompleteMultipartUploadIsIdempotent|TestVersioningSelfCopyMetadataReplaceCreatesNewVersion|TestVersioningSelfCopyMetadataReplaceSuspendedKeepsNullVersion|TestSuspendedDeleteCreatesDeleteMarker"
- name: Show server logs on failure
if: failure()
working-directory: test/s3/versioning
run: |
echo "=== Server Logs ==="
if [ -f weed-test.log ]; then
tail -100 weed-test.log
fi
- name: Upload versioning logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-versioning-regression-logs
path: test/s3/versioning/weed-test*.log
retention-days: 3
s3-delete-regressions:
name: S3 Delete Regression Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Run S3 delete regression tests
timeout-minutes: 15
working-directory: test/s3/delete
run: |
set -x
make test-with-server
- name: Show server logs on failure
if: failure()
working-directory: test/s3/delete
run: |
echo "=== Server Logs ==="
if [ -f weed-test.log ]; then
tail -100 weed-test.log
fi
- name: Upload delete logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-delete-regression-logs
path: test/s3/delete/weed-test*.log
retention-days: 3
s3-distributed-lock-regressions:
name: S3 Distributed Lock Regression 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'
- name: Build SeaweedFS
run: |
go build -o weed/weed -buildvcs=false ./weed
- name: Run distributed lock regressions
timeout-minutes: 25
env:
TMPDIR: ${{ github.workspace }}/test/s3/distributed_lock/tmp
S3_DISTRIBUTED_LOCK_KEEP_LOGS: "1"
WEED_BINARY: ${{ github.workspace }}/weed/weed
run: |
set -x
mkdir -p "$TMPDIR"
go test -v -count=1 -timeout=20m ./test/s3/distributed_lock
- name: Upload distributed lock logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-distributed-lock-regression-logs
path: test/s3/distributed_lock/tmp/seaweedfs_s3_distributed_lock_*
retention-days: 3
+3 -3
View File
@@ -41,7 +41,7 @@ jobs:
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
- name: Set up Python ${{ matrix.python-version }}
@@ -121,7 +121,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: test-logs-python-${{ matrix.python-version }}
path: |
@@ -148,7 +148,7 @@ jobs:
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
cache: true
- name: Run Go unit tests
-426
View File
@@ -1,426 +0,0 @@
name: "S3 Policy Integration Tests"
on:
pull_request:
paths:
- 'weed/s3api/s3_iam_middleware.go'
- 'weed/s3api/s3api_bucket_policy*.go'
- 'weed/s3api/s3_action_resolver.go'
- 'weed/s3api/policy/**'
- 'weed/iam/**'
- 'test/s3/iam/**'
- 'test/s3/policy/**'
- '.github/workflows/s3-policy-tests.yml'
push:
branches: [ master, main ]
paths:
- 'weed/s3api/s3_iam_middleware.go'
- 'weed/s3api/s3api_bucket_policy*.go'
- 'weed/s3api/s3_action_resolver.go'
- 'weed/s3api/policy/**'
- 'weed/iam/**'
- 'test/s3/iam/**'
- 'test/s3/policy/**'
- '.github/workflows/s3-policy-tests.yml'
concurrency:
group: ${{ github.head_ref }}/s3-policy-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
# Unit tests for policy components
policy-unit-tests:
name: S3 Policy Unit Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Get dependencies
run: |
go mod download
- name: Run S3 Policy Unit Tests
timeout-minutes: 10
run: |
set -x
echo "=== Running S3 Action Resolver Tests ==="
go test -v -timeout 5m ./s3api/... -run ".*ActionResolver.*"
echo "=== Running S3 Bucket Policy Engine Tests ==="
go test -v -timeout 5m ./s3api/... -run ".*BucketPolicy.*|.*PolicyEngine.*"
echo "=== Running IAM Policy Tests ==="
go test -v -timeout 5m ./iam/policy/...
- name: Upload test results on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: policy-unit-test-results
path: |
weed/testdata/
weed/**/testdata/
retention-days: 3
# S3 Policy Variables Integration Tests
s3-policy-variables-tests:
name: S3 Policy Variables Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 25
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Policy Variables Integration Tests
timeout-minutes: 20
working-directory: test/s3/iam
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 Policy Variables Integration Tests ==="
# Set WEED_BINARY to use the installed version
export WEED_BINARY=$(which weed)
export TEST_TIMEOUT=15m
# Run policy variables tests
echo "Running policy variables tests..."
# Kill any existing weed server on port 8333
if lsof -Pi :8333 -sTCP:LISTEN -t >/dev/null 2>&1 ; then
kill $(lsof -t -i:8333) 2>/dev/null || true
sleep 2
fi
# Start weed server with IAM configuration
echo "Starting weed server with IAM configuration..."
$WEED_BINARY server \
-s3 \
-s3.port=8333 \
-s3.iam.config="$(pwd)/test_iam_config.json" \
-filer \
-volume.max=0 \
-master.volumeSizeLimitMB=100 \
-s3.allowDeleteBucketNotEmpty=true \
> /tmp/weed_policy_test_server.log 2>&1 &
SERVER_PID=$!
echo "Server started with PID: $SERVER_PID"
# Wait for server to be ready
echo "Waiting for server to be ready..."
MAX_WAIT=30
COUNTER=0
while ! curl -s http://localhost:8333/status > /dev/null 2>&1; do
sleep 1
COUNTER=$((COUNTER + 1))
if [ $COUNTER -ge $MAX_WAIT ]; then
echo "Server failed to start within ${MAX_WAIT} seconds"
echo "Server log:"
cat /tmp/weed_policy_test_server.log
kill $SERVER_PID 2>/dev/null || true
exit 1
fi
done
echo "Server is ready!"
# Trap to ensure server is killed on exit
trap "kill $SERVER_PID 2>/dev/null || true" EXIT
# Run the tests
go test -v -timeout 15m -run TestS3PolicyVariables ./...
- name: Show service logs on failure
if: failure()
working-directory: test/s3/iam
run: |
echo "=== Service Logs ==="
if [ -f /tmp/weed_policy_test_server.log ]; then
echo "--- Last 100 lines of Server Log ---"
tail -100 /tmp/weed_policy_test_server.log
fi
echo ""
echo "=== Process Information ==="
ps aux | grep -E "(weed|test)" || true
netstat -tlnp | grep -E "(8333|8888|9333|8080)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-policy-variables-test-logs
path: /tmp/weed_policy_test_server.log
retention-days: 5
# S3 Policy Enforcement Integration Tests
s3-policy-enforcement-tests:
name: S3 Policy Enforcement Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
strategy:
matrix:
test-case: ["basic-policy", "contextual-policy", "advanced-policy"]
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Policy Enforcement Tests - ${{ matrix.test-case }}
timeout-minutes: 25
working-directory: test/s3/iam
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 Policy Enforcement Tests (${{ matrix.test-case }}) ==="
export WEED_BINARY=$(which weed)
export TEST_TIMEOUT=20m
# Kill any existing weed server on port 8333
if lsof -Pi :8333 -sTCP:LISTEN -t >/dev/null 2>&1 ; then
kill $(lsof -t -i:8333) 2>/dev/null || true
sleep 2
fi
# Start weed server with IAM configuration
echo "Starting weed server with IAM configuration..."
$WEED_BINARY server \
-s3 \
-s3.port=8333 \
-s3.iam.config="$(pwd)/test_iam_config.json" \
-filer \
-volume.max=0 \
-master.volumeSizeLimitMB=100 \
-s3.allowDeleteBucketNotEmpty=true \
> /tmp/weed_policy_enforcement_${{ matrix.test-case }}.log 2>&1 &
SERVER_PID=$!
echo "Server started with PID: $SERVER_PID"
# Wait for server to be ready
echo "Waiting for server to be ready..."
MAX_WAIT=30
COUNTER=0
while ! curl -s http://localhost:8333/status > /dev/null 2>&1; do
sleep 1
COUNTER=$((COUNTER + 1))
if [ $COUNTER -ge $MAX_WAIT ]; then
echo "Server failed to start within ${MAX_WAIT} seconds"
cat /tmp/weed_policy_enforcement_${{ matrix.test-case }}.log
kill $SERVER_PID 2>/dev/null || true
exit 1
fi
done
echo "Server is ready!"
# Trap to ensure server is killed on exit
trap "kill $SERVER_PID 2>/dev/null || true" EXIT
# Run tests based on test case
case "${{ matrix.test-case }}" in
"basic-policy")
echo "Running basic policy enforcement tests..."
go test -v -timeout 20m -run "TestS3IAMBucketPolicy|TestS3IAMPolicyEnforcement" ./...
;;
"contextual-policy")
echo "Running contextual policy tests..."
go test -v -timeout 20m -run "TestS3PolicyVariables|TestS3IAMContextual" ./...
;;
"advanced-policy")
echo "Running advanced policy tests..."
go test -v -timeout 20m -run "TestS3IAMMultipart|TestS3IAMPresigned" ./...
;;
*)
echo "Unknown test case: ${{ matrix.test-case }}"
exit 1
;;
esac
- name: Show service logs on failure
if: failure()
working-directory: test/s3/iam
run: |
echo "=== Service Logs ==="
if [ -f /tmp/weed_policy_enforcement_${{ matrix.test-case }}.log ]; then
echo "--- Last 100 lines of Server Log ---"
tail -100 /tmp/weed_policy_enforcement_${{ matrix.test-case }}.log
fi
echo ""
echo "=== Process Information ==="
ps aux | grep -E "(weed|test)" || true
netstat -tlnp | grep -E "(8333|8888|9333|8080)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-policy-enforcement-logs-${{ matrix.test-case }}
path: /tmp/weed_policy_enforcement_${{ matrix.test-case }}.log
retention-days: 5
# Trusted Proxy Detection Tests
trusted-proxy-tests:
name: Trusted Proxy Detection Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run Trusted Proxy Tests
timeout-minutes: 15
working-directory: test/s3/iam
run: |
set -x
echo "=== Running Trusted Proxy Detection Tests ==="
export WEED_BINARY=$(which weed)
# Kill any existing weed server on port 8333
if lsof -Pi :8333 -sTCP:LISTEN -t >/dev/null 2>&1 ; then
kill $(lsof -t -i:8333) 2>/dev/null || true
sleep 2
fi
# Start weed server
echo "Starting weed server..."
$WEED_BINARY server \
-s3 \
-s3.port=8333 \
-s3.iam.config="$(pwd)/test_iam_config.json" \
-filer \
-volume.max=0 \
-master.volumeSizeLimitMB=100 \
-s3.allowDeleteBucketNotEmpty=true \
> /tmp/weed_proxy_test.log 2>&1 &
SERVER_PID=$!
echo "Server started with PID: $SERVER_PID"
# Wait for server to be ready
echo "Waiting for server to be ready..."
MAX_WAIT=30
COUNTER=0
while ! curl -s http://localhost:8333/status > /dev/null 2>&1; do
sleep 1
COUNTER=$((COUNTER + 1))
if [ $COUNTER -ge $MAX_WAIT ]; then
echo "Server failed to start within ${MAX_WAIT} seconds"
kill $SERVER_PID 2>/dev/null || true
exit 1
fi
done
# Trap to ensure server is killed on exit
trap "kill $SERVER_PID 2>/dev/null || true" EXIT
# Run proxy tests
go test -v -timeout 10m -run "TestTrustedProxy|TestPrivateIP" ./...
- name: Show service logs on failure
if: failure()
run: |
echo "=== Service Logs ==="
if [ -f /tmp/weed_proxy_test.log ]; then
echo "--- Last 100 lines of Server Log ---"
tail -100 /tmp/weed_proxy_test.log
fi
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: trusted-proxy-test-logs
path: /tmp/weed_proxy_test.log
retention-days: 3
# S3 Policy Shell Integration Tests
s3-policy-shell-tests:
name: S3 Policy Shell Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Policy Shell Tests
timeout-minutes: 10
working-directory: test/s3/policy
run: |
set -x
echo "=== Running S3 Policy Shell Tests ==="
# Set WEED_BINARY to use the installed version (though test uses 'weed' command)
export WEED_BINARY=$(which weed)
export PATH=$PATH:$(dirname $WEED_BINARY)
go test -v -timeout 10m ./...
@@ -1,122 +0,0 @@
name: "S3 Proxy Signature Tests"
on:
push:
branches: [ master ]
pull_request:
branches: [ master ]
concurrency:
group: ${{ github.head_ref || github.ref }}/s3-proxy-signature-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
proxy-signature-tests:
name: S3 Proxy Signature Verification Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v6
- name: Set up Go 1.x
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Build SeaweedFS binary for Linux
run: |
set -x
CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -buildvcs=false -v -o test/s3/proxy_signature/weed ./weed
- name: Run S3 Proxy Signature Tests
timeout-minutes: 10
working-directory: test/s3/proxy_signature
run: |
set -x
echo "Starting Docker Compose services..."
docker compose up -d --build
# Check if containers are running
echo "Checking container status..."
docker compose ps
# Wait for services to be ready
echo "Waiting for nginx proxy to be ready..."
PROXY_READY=0
for i in $(seq 1 30); do
if curl -s http://localhost:9000/ > /dev/null 2>&1; then
echo "Proxy is ready"
PROXY_READY=1
break
fi
echo "Waiting for proxy... ($i/30)"
sleep 1
done
if [ $PROXY_READY -eq 0 ]; then
echo "ERROR: Proxy failed to become ready after 30 seconds"
echo "Docker compose logs:"
docker compose logs --no-color || true
exit 1
fi
# Wait for SeaweedFS to be ready
echo "Waiting for SeaweedFS S3 gateway to be ready via proxy..."
S3_READY=0
for i in $(seq 1 30); do
# Check logs first for startup message (weed mini says "S3 service is ready")
if docker compose logs seaweedfs 2>&1 | grep -qE "S3 (gateway|service).*(started|ready)"; then
echo "SeaweedFS S3 gateway is ready"
S3_READY=1
break
fi
# Fallback: check headers via proxy (which is already ready)
if curl -s -I http://localhost:9000/ | grep -qi "SeaweedFS"; then
echo "SeaweedFS S3 gateway is responding via proxy"
S3_READY=1
break
fi
echo "Waiting for S3 gateway... ($i/30)"
sleep 1
done
if [ $S3_READY -eq 0 ]; then
echo "ERROR: SeaweedFS S3 gateway failed to become ready after 30 seconds"
echo "Latest seaweedfs logs:"
docker compose logs --no-color --tail 20 seaweedfs || true
exit 1
fi
# Run the test script inside AWS CLI container
echo "Running test script..."
docker run --rm --network host \
--entrypoint bash \
amazon/aws-cli:latest \
-c "$(cat test.sh)"
TEST_RESULT=$?
# Cleanup
docker compose down
exit $TEST_RESULT
- name: Cleanup on failure
if: failure()
working-directory: test/s3/proxy_signature
run: |
echo "Cleaning up Docker containers..."
ls -al weed || true
ldd weed || true
echo "Docker compose logs:"
docker compose logs --no-color || true
echo "Container status before cleanup:"
docker ps -a
echo "Stopping services..."
docker compose down || true
-81
View File
@@ -1,81 +0,0 @@
name: "S3 Spark Integration Tests"
on:
pull_request:
paths:
- 'weed/s3api/**'
- 'weed/filer/**'
- 'test/s3/spark/**'
- 'test/s3tables/testutil/**'
- '.github/workflows/s3-spark-tests.yml'
workflow_dispatch:
concurrency:
group: ${{ github.head_ref }}/s3-spark-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
s3-spark-issue-repro-tests:
name: S3 Spark Issue Reproduction Tests
runs-on: ubuntu-22.04
timeout-minutes: 45
steps:
- name: Check out code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
id: go
- name: Set up Docker
uses: docker/setup-buildx-action@v4
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Pre-pull Spark image
run: docker pull apache/spark:3.5.8
- name: Run S3 Spark integration tests
working-directory: test/s3/spark
timeout-minutes: 35
run: |
set -x
set -o pipefail
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 Spark Integration Tests ==="
go test -v -timeout 30m . 2>&1 | tee test-output.log || {
echo "S3 Spark integration tests failed"
exit 1
}
- name: Show test output on failure
if: failure()
working-directory: test/s3/spark
run: |
echo "=== Test Output ==="
if [ -f test-output.log ]; then
tail -200 test-output.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test|docker|spark)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-spark-test-logs
path: test/s3/spark/test-output.log
retention-days: 3
+6 -56
View File
@@ -95,7 +95,7 @@ jobs:
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-sse-test-logs-${{ matrix.test-type }}
path: test/s3/sse/weed-test*.log
@@ -143,7 +143,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-sse-compatibility-logs
path: test/s3/sse/weed-test*.log
@@ -192,7 +192,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-sse-metadata-persistence-logs
path: test/s3/sse/weed-test*.log
@@ -241,7 +241,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-sse-copy-operations-logs
path: test/s3/sse/weed-test*.log
@@ -290,7 +290,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-sse-multipart-logs
path: test/s3/sse/weed-test*.log
@@ -340,58 +340,8 @@ jobs:
- name: Upload performance test logs
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: s3-sse-performance-logs
path: test/s3/sse/weed-test*.log
retention-days: 7
s3-volume-encryption:
name: S3 Volume Encryption Test
runs-on: ubuntu-22.04
timeout-minutes: 20
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Volume Encryption Integration Tests
timeout-minutes: 15
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run volume encryption tests with -s3.encryptVolumeData flag
echo "🚀 Running S3 volume encryption integration tests..."
make test-volume-encryption || {
echo "❌ Volume encryption tests failed, checking logs..."
if [ -f /tmp/seaweedfs-sse-mini.log ]; then
echo "=== Server logs ==="
tail -100 /tmp/seaweedfs-sse-mini.log
fi
echo "=== Process information ==="
ps aux | grep -E "(weed|test)" || true
exit 1
}
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-volume-encryption-logs
path: /tmp/seaweedfs-sse-*.log
retention-days: 3
-686
View File
@@ -1,686 +0,0 @@
name: "S3 Tables Integration Tests"
on:
pull_request:
concurrency:
group: ${{ github.head_ref }}/s3-tables-tests
cancel-in-progress: true
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: 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: Set up Docker
uses: docker/setup-buildx-action@v4
- name: Pre-pull Trino image
run: docker 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
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: Pre-pull Polaris image
run: docker 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: Set up Docker
uses: docker/setup-buildx-action@v4
- name: Pre-pull Spark image
run: docker 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: Set up Docker
uses: docker/setup-buildx-action@v4
- name: Pre-pull RisingWave image
run: |
docker pull risingwavelabs/risingwave:v2.5.0
docker 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: Set up Docker
uses: docker/setup-buildx-action@v4
- name: Pre-pull Python image
run: docker pull python:3
- 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: Set up Docker
uses: docker/setup-buildx-action@v4
- name: Pre-pull Python image
run: docker pull python:3
- name: Pre-pull LocalStack image (if needed)
run: docker pull localstack/localstack:latest || true
- 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
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"
+5 -5
View File
@@ -64,7 +64,7 @@ jobs:
-master.raftHashicorp -master.electionTimeout 1s -master.volumeSizeLimitMB=100 \
-volume.max=100 -volume.preStopSeconds=1 \
-master.port=9333 -volume.port=8080 -filer.port=8888 -s3.port=8000 -metricsPort=9324 \
-s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
-s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
pid=$!
# Wait for all SeaweedFS components to be ready
@@ -368,7 +368,7 @@ jobs:
-master.raftHashicorp -master.electionTimeout 1s -master.volumeSizeLimitMB=100 \
-volume.max=100 -volume.preStopSeconds=1 \
-master.port=9334 -volume.port=8081 -filer.port=8889 -s3.port=8001 -metricsPort=9325 \
-s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
-s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
pid=$!
# Wait for all SeaweedFS components to be ready
@@ -526,7 +526,7 @@ jobs:
-master.raftHashicorp -master.electionTimeout 1s -master.volumeSizeLimitMB=100 \
-volume.max=100 -volume.preStopSeconds=1 \
-master.port=9335 -volume.port=8082 -filer.port=8890 -s3.port=8002 -metricsPort=9326 \
-s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
-s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
pid=$!
# Wait for all SeaweedFS components to be ready
@@ -636,7 +636,7 @@ jobs:
-master.raftHashicorp -master.electionTimeout 1s -master.volumeSizeLimitMB=100 \
-volume.max=100 -volume.preStopSeconds=1 \
-master.port=9336 -volume.port=8083 -filer.port=8891 -s3.port=8003 -metricsPort=9327 \
-s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
-s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" -master.peers=none &
pid=$!
# Wait for all SeaweedFS components to be ready
@@ -817,7 +817,7 @@ jobs:
-master.raftHashicorp -master.electionTimeout 1s -master.volumeSizeLimitMB=100 \
-volume.max=100 -volume.preStopSeconds=1 \
-master.port=9337 -volume.port=8085 -filer.port=8892 -s3.port=8004 -metricsPort=9328 \
-s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" \
-s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=true -s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" \
-master.peers=none \
> /tmp/seaweedfs-sql-server.log 2>&1 &
pid=$!
-93
View File
@@ -1,93 +0,0 @@
name: "SFTP Integration Tests"
on:
push:
branches: [ master, main ]
paths:
- 'weed/sftpd/**'
- 'weed/command/sftp.go'
- 'test/sftp/**'
- '.github/workflows/sftp-tests.yml'
pull_request:
branches: [ master, main ]
paths:
- 'weed/sftpd/**'
- 'weed/command/sftp.go'
- 'test/sftp/**'
- '.github/workflows/sftp-tests.yml'
concurrency:
group: ${{ github.head_ref }}/sftp-tests
cancel-in-progress: true
permissions:
contents: read
env:
TEST_TIMEOUT: '15m'
jobs:
sftp-integration:
name: SFTP Integration Testing
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y openssh-client
- name: Build SeaweedFS
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
- name: Run SFTP Integration Tests
run: |
cd test/sftp
echo "🧪 Running SFTP integration tests..."
echo "============================================"
# Install test dependencies
go mod download
# Run all SFTP tests
go test -v -timeout=${{ env.TEST_TIMEOUT }} ./...
echo "============================================"
echo "✅ SFTP integration tests completed"
- name: Test Summary
if: always()
run: |
echo "## 🔐 SFTP Integration Test Summary" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Test Coverage" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **HomeDir Path Translation**: User home directory mapping (fixes #7470)" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **File Operations**: Upload, download, delete" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Directory Operations**: Create, list, remove" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Large File Handling**: 1MB+ file support" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Path Edge Cases**: Unicode, trailing slashes, .. paths" >> $GITHUB_STEP_SUMMARY
echo "- ✅ **Admin Access**: Root user verification" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Test Configuration" >> $GITHUB_STEP_SUMMARY
echo "| User | HomeDir | Permissions |" >> $GITHUB_STEP_SUMMARY
echo "|------|---------|-------------|" >> $GITHUB_STEP_SUMMARY
echo "| admin | / | Full access |" >> $GITHUB_STEP_SUMMARY
echo "| testuser | /sftp/testuser | Home directory only |" >> $GITHUB_STEP_SUMMARY
echo "| readonly | /public | Read-only |" >> $GITHUB_STEP_SUMMARY
@@ -34,7 +34,7 @@ jobs:
uses: actions/checkout@v6
- name: Set up JDK 11
uses: actions/setup-java@v5
uses: actions/setup-java@v4
with:
java-version: '11'
distribution: 'temurin'
@@ -43,7 +43,7 @@ jobs:
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
go-version: '1.24'
- name: Build SeaweedFS binary
run: |
@@ -125,7 +125,7 @@ jobs:
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v4
with:
name: spark-test-results
path: test/java/spark/target/surefire-reports/
@@ -133,7 +133,7 @@ jobs:
- name: Publish test report
if: always()
uses: dorny/test-reporter@v3
uses: dorny/test-reporter@v1
with:
name: Spark Test Results
path: test/java/spark/target/surefire-reports/*.xml
@@ -150,7 +150,7 @@ jobs:
- name: Cache Apache Spark
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
id: cache-spark
uses: actions/cache@v5
uses: actions/cache@v4
with:
path: spark-3.5.0-bin-hadoop3
key: spark-3.5.0-hadoop3
@@ -1,46 +0,0 @@
name: Telemetry Integration Tests
on:
push:
branches: [ master ]
paths:
- 'telemetry/**'
- 'weed/telemetry/**'
- '.github/workflows/telemetry-integration.yml'
pull_request:
branches: [ master ]
paths:
- 'telemetry/**'
- 'weed/telemetry/**'
- '.github/workflows/telemetry-integration.yml'
permissions:
contents: read
jobs:
telemetry-integration-test:
runs-on: ubuntu-latest
timeout-minutes: 5
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Build telemetry server
run: cd telemetry/server && go build -o telemetry-server .
- name: Run telemetry integration test
run: go run telemetry/test/integration.go
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: telemetry-test-logs
path: telemetry-server-test.log
retention-days: 7
@@ -18,13 +18,13 @@ defaults:
jobs:
awscli-tests:
runs-on: ubuntu-latest
timeout-minutes: 10
timeout-minutes: 5
steps:
- uses: actions/checkout@v6
- uses: actions/setup-go@v6
with:
go-version: ^1.25
go-version: ^1.24
- name: Build SeaweedFS
run: |
@@ -35,7 +35,7 @@ jobs:
set -e
mkdir -p /tmp/data
./weed -v=3 server -s3 -dir=/tmp/data -s3.config=../docker/compose/s3.json -master.peers=none > weed.log 2>&1 &
until curl -s http://localhost:8333/healthz > /dev/null; do sleep 1; done
until curl -s http://localhost:8333/ > /dev/null; do sleep 1; done
- name: Setup Caddy
run: |
@@ -54,7 +54,7 @@ jobs:
- name: Start Caddy
run: |
./caddy start
until curl -fsS --insecure https://localhost:8443/healthz > /dev/null; do sleep 1; done
until curl -fsS --insecure https://localhost:8443 > /dev/null; do sleep 1; done
- name: Create Bucket
run: |
@@ -103,7 +103,7 @@ jobs:
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v5
with:
name: seaweedfs-logs
# Note: actions don't use defaults.run.working-directory, so path is relative to workspace root
-103
View File
@@ -1,103 +0,0 @@
name: "TUS Protocol Tests"
on:
pull_request:
concurrency:
group: ${{ github.head_ref || github.ref }}/tus-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
tus-integration-tests:
name: TUS Protocol Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
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: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run TUS Integration Tests
timeout-minutes: 15
working-directory: test/tus
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting TUS Tests ==="
# Run tests with automatic server management
make test-with-server || {
echo "TUS integration tests failed, checking logs..."
if [ -f /tmp/seaweedfs-tus-filer.log ]; then
echo "=== Filer logs ==="
tail -100 /tmp/seaweedfs-tus-filer.log
fi
if [ -f /tmp/seaweedfs-tus-master.log ]; then
echo "=== Master logs ==="
tail -50 /tmp/seaweedfs-tus-master.log
fi
if [ -f /tmp/seaweedfs-tus-volume.log ]; then
echo "=== Volume logs ==="
tail -50 /tmp/seaweedfs-tus-volume.log
fi
exit 1
}
- name: Show server logs on failure
if: failure()
working-directory: test/tus
run: |
echo "=== Filer Server Logs ==="
if [ -f /tmp/seaweedfs-tus-filer.log ]; then
echo "Last 100 lines of filer logs:"
tail -100 /tmp/seaweedfs-tus-filer.log
else
echo "No filer log file found"
fi
echo "=== Master Server Logs ==="
if [ -f /tmp/seaweedfs-tus-master.log ]; then
tail -50 /tmp/seaweedfs-tus-master.log
else
echo "No master log file found"
fi
echo "=== Volume Server Logs ==="
if [ -f /tmp/seaweedfs-tus-volume.log ]; then
tail -50 /tmp/seaweedfs-tus-volume.log
else
echo "No volume log file found"
fi
echo "=== Test Environment ==="
ps aux | grep -E "(weed|test)" || true
netstat -tlnp 2>/dev/null | grep -E "(18888|19333|18080)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: tus-test-logs
path: |
/tmp/seaweedfs-tus-*.log
retention-days: 3
@@ -1,121 +0,0 @@
name: "Volume Server Integration Tests"
on:
pull_request:
branches: [ master ]
paths:
- 'test/volume_server/**'
- 'weed/server/**'
- 'weed/storage/**'
- 'weed/pb/volume_server.proto'
- 'weed/pb/volume_server_pb/**'
- '.github/workflows/volume-server-integration-tests.yml'
push:
branches: [ master, main ]
paths:
- 'test/volume_server/**'
- 'weed/server/**'
- 'weed/storage/**'
- 'weed/pb/volume_server.proto'
- 'weed/pb/volume_server_pb/**'
- '.github/workflows/volume-server-integration-tests.yml'
concurrency:
group: ${{ github.head_ref || github.ref }}/volume-server-integration-tests
cancel-in-progress: true
permissions:
contents: read
env:
TEST_TIMEOUT: '30m'
jobs:
volume-server-integration-tests:
name: Volume Server Integration Tests (${{ matrix.test-type }} - Shard ${{ matrix.shard }})
runs-on: ubuntu-22.04
timeout-minutes: 45
strategy:
fail-fast: false
matrix:
test-type: [grpc, http]
shard: [1, 2, 3]
steps:
- name: Checkout code
uses: actions/checkout@v6
- name: Set up Go
uses: actions/setup-go@v6
with:
go-version-file: 'go.mod'
- name: Build SeaweedFS binary
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
- name: Run volume server integration tests
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
run: |
if [ "${{ matrix.test-type }}" == "grpc" ]; then
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-H]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[I-S]"
else
TEST_PATTERN="^Test[T-Z]"
fi
else
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-G]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[H-R]"
else
TEST_PATTERN="^Test[S-Z]"
fi
fi
echo "Running volume server integration tests for ${{ matrix.test-type }} (Shard ${{ matrix.shard }}, pattern: ${TEST_PATTERN})..."
go test -v -count=1 -timeout=${{ env.TEST_TIMEOUT }} ./test/volume_server/${{ matrix.test-type }}/... -run "${TEST_PATTERN}"
- name: Collect logs on failure
if: failure()
run: |
mkdir -p /tmp/volume-server-it-logs
find /tmp -maxdepth 1 -type d -name "seaweedfs_volume_server_it_*" -print -exec cp -r {} /tmp/volume-server-it-logs/ \; || true
- name: Archive logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: volume-server-integration-test-logs
path: /tmp/volume-server-it-logs/
if-no-files-found: warn
retention-days: 7
- name: Test summary
if: always()
run: |
if [ "${{ matrix.test-type }}" == "grpc" ]; then
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-H]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[I-S]"
else
TEST_PATTERN="^Test[T-Z]"
fi
else
if [ "${{ matrix.shard }}" == "1" ]; then
TEST_PATTERN="^Test[A-G]"
elif [ "${{ matrix.shard }}" == "2" ]; then
TEST_PATTERN="^Test[H-R]"
else
TEST_PATTERN="^Test[S-Z]"
fi
fi
echo "## Volume Server Integration Test Summary (${{ matrix.test-type }} - Shard ${{ matrix.shard }})" >> "$GITHUB_STEP_SUMMARY"
echo "- Suite: test/volume_server/${{ matrix.test-type }} (Pattern: ${TEST_PATTERN})" >> "$GITHUB_STEP_SUMMARY"
echo "- Command: go test -v -count=1 -timeout=${{ env.TEST_TIMEOUT }} ./test/volume_server/${{ matrix.test-type }}/... -run \"${TEST_PATTERN}\"" >> "$GITHUB_STEP_SUMMARY"
-20
View File
@@ -124,23 +124,3 @@ ADVANCED_IAM_DEVELOPMENT_PLAN.md
*.log
weed-iam
test/kafka/kafka-client-loadtest/weed-linux-arm64
/test/tus/filerldb2
coverage.out
/test/s3/remote_cache/test-primary-data
/test/s3/remote_cache/test-remote-data
test/s3/remote_cache/remote-server.pid
test/s3/remote_cache/primary-server.pid
/test/erasure_coding/filerldb2
/test/s3/cors/test-mini-data
/test/s3/filer_group/test-volume-data
# ID and PID files
*.id
*.pid
test/s3/iam/.test_env
/test/erasure_coding/admin_dockertest/tmp
/test/erasure_coding/admin_dockertest/task_logs
weed_bin
telemetry/server/telemetry-server
.aider*
/seaweed-volume/docs
+242
View File
@@ -0,0 +1,242 @@
# Bucket Policy Engine Integration - Complete
## Summary
Successfully integrated the `policy_engine` package to evaluate bucket policies for **all requests** (both anonymous and authenticated). This provides comprehensive AWS S3-compatible bucket policy support.
## What Changed
### 1. **New File: `s3api_bucket_policy_engine.go`**
Created a wrapper around `policy_engine.PolicyEngine` to:
- Load bucket policies from filer entries
- Sync policies from the bucket config cache
- Evaluate policies for any request (bucket, object, action, principal)
- Return structured results (allowed, evaluated, error)
### 2. **Modified: `s3api_server.go`**
- Added `policyEngine *BucketPolicyEngine` field to `S3ApiServer` struct
- Initialized the policy engine in `NewS3ApiServerWithStore()`
- Linked `IdentityAccessManagement` back to `S3ApiServer` for policy evaluation
### 3. **Modified: `auth_credentials.go`**
- Added `s3ApiServer *S3ApiServer` field to `IdentityAccessManagement` struct
- Added `buildPrincipalARN()` helper to convert identities to AWS ARN format
- **Integrated bucket policy evaluation into the authentication flow:**
- Policies are now checked **before** IAM/identity-based permissions
- Explicit `Deny` in bucket policy blocks access immediately
- Explicit `Allow` in bucket policy grants access and **bypasses IAM checks** (enables cross-account access)
- If no policy exists, falls through to normal IAM checks
- Policy evaluation errors result in access denial (fail-close security)
### 4. **Modified: `s3api_bucket_config.go`**
- Added policy engine sync when bucket configs are loaded
- Ensures policies are loaded into the engine for evaluation
### 5. **Modified: `auth_credentials_subscribe.go`**
- Added policy engine sync when bucket metadata changes
- Keeps the policy engine up-to-date via event-driven updates
## How It Works
### Anonymous Requests
```
1. Request comes in (no credentials)
2. Check ACL-based public access → if public, allow
3. Check bucket policy for anonymous ("*") access → if allowed, allow
4. Otherwise, deny
```
### Authenticated Requests (NEW!)
```
1. Request comes in (with credentials)
2. Authenticate user → get Identity
3. Build principal ARN (e.g., "arn:aws:iam::123456:user/bob")
4. Check bucket policy:
- If DENY → reject immediately
- If ALLOW → grant access immediately (bypasses IAM checks)
- If no policy or no matching statements → continue to step 5
5. Check IAM/identity-based permissions (only if not already allowed by bucket policy)
6. Allow or deny based on identity permissions
```
## Policy Evaluation Flow
```
┌─────────────────────────────────────────────────────────┐
│ Request (GET /bucket/file) │
└───────────────────────────┬─────────────────────────────┘
│
┌───────────▼──────────┐
│ Authenticate User │
│ (or Anonymous) │
└───────────┬──────────┘
│
┌───────────▼──────────────────────────────┐
│ Build Principal ARN │
│ - Anonymous: "*" │
│ - User: "arn:aws:iam::123456:user/bob" │
└───────────┬──────────────────────────────┘
│
┌───────────▼──────────────────────────────┐
│ Evaluate Bucket Policy (PolicyEngine) │
│ - Action: "s3:GetObject" │
│ - Resource: "arn:aws:s3:::bucket/file" │
│ - Principal: (from above) │
└───────────┬──────────────────────────────┘
│
┌─────────────┼─────────────┐
│ │ │
DENY │ ALLOW │ NO POLICY
│ │ │
▼ ▼ ▼
Reject Request Grant Access Continue
│
┌───────────────────┘
│
┌────────────▼─────────────┐
│ IAM/Identity Check │
│ (identity.canDo) │
└────────────┬─────────────┘
│
┌─────────┴─────────┐
│ │
ALLOW │ DENY │
▼ ▼
Grant Access Reject Request
```
## Example Policies That Now Work
### 1. **Public Read Access** (Anonymous)
```json
{
"Version": "2012-10-17",
"Statement": [{
"Effect": "Allow",
"Principal": "*",
"Action": "s3:GetObject",
"Resource": "arn:aws:s3:::mybucket/*"
}]
}
```
- Anonymous users can read all objects
- Authenticated users are also evaluated against this policy. If they don't match an explicit `Allow` for this action, they will fall back to their own IAM permissions
### 2. **Grant Access to Specific User** (Authenticated)
```json
{
"Version": "2012-10-17",
"Statement": [{
"Effect": "Allow",
"Principal": {"AWS": "arn:aws:iam::123456789012:user/bob"},
"Action": ["s3:GetObject", "s3:PutObject"],
"Resource": "arn:aws:s3:::mybucket/shared/*"
}]
}
```
- User "bob" can read/write objects in `/shared/` prefix
- Other users cannot (unless granted by their IAM policies)
### 3. **Deny Access to Specific Path** (Both)
```json
{
"Version": "2012-10-17",
"Statement": [{
"Effect": "Deny",
"Principal": "*",
"Action": "s3:*",
"Resource": "arn:aws:s3:::mybucket/confidential/*"
}]
}
```
- **No one** can access `/confidential/` objects
- Denies override all other allows (AWS policy evaluation rules)
## Performance Characteristics
### Policy Loading
- **Cold start**: Policy loaded from filer → parsed → compiled → cached
- **Warm path**: Policy retrieved from `BucketConfigCache` (already parsed)
- **Updates**: Event-driven sync via metadata subscription (real-time)
### Policy Evaluation
- **Compiled policies**: Pre-compiled regex patterns and matchers
- **Pattern cache**: Regex patterns cached with LRU eviction (max 1000)
- **Fast path**: Common patterns (`*`, exact matches) optimized
- **Case sensitivity**: Actions case-insensitive, resources case-sensitive (AWS-compatible)
### Overhead
- **Anonymous requests**: Minimal (policy already checked, now using compiled engine)
- **Authenticated requests**: ~1-2ms added for policy evaluation (compiled patterns)
- **No policy**: Near-zero overhead (quick indeterminate check)
## Testing
All tests pass:
```bash
✅ TestBucketPolicyValidationBasics
✅ TestPrincipalMatchesAnonymous
✅ TestActionToS3Action
✅ TestResourceMatching
✅ TestMatchesPatternRegexEscaping (security tests)
✅ TestActionMatchingCaseInsensitive
✅ TestResourceMatchingCaseSensitive
✅ All policy_engine package tests (30+ tests)
```
## Security Improvements
1. **Regex Metacharacter Escaping**: Patterns like `*.json` properly match only files ending in `.json` (not `filexjson`)
2. **Case-Insensitive Actions**: S3 actions matched case-insensitively per AWS spec
3. **Case-Sensitive Resources**: Resource paths matched case-sensitively for security
4. **Pattern Cache Size Limit**: Prevents DoS attacks via unbounded cache growth
5. **Principal Validation**: Supports `[]string` for manually constructed policies
## AWS Compatibility
The implementation follows AWS S3 bucket policy evaluation rules:
1. **Explicit Deny** always wins (checked first)
2. **Explicit Allow** grants access (checked second)
3. **Default Deny** if no matching statements (implicit)
4. Bucket policies work alongside IAM policies (both are evaluated)
## Files Changed
```
Modified:
weed/s3api/auth_credentials.go (+47 lines)
weed/s3api/auth_credentials_subscribe.go (+8 lines)
weed/s3api/s3api_bucket_config.go (+8 lines)
weed/s3api/s3api_server.go (+5 lines)
New:
weed/s3api/s3api_bucket_policy_engine.go (115 lines)
```
## Migration Notes
- **Backward Compatible**: Existing setups without bucket policies work unchanged
- **No Breaking Changes**: All existing ACL and IAM-based authorization still works
- **Additive Feature**: Bucket policies are an additional layer of authorization
- **Performance**: Minimal impact on existing workloads
## Future Enhancements
Potential improvements (not implemented yet):
- [ ] Condition support (IP address, time-based, etc.) - already in policy_engine
- [ ] Cross-account policies (different AWS accounts)
- [ ] Policy validation API endpoint
- [ ] Policy simulation/testing tool
- [ ] Metrics for policy evaluations (allow/deny counts)
## Conclusion
Bucket policies now work for **all requests** in SeaweedFS S3 API:
- ✅ Anonymous requests (public access)
- ✅ Authenticated requests (user-specific policies)
- ✅ High performance (compiled policies, caching)
- ✅ AWS-compatible (follows AWS evaluation rules)
- ✅ Secure (proper escaping, case sensitivity)
The integration is complete, tested, and ready for use!
+413
View File
@@ -0,0 +1,413 @@
# SeaweedFS Task Distribution System Design
## Overview
This document describes the design of a distributed task management system for SeaweedFS that handles Erasure Coding (EC) and vacuum operations through a scalable admin server and worker process architecture.
## System Architecture
### High-Level Components
```
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Master │◄──►│ Admin Server │◄──►│ Workers │
│ │ │ │ │ │
│ - Volume Info │ │ - Task Discovery │ │ - Task Exec │
│ - Shard Status │ │ - Task Assign │ │ - Progress │
│ - Heartbeats │ │ - Progress Track │ │ - Error Report │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│ │ │
│ │ │
▼ ▼ ▼
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Volume Servers │ │ Volume Monitor │ │ Task Execution │
│ │ │ │ │ │
│ - Store Volumes │ │ - Health Check │ │ - EC Convert │
│ - EC Shards │ │ - Usage Stats │ │ - Vacuum Clean │
│ - Report Status │ │ - State Sync │ │ - Status Report │
└─────────────────┘ └──────────────────┘ └─────────────────┘
```
## 1. Admin Server Design
### 1.1 Core Responsibilities
- **Task Discovery**: Scan volumes to identify EC and vacuum candidates
- **Worker Management**: Track available workers and their capabilities
- **Task Assignment**: Match tasks to optimal workers
- **Progress Tracking**: Monitor in-progress tasks for capacity planning
- **State Reconciliation**: Sync with master server for volume state updates
### 1.2 Task Discovery Engine
```go
type TaskDiscoveryEngine struct {
masterClient MasterClient
volumeScanner VolumeScanner
taskDetectors map[TaskType]TaskDetector
scanInterval time.Duration
}
type VolumeCandidate struct {
VolumeID uint32
Server string
Collection string
TaskType TaskType
Priority TaskPriority
Reason string
DetectedAt time.Time
Parameters map[string]interface{}
}
```
**EC Detection Logic**:
- Find volumes >= 95% full and idle for > 1 hour
- Exclude volumes already in EC format
- Exclude volumes with ongoing operations
- Prioritize by collection and age
**Vacuum Detection Logic**:
- Find volumes with garbage ratio > 30%
- Exclude read-only volumes
- Exclude volumes with recent vacuum operations
- Prioritize by garbage percentage
### 1.3 Worker Registry & Management
```go
type WorkerRegistry struct {
workers map[string]*Worker
capabilities map[TaskType][]*Worker
lastHeartbeat map[string]time.Time
taskAssignment map[string]*Task
mutex sync.RWMutex
}
type Worker struct {
ID string
Address string
Capabilities []TaskType
MaxConcurrent int
CurrentLoad int
Status WorkerStatus
LastSeen time.Time
Performance WorkerMetrics
}
```
### 1.4 Task Assignment Algorithm
```go
type TaskScheduler struct {
registry *WorkerRegistry
taskQueue *PriorityQueue
inProgressTasks map[string]*InProgressTask
volumeReservations map[uint32]*VolumeReservation
}
// Worker Selection Criteria:
// 1. Has required capability (EC or Vacuum)
// 2. Available capacity (CurrentLoad < MaxConcurrent)
// 3. Best performance history for task type
// 4. Lowest current load
// 5. Geographically close to volume server (optional)
```
## 2. Worker Process Design
### 2.1 Worker Architecture
```go
type MaintenanceWorker struct {
id string
config *WorkerConfig
adminClient AdminClient
taskExecutors map[TaskType]TaskExecutor
currentTasks map[string]*RunningTask
registry *TaskRegistry
heartbeatTicker *time.Ticker
requestTicker *time.Ticker
}
```
### 2.2 Task Execution Framework
```go
type TaskExecutor interface {
Execute(ctx context.Context, task *Task) error
EstimateTime(task *Task) time.Duration
ValidateResources(task *Task) error
GetProgress() float64
Cancel() error
}
type ErasureCodingExecutor struct {
volumeClient VolumeServerClient
progress float64
cancelled bool
}
type VacuumExecutor struct {
volumeClient VolumeServerClient
progress float64
cancelled bool
}
```
### 2.3 Worker Capabilities & Registration
```go
type WorkerCapabilities struct {
SupportedTasks []TaskType
MaxConcurrent int
ResourceLimits ResourceLimits
PreferredServers []string // Affinity for specific volume servers
}
type ResourceLimits struct {
MaxMemoryMB int64
MaxDiskSpaceMB int64
MaxNetworkMbps int64
MaxCPUPercent float64
}
```
## 3. Task Lifecycle Management
### 3.1 Task States
```go
type TaskState string
const (
TaskStatePending TaskState = "pending"
TaskStateAssigned TaskState = "assigned"
TaskStateInProgress TaskState = "in_progress"
TaskStateCompleted TaskState = "completed"
TaskStateFailed TaskState = "failed"
TaskStateCancelled TaskState = "cancelled"
TaskStateStuck TaskState = "stuck" // Taking too long
TaskStateDuplicate TaskState = "duplicate" // Detected duplicate
)
```
### 3.2 Progress Tracking & Monitoring
```go
type InProgressTask struct {
Task *Task
WorkerID string
StartedAt time.Time
LastUpdate time.Time
Progress float64
EstimatedEnd time.Time
VolumeReserved bool // Reserved for capacity planning
}
type TaskMonitor struct {
inProgressTasks map[string]*InProgressTask
timeoutChecker *time.Ticker
stuckDetector *time.Ticker
duplicateChecker *time.Ticker
}
```
## 4. Volume Capacity Reconciliation
### 4.1 Volume State Tracking
```go
type VolumeStateManager struct {
masterClient MasterClient
inProgressTasks map[uint32]*InProgressTask // VolumeID -> Task
committedChanges map[uint32]*VolumeChange // Changes not yet in master
reconcileInterval time.Duration
}
type VolumeChange struct {
VolumeID uint32
ChangeType ChangeType // "ec_encoding", "vacuum_completed"
OldCapacity int64
NewCapacity int64
TaskID string
CompletedAt time.Time
ReportedToMaster bool
}
```
### 4.2 Shard Assignment Integration
When the master needs to assign shards, it must consider:
1. **Current volume state** from its own records
2. **In-progress capacity changes** from admin server
3. **Committed but unreported changes** from admin server
```go
type CapacityOracle struct {
adminServer AdminServerClient
masterState *MasterVolumeState
updateFreq time.Duration
}
func (o *CapacityOracle) GetAdjustedCapacity(volumeID uint32) int64 {
baseCapacity := o.masterState.GetCapacity(volumeID)
// Adjust for in-progress tasks
if task := o.adminServer.GetInProgressTask(volumeID); task != nil {
switch task.Type {
case TaskTypeErasureCoding:
// EC reduces effective capacity
return baseCapacity / 2 // Simplified
case TaskTypeVacuum:
// Vacuum may increase available space
return baseCapacity + int64(float64(baseCapacity) * 0.3)
}
}
// Adjust for completed but unreported changes
if change := o.adminServer.GetPendingChange(volumeID); change != nil {
return change.NewCapacity
}
return baseCapacity
}
```
## 5. Error Handling & Recovery
### 5.1 Worker Failure Scenarios
```go
type FailureHandler struct {
taskRescheduler *TaskRescheduler
workerMonitor *WorkerMonitor
alertManager *AlertManager
}
// Failure Scenarios:
// 1. Worker becomes unresponsive (heartbeat timeout)
// 2. Task execution fails (reported by worker)
// 3. Task gets stuck (progress timeout)
// 4. Duplicate task detection
// 5. Resource exhaustion
```
### 5.2 Recovery Strategies
**Worker Timeout Recovery**:
- Mark worker as inactive after 3 missed heartbeats
- Reschedule all assigned tasks to other workers
- Cleanup any partial state
**Task Stuck Recovery**:
- Detect tasks with no progress for > 2x estimated time
- Cancel stuck task and mark volume for cleanup
- Reschedule if retry count < max_retries
**Duplicate Task Prevention**:
```go
type DuplicateDetector struct {
activeFingerprints map[string]bool // VolumeID+TaskType
recentCompleted *LRUCache // Recently completed tasks
}
func (d *DuplicateDetector) IsTaskDuplicate(task *Task) bool {
fingerprint := fmt.Sprintf("%d-%s", task.VolumeID, task.Type)
return d.activeFingerprints[fingerprint] ||
d.recentCompleted.Contains(fingerprint)
}
```
## 6. Simulation & Testing Framework
### 6.1 Failure Simulation
```go
type TaskSimulator struct {
scenarios map[string]SimulationScenario
}
type SimulationScenario struct {
Name string
WorkerCount int
VolumeCount int
FailurePatterns []FailurePattern
Duration time.Duration
}
type FailurePattern struct {
Type FailureType // "worker_timeout", "task_stuck", "duplicate"
Probability float64 // 0.0 to 1.0
Timing TimingSpec // When during task execution
Duration time.Duration
}
```
### 6.2 Test Scenarios
**Scenario 1: Worker Timeout During EC**
- Start EC task on 30GB volume
- Kill worker at 50% progress
- Verify task reassignment
- Verify no duplicate EC operations
**Scenario 2: Stuck Vacuum Task**
- Start vacuum on high-garbage volume
- Simulate worker hanging at 75% progress
- Verify timeout detection and cleanup
- Verify volume state consistency
**Scenario 3: Duplicate Task Prevention**
- Submit same EC task from multiple sources
- Verify only one task executes
- Verify proper conflict resolution
**Scenario 4: Master-Admin State Divergence**
- Create in-progress EC task
- Simulate master restart
- Verify state reconciliation
- Verify shard assignment accounts for in-progress work
## 7. Performance & Scalability
### 7.1 Metrics & Monitoring
```go
type SystemMetrics struct {
TasksPerSecond float64
WorkerUtilization float64
AverageTaskTime time.Duration
FailureRate float64
QueueDepth int
VolumeStatesSync bool
}
```
### 7.2 Scalability Considerations
- **Horizontal Worker Scaling**: Add workers without admin server changes
- **Admin Server HA**: Master-slave admin servers for fault tolerance
- **Task Partitioning**: Partition tasks by collection or datacenter
- **Batch Operations**: Group similar tasks for efficiency
## 8. Implementation Plan
### Phase 1: Core Infrastructure
1. Admin server basic framework
2. Worker registration and heartbeat
3. Simple task assignment
4. Basic progress tracking
### Phase 2: Advanced Features
1. Volume state reconciliation
2. Sophisticated worker selection
3. Failure detection and recovery
4. Duplicate prevention
### Phase 3: Optimization & Monitoring
1. Performance metrics
2. Load balancing algorithms
3. Capacity planning integration
4. Comprehensive monitoring
This design provides a robust, scalable foundation for distributed task management in SeaweedFS while maintaining consistency with the existing architecture patterns.
+4 -7
View File
@@ -1,4 +1,4 @@
.PHONY: test admin-generate admin-build admin-clean admin-dev admin-run admin-test admin-fmt admin-help weed-commands
.PHONY: test admin-generate admin-build admin-clean admin-dev admin-run admin-test admin-fmt admin-help
BINARY = weed
ADMIN_DIR = weed/admin
@@ -11,9 +11,6 @@ all: install
install: admin-generate
cd weed; go install
weed-commands:
cd weed && $(MAKE) weed-db weed-sql
warp_install:
go install github.com/minio/warp@v0.7.6
@@ -21,12 +18,12 @@ full_install: admin-generate
cd weed; go install -tags "elastic gocdk sqlite ydb tarantool tikv rclone"
server: install
weed -v 0 server -s3 -filer -filer.maxMB=64 -volume.max=0 -master.volumeSizeLimitMB=100 -volume.preStopSeconds=1 -s3.port=8000 -s3.allowDeleteBucketNotEmpty=true -s3.config=./docker/compose/s3.json -metricsPort=9324
weed -v 0 server -s3 -filer -filer.maxMB=64 -volume.max=0 -master.volumeSizeLimitMB=100 -volume.preStopSeconds=1 -s3.port=8000 -s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=true -s3.config=./docker/compose/s3.json -metricsPort=9324
benchmark: install warp_install
pkill weed || true
pkill warp || true
weed server -debug=$(debug) -s3 -filer -volume.max=0 -master.volumeSizeLimitMB=100 -volume.preStopSeconds=1 -s3.port=8000 -s3.allowDeleteBucketNotEmpty=false -s3.config=./docker/compose/s3.json &
weed server -debug=$(debug) -s3 -filer -volume.max=0 -master.volumeSizeLimitMB=100 -volume.preStopSeconds=1 -s3.port=8000 -s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=false -s3.config=./docker/compose/s3.json &
warp client &
while ! nc -z localhost 8000 ; do sleep 1 ; done
warp mixed --host=127.0.0.1:8000 --access-key=some_access_key1 --secret-key=some_secret_key1 --autoterm
@@ -43,7 +40,7 @@ test: admin-generate
# Admin component targets
admin-generate:
@echo "Generating admin component templates..."
@cd $(ADMIN_DIR) && templ generate ./view
@cd $(ADMIN_DIR) && $(MAKE) generate
admin-build: admin-generate
@echo "Building admin component..."
+105 -77
View File
@@ -54,9 +54,9 @@ Table of Contents
=================
* [Quick Start](#quick-start)
* [Quick Start with weed mini](#quick-start-with-weed-mini)
* [Quick Start for S3 API on Docker](#quick-start-for-s3-api-on-docker)
* [Quick Start with Single Binary](#quick-start-with-single-binary)
* [Quick Start SeaweedFS S3 on AWS](#quick-start-seaweedfs-s3-on-aws)
* [Introduction](#introduction)
* [Features](#features)
* [Additional Features](#additional-features)
@@ -78,31 +78,6 @@ Table of Contents
# Quick Start #
## Quick Start with weed mini ##
The easiest way to get started with SeaweedFS for development and testing:
* Download the latest binary from https://github.com/seaweedfs/seaweedfs/releases and unzip a single binary file `weed` or `weed.exe`.
Example:
```bash
# remove quarantine on macOS
# xattr -d com.apple.quarantine ./weed
./weed mini -dir=/data
```
This single command starts a complete SeaweedFS setup with:
- **Master UI**: http://localhost:9333
- **Volume Server**: http://localhost:9340
- **Filer UI**: http://localhost:8888
- **S3 Endpoint**: http://localhost:8333
- **WebDAV**: http://localhost:7333
- **Admin UI**: http://localhost:23646
Perfect for development, testing, learning SeaweedFS, and single node deployments!
## Quick Start for S3 API on Docker ##
`docker run -p 8333:8333 chrislusf/seaweedfs server -s3`
@@ -110,9 +85,12 @@ Perfect for development, testing, learning SeaweedFS, and single node deployment
## Quick Start with Single Binary ##
* Download the latest binary from https://github.com/seaweedfs/seaweedfs/releases and unzip a single binary file `weed` or `weed.exe`. Or run `go install github.com/seaweedfs/seaweedfs/weed@latest`.
* `export AWS_ACCESS_KEY_ID=admin ; export AWS_SECRET_ACCESS_KEY=key` as the admin credentials to access the object store.
* Run `weed server -dir=/some/data/dir -s3` to start one master, one volume server, one filer, and one S3 gateway. The difference with `weed mini` is that `weed mini` can auto configure based on the single host environment, while `weed server` requires manual configuration and are designed for production use.
* Run `weed server -dir=/some/data/dir -s3` to start one master, one volume server, one filer, and one S3 gateway.
Also, to increase capacity, just add more volume servers by running `weed volume -dir="/some/data/dir2" -master="<master_host>:9333" -port=8081` locally, or on a different machine, or on thousands of machines. That is it!
Also, to increase capacity, just add more volume servers by running `weed volume -dir="/some/data/dir2" -mserver="<master_host>:9333" -port=8081` locally, or on a different machine, or on thousands of machines. That is it!
## Quick Start SeaweedFS S3 on AWS ##
* Setup fast production-ready [SeaweedFS S3 on AWS with cloudformation](https://aws.amazon.com/marketplace/pp/prodview-nzelz5gprlrjc)
# Introduction #
@@ -121,7 +99,7 @@ SeaweedFS is a simple and highly scalable distributed file system. There are two
1. to store billions of files!
2. to serve the files fast!
SeaweedFS started as a blob store to handle small files efficiently.
SeaweedFS started as an Object Store to handle small files efficiently.
Instead of managing all file metadata in a central master,
the central master only manages volumes on volume servers,
and these volume servers manage files and their metadata.
@@ -133,12 +111,16 @@ It is so simple with O(1) disk reads that you are welcome to challenge the perfo
SeaweedFS started by implementing [Facebook's Haystack design paper](http://www.usenix.org/event/osdi10/tech/full_papers/Beaver.pdf).
Also, SeaweedFS implements erasure coding with ideas from
[f4: Facebook’s Warm BLOB Storage System](https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-muralidhar.pdf), and has a lot of similarities with [Facebook’s Tectonic Filesystem](https://www.usenix.org/system/files/fast21-pan.pdf) and [Google's Colossus File System](https://cloud.google.com/blog/products/storage-data-transfer/a-peek-behind-colossus-googles-file-system)
[f4: Facebook’s Warm BLOB Storage System](https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-muralidhar.pdf), and has a lot of similarities with [Facebook’s Tectonic Filesystem](https://www.usenix.org/system/files/fast21-pan.pdf)
On top of the blob store, optional [Filer] can support directories and POSIX attributes.
On top of the object store, optional [Filer] can support directories and POSIX attributes.
Filer is a separate linearly-scalable stateless server with customizable metadata stores,
e.g., MySql, Postgres, Redis, Cassandra, HBase, Mongodb, Elastic Search, LevelDB, RocksDB, Sqlite, MemSql, TiDB, Etcd, CockroachDB, YDB, etc.
For any distributed key value stores, the large values can be offloaded to SeaweedFS.
With the fast access speed and linearly scalable capacity,
SeaweedFS can work as a distributed [Key-Large-Value store][KeyLargeValueStore].
SeaweedFS can transparently integrate with the cloud.
With hot data on local cluster, and warm data on the cloud with O(1) access time,
SeaweedFS can achieve both fast local access time and elastic cloud storage capacity.
@@ -148,13 +130,13 @@ Faster and cheaper than direct cloud storage!
[Back to TOC](#table-of-contents)
# Features #
## Additional Blob Store Features ##
* Support different replication levels, with rack and data center aware.
## Additional Features ##
* Can choose no replication or different replication levels, rack and data center aware.
* Automatic master servers failover - no single point of failure (SPOF).
* Automatic compression depending on file MIME type.
* Automatic Gzip compression depending on file MIME type.
* Automatic compaction to reclaim disk space after deletion or update.
* [Automatic entry TTL expiration][VolumeServerTTL].
* Flexible Capacity Expansion: Any server with some disk space can add to the total storage space.
* Any server with some disk space can add to the total storage space.
* Adding/Removing servers does **not** cause any data re-balancing unless triggered by admin commands.
* Optional picture resizing.
* Support ETag, Accept-Range, Last-Modified, etc.
@@ -162,7 +144,7 @@ Faster and cheaper than direct cloud storage!
* Support rebalancing the writable and readonly volumes.
* [Customizable Multiple Storage Tiers][TieredStorage]: Customizable storage disk types to balance performance and cost.
* [Transparent cloud integration][CloudTier]: unlimited capacity via tiered cloud storage for warm data.
* [Erasure Coding for warm storage][ErasureCoding] Rack-Aware 10.4 erasure coding reduces storage cost and increases availability. Enterprise version can customize EC ratio.
* [Erasure Coding for warm storage][ErasureCoding] Rack-Aware 10.4 erasure coding reduces storage cost and increases availability.
[Back to TOC](#table-of-contents)
@@ -208,7 +190,7 @@ Faster and cheaper than direct cloud storage!
[Back to TOC](#table-of-contents)
## Example: Using Seaweed Blob Store ##
## Example: Using Seaweed Object Store ##
By default, the master node runs on port 9333, and the volume nodes run on port 8080.
Let's start one master node, and two volume nodes on port 8080 and 8081. Ideally, they should be started from different machines. We'll use localhost as an example.
@@ -224,29 +206,27 @@ SeaweedFS uses HTTP REST operations to read, write, and delete. The responses ar
### Start Volume Servers ###
```
> weed volume -dir="/tmp/data1" -max=5 -master="localhost:9333" -port=8080 &
> weed volume -dir="/tmp/data2" -max=10 -master="localhost:9333" -port=8081 &
> weed volume -dir="/tmp/data1" -max=5 -mserver="localhost:9333" -port=8080 &
> weed volume -dir="/tmp/data2" -max=10 -mserver="localhost:9333" -port=8081 &
```
### Write A Blob ###
### Write File ###
A blob, also referred as a needle, a chunk, or mistakenly as a file, is just a byte array. It can have attributes, such as name, mime type, create or update time, etc. But basically it is just a byte array of a relatively small size, such as 2 MB ~ 64 MB. The size is not fixed.
To upload a blob: first, send a HTTP POST, PUT, or GET request to `/dir/assign` to get an `fid` and a volume server URL:
To upload a file: first, send a HTTP POST, PUT, or GET request to `/dir/assign` to get an `fid` and a volume server URL:
```
> curl http://localhost:9333/dir/assign
{"count":1,"fid":"3,01637037d6","url":"127.0.0.1:8080","publicUrl":"localhost:8080"}
```
Second, to store the blob content, send a HTTP multi-part POST request to `url + '/' + fid` from the response:
Second, to store the file content, send a HTTP multi-part POST request to `url + '/' + fid` from the response:
```
> curl -F file=@/home/chris/myphoto.jpg http://127.0.0.1:8080/3,01637037d6
{"name":"myphoto.jpg","size":43234,"eTag":"1cc0118e"}
```
To update, send another POST request with updated blob content.
To update, send another POST request with updated file content.
For deletion, send an HTTP DELETE request to the same `url + '/' + fid` URL:
@@ -254,7 +234,7 @@ For deletion, send an HTTP DELETE request to the same `url + '/' + fid` URL:
> curl -X DELETE http://127.0.0.1:8080/3,01637037d6
```
### Save Blob Id ###
### Save File Id ###
Now, you can save the `fid`, 3,01637037d6 in this case, to a database field.
@@ -266,9 +246,9 @@ The file key and file cookie are both coded in hex. You can store the <volume id
If stored as a string, in theory, you would need 8+1+16+8=33 bytes. A char(33) would be enough, if not more than enough, since most uses will not need 2^32 volumes.
If space is really a concern, you can store the file id in the binary format. You would need one 4-byte integer for volume id, 8-byte long number for file key, and a 4-byte integer for the file cookie. So 16 bytes are more than enough.
If space is really a concern, you can store the file id in your own format. You would need one 4-byte integer for volume id, 8-byte long number for file key, and a 4-byte integer for the file cookie. So 16 bytes are more than enough.
### Read a Blob ###
### Read File ###
Here is an example of how to render the URL.
@@ -309,7 +289,7 @@ http://localhost:8080/3/01637037d6.jpg?height=200&width=200&mode=fill
### Rack-Aware and Data Center-Aware Replication ###
SeaweedFS applies the replication strategy at a volume level. So, when you are getting a blob id, you can specify the replication strategy. For example:
SeaweedFS applies the replication strategy at a volume level. So, when you are getting a file id, you can specify the replication strategy. For example:
```
curl http://localhost:9333/dir/assign?replication=001
@@ -332,7 +312,7 @@ More details about replication can be found [on the wiki][Replication].
You can also set the default replication strategy when starting the master server.
### Allocate Blob Key on Specific Data Center ###
### Allocate File Key on Specific Data Center ###
Volume servers can be started with a specific data center name:
@@ -341,7 +321,7 @@ Volume servers can be started with a specific data center name:
weed volume -dir=/tmp/2 -port=8081 -dataCenter=dc2
```
When requesting a blob key, an optional "dataCenter" parameter can limit the assigned volume to the specific data center. For example, this specifies that the assigned volume should be limited to 'dc1':
When requesting a file key, an optional "dataCenter" parameter can limit the assigned volume to the specific data center. For example, this specifies that the assigned volume should be limited to 'dc1':
```
http://localhost:9333/dir/assign?dataCenter=dc1
@@ -360,15 +340,15 @@ When requesting a blob key, an optional "dataCenter" parameter can limit the ass
[Back to TOC](#table-of-contents)
## Blob Store Architecture ##
## Object Store Architecture ##
Usually distributed file systems split each file into chunks. A central server keeps a mapping of filenames to chunks, and also which chunks each chunk server has.
Usually distributed file systems split each file into chunks, a central master keeps a mapping of filenames, chunk indices to chunk handles, and also which chunks each chunk server has.
The main drawback is that the central server can't handle many small files efficiently, and since all read requests need to go through the central master, so it might not scale well for many concurrent users.
The main drawback is that the central master can't handle many small files efficiently, and since all read requests need to go through the chunk master, so it might not scale well for many concurrent users.
Instead of managing chunks, SeaweedFS manages data volumes in the master server. Each data volume is 32GB in size, and can hold a lot of blobs. And each storage node can have many data volumes. So the master node only needs to store the metadata about the volumes, which is a fairly small amount of data and is generally stable.
Instead of managing chunks, SeaweedFS manages data volumes in the master server. Each data volume is 32GB in size, and can hold a lot of files. And each storage node can have many data volumes. So the master node only needs to store the metadata about the volumes, which is a fairly small amount of data and is generally stable.
The actual blob metadata, which are the blob volume, offset, and size, is stored in each volume on volume servers. Since each volume server only manages metadata of blobs on its own disk, with only 16 bytes for each blob, all access can read the metadata just from memory and only needs one disk operation to actually read file data.
The actual file metadata is stored in each volume on volume servers. Since each volume server only manages metadata of files on its own disk, with only 16 bytes for each file, all file access can read file metadata just from memory and only needs one disk operation to actually read file data.
For comparison, consider that an xfs inode structure in Linux is 536 bytes.
@@ -382,13 +362,23 @@ On each write request, the master server also generates a file key, which is a g
### Write and Read files ###
When a client sends a write request, the master server returns (volume id, file key, file cookie, volume node URL) for the blob. The client then contacts the volume node and POSTs the blob content.
When a client sends a write request, the master server returns (volume id, file key, file cookie, volume node URL) for the file. The client then contacts the volume node and POSTs the file content.
When a client needs to read a blob based on (volume id, file key, file cookie), it asks the master server by the volume id for the (volume node URL, volume node public URL), or retrieves this from a cache. Then the client can GET the content, or just render the URL on web pages and let browsers fetch the content.
When a client needs to read a file based on (volume id, file key, file cookie), it asks the master server by the volume id for the (volume node URL, volume node public URL), or retrieves this from a cache. Then the client can GET the content, or just render the URL on web pages and let browsers fetch the content.
Please see the example for details on the write-read process.
### Storage Size ###
In the current implementation, each volume can hold 32 gibibytes (32GiB or 8x2^32 bytes). This is because we align content to 8 bytes. We can easily increase this to 64GiB, or 128GiB, or more, by changing 2 lines of code, at the cost of some wasted padding space due to alignment.
There can be 4 gibibytes (4GiB or 2^32 bytes) of volumes. So the total system size is 8 x 4GiB x 4GiB which is 128 exbibytes (128EiB or 2^67 bytes).
Each individual file size is limited to the volume size.
### Saving memory ###
All blob metadata stored on a volume server is readable from memory without disk access. Each file takes just a 16-byte map entry of <64bit key, 32bit offset, 32bit size>. Of course, each map entry has its own space cost for the map. But usually the disk space runs out before the memory does.
All file meta information stored on a volume server is readable from memory without disk access. Each file takes just a 16-byte map entry of <64bit key, 32bit offset, 32bit size>. Of course, each map entry has its own space cost for the map. But usually the disk space runs out before the memory does.
### Tiered Storage to the cloud ###
@@ -402,12 +392,6 @@ If the hot/warm data is split as 20/80, with 20 servers, you can achieve storage
[Back to TOC](#table-of-contents)
## SeaweedFS Filer ##
Built on top of the blob store, SeaweedFS Filer adds directory structure to create a file system. The directory sturcture is an interface that is implemented in many key-value stores or databases.
The content of a file is mapped to one or many blobs, distributed to multiple volumes on multiple volume servers.
## Compared to Other File Systems ##
Most other distributed file systems seem more complicated than necessary.
@@ -608,22 +592,65 @@ Percentage of the requests served within a certain time (ms)
```
make benchmark
warp: Benchmark data written to "warp-mixed-2025-12-05[194844]-kBpU.csv.zst"
warp: Benchmark data written to "warp-mixed-2023-10-16[102354]-l70a.csv.zst"
Mixed operations.
Operation: DELETE, 10%, Concurrency: 20, Ran 42s.
* Throughput: 55.13 obj/s
Operation: DELETE, 10%, Concurrency: 20, Ran 4m59s.
* Throughput: 6.19 obj/s
Operation: GET, 45%, Concurrency: 20, Ran 42s.
* Throughput: 2477.45 MiB/s, 247.75 obj/s
Operation: GET, 45%, Concurrency: 20, Ran 5m0s.
* Throughput: 279.85 MiB/s, 27.99 obj/s
Operation: PUT, 15%, Concurrency: 20, Ran 42s.
* Throughput: 825.85 MiB/s, 82.59 obj/s
Operation: PUT, 15%, Concurrency: 20, Ran 5m0s.
* Throughput: 89.86 MiB/s, 8.99 obj/s
Operation: STAT, 30%, Concurrency: 20, Ran 42s.
* Throughput: 165.27 obj/s
Operation: STAT, 30%, Concurrency: 20, Ran 5m0s.
* Throughput: 18.63 obj/s
Cluster Total: 3302.88 MiB/s, 550.51 obj/s over 43s.
Cluster Total: 369.74 MiB/s, 61.79 obj/s, 0 errors over 5m0s.
```
To see segmented request statistics, use the --analyze.v parameter.
```
warp analyze --analyze.v warp-mixed-2023-10-16[102354]-l70a.csv.zst
18642 operations loaded... Done!
Mixed operations.
----------------------------------------
Operation: DELETE - total: 1854, 10.0%, Concurrency: 20, Ran 5m0s, starting 2023-10-16 10:23:57.115 +0500 +05
* Throughput: 6.19 obj/s
Requests considered: 1855:
* Avg: 104ms, 50%: 30ms, 90%: 207ms, 99%: 1.355s, Fastest: 1ms, Slowest: 4.613s, StdDev: 320ms
----------------------------------------
Operation: GET - total: 8388, 45.3%, Size: 10485760 bytes. Concurrency: 20, Ran 5m0s, starting 2023-10-16 10:23:57.12 +0500 +05
* Throughput: 279.77 MiB/s, 27.98 obj/s
Requests considered: 8389:
* Avg: 221ms, 50%: 106ms, 90%: 492ms, 99%: 1.739s, Fastest: 8ms, Slowest: 8.633s, StdDev: 383ms
* TTFB: Avg: 81ms, Best: 2ms, 25th: 24ms, Median: 39ms, 75th: 65ms, 90th: 171ms, 99th: 669ms, Worst: 4.783s StdDev: 163ms
* First Access: Avg: 240ms, 50%: 105ms, 90%: 511ms, 99%: 2.08s, Fastest: 12ms, Slowest: 8.633s, StdDev: 480ms
* First Access TTFB: Avg: 88ms, Best: 2ms, 25th: 24ms, Median: 38ms, 75th: 64ms, 90th: 179ms, 99th: 919ms, Worst: 4.783s StdDev: 199ms
* Last Access: Avg: 219ms, 50%: 106ms, 90%: 463ms, 99%: 1.782s, Fastest: 9ms, Slowest: 8.633s, StdDev: 416ms
* Last Access TTFB: Avg: 81ms, Best: 2ms, 25th: 24ms, Median: 39ms, 75th: 65ms, 90th: 161ms, 99th: 657ms, Worst: 4.783s StdDev: 176ms
----------------------------------------
Operation: PUT - total: 2688, 14.5%, Size: 10485760 bytes. Concurrency: 20, Ran 5m0s, starting 2023-10-16 10:23:57.115 +0500 +05
* Throughput: 89.83 MiB/s, 8.98 obj/s
Requests considered: 2689:
* Avg: 1.165s, 50%: 878ms, 90%: 2.015s, 99%: 5.74s, Fastest: 99ms, Slowest: 8.264s, StdDev: 968ms
----------------------------------------
Operation: STAT - total: 5586, 30.2%, Concurrency: 20, Ran 5m0s, starting 2023-10-16 10:23:57.113 +0500 +05
* Throughput: 18.63 obj/s
Requests considered: 5587:
* Avg: 15ms, 50%: 11ms, 90%: 34ms, 99%: 80ms, Fastest: 0s, Slowest: 245ms, StdDev: 17ms
* First Access: Avg: 14ms, 50%: 10ms, 90%: 33ms, 99%: 69ms, Fastest: 0s, Slowest: 203ms, StdDev: 16ms
* Last Access: Avg: 15ms, 50%: 11ms, 90%: 34ms, 99%: 74ms, Fastest: 0s, Slowest: 203ms, StdDev: 17ms
Cluster Total: 369.64 MiB/s, 61.77 obj/s, 0 errors over 5m0s.
Total Errors:0.
```
[Back to TOC](#table-of-contents)
@@ -654,4 +681,5 @@ The text of this page is available for modification and reuse under the terms of
[Back to TOC](#table-of-contents)
## Stargazers over time
[![Stargazers over time](https://starchart.cc/seaweedfs/seaweedfs.svg?variant=adaptive)](https://starchart.cc/seaweedfs/seaweedfs)
[![Stargazers over time](https://starchart.cc/chrislusf/seaweedfs.svg)](https://starchart.cc/chrislusf/seaweedfs)
+145
View File
@@ -0,0 +1,145 @@
# SQL Query Engine Feature, Dev, and Test Plan
This document outlines the plan for adding SQL querying support to SeaweedFS, focusing on reading and analyzing data from Message Queue (MQ) topics.
## Feature Plan
**1. Goal**
To provide a SQL querying interface for SeaweedFS, enabling analytics on existing MQ topics. This enables:
- Basic querying with SELECT, WHERE, aggregations on MQ topics
- Schema discovery and metadata operations (SHOW DATABASES, SHOW TABLES, DESCRIBE)
- In-place analytics on Parquet-stored messages without data movement
**2. Key Features**
* **Schema Discovery and Metadata:**
* `SHOW DATABASES` - List all MQ namespaces
* `SHOW TABLES` - List all topics in a namespace
* `DESCRIBE table_name` - Show topic schema details
* Automatic schema detection from existing Parquet data
* **Basic Query Engine:**
* `SELECT` support with `WHERE`, `LIMIT`, `OFFSET`
* Aggregation functions: `COUNT()`, `SUM()`, `AVG()`, `MIN()`, `MAX()`
* Temporal queries with timestamp-based filtering
* **User Interfaces:**
* New CLI command `weed sql` with interactive shell mode
* Optional: Web UI for query execution and result visualization
* **Output Formats:**
* JSON (default), CSV, Parquet for result sets
* Streaming results for large queries
* Pagination support for result navigation
## Development Plan
**3. Data Source Integration**
* **MQ Topic Connector (Primary):**
* Build on existing `weed/mq/logstore/read_parquet_to_log.go`
* Implement efficient Parquet scanning with predicate pushdown
* Support schema evolution and backward compatibility
* Handle partition-based parallelism for scalable queries
* **Schema Registry Integration:**
* Extend `weed/mq/schema/schema.go` for SQL metadata operations
* Read existing topic schemas for query planning
* Handle schema evolution during query execution
**4. API & CLI Integration**
* **CLI Command:**
* New `weed sql` command with interactive shell mode (similar to `weed shell`)
* Support for script execution and result formatting
* Connection management for remote SeaweedFS clusters
* **gRPC API:**
* Add SQL service to existing MQ broker gRPC interface
* Enable efficient query execution with streaming results
## Example Usage Scenarios
**Scenario 1: Schema Discovery and Metadata**
```sql
-- List all namespaces (databases)
SHOW DATABASES;
-- List topics in a namespace
USE my_namespace;
SHOW TABLES;
-- View topic structure and discovered schema
DESCRIBE user_events;
```
**Scenario 2: Data Querying**
```sql
-- Basic filtering and projection
SELECT user_id, event_type, timestamp
FROM user_events
WHERE timestamp > 1640995200000
LIMIT 100;
-- Aggregation queries
SELECT COUNT(*) as event_count
FROM user_events
WHERE timestamp >= 1640995200000;
-- More aggregation examples
SELECT MAX(timestamp), MIN(timestamp)
FROM user_events;
```
**Scenario 3: Analytics & Monitoring**
```sql
-- Basic analytics
SELECT COUNT(*) as total_events
FROM user_events
WHERE timestamp >= 1640995200000;
-- Simple monitoring
SELECT AVG(response_time) as avg_response
FROM api_logs
WHERE timestamp >= 1640995200000;
## Architecture Overview
```
SQL Query Flow:
1. Parse SQL 2. Plan & Optimize 3. Execute Query
┌─────────────┐ ┌──────────────┐ ┌─────────────────┐ ┌──────────────┐
│ Client │ │ SQL Parser │ │ Query Planner │ │ Execution │
│ (CLI) │──→ │ PostgreSQL │──→ │ & Optimizer │──→ │ Engine │
│ │ │ (Custom) │ │ │ │ │
└─────────────┘ └──────────────┘ └─────────────────┘ └──────────────┘
│ │
│ Schema Lookup │ Data Access
▼ ▼
┌─────────────────────────────────────────────────────────────┐
│ Schema Catalog │
│ • Namespace → Database mapping │
│ • Topic → Table mapping │
│ • Schema version management │
└─────────────────────────────────────────────────────────────┘
▲
│ Metadata
│
┌─────────────────────────────────────────────────────────────────────────────┐
│ MQ Storage Layer │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ▲ │
│ │ Topic A │ │ Topic B │ │ Topic C │ │ ... │ │ │
│ │ (Parquet) │ │ (Parquet) │ │ (Parquet) │ │ (Parquet) │ │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘ │ │
└──────────────────────────────────────────────────────────────────────────│──┘
│
Data Access
```
## Success Metrics
* **Feature Completeness:** Support for all specified SELECT operations and metadata commands
* **Performance:**
* **Simple SELECT queries**: < 100ms latency for single-table queries with up to 3 WHERE predicates on ≤ 100K records
* **Complex queries**: < 1s latency for queries involving aggregations (COUNT, SUM, MAX, MIN) on ≤ 1M records
* **Time-range queries**: < 500ms for timestamp-based filtering on ≤ 500K records within 24-hour windows
* **Scalability:** Handle topics with millions of messages efficiently
+169
View File
@@ -0,0 +1,169 @@
# Server-Side Encryption with Customer-Provided Keys (SSE-C) Implementation
This document describes the implementation of SSE-C support in SeaweedFS, addressing the feature request from [GitHub Discussion #5361](https://github.com/seaweedfs/seaweedfs/discussions/5361).
## Overview
SSE-C allows clients to provide their own encryption keys for server-side encryption of objects stored in SeaweedFS. The server encrypts the data using the customer-provided AES-256 key but does not store the key itself - only an MD5 hash of the key for validation purposes.
## Implementation Details
### Architecture
The SSE-C implementation follows a transparent encryption/decryption pattern:
1. **Upload (PUT/POST)**: Data is encrypted with the customer key before being stored
2. **Download (GET/HEAD)**: Encrypted data is decrypted on-the-fly using the customer key
3. **Metadata Storage**: Only the encryption algorithm and key MD5 are stored as metadata
### Key Components
#### 1. Constants and Headers (`weed/s3api/s3_constants/header.go`)
- Added AWS-compatible SSE-C header constants
- Support for both regular and copy-source SSE-C headers
#### 2. Core SSE-C Logic (`weed/s3api/s3_sse_c.go`)
- **SSECustomerKey**: Structure to hold customer encryption key and metadata
- **SSECEncryptedReader**: Streaming encryption with AES-256-CTR mode
- **SSECDecryptedReader**: Streaming decryption with IV extraction
- **validateAndParseSSECHeaders**: Shared validation logic (DRY principle)
- **ParseSSECHeaders**: Parse regular SSE-C headers
- **ParseSSECCopySourceHeaders**: Parse copy-source SSE-C headers
- Header validation and parsing functions
- Metadata extraction and response handling
#### 3. Error Handling (`weed/s3api/s3err/s3api_errors.go`)
- New error codes for SSE-C validation failures
- AWS-compatible error messages and HTTP status codes
#### 4. S3 API Integration
- **PUT Object Handler**: Encrypts data streams transparently
- **GET Object Handler**: Decrypts data streams transparently
- **HEAD Object Handler**: Validates keys and returns appropriate headers
- **Metadata Storage**: Integrates with existing `SaveAmzMetaData` function
### Encryption Scheme
- **Algorithm**: AES-256-CTR (Counter mode)
- **Key Size**: 256 bits (32 bytes)
- **IV Generation**: Random 16-byte IV per object
- **Storage Format**: `[IV][EncryptedData]` where IV is prepended to encrypted content
### Metadata Storage
SSE-C metadata is stored in the filer's extended attributes:
```
x-amz-server-side-encryption-customer-algorithm: "AES256"
x-amz-server-side-encryption-customer-key-md5: "<md5-hash-of-key>"
```
## API Compatibility
### Required Headers for Encryption (PUT/POST)
```
x-amz-server-side-encryption-customer-algorithm: AES256
x-amz-server-side-encryption-customer-key: <base64-encoded-256-bit-key>
x-amz-server-side-encryption-customer-key-md5: <md5-hash-of-key>
```
### Required Headers for Decryption (GET/HEAD)
Same headers as encryption - the server validates the key MD5 matches.
### Copy Operations
Support for copy-source SSE-C headers:
```
x-amz-copy-source-server-side-encryption-customer-algorithm
x-amz-copy-source-server-side-encryption-customer-key
x-amz-copy-source-server-side-encryption-customer-key-md5
```
## Error Handling
The implementation provides AWS-compatible error responses:
- **InvalidEncryptionAlgorithmError**: Non-AES256 algorithm specified
- **InvalidArgument**: Invalid key format, size, or MD5 mismatch
- **Missing customer key**: Object encrypted but no key provided
- **Unnecessary customer key**: Object not encrypted but key provided
## Security Considerations
1. **Key Management**: Customer keys are never stored - only MD5 hashes for validation
2. **IV Randomness**: Fresh random IV generated for each object
3. **Transparent Security**: Volume servers never see unencrypted data
4. **Key Validation**: Strict validation of key format, size, and MD5
## Testing
Comprehensive test suite covers:
- Header validation and parsing (regular and copy-source)
- Encryption/decryption round-trip
- Error condition handling
- Metadata extraction
- Code reuse validation (DRY principle)
- AWS S3 compatibility
Run tests with:
```bash
go test -v ./weed/s3api
## Usage Example
### Upload with SSE-C
```bash
# Generate a 256-bit key
KEY=$(openssl rand -base64 32)
KEY_MD5=$(echo -n "$KEY" | base64 -d | openssl dgst -md5 -binary | base64)
# Upload object with SSE-C
curl -X PUT "http://localhost:8333/bucket/object" \
-H "x-amz-server-side-encryption-customer-algorithm: AES256" \
-H "x-amz-server-side-encryption-customer-key: $KEY" \
-H "x-amz-server-side-encryption-customer-key-md5: $KEY_MD5" \
--data-binary @file.txt
```
### Download with SSE-C
```bash
# Download object with SSE-C (same key required)
curl "http://localhost:8333/bucket/object" \
-H "x-amz-server-side-encryption-customer-algorithm: AES256" \
-H "x-amz-server-side-encryption-customer-key: $KEY" \
-H "x-amz-server-side-encryption-customer-key-md5: $KEY_MD5"
```
## Integration Points
### Existing SeaweedFS Features
- **Filer Metadata**: Extends existing metadata storage
- **Volume Servers**: No changes required - store encrypted data transparently
- **S3 API**: Integrates seamlessly with existing handlers
- **Versioning**: Compatible with object versioning
- **Multipart Upload**: Ready for multipart upload integration
### Future Enhancements
- **SSE-S3**: Server-managed encryption keys
- **SSE-KMS**: External key management service integration
- **Performance Optimization**: Hardware acceleration for encryption
- **Compliance**: Enhanced audit logging for encrypted objects
## File Changes Summary
1. **`weed/s3api/s3_constants/header.go`** - Added SSE-C header constants
2. **`weed/s3api/s3_sse_c.go`** - Core SSE-C implementation (NEW)
3. **`weed/s3api/s3_sse_c_test.go`** - Comprehensive test suite (NEW)
4. **`weed/s3api/s3err/s3api_errors.go`** - Added SSE-C error codes
5. **`weed/s3api/s3api_object_handlers.go`** - GET/HEAD with SSE-C support
6. **`weed/s3api/s3api_object_handlers_put.go`** - PUT with SSE-C support
7. **`weed/server/filer_server_handlers_write_autochunk.go`** - Metadata storage
## Compliance
This implementation follows the [AWS S3 SSE-C specification](https://docs.aws.amazon.com/AmazonS3/latest/userguide/ServerSideEncryptionCustomerKeys.html) for maximum compatibility with existing S3 clients and tools.
## Performance Impact
- **Encryption Overhead**: Minimal CPU impact with efficient AES-CTR streaming
- **Memory Usage**: Constant memory usage via streaming encryption/decryption
- **Storage Overhead**: 16 bytes per object for IV storage
- **Network**: No additional network overhead
-790
View File
@@ -1,790 +0,0 @@
# Execution Plan: SeaweedFS Volume Server — Go to Rust Port
## Scope Summary
| Component | Go Source | Lines (non-test) | Description |
|---|---|---|---|
| CLI & startup | `weed/command/volume.go` | 476 | ~40 CLI flags, server bootstrap |
| HTTP server + handlers | `weed/server/volume_server*.go` | 1,517 | Struct, routes, read/write/delete handlers |
| gRPC handlers | `weed/server/volume_grpc_*.go` | 3,073 | 40 RPC method implementations |
| Storage engine | `weed/storage/` | 15,271 | Volumes, needles, index, compaction, EC, backend |
| Protobuf definitions | `weed/pb/volume_server.proto` | 759 | Service + message definitions |
| Shared utilities | `weed/security/`, `weed/stats/`, `weed/util/` | ~2,000+ | JWT, TLS, metrics, helpers |
| **Total** | | **~23,000+** | |
## Rust Crate & Dependency Strategy
```
seaweed-volume/
├── Cargo.toml
├── build.rs # protobuf codegen
├── proto/
│ ├── volume_server.proto # copied from Go, adapted
│ └── remote.proto
├── src/
│ ├── main.rs # CLI entry point
│ ├── config.rs # CLI flags + config
│ ├── server/
│ │ ├── mod.rs
│ │ ├── volume_server.rs # VolumeServer struct + lifecycle
│ │ ├── http_handlers.rs # HTTP route dispatch
│ │ ├── http_read.rs # GET/HEAD handlers
│ │ ├── http_write.rs # POST/PUT handlers
│ │ ├── http_delete.rs # DELETE handler
│ │ ├── http_admin.rs # /status, /healthz, /ui
│ │ ├── grpc_service.rs # gRPC trait impl dispatch
│ │ ├── grpc_vacuum.rs
│ │ ├── grpc_copy.rs
│ │ ├── grpc_erasure_coding.rs
│ │ ├── grpc_tail.rs
│ │ ├── grpc_admin.rs
│ │ ├── grpc_read_write.rs
│ │ ├── grpc_batch_delete.rs
│ │ ├── grpc_scrub.rs
│ │ ├── grpc_tier.rs
│ │ ├── grpc_remote.rs
│ │ ├── grpc_query.rs
│ │ ├── grpc_state.rs
│ │ └── grpc_client_to_master.rs # heartbeat
│ ├── storage/
│ │ ├── mod.rs
│ │ ├── store.rs # Store (multi-disk manager)
│ │ ├── volume.rs # Volume struct + lifecycle
│ │ ├── volume_read.rs
│ │ ├── volume_write.rs
│ │ ├── volume_compact.rs
│ │ ├── volume_info.rs
│ │ ├── needle/
│ │ │ ├── mod.rs
│ │ │ ├── needle.rs # Needle struct + serialization
│ │ │ ├── needle_read.rs
│ │ │ ├── needle_write.rs
│ │ │ ├── needle_map.rs # in-memory NeedleMap
│ │ │ ├── needle_value.rs
│ │ │ └── crc.rs
│ │ ├── super_block.rs
│ │ ├── idx/
│ │ │ ├── mod.rs
│ │ │ └── idx.rs # .idx file format read/write
│ │ ├── needle_map_leveldb.rs
│ │ ├── types.rs # NeedleId, Offset, Size, DiskType
│ │ ├── disk_location.rs # DiskLocation per-directory
│ │ ├── erasure_coding/
│ │ │ ├── mod.rs
│ │ │ ├── ec_volume.rs
│ │ │ ├── ec_shard.rs
│ │ │ ├── ec_encoder.rs # Reed-Solomon encoding
│ │ │ └── ec_decoder.rs
│ │ └── backend/
│ │ ├── mod.rs
│ │ ├── disk.rs
│ │ └── s3_backend.rs # tiered storage to S3
│ ├── topology/
│ │ └── volume_layout.rs # replication placement
│ ├── security/
│ │ ├── mod.rs
│ │ ├── guard.rs # whitelist + JWT gate
│ │ ├── jwt.rs
│ │ └── tls.rs
│ ├── stats/
│ │ ├── mod.rs
│ │ └── metrics.rs # Prometheus counters/gauges
│ └── util/
│ ├── mod.rs
│ ├── grpc.rs
│ ├── http.rs
│ └── file.rs
└── tests/
├── integration/
│ ├── http_read_test.rs
│ ├── http_write_test.rs
│ ├── grpc_test.rs
│ └── storage_test.rs
└── unit/
├── needle_test.rs
├── idx_test.rs
├── super_block_test.rs
└── ec_test.rs
```
### Key Rust dependencies
| Purpose | Crate |
|---|---|
| Async runtime | `tokio` |
| gRPC | `tonic` + `prost` |
| HTTP server | `hyper` + `axum` |
| CLI parsing | `clap` (derive) |
| Prometheus metrics | `prometheus` |
| JWT | `jsonwebtoken` |
| TLS | `rustls` + `tokio-rustls` |
| LevelDB | `rusty-leveldb` or `rocksdb` |
| Reed-Solomon EC | `reed-solomon-erasure` |
| Logging | `tracing` + `tracing-subscriber` |
| Config (security.toml) | `toml` + `serde` |
| CRC32 | `crc32fast` |
| Memory-mapped files | `memmap2` |
---
## Phased Execution Plan
### Phase 1: Project Skeleton & Protobuf Codegen
**Goal:** Cargo project compiles, proto codegen works, CLI parses all flags.
**Steps:**
1.1. Create `seaweed-volume/Cargo.toml` with all dependencies listed above.
1.2. Copy `volume_server.proto` and `remote.proto` into `proto/`. Adjust package paths for Rust codegen.
1.3. Create `build.rs` using `tonic-build` to compile `.proto` files into Rust types.
1.4. Create `src/main.rs` with `clap` derive structs mirroring all 40 CLI flags from `weed/command/volume.go`:
- `--port` (default 8080)
- `--port.grpc` (default 0 → 10000+port)
- `--port.public` (default 0 → same as port)
- `--ip` (auto-detect)
- `--id` (default empty → ip:port)
- `--publicUrl`
- `--ip.bind`
- `--master` (default "localhost:9333")
- `--mserver` (deprecated compat)
- `--preStopSeconds` (default 10)
- `--idleTimeout` (default 30)
- `--dataCenter`
- `--rack`
- `--index` [memory|leveldb|leveldbMedium|leveldbLarge]
- `--disk` [hdd|ssd|<tag>]
- `--tags`
- `--dir` (default temp dir)
- `--dir.idx`
- `--max` (default "8")
- `--whiteList`
- `--minFreeSpacePercent` (default "1")
- `--minFreeSpace`
- `--images.fix.orientation` (default false)
- `--readMode` [local|proxy|redirect] (default "proxy")
- `--cpuprofile`
- `--memprofile`
- `--compactionMBps` (default 0)
- `--maintenanceMBps` (default 0)
- `--fileSizeLimitMB` (default 256)
- `--concurrentUploadLimitMB` (default 0)
- `--concurrentDownloadLimitMB` (default 0)
- `--pprof` (default false)
- `--metricsPort` (default 0)
- `--metricsIp`
- `--inflightUploadDataTimeout` (default 60s)
- `--inflightDownloadDataTimeout` (default 60s)
- `--hasSlowRead` (default true)
- `--readBufferSizeMB` (default 4)
- `--index.leveldbTimeout` (default 0)
- `--debug` (default false)
- `--debug.port` (default 6060)
1.5. Implement the same flag validation logic from `startVolumeServer()`:
- Parse comma-separated `--dir`, `--max`, `--minFreeSpace`, `--disk`, `--tags`
- Replicate single-value-to-all-dirs expansion
- Validate count matches between dirs and limits
- `--mserver` backward compat
1.6. **Test:** `cargo build` succeeds. `cargo run -- --help` shows all flags. Proto types generated.
**Verification:** Run with `--port 8080 --dir /tmp --master localhost:9333` — should parse without error and print config.
---
### Phase 2: Core Storage Types & On-Disk Format
**Goal:** Read and write the SeaweedFS needle/volume binary format bit-for-bit compatible with Go.
**Source files to port:**
- `weed/storage/types/needle_types.go` → `src/storage/types.rs`
- `weed/storage/needle/needle.go` → `src/storage/needle/needle.rs`
- `weed/storage/needle/needle_read.go` → `src/storage/needle/needle_read.rs`
- `weed/storage/needle/needle_write.go` (partial) → `src/storage/needle/needle_write.rs`
- `weed/storage/needle/crc.go` → `src/storage/needle/crc.rs`
- `weed/storage/needle/needle_value_map.go` → `src/storage/needle/needle_value.rs`
- `weed/storage/super_block/super_block.go` → `src/storage/super_block.rs`
- `weed/storage/idx/` → `src/storage/idx/`
**Steps:**
2.1. **Fundamental types** (`types.rs`):
- `NeedleId` (u64), `Offset` (u32 or u64 depending on version), `Size` (i32, negative = deleted)
- `Cookie` (u32)
- `DiskType` enum (HDD, SSD, Custom)
- Version constants (Version1=1, Version2=2, Version3=3, CurrentVersion=3)
- Byte serialization matching Go's `binary.BigEndian` encoding
2.2. **SuperBlock** (`super_block.rs`):
- 8-byte header: Version(1) + ReplicaPlacement(1) + TTL(2) + CompactRevision(2) + Reserved(2)
- `ReplicaPlacement` struct with same/diff rack/dc counts
- `TTL` struct with count + unit
- Read/write from first 8 bytes of `.dat` file
- Match exact byte layout from `super_block.go`
2.3. **Needle binary format** (`needle.rs`, `needle_read.rs`):
- Version 2/3 header: Cookie(4) + NeedleId(8) + Size(4)
- Body: Data, Flags, Name, Mime, PairsSize, Pairs, LastModified, TTL, Checksum, AppendAtNs, Padding
- CRC32 checksum (matching Go's `crc32.ChecksumIEEE`)
- Padding to 8-byte alignment
- Read path: read header → compute body length → read body → verify CRC
2.4. **Idx file format** (`idx/`):
- Fixed 16-byte records: NeedleId(8) + Offset(4) + Size(4)
- Sequential append-only file
- Walk/iterate all entries
- Binary search not used (loaded into memory map)
2.5. **NeedleMap (in-memory)** (`needle_map.rs`):
- HashMap<NeedleId, NeedleValue> where NeedleValue = {Offset, Size}
- Load from `.idx` file on volume mount
- Support Get, Set, Delete operations
- Track file count, deleted count, deleted byte count
2.6. **Tests:**
- Unit test: write a needle to bytes → read it back → verify fields match
- Unit test: write/read SuperBlock round-trip
- Unit test: write/read idx entries round-trip
- **Cross-compat test:** Use Go volume server to create a small volume with known data. Read it from Rust and verify all needles decoded correctly. (Keep test fixture `.dat`/`.idx` files in `tests/fixtures/`)
---
### Phase 3: Volume Struct & Lifecycle
**Goal:** Mount, read from, write to, and unmount a volume.
**Source files to port:**
- `weed/storage/volume.go` → `src/storage/volume.rs`
- `weed/storage/volume_read.go` → `src/storage/volume_read.rs`
- `weed/storage/volume_write.go` → `src/storage/volume_write.rs`
- `weed/storage/volume_loading.go`
- `weed/storage/volume_vacuum.go` → `src/storage/volume_compact.rs`
- `weed/storage/volume_info/volume_info.go` → `src/storage/volume_info.rs`
- `weed/storage/volume_super_block.go`
**Steps:**
3.1. **Volume struct** (`volume.rs`):
- Fields: Id, dir, dataFile, nm (NeedleMap), SuperBlock, readOnly, lastModifiedTs, lastCompactIndexOffset, lastCompactRevision
- `noWriteOrDelete` / `noWriteCanDelete` / `readOnly` state flags
- File handles for `.dat` file (read + append)
- Lock strategy: `RwLock` for concurrent reads, exclusive writes
3.2. **Volume loading** — exact logic from `volume_loading.go`:
- Open `.dat` file, read SuperBlock from first 8 bytes
- Load `.idx` file into NeedleMap
- Handle `.vif` (VolumeInfo) JSON sidecar file
- Set volume state based on SuperBlock + VolumeInfo
3.3. **Volume read** (`volume_read.rs`) — from `volume_read.go`:
- `ReadNeedle(needleId, cookie)`: lookup in NeedleMap → seek in .dat → read needle bytes → verify cookie + CRC → return data
- Handle deleted needles (Size < 0)
- `ReadNeedleBlob(offset, size)`: raw blob read
- `ReadNeedleMeta(needleId, offset, size)`: read metadata only
3.4. **Volume write** (`volume_write.rs`) — from `volume_write.go`:
- `WriteNeedle(needle)`: serialize needle → append to .dat → update .idx → update NeedleMap
- `DeleteNeedle(needleId)`: mark as deleted in NeedleMap + append tombstone to .idx
- File size limit check
- Concurrent write serialization (mutex on write path)
3.5. **Volume compaction** (`volume_compact.rs`) — from `volume_vacuum.go`:
- `CheckCompact()`: compute garbage ratio
- `Compact()`: create new .dat/.idx, copy only live needles, update compact revision
- `CommitCompact()`: rename compacted files over originals
- `CleanupCompact()`: remove temp files
- Throttle by `compactionBytePerSecond`
3.6. **Volume info** (`volume_info.rs`):
- Read/write `.vif` JSON sidecar
- VolumeInfo protobuf struct mapping
- Remote file references for tiered storage
3.7. **Tests:**
- Mount a volume, write 100 needles, read them all back, verify content
- Delete 50 needles, verify they return "deleted"
- Compact, verify only 50 remain, verify content
- Read Go-created volume fixtures
---
### Phase 4: Store (Multi-Volume, Multi-Disk Manager)
**Goal:** Manage multiple volumes across multiple disk directories.
**Source files to port:**
- `weed/storage/store.go` → `src/storage/store.rs`
- `weed/storage/disk_location.go` → `src/storage/disk_location.rs`
- `weed/storage/store_ec.go`
- `weed/storage/store_state.go`
**Steps:**
4.1. **DiskLocation** (`disk_location.rs`):
- Directory path, max volume count, min free space, disk type, tags
- Load all volumes from directory on startup
- Track free space, check writable
4.2. **Store** (`store.rs`):
- Vector of `DiskLocation`s
- `GetVolume(volumeId)` → lookup across all locations
- `HasVolume(volumeId)` check
- `AllocateVolume(...)` — create new volume in appropriate location
- `DeleteVolume(...)`, `MountVolume(...)`, `UnmountVolume(...)`
- `DeleteCollection(collection)` — delete all volumes of a collection
- Collect volume status for heartbeat
- `SetStopping()`, `Close()`
- Persistent state (maintenance mode) via `store_state.go`
4.3. **Store state** — `VolumeServerState` protobuf with maintenance flag, persisted to disk.
4.4. **Tests:**
- Create store with 2 dirs, allocate volumes in each, verify load balancing
- Mount/unmount/delete lifecycle
- State persistence across restart
---
### Phase 5: Erasure Coding
**Goal:** Full EC shard encode/decode/read/write/rebuild.
**Source files to port:**
- `weed/storage/erasure_coding/` (3,599 lines)
**Steps:**
5.1. **EC volume + shard structs** — `EcVolume`, `EcShard` with file handles for `.ec00`–`.ec13` shard files + `.ecx` index + `.ecj` journal.
5.2. **EC encoder** — Reed-Solomon 10+4 (configurable) encoding using `reed-solomon-erasure` crate:
- `VolumeEcShardsGenerate`: read .dat → split into data shards → compute parity → write .ec00-.ec13 + .ecx
5.3. **EC decoder/reader** — reconstruct data from any 10 of 14 shards:
- `EcShardRead`: read range from a specific shard
- Locate needle in EC volume via .ecx index
- Handle cross-shard needle reads
5.4. **EC shard operations:**
- Copy, delete, mount, unmount shards
- `VolumeEcShardsRebuild`: rebuild missing shards from remaining
- `VolumeEcShardsToVolume`: reconstruct .dat from EC shards
- `VolumeEcBlobDelete`: mark deleted in EC journal
- `VolumeEcShardsInfo`: report shard metadata
5.5. **Tests:**
- Encode a volume → verify 14 shards created
- Delete 4 shards → rebuild → verify data intact
- Read individual needles from EC volume
- Cross-compat with Go-generated EC shards
---
### Phase 6: Backend / Tiered Storage
**Goal:** Support tiered storage to remote backends (S3, etc).
**Source files to port:**
- `weed/storage/backend/` (1,850 lines)
**Steps:**
6.1. **Backend trait** — abstract `BackendStorage` trait with `ReadAt`, `WriteAt`, `Truncate`, `Close`, `Name`.
6.2. **Disk backend** — default local disk implementation.
6.3. **S3 backend** — upload .dat to S3, read ranges via S3 range requests.
6.4. **Tier move operations:**
- `VolumeTierMoveDatToRemote`: upload .dat to remote, optionally delete local
- `VolumeTierMoveDatFromRemote`: download .dat from remote
6.5. **Tests:**
- Disk backend read/write round-trip
- S3 backend with mock/localstack
---
### Phase 7: Security Layer
**Goal:** JWT authentication, whitelist guard, TLS configuration.
**Source files to port:**
- `weed/security/guard.go` → `src/security/guard.rs`
- `weed/security/jwt.go` → `src/security/jwt.rs`
- `weed/security/tls.go` → `src/security/tls.rs`
**Steps:**
7.1. **Guard** (`guard.rs`):
- Whitelist IP check (exact match on `r.RemoteAddr`)
- Wrap handlers with whitelist enforcement
- `UpdateWhiteList()` for live reload
7.2. **JWT** (`jwt.rs`):
- `SeaweedFileIdClaims` with `fid` field
- Sign with HMAC-SHA256
- Verify + decode with expiry check
- Separate signing keys for read vs write
- `GetJwt(request)` — extract from `Authorization: Bearer` header or `jwt` query param
7.3. **TLS** (`tls.rs`):
- Load server TLS cert/key for gRPC and HTTPS
- Load client TLS for mutual TLS
- Read from `security.toml` config (same format as Go's viper config)
7.4. **Tests:**
- JWT sign → verify round-trip
- JWT with wrong key → reject
- JWT with expired token → reject
- JWT fid mismatch → reject
- Whitelist allow/deny
---
### Phase 8: Prometheus Metrics
**Goal:** Export same metric names as Go for dashboard compatibility.
**Source files to port:**
- `weed/stats/metrics.go` (volume server counters/gauges/histograms)
**Steps:**
8.1. Define all Prometheus metrics matching Go names:
- `VolumeServerRequestCounter` (labels: method, status)
- `VolumeServerRequestHistogram` (labels: method)
- `VolumeServerInFlightRequestsGauge` (labels: method)
- `VolumeServerInFlightUploadSize`
- `VolumeServerInFlightDownloadSize`
- `VolumeServerConcurrentUploadLimit`
- `VolumeServerConcurrentDownloadLimit`
- `VolumeServerHandlerCounter` (labels: type — UploadLimitCond, DownloadLimitCond)
- Read/Write/Delete request counters
8.2. Metrics HTTP endpoint on `--metricsPort`.
8.3. Optional push-based metrics loop (`LoopPushingMetric`).
8.4. **Test:** Verify metric names and labels match Go output.
---
### Phase 9: HTTP Server & Handlers
**Goal:** All HTTP endpoints with exact same behavior as Go.
**Source files to port:**
- `weed/server/volume_server.go` → `src/server/volume_server.rs`
- `weed/server/volume_server_handlers.go` → `src/server/http_handlers.rs`
- `weed/server/volume_server_handlers_read.go` → `src/server/http_read.rs`
- `weed/server/volume_server_handlers_write.go` → `src/server/http_write.rs`
- `weed/server/volume_server_handlers_admin.go` → `src/server/http_admin.rs`
- `weed/server/volume_server_handlers_helper.go` (URL parsing, proxy, JSON responses)
- `weed/server/volume_server_handlers_ui.go` → `src/server/http_admin.rs`
**Steps:**
9.1. **URL path parsing** — from `handlers_helper.go`:
- Parse `/<vid>,<fid>` and `/<vid>/<fid>` patterns
- Extract volume ID, file ID, filename, ext
9.2. **Route dispatch** — from `privateStoreHandler` and `publicReadOnlyHandler`:
- `GET /` → `GetOrHeadHandler`
- `HEAD /` → `GetOrHeadHandler`
- `POST /` → `PostHandler` (whitelist gated)
- `PUT /` → `PostHandler` (whitelist gated)
- `DELETE /` → `DeleteHandler` (whitelist gated)
- `OPTIONS /` → CORS preflight
- `GET /status` → JSON status
- `GET /healthz` → health check
- `GET /ui/index.html` → HTML UI page
- Static resources (CSS/JS for UI)
9.3. **GET/HEAD handler** (`http_read.rs`) — from `handlers_read.go` (468 lines):
- JWT read authorization check
- Lookup needle by volume ID + needle ID + cookie
- ETag / If-None-Match / If-Modified-Since conditional responses
- Content-Type from stored MIME or filename extension
- Content-Disposition header
- Content-Encoding (gzip/zstd stored data)
- Range request support (HTTP 206 Partial Content)
- JPEG orientation fix (if configured)
- Proxy to replica on local miss (readMode=proxy)
- Redirect to replica (readMode=redirect)
- Download tracking (in-flight size accounting)
9.4. **POST/PUT handler** (`http_write.rs`) — from `handlers_write.go` (170 lines):
- JWT write authorization check
- Multipart form parsing
- Extract file data, filename, content type, TTL, last-modified
- Optional gzip/zstd compression
- Write needle to volume
- Replicate to peers (same logic as Go's `DistributedOperation`)
- Return JSON: {name, size, eTag, error}
9.5. **DELETE handler** — already in handlers.go:
- JWT authorization
- Delete from local volume
- Replicate delete to peers
- Return JSON result
9.6. **Admin handlers** (`http_admin.rs`):
- `/status` → JSON with volumes, version, disk status
- `/healthz` → 200 OK if serving
- `/ui/index.html` → HTML dashboard
9.7. **Concurrency limiting** — from `handlers.go`:
- Upload concurrency limit with `sync::Condvar` + timeout
- Download concurrency limit with proxy fallback to replicas
- HTTP 429 on timeout, 499 on client cancel
- Replication traffic bypasses upload limits
9.8. **Public port** — if configured, separate listener with read-only routes (GET/HEAD/OPTIONS only).
9.9. **Request ID middleware** — generate unique request ID per request.
9.10. **Tests:**
- Integration: start server → upload file via POST → GET it back → verify content
- Integration: upload → DELETE → GET returns 404
- Integration: conditional GET with ETag → 304
- Integration: range request → 206 with correct bytes
- Integration: exceed upload limit → 429
- Integration: whitelist enforcement
- Integration: JWT enforcement
---
### Phase 10: gRPC Service Implementation
**Goal:** All 40 gRPC methods with exact logic.
**Source files to port:**
- `weed/server/volume_grpc_admin.go` (380 lines)
- `weed/server/volume_grpc_vacuum.go` (124 lines)
- `weed/server/volume_grpc_copy.go` (636 lines)
- `weed/server/volume_grpc_copy_incremental.go` (66 lines)
- `weed/server/volume_grpc_read_write.go` (74 lines)
- `weed/server/volume_grpc_batch_delete.go` (124 lines)
- `weed/server/volume_grpc_tail.go` (140 lines)
- `weed/server/volume_grpc_erasure_coding.go` (619 lines)
- `weed/server/volume_grpc_scrub.go` (121 lines)
- `weed/server/volume_grpc_tier_upload.go` (98 lines)
- `weed/server/volume_grpc_tier_download.go` (85 lines)
- `weed/server/volume_grpc_remote.go` (95 lines)
- `weed/server/volume_grpc_query.go` (69 lines)
- `weed/server/volume_grpc_state.go` (26 lines)
- `weed/server/volume_grpc_read_all.go` (35 lines)
- `weed/server/volume_grpc_client_to_master.go` (325 lines)
**Steps (grouped by functional area):**
10.1. **Implement `tonic::Service` for `VolumeServer`** — the generated trait from proto.
10.2. **Admin RPCs** (`grpc_admin.rs`):
- `AllocateVolume` — create volume on appropriate disk location
- `VolumeMount` / `VolumeUnmount` / `VolumeDelete`
- `VolumeMarkReadonly` / `VolumeMarkWritable`
- `VolumeConfigure` — change replication
- `VolumeStatus` — return read-only, size, file counts
- `VolumeServerStatus` — disk statuses, memory, version, DC, rack
- `VolumeServerLeave` — deregister from master
- `DeleteCollection`
- `VolumeNeedleStatus` — get needle metadata by ID
- `Ping` — latency measurement
- `GetState` / `SetState` — maintenance mode
10.3. **Vacuum RPCs** (`grpc_vacuum.rs`):
- `VacuumVolumeCheck` — return garbage ratio
- `VacuumVolumeCompact` — stream progress (streaming response)
- `VacuumVolumeCommit` — finalize compaction
- `VacuumVolumeCleanup` — remove temp files
10.4. **Copy RPCs** (`grpc_copy.rs`):
- `VolumeCopy` — stream .dat/.idx from source to create local copy
- `VolumeSyncStatus` — return sync metadata
- `VolumeIncrementalCopy` — stream .dat delta since timestamp (streaming)
- `CopyFile` — generic file copy by extension (streaming)
- `ReceiveFile` — receive streamed file (client streaming)
- `ReadVolumeFileStatus` — return file timestamps and sizes
10.5. **Read/Write RPCs** (`grpc_read_write.rs`):
- `ReadNeedleBlob` — raw needle blob read
- `ReadNeedleMeta` — needle metadata
- `WriteNeedleBlob` — raw needle blob write
- `ReadAllNeedles` — stream all needles from volume(s) (streaming)
10.6. **Batch delete** (`grpc_batch_delete.rs`):
- `BatchDelete` — delete multiple file IDs, return per-ID results
10.7. **Tail RPCs** (`grpc_tail.rs`):
- `VolumeTailSender` — stream new needles since timestamp (streaming)
- `VolumeTailReceiver` — connect to another volume server and tail its changes
10.8. **Erasure coding RPCs** (`grpc_erasure_coding.rs`):
- `VolumeEcShardsGenerate` — generate EC shards from volume
- `VolumeEcShardsRebuild` — rebuild missing shards
- `VolumeEcShardsCopy` — copy shards from another server
- `VolumeEcShardsDelete` — delete EC shards
- `VolumeEcShardsMount` / `VolumeEcShardsUnmount`
- `VolumeEcShardRead` — read from EC shard (streaming)
- `VolumeEcBlobDelete` — mark blob deleted in EC volume
- `VolumeEcShardsToVolume` — reconstruct volume from EC shards
- `VolumeEcShardsInfo` — return shard metadata
10.9. **Scrub RPCs** (`grpc_scrub.rs`):
- `ScrubVolume` — integrity check volumes (INDEX / FULL / LOCAL modes)
- `ScrubEcVolume` — integrity check EC volumes
10.10. **Tier RPCs** (`grpc_tier.rs`):
- `VolumeTierMoveDatToRemote` — upload to remote backend (streaming progress)
- `VolumeTierMoveDatFromRemote` — download from remote (streaming progress)
10.11. **Remote storage** (`grpc_remote.rs`):
- `FetchAndWriteNeedle` — fetch from remote storage, write locally, replicate
10.12. **Query** (`grpc_query.rs`):
- `Query` — experimental CSV/JSON/Parquet select on stored data (streaming)
10.13. **Master heartbeat** (`grpc_client_to_master.rs`):
- `heartbeat()` background task — periodic gRPC stream to master
- Send: volume info, EC shard info, disk stats, has-no-space flags, deleted volumes
- Receive: volume size limit, leader address, metrics config
- Reconnect on failure with backoff
- `StopHeartbeat()` for graceful shutdown
10.14. **Tests:**
- Integration test per RPC: call via tonic client → verify response
- Streaming RPCs: verify all chunks received
- Error cases: invalid volume ID, non-existent volume, etc.
- Heartbeat: mock master gRPC server, verify registration
---
### Phase 11: Startup, Lifecycle & Graceful Shutdown
**Goal:** Full server startup matching Go's `runVolume()` and `startVolumeServer()`.
**Steps:**
11.1. **Startup sequence** (match `volume.go` exactly):
1. Load security configuration from `security.toml`
2. Start metrics server on metrics port
3. Parse folder/max/minFreeSpace/diskType/tags
4. Validate all directory writable
5. Resolve IP, bind IP, public URL, gRPC port
6. Create `VolumeServer` struct
7. Check with master (initial handshake)
8. Create `Store` (loads all existing volumes from disk)
9. Create security `Guard`
10. Register HTTP routes on admin mux
11. Optionally register public mux
12. Start gRPC server on gRPC port
13. Start public HTTP server (if separated)
14. Start cluster HTTP server (with optional TLS)
15. Start heartbeat background task
16. Start metrics push loop
17. Register SIGHUP handler for config reload + new volume loading
11.2. **Graceful shutdown** (match Go exactly):
1. On SIGINT/SIGTERM:
2. Stop heartbeat (notify master we're leaving)
3. Wait `preStopSeconds`
4. Stop public HTTP server
5. Stop cluster HTTP server
6. Graceful stop gRPC server
7. `volumeServer.Shutdown()` → `store.Close()` (flush all volumes)
11.3. **Reload** (SIGHUP):
- Reload security config
- Update whitelist
- Load newly appeared volumes from disk
11.4. **Tests:**
- Start server → send SIGTERM → verify clean shutdown
- Start server → SIGHUP → verify config reloaded
---
### Phase 12: Integration & Cross-Compatibility Testing
**Goal:** Rust volume server is a drop-in replacement for Go volume server.
**Steps:**
12.1. **Binary compatibility tests:**
- Create volumes with Go volume server
- Start Rust volume server on same data directory
- Read all data → verify identical
- Write new data with Rust → read with Go → verify
12.2. **API compatibility tests:**
- Run same HTTP requests against both Go and Rust servers
- Compare response bodies, headers, status codes
- Test all gRPC RPCs against both
12.3. **Master interop test:**
- Start Go master server
- Register Rust volume server
- Verify heartbeat works
- Verify volume assignment works
- Upload via filer → stored on Rust volume server → read back
12.4. **Performance benchmarks:**
- Throughput: sequential writes, sequential reads
- Latency: p50/p99 for read/write
- Concurrency: parallel reads/writes
- Compare Rust vs Go numbers
12.5. **Edge cases:**
- Volume at max size
- Disk full handling
- Corrupt .dat file recovery
- Network partition during replication
- EC shard loss + rebuild
---
## Execution Order & Dependencies
```
Phase 1 (Skeleton + CLI) ← no deps, start here
↓
Phase 2 (Storage types) ← needs Phase 1 (types used everywhere)
↓
Phase 3 (Volume struct) ← needs Phase 2
↓
Phase 4 (Store manager) ← needs Phase 3
↓
Phase 7 (Security) ← independent, can parallel with 3-4
Phase 8 (Metrics) ← independent, can parallel with 3-4
↓
Phase 9 (HTTP server) ← needs Phase 4 + 7 + 8
Phase 10 (gRPC server) ← needs Phase 4 + 7 + 8
↓
Phase 5 (Erasure coding) ← needs Phase 4, wire into Phase 10
Phase 6 (Tiered storage) ← needs Phase 4, wire into Phase 10
↓
Phase 11 (Startup + shutdown) ← needs Phase 9 + 10
↓
Phase 12 (Integration tests) ← needs all above
```
## Estimated Scope
| Phase | Estimated Rust Lines | Complexity |
|---|---|---|
| 1. Skeleton + CLI | ~400 | Low |
| 2. Storage types | ~2,000 | High (binary compat critical) |
| 3. Volume struct | ~2,500 | High |
| 4. Store manager | ~1,000 | Medium |
| 5. Erasure coding | ~3,000 | High |
| 6. Tiered storage | ~1,500 | Medium |
| 7. Security | ~500 | Medium |
| 8. Metrics | ~300 | Low |
| 9. HTTP server | ~2,000 | High |
| 10. gRPC server | ~3,500 | High |
| 11. Startup/shutdown | ~500 | Medium |
| 12. Integration tests | ~2,000 | Medium |
| **Total** | **~19,000** | |
## Critical Invariants to Preserve
1. **Binary format compatibility** — Rust must read/write `.dat`, `.idx`, `.vif`, `.ecX` files identically to Go. A single byte off = data loss.
2. **gRPC wire compatibility** — Same proto, same field semantics. Go master must talk to Rust volume server seamlessly.
3. **HTTP API compatibility** — Same URL patterns, same JSON response shapes, same headers, same status codes.
4. **Replication protocol** — Write replication between Go and Rust volume servers must work bidirectionally.
5. **Heartbeat protocol** — Rust volume server must register with Go master and maintain heartbeat.
6. **CRC32 algorithm** — Must use IEEE polynomial (same as Go's `crc32.ChecksumIEEE`).
7. **JWT compatibility** — Tokens signed by Go filer/master must be verifiable by Rust volume server and vice versa.
-7
View File
@@ -1,7 +0,0 @@
package main
import "os"
func main() {
os.Exit(Run(os.Args[1:]))
}
-7
View File
@@ -1,7 +0,0 @@
package main
import "os"
func main() {
os.Exit(Run(os.Args[1:]))
}
+1 -2
View File
@@ -1,4 +1,4 @@
FROM golang:1.25 AS builder
FROM golang:1.24 AS builder
RUN apt-get update && \
apt-get install -y build-essential wget ca-certificates && \
@@ -77,7 +77,6 @@ LABEL author="Chris Lu"
RUN apt-get update && \
apt-get install -y --no-install-recommends \
ca-certificates \
curl \
fuse \
wget && \
rm -rf /var/lib/apt/lists/*
+2 -29
View File
@@ -1,4 +1,4 @@
FROM golang:1.25-alpine AS builder
FROM golang:1.24-alpine as builder
RUN apk add git g++ fuse
RUN mkdir -p /go/src/github.com/seaweedfs/
ARG BRANCH=${BRANCH:-master}
@@ -16,42 +16,15 @@ RUN cd /go/src/github.com/seaweedfs/seaweedfs/weed \
&& export LDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=$(git rev-parse --short HEAD)" \
&& CGO_ENABLED=0 go install -tags "$TAGS" -ldflags "-extldflags -static ${LDFLAGS}"
# Rust volume server builder. Alpine packages avoid depending on the
# upstream rust:alpine manifest list, which no longer includes linux/386.
FROM alpine:3.23 as rust_builder
ARG TARGETARCH
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/seaweed-volume /build/seaweed-volume
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/weed /build/weed
WORKDIR /build/seaweed-volume
ARG TAGS
RUN if [ "$TARGETARCH" = "amd64" ] || [ "$TARGETARCH" = "arm64" ]; then \
apk add --no-cache musl-dev openssl-dev protobuf-dev git rust cargo; \
if [ "$TAGS" = "5BytesOffset" ]; then \
cargo build --release; \
else \
cargo build --release --no-default-features; \
fi && \
cp target/release/weed-volume /weed-volume; \
else \
echo "Skipping Rust build for $TARGETARCH (unsupported)" && \
touch /weed-volume; \
fi
FROM alpine AS final
LABEL author="Chris Lu"
COPY --from=builder /go/bin/weed /usr/bin/
# Copy Rust volume server binary (real binary on amd64/arm64, empty placeholder on other platforms)
COPY --from=rust_builder /weed-volume /usr/bin/weed-volume
RUN mkdir -p /etc/seaweedfs
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer.toml /etc/seaweedfs/filer.toml
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
# FIPS 140-3 mode is ON by default (Go 1.24+)
# To disable: docker run -e GODEBUG=fips140=off ...
# Install dependencies and create non-root user
RUN apk upgrade --no-cache zlib && \
apk add --no-cache fuse curl su-exec && \
RUN apk add --no-cache fuse su-exec && \
addgroup -g 1000 seaweed && \
adduser -D -u 1000 -G seaweed seaweed
+1 -2
View File
@@ -7,8 +7,7 @@ COPY ./filer.toml /etc/seaweedfs/filer.toml
COPY ./entrypoint.sh /entrypoint.sh
# Install dependencies and create non-root user
RUN apk upgrade --no-cache zlib && \
apk add --no-cache fuse curl su-exec && \
RUN apk add --no-cache fuse curl su-exec && \
addgroup -g 1000 seaweed && \
adduser -D -u 1000 -G seaweed seaweed
+2 -2
View File
@@ -1,9 +1,9 @@
FROM golang:1.25 AS builder
FROM golang:1.24 AS builder
RUN apt-get update
RUN apt-get install -y build-essential libsnappy-dev zlib1g-dev libbz2-dev libgflags-dev liblz4-dev libzstd-dev
ARG ROCKSDB_VERSION=v10.10.1
ARG ROCKSDB_VERSION=v10.5.1
ENV ROCKSDB_VERSION=${ROCKSDB_VERSION}
# build RocksDB
+3 -4
View File
@@ -1,9 +1,9 @@
FROM golang:1.25 AS builder
FROM golang:1.24 AS builder
RUN apt-get update
RUN apt-get install -y build-essential libsnappy-dev zlib1g-dev libbz2-dev libgflags-dev liblz4-dev libzstd-dev
ARG ROCKSDB_VERSION=v10.10.1
ARG ROCKSDB_VERSION=v10.5.1
ENV ROCKSDB_VERSION=${ROCKSDB_VERSION}
# build RocksDB
@@ -34,8 +34,7 @@ COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer_rocksdb.
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
# Install dependencies and create non-root user
RUN apk upgrade --no-cache zlib && \
apk add --no-cache fuse snappy gflags curl su-exec && \
RUN apk add --no-cache fuse snappy gflags su-exec && \
addgroup -g 1000 seaweed && \
adduser -D -u 1000 -G seaweed seaweed
+1 -2
View File
@@ -17,8 +17,7 @@ COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer_rocksdb.
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
# Install dependencies and create non-root user
RUN apk upgrade --no-cache zlib && \
apk add --no-cache fuse snappy gflags curl tmux su-exec && \
RUN apk add --no-cache fuse snappy gflags tmux su-exec && \
addgroup -g 1000 seaweed && \
adduser -D -u 1000 -G seaweed seaweed
@@ -25,7 +25,7 @@ services:
ports:
- "8080:8080"
- "18080:18080"
command: "volume -master=master:9333 -ip=volume1 -dir=/data -max=10"
command: "volume -mserver=master:9333 -ip=volume1 -dir=/data -max=10"
depends_on:
- master
volumes:
@@ -38,7 +38,7 @@ services:
ports:
- "8081:8080"
- "18081:18080"
command: "volume -master=master:9333 -ip=volume2 -dir=/data -max=10"
command: "volume -mserver=master:9333 -ip=volume2 -dir=/data -max=10"
depends_on:
- master
volumes:
@@ -51,7 +51,7 @@ services:
ports:
- "8082:8080"
- "18082:18080"
command: "volume -master=master:9333 -ip=volume3 -dir=/data -max=10"
command: "volume -mserver=master:9333 -ip=volume3 -dir=/data -max=10"
depends_on:
- master
volumes:
@@ -64,7 +64,7 @@ services:
ports:
- "8083:8080"
- "18083:18080"
command: "volume -master=master:9333 -ip=volume4 -dir=/data -max=10"
command: "volume -mserver=master:9333 -ip=volume4 -dir=/data -max=10"
depends_on:
- master
volumes:
@@ -77,7 +77,7 @@ services:
ports:
- "8084:8080"
- "18084:18080"
command: "volume -master=master:9333 -ip=volume5 -dir=/data -max=10"
command: "volume -mserver=master:9333 -ip=volume5 -dir=/data -max=10"
depends_on:
- master
volumes:
@@ -90,7 +90,7 @@ services:
ports:
- "8085:8080"
- "18085:18080"
command: "volume -master=master:9333 -ip=volume6 -dir=/data -max=10"
command: "volume -mserver=master:9333 -ip=volume6 -dir=/data -max=10"
depends_on:
- master
volumes:
+1 -1
View File
@@ -13,7 +13,7 @@ services:
volume:
image: chrislusf/seaweedfs:e2e
command: "-v=4 volume -master=master:9333 -ip=volume -ip.bind=0.0.0.0 -preStopSeconds=1"
command: "-v=4 volume -mserver=master:9333 -ip=volume -ip.bind=0.0.0.0 -preStopSeconds=1"
healthcheck:
test: [ "CMD", "curl", "--fail", "-I", "http://localhost:8080/healthz" ]
interval: 2s
+3 -3
View File
@@ -36,7 +36,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: 'volume -dataCenter=dc1 -rack=v1 -master="master0:9333,master1:9334,master2:9335" -port=8080 -ip=volume1 -publicUrl=localhost:8080 -preStopSeconds=1'
command: 'volume -dataCenter=dc1 -rack=v1 -mserver="master0:9333,master1:9334,master2:9335" -port=8080 -ip=volume1 -publicUrl=localhost:8080 -preStopSeconds=1'
depends_on:
- master0
- master1
@@ -46,7 +46,7 @@ services:
ports:
- 8082:8082
- 18082:18082
command: 'volume -dataCenter=dc2 -rack=v2 -master="master0:9333,master1:9334,master2:9335" -port=8082 -ip=volume2 -publicUrl=localhost:8082 -preStopSeconds=1'
command: 'volume -dataCenter=dc2 -rack=v2 -mserver="master0:9333,master1:9334,master2:9335" -port=8082 -ip=volume2 -publicUrl=localhost:8082 -preStopSeconds=1'
depends_on:
- master0
- master1
@@ -56,7 +56,7 @@ services:
ports:
- 8083:8083
- 18083:18083
command: 'volume -dataCenter=dc3 -rack=v3 -master="master0:9333,master1:9334,master2:9335" -port=8083 -ip=volume3 -publicUrl=localhost:8083 -preStopSeconds=1'
command: 'volume -dataCenter=dc3 -rack=v3 -mserver="master0:9333,master1:9334,master2:9335" -port=8083 -ip=volume3 -publicUrl=localhost:8083 -preStopSeconds=1'
depends_on:
- master0
- master1
+3 -3
View File
@@ -36,7 +36,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: 'volume -dataCenter=dc1 -rack=v1 -master="master0:9333,master1:9334,master2:9335" -port=8080 -ip=volume1 -publicUrl=localhost:8080 -preStopSeconds=1'
command: 'volume -dataCenter=dc1 -rack=v1 -mserver="master0:9333,master1:9334,master2:9335" -port=8080 -ip=volume1 -publicUrl=localhost:8080 -preStopSeconds=1'
depends_on:
- master0
- master1
@@ -46,7 +46,7 @@ services:
ports:
- 8082:8082
- 18082:18082
command: 'volume -dataCenter=dc2 -rack=v2 -master="master0:9333,master1:9334,master2:9335" -port=8082 -ip=volume2 -publicUrl=localhost:8082 -preStopSeconds=1'
command: 'volume -dataCenter=dc2 -rack=v2 -mserver="master0:9333,master1:9334,master2:9335" -port=8082 -ip=volume2 -publicUrl=localhost:8082 -preStopSeconds=1'
depends_on:
- master0
- master1
@@ -56,7 +56,7 @@ services:
ports:
- 8083:8083
- 18083:18083
command: 'volume -dataCenter=dc3 -rack=v3 -master="master0:9333,master1:9334,master2:9335" -port=8083 -ip=volume3 -publicUrl=localhost:8083 -preStopSeconds=1'
command: 'volume -dataCenter=dc3 -rack=v3 -mserver="master0:9333,master1:9334,master2:9335" -port=8083 -ip=volume3 -publicUrl=localhost:8083 -preStopSeconds=1'
depends_on:
- master0
- master1
+1 -1
View File
@@ -16,7 +16,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "-v=1 volume -master=master:9333 -port=8080 -ip=volume -preStopSeconds=1 -max=10000"
command: "-v=1 volume -mserver=master:9333 -port=8080 -ip=volume -preStopSeconds=1 -max=10000"
depends_on:
- master
volumes:
@@ -42,7 +42,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: 'volume -dataCenter=dc1 -rack=v1 -master="master0:9333,master1:9334,master2:9335" -port=8080 -ip=volume1 -publicUrl=localhost:8080 -preStopSeconds=1'
command: 'volume -dataCenter=dc1 -rack=v1 -mserver="master0:9333,master1:9334,master2:9335" -port=8080 -ip=volume1 -publicUrl=localhost:8080 -preStopSeconds=1'
depends_on:
- master0
- master1
@@ -51,7 +51,7 @@ services:
ports:
- 8082:8082
- 18082:18082
command: 'volume -dataCenter=dc2 -rack=v2 -master="master0:9333,master1:9334,master2:9335" -port=8082 -ip=volume2 -publicUrl=localhost:8082 -preStopSeconds=1'
command: 'volume -dataCenter=dc2 -rack=v2 -mserver="master0:9333,master1:9334,master2:9335" -port=8082 -ip=volume2 -publicUrl=localhost:8082 -preStopSeconds=1'
depends_on:
- master0
- master1
@@ -60,7 +60,7 @@ services:
ports:
- 8083:8083
- 18083:18083
command: 'volume -dataCenter=dc3 -rack=v3 -master="master0:9333,master1:9334,master2:9335" -port=8083 -ip=volume3 -publicUrl=localhost:8083 -preStopSeconds=1'
command: 'volume -dataCenter=dc3 -rack=v3 -mserver="master0:9333,master1:9334,master2:9335" -port=8083 -ip=volume3 -publicUrl=localhost:8083 -preStopSeconds=1'
depends_on:
- master0
- master1
+1 -1
View File
@@ -12,7 +12,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume"
command: "volume -mserver=master:9333 -port=8080 -ip=volume"
depends_on:
- master
mysql:
@@ -12,7 +12,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume -max=0 -preStopSeconds=1"
command: "volume -mserver=master:9333 -port=8080 -ip=volume -max=0 -preStopSeconds=1"
depends_on:
- master
s3:
+1 -1
View File
@@ -12,7 +12,7 @@ services:
ports:
- 7455:8080
- 9325:9325
command: 'volume -master="master:9333" -port=8080 -metricsPort=9325 -preStopSeconds=1 -publicUrl=localhost:7455'
command: 'volume -mserver="master:9333" -port=8080 -metricsPort=9325 -preStopSeconds=1 -publicUrl=localhost:7455'
depends_on:
- master
filer:
@@ -14,7 +14,7 @@ services:
- 9325:9325
volumes:
- /Volumes/mobile_disk/99:/data
command: 'volume -master="master:9333" -port=8080 -metricsPort=9325 -preStopSeconds=1 -publicUrl=localhost:7455'
command: 'volume -mserver="master:9333" -port=8080 -metricsPort=9325 -preStopSeconds=1 -publicUrl=localhost:7455'
depends_on:
- master
filer:
+1 -1
View File
@@ -12,7 +12,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume"
command: "volume -mserver=master:9333 -port=8080 -ip=volume"
depends_on:
- master
s3:
+1 -1
View File
@@ -12,7 +12,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume -max=0 -preStopSeconds=1"
command: "volume -mserver=master:9333 -port=8080 -ip=volume -max=0 -preStopSeconds=1"
depends_on:
- master
s3:
+1 -1
View File
@@ -12,7 +12,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume -preStopSeconds=1"
command: "volume -mserver=master:9333 -port=8080 -ip=volume -preStopSeconds=1"
depends_on:
- master
filer:
+2 -2
View File
@@ -15,7 +15,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume -preStopSeconds=1"
command: "volume -mserver=master:9333 -port=8080 -ip=volume -preStopSeconds=1"
depends_on:
- master
s3:
@@ -24,7 +24,7 @@ services:
- 8888:8888
- 18888:18888
- 8000:8000
command: 'filer -master="master:9333" -s3 -s3.config=/etc/seaweedfs/s3.json -s3.port=8000 -s3.allowDeleteBucketNotEmpty=false'
command: 'filer -master="master:9333" -s3 -s3.config=/etc/seaweedfs/s3.json -s3.port=8000 -s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=false'
volumes:
- ./s3.json:/etc/seaweedfs/s3.json
depends_on:
-1
View File
@@ -7,7 +7,6 @@
[master.maintenance]
# periodically run these scripts are the same as running them from 'weed shell'
# Scripts are skipped while an admin server is connected.
scripts = """
lock
ec.encode -fullPercent=95 -quietFor=1h
+1 -1
View File
@@ -71,7 +71,7 @@ services:
- net
command:
- 'volume'
- '-master=master:9333'
- '-mserver=master:9333'
- '-port=8080'
deploy:
mode: global
+1 -1
View File
@@ -17,7 +17,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: "volume -master=master:9333 -port=8080 -ip=volume -max=0 -preStopSeconds=1"
command: "volume -mserver=master:9333 -port=8080 -ip=volume -max=0 -preStopSeconds=1"
depends_on:
- master
s3:
-260
View File
@@ -1,260 +0,0 @@
#!/usr/bin/env bash
#
# Integration test: git clone & pull on a SeaweedFS FUSE mount.
#
# Verifies that the mount correctly supports git's file operations by:
# 1. Creating a bare repo on the mount (acts as a remote)
# 2. Cloning it, making commits, and pushing back to the mount
# 3. Cloning from the mount into a working directory also on the mount
# 4. Pushing additional commits to the bare repo
# 5. Checking out an older revision in the on-mount clone
# 6. Running git pull to fast-forward with real changes
# 7. Verifying file content integrity at each step
#
# Usage:
# bash test-git-on-mount.sh /path/to/mount/point
#
# The mount must already be running. All test artifacts are created under
# <mount>/git-test-<pid> and cleaned up on exit (unless TEST_KEEP=1).
#
set -euo pipefail
MOUNT_DIR="${1:?Usage: $0 <mount-dir>}"
TEST_DIR="$MOUNT_DIR/git-test-$$"
LOCAL_DIR=$(mktemp -d)
PASS=0
FAIL=0
cleanup() {
if [[ "${TEST_KEEP:-}" == "1" ]]; then
echo "TEST_KEEP=1 — leaving artifacts:"
echo " mount: $TEST_DIR"
echo " local: $LOCAL_DIR"
else
rm -rf "$TEST_DIR" 2>/dev/null || true
rm -rf "$LOCAL_DIR" 2>/dev/null || true
fi
}
trap cleanup EXIT
# --- helpers ---------------------------------------------------------------
pass() { PASS=$((PASS + 1)); echo " PASS: $1"; }
fail() { FAIL=$((FAIL + 1)); echo " FAIL: $1"; }
assert_file_contains() {
local file=$1 expected=$2 label=$3
if [[ -f "$file" ]] && grep -qF "$expected" "$file" 2>/dev/null; then
pass "$label"
else
fail "$label (expected '$expected' in $file)"
fi
}
assert_file_exists() {
local file=$1 label=$2
if [[ -f "$file" ]]; then
pass "$label"
else
fail "$label ($file not found)"
fi
}
assert_file_not_exists() {
local file=$1 label=$2
if [[ ! -f "$file" ]]; then
pass "$label"
else
fail "$label ($file should not exist)"
fi
}
assert_eq() {
local actual=$1 expected=$2 label=$3
if [[ "$actual" == "$expected" ]]; then
pass "$label"
else
fail "$label (expected '$expected', got '$actual')"
fi
}
# --- setup -----------------------------------------------------------------
echo "========================================"
echo " Git-on-mount integration test"
echo "========================================"
echo "Mount: $MOUNT_DIR"
echo "Test: $TEST_DIR"
echo "Local: $LOCAL_DIR"
echo ""
if ! mountpoint -q "$MOUNT_DIR" 2>/dev/null && [[ ! -d "$MOUNT_DIR" ]]; then
echo "ERROR: $MOUNT_DIR is not a valid directory"
exit 1
fi
mkdir -p "$TEST_DIR"
# --- Phase 1: Create bare repo on mount -----------------------------------
echo "--- Phase 1: Create bare repo on mount ---"
BARE_REPO="$TEST_DIR/repo.git"
git init --bare "$BARE_REPO" >/dev/null 2>&1
pass "bare repo created on mount"
# --- Phase 2: Clone locally, make initial commits, push -------------------
echo "--- Phase 2: Clone locally, make initial commits, push ---"
LOCAL_CLONE="$LOCAL_DIR/clone1"
git clone "$BARE_REPO" "$LOCAL_CLONE" >/dev/null 2>&1
cd "$LOCAL_CLONE"
git config user.email "test@seaweedfs.test"
git config user.name "SeaweedFS Test"
# Commit 1: initial files
echo "hello world" > README.md
mkdir -p src
echo 'package main; import "fmt"; func main() { fmt.Println("v1") }' > src/main.go
git add -A && git commit -m "initial commit" >/dev/null 2>&1
COMMIT1=$(git rev-parse HEAD)
# Commit 2: add more files
mkdir -p data
for i in $(seq 1 20); do
printf "file-%03d: %s\n" "$i" "$(head -c 64 /dev/urandom | base64)" > "data/file-$(printf '%03d' $i).txt"
done
git add -A && git commit -m "add data files" >/dev/null 2>&1
COMMIT2=$(git rev-parse HEAD)
# Commit 3: modify and add
echo 'package main; import "fmt"; func main() { fmt.Println("v2") }' > src/main.go
echo "# Updated readme" >> README.md
mkdir -p docs
echo "documentation content" > docs/guide.md
git add -A && git commit -m "update src and add docs" >/dev/null 2>&1
COMMIT3=$(git rev-parse HEAD)
git push origin master >/dev/null 2>&1 || git push origin main >/dev/null 2>&1
BRANCH=$(git rev-parse --abbrev-ref HEAD)
pass "3 commits pushed to mount bare repo (branch=$BRANCH)"
# --- Phase 3: Clone from mount bare repo to mount working dir -------------
echo "--- Phase 3: Clone from mount bare repo to on-mount working dir ---"
MOUNT_CLONE="$TEST_DIR/working"
git clone "$BARE_REPO" "$MOUNT_CLONE" >/dev/null 2>&1
# Verify clone integrity
assert_file_exists "$MOUNT_CLONE/README.md" "README.md exists after clone"
assert_file_contains "$MOUNT_CLONE/README.md" "# Updated readme" "README.md has latest content"
assert_file_contains "$MOUNT_CLONE/src/main.go" 'v2' "src/main.go has v2"
assert_file_exists "$MOUNT_CLONE/docs/guide.md" "docs/guide.md exists"
assert_file_exists "$MOUNT_CLONE/data/file-001.txt" "data files exist"
assert_file_exists "$MOUNT_CLONE/data/file-020.txt" "data/file-020.txt exists"
CLONE_HEAD=$(cd "$MOUNT_CLONE" && git rev-parse HEAD)
assert_eq "$CLONE_HEAD" "$COMMIT3" "on-mount clone HEAD matches commit 3"
# Count files
FILE_COUNT=$(find "$MOUNT_CLONE/data" -name '*.txt' | wc -l | tr -d ' ')
assert_eq "$FILE_COUNT" "20" "data/ has 20 files"
# --- Phase 4: Push more commits from local clone --------------------------
echo "--- Phase 4: Push more commits from local clone ---"
cd "$LOCAL_CLONE"
# Commit 4: larger changes
for i in $(seq 21 50); do
printf "file-%03d: %s\n" "$i" "$(head -c 128 /dev/urandom | base64)" > "data/file-$(printf '%03d' $i).txt"
done
echo 'package main; import "fmt"; func main() { fmt.Println("v3") }' > src/main.go
git add -A && git commit -m "expand data and update to v3" >/dev/null 2>&1
COMMIT4=$(git rev-parse HEAD)
# Commit 5: rename and delete
git mv docs/guide.md docs/manual.md
git rm data/file-001.txt >/dev/null 2>&1
git commit -m "rename guide, remove file-001" >/dev/null 2>&1
COMMIT5=$(git rev-parse HEAD)
git push origin "$BRANCH" >/dev/null 2>&1
pass "2 more commits pushed (5 total)"
# --- Phase 5: Checkout older revision in on-mount clone -------------------
echo "--- Phase 5: Checkout older revision in on-mount clone ---"
cd "$MOUNT_CLONE"
git checkout "$COMMIT2" >/dev/null 2>&1
# Verify we're at commit 2 state
DETACHED_HEAD=$(git rev-parse HEAD)
assert_eq "$DETACHED_HEAD" "$COMMIT2" "on-mount clone at commit 2 (detached)"
assert_file_not_exists "$MOUNT_CLONE/docs/guide.md" "docs/guide.md not in commit 2"
assert_file_contains "$MOUNT_CLONE/src/main.go" 'v1' "src/main.go has v1 at commit 2"
# --- Phase 6: Return to branch and pull -----------------------------------
echo "--- Phase 6: Return to branch and pull with real changes ---"
cd "$MOUNT_CLONE"
git checkout "$BRANCH" >/dev/null 2>&1
# At this point the on-mount clone is at commit 3, remote is at commit 5
OLD_HEAD=$(git rev-parse HEAD)
assert_eq "$OLD_HEAD" "$COMMIT3" "on-mount clone at commit 3 before pull"
git pull >/dev/null 2>&1
NEW_HEAD=$(git rev-parse HEAD)
assert_eq "$NEW_HEAD" "$COMMIT5" "HEAD matches commit 5 after pull"
# Verify commit 5 state
assert_file_contains "$MOUNT_CLONE/src/main.go" 'v3' "src/main.go has v3 after pull"
assert_file_exists "$MOUNT_CLONE/docs/manual.md" "docs/manual.md exists (renamed)"
assert_file_not_exists "$MOUNT_CLONE/docs/guide.md" "docs/guide.md gone (renamed)"
assert_file_not_exists "$MOUNT_CLONE/data/file-001.txt" "data/file-001.txt removed"
assert_file_exists "$MOUNT_CLONE/data/file-050.txt" "data/file-050.txt exists"
FINAL_COUNT=$(find "$MOUNT_CLONE/data" -name '*.txt' | wc -l | tr -d ' ')
assert_eq "$FINAL_COUNT" "49" "data/ has 49 files (50 added, 1 removed)"
# --- Phase 7: Verify git log integrity -----------------------------------
echo "--- Phase 7: Verify git log integrity ---"
cd "$MOUNT_CLONE"
GIT_LOG=$(git log --format=%s)
LOG_COUNT=$(echo "$GIT_LOG" | wc -l | tr -d ' ')
assert_eq "$LOG_COUNT" "5" "git log shows 5 commits"
# Verify commit messages
echo "$GIT_LOG" | grep -qF "initial commit" && pass "commit 1 message in log" || fail "commit 1 message missing"
echo "$GIT_LOG" | grep -qF "expand data" && pass "commit 4 message in log" || fail "commit 4 message missing"
echo "$GIT_LOG" | grep -qF "rename guide" && pass "commit 5 message in log" || fail "commit 5 message missing"
# --- Phase 8: Verify git status is clean ----------------------------------
echo "--- Phase 8: Verify git status is clean ---"
cd "$MOUNT_CLONE"
STATUS=$(git status --porcelain)
if [[ -z "$STATUS" ]]; then
pass "git status is clean"
else
fail "git status has changes: $STATUS"
fi
# --- Results ---------------------------------------------------------------
echo ""
echo "========================================"
echo " Results: $PASS passed, $FAIL failed"
echo "========================================"
if [[ "$FAIL" -gt 0 ]]; then
exit 1
fi
+1 -1
View File
@@ -15,7 +15,7 @@ services:
s3:
image: chrislusf/seaweedfs:local
command: "server -ip=127.0.0.1 -filer -master.volumeSizeLimitMB=16 -volume.max=0 -volume -volume.preStopSeconds=1 -s3 -s3.config=/etc/seaweedfs/s3.json -s3.port=8000 -s3.allowDeleteBucketNotEmpty=false"
command: "server -ip=127.0.0.1 -filer -master.volumeSizeLimitMB=16 -volume.max=0 -volume -volume.preStopSeconds=1 -s3 -s3.config=/etc/seaweedfs/s3.json -s3.port=8000 -s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=false"
volumes:
- ./s3.json:/etc/seaweedfs/s3.json
environment:
+1 -1
View File
@@ -20,7 +20,7 @@ services:
- 8888:8888
- 8000:8000
- 18888:18888
command: "server -ip=s3 -filer -master.volumeSizeLimitMB=16 -volume.max=0 -volume -volume.preStopSeconds=1 -s3 -s3.config=/etc/seaweedfs/s3.json -s3.port=8000 -s3.allowDeleteBucketNotEmpty=false"
command: "server -ip=s3 -filer -master.volumeSizeLimitMB=16 -volume.max=0 -volume -volume.preStopSeconds=1 -s3 -s3.config=/etc/seaweedfs/s3.json -s3.port=8000 -s3.allowEmptyFolder=false -s3.allowDeleteBucketNotEmpty=false"
volumes:
- ./s3.json:/etc/seaweedfs/s3.json
environment:
+5 -27
View File
@@ -1,9 +1,5 @@
#!/bin/sh
# Enable FIPS 140-3 mode by default (Go 1.24+)
# To disable: docker run -e GODEBUG=fips140=off ...
export GODEBUG="${GODEBUG:+$GODEBUG,}fips140=on"
# Fix permissions for mounted volumes
# If /data is mounted from host, it might have different ownership
# Fix this by ensuring seaweed user owns the directory
@@ -20,17 +16,13 @@ if [ "$(id -u)" = "0" ]; then
DATA_UID=$(stat -c '%u' /data 2>/dev/null)
DATA_GID=$(stat -c '%g' /data 2>/dev/null)
# Only run chown -R if ownership doesn't already match (avoids expensive
# recursive chown on subsequent starts, and is a no-op on OpenShift when
# fsGroup has already set correct ownership on the PVC).
if [ "$DATA_UID" != "$SEAWEED_UID" ] || [ "$DATA_GID" != "$SEAWEED_GID" ]; then
# Only run chown -R if ownership doesn't match (much faster for subsequent starts)
echo "Fixing /data ownership for seaweed user (uid=$SEAWEED_UID, gid=$SEAWEED_GID)"
if ! chown -R seaweed:seaweed /data; then
echo "Warning: Failed to change ownership of /data. This may cause permission errors." >&2
echo "If /data is read-only or has mount issues, the application may fail to start." >&2
fi
fi
# Use su-exec to drop privileges and run as seaweed user
exec su-exec seaweed "$0" "$@"
@@ -58,7 +50,7 @@ isArgPassed() {
case "$1" in
'master')
ARGS="-mdir=/data -volumeSizeLimitMB=1024"
ARGS="-mdir=/data -volumePreallocate -volumeSizeLimitMB=1024"
shift
exec /usr/bin/weed -logtostderr=true master $ARGS $@
;;
@@ -72,24 +64,10 @@ case "$1" in
exec /usr/bin/weed -logtostderr=true volume $ARGS $@
;;
'volume-rust')
ARGS="-dir /data -max 0"
if isArgPassed "-max" "$@"; then
ARGS="-dir /data"
fi
shift
if [ ! -s /usr/bin/weed-volume ]; then
echo "Error: Rust volume server is not available on this platform ($(uname -m))." >&2
echo "Use 'volume' for the Go volume server instead." >&2
exit 1
fi
exec /usr/bin/weed-volume $ARGS $@
;;
'server')
ARGS="-dir=/data -volume.max=0 -master.volumeSizeLimitMB=1024"
ARGS="-dir=/data -volume.max=0 -master.volumePreallocate -master.volumeSizeLimitMB=1024"
if isArgPassed "-volume.max" "$@"; then
ARGS="-dir=/data -master.volumeSizeLimitMB=1024"
ARGS="-dir=/data -master.volumePreallocate -master.volumeSizeLimitMB=1024"
fi
shift
exec /usr/bin/weed -logtostderr=true server $ARGS $@
+3 -3
View File
@@ -33,7 +33,7 @@ isArgPassed() {
case "$1" in
'master')
ARGS="-mdir=/data -volumeSizeLimitMB=1024"
ARGS="-mdir=/data -volumePreallocate -volumeSizeLimitMB=1024"
shift
exec /usr/bin/weed -logtostderr=true master $ARGS "$@"
;;
@@ -48,9 +48,9 @@ case "$1" in
;;
'server')
ARGS="-dir=/data -volume.max=0 -master.volumeSizeLimitMB=1024"
ARGS="-dir=/data -volume.max=0 -master.volumePreallocate -master.volumeSizeLimitMB=1024"
if isArgPassed "-volume.max" "$@"; then
ARGS="-dir=/data -master.volumeSizeLimitMB=1024"
ARGS="-dir=/data -master.volumePreallocate -master.volumeSizeLimitMB=1024"
fi
shift
exec /usr/bin/weed -logtostderr=true server $ARGS "$@"
+1 -1
View File
@@ -14,7 +14,7 @@ services:
- 8080:8080
- 18080:18080
- 9325:9325
command: 'volume -ip=volume -master="master:9333" -ip.bind=0.0.0.0 -port=8080 -metricsPort=9325'
command: 'volume -ip=volume -mserver="master:9333" -ip.bind=0.0.0.0 -port=8080 -metricsPort=9325'
depends_on:
- master
filer:
+1 -10
View File
@@ -12,7 +12,7 @@ services:
ports:
- 8080:8080
- 18080:18080
command: 'volume -ip=volume -master="master:9333" -ip.bind=0.0.0.0 -port=8080'
command: 'volume -ip=volume -mserver="master:9333" -ip.bind=0.0.0.0 -port=8080'
depends_on:
- master
filer:
@@ -42,12 +42,3 @@ services:
- master
- volume
- filer
admin:
image: chrislusf/seaweedfs:dev # use a remote dev image
ports:
- 23646:23646
command: 'admin -master=master:9333'
depends_on:
- master
- volume
- filer

Some files were not shown because too many files have changed in this diff Show More