Compare commits

..
1 Commits
Author SHA1 Message Date
chrislu 4f15a52044 temp disable locking 2022-12-05 20:20:44 -08:00
3875 changed files with 52554 additions and 945127 deletions
-22
View File
@@ -1,22 +0,0 @@
[codespell]
# Ref: https://github.com/codespell-project/codespell#using-a-config-file
skip = .git,.git-meta,.gitignore,.gitattributes,*.svg,go.sum,vendor,*.lock,*.css,*.min.*,.codespellrc,*_templ.go
check-hidden = true
# Ignore camelCase and PascalCase identifiers (very common in Go/Rust/JS
# source, e.g. allLocations, publishErr, ReadInside, FlushInterval).
ignore-regex = \b[a-z]+[A-Z]\w*\b|\b[A-Z][a-z]+[A-Z]\w*\b
# visibles: variable name for VisibleInterval collections in filer/mount code
# fo: `*FilerOptions` receiver name (e.g. `func (fo *FilerOptions) ...`)
# te: "truncate error" local variable (e.g. `if te := w.Truncate(end); te != nil`)
# ser: Rust serde serializer variable (`serde_json::ser`, `let mut ser = ...`)
# bject: intentional wildcard test data (e.g. `s3:Get?bject` matching `s3:GetObject`)
# unparseable: accepted alternate spelling used throughout the codebase
# keep-alives: correct plural of the technical term (SSH/HTTP keep-alive)
# tread: valid English word in the idiom "tread carefully" (help text)
# anc: variable abbreviation for "ancestor" in tree/path tests
# ue: appears inside JSON test fixtures with embedded escaped quotes (Bl\"ue)
# auther: local variable meaning "authenticator" (tls.go: `auther := Authenticator{}`)
# thirdparty: literal Maven groupId `org.apache.hadoop.thirdparty` (external, cannot rename)
# unknwon: GitHub username / Go module path (`github.com/unknwon/goconfig`)
# atleast: CLI mode literal string in test/benchmark/fuse_db/bin/sqlite_verify.py
ignore-words-list = visibles,fo,te,ser,bject,unparseable,keep-alives,tread,anc,ue,auther,thirdparty,unknwon,atleast
@@ -1,66 +0,0 @@
name: Fix fusermount3 setuid
description: >
Make sure the fusermount3 an unprivileged mount will find can actually mount.
Some runner images carry a second, source-built fusermount3 in /usr/local/bin
that shadows the distro one in PATH; it is neither setuid nor root-owned, so
every mount fails with "mount failed: Operation not permitted". Both the Go
mount and sw-fuse resolve the helper through PATH.
Run it after the step that apt-installs fuse3.
runs:
using: composite
steps:
- name: Point PATH at a fusermount3 that can mount
shell: bash
run: |
set -euo pipefail
# setuid only grants root when root owns the file, and exec follows
# symlinks, so judge the target.
can_mount() {
[ -u "$1" ] && [ "$(stat -Lc %u "$1")" = 0 ]
}
bin=$(command -v fusermount3 || true)
if [ -z "$bin" ]; then
echo "no fusermount3 in PATH" >&2
exit 1
fi
if can_mount "$bin"; then
ls -l "$bin"
exit 0
fi
echo "$bin cannot mount unprivileged:"
ls -l "$bin"
# The distro fusermount3 is setuid root and is the one meant to be used.
# Reach it through a symlink earlier in PATH: exec resolves the link, so
# the target keeps its setuid bit, and nothing on the image is modified.
for distro in /usr/bin/fusermount3 /bin/fusermount3; do
if [ "$distro" != "$bin" ] && can_mount "$distro"; then
mkdir -p "$RUNNER_TEMP/fuse-bin"
ln -sf "$distro" "$RUNNER_TEMP/fuse-bin/fusermount3"
echo "$RUNNER_TEMP/fuse-bin" >> "$GITHUB_PATH"
echo "using $distro instead"
ls -l "$distro"
exit 0
fi
done
# No usable distro binary, so setting the bit is the only way out - but
# the target came from PATH: do that only for a root-owned system binary,
# never for anything else that happens to sit there.
case "$bin" in
/bin/*|/sbin/*|/usr/bin/*|/usr/sbin/*|/usr/local/bin/*|/usr/local/sbin/*) ;;
*) echo "refusing to setuid $bin: outside the system bin paths" >&2; exit 1 ;;
esac
if [ -L "$bin" ] || [ ! -f "$bin" ] || [ ! -x "$bin" ]; then
echo "refusing to setuid $bin: not a regular executable file" >&2
exit 1
fi
if [ "$(stat -c %u "$bin")" != 0 ] || [ "$(stat -c %g "$bin")" != 0 ]; then
echo "refusing to setuid $bin: not owned by root:root" >&2
exit 1
fi
sudo chmod u+s "$bin"
ls -l "$bin"
+1 -5
View File
@@ -5,6 +5,7 @@
# How are we solving the problem?
# How is the PR tested?
@@ -12,8 +13,3 @@
# Checks
- [ ] I have added unit tests if possible.
- [ ] I will add related wiki document changes and link to this PR after merging.
- [ ] All AI code review comments have been addressed. No more comments to fix if reviewed again. Reviewer may request additional gemini and copilot reviews.
# Checks for AI generated PRs
- [ ] I have reviewed every line of code.
- [ ] The PR is kept as minimum as possible. Large PRs would not be accepted.
+10 -20
View File
@@ -3,15 +3,6 @@ name: "go: build dev binaries"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/binaries_dev.yml'
concurrency:
group: binaries-dev-${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
@@ -27,7 +18,6 @@ jobs:
- name: Delete old release assets
uses: mknejp/delete-release-assets@v1
continue-on-error: true
with:
token: ${{ github.token }}
tag: dev
@@ -48,13 +38,13 @@ jobs:
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Set BUILD_TIME env
run: echo BUILD_TIME=$(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@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -63,14 +53,14 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed-large-disk
asset_name: "weed-large-disk-${{ 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@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -78,7 +68,7 @@ jobs:
release_tag: dev
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed-normal-disk
@@ -97,13 +87,13 @@ jobs:
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Set BUILD_TIME env
run: echo BUILD_TIME=$(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@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -112,14 +102,14 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed-large-disk
asset_name: "weed-large-disk-${{ 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@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -127,7 +117,7 @@ jobs:
release_tag: dev
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed-normal-disk
+5 -5
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@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -38,13 +38,13 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
# build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -52,7 +52,7 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
+5 -5
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@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -38,13 +38,13 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
# build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -52,7 +52,7 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
+5 -5
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@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -38,13 +38,13 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
# build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -52,7 +52,7 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
+5 -5
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@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -38,13 +38,13 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
# build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
@@ -52,7 +52,7 @@ jobs:
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
+7 -7
View File
@@ -28,32 +28,32 @@ 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@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
goarch: ${{ matrix.goarch }}
overwrite: true
build_flags: -tags elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
build_flags: -tags elastic,ydb,gocdk,tikv
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
# build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}_full"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
uses: wangyoucao577/go-release-action@90da8ebfdc010a0e7d378419a76fd90230a05228 # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
goarch: ${{ matrix.goarch }}
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
build_flags: -tags 5BytesOffset,elastic,ydb,gocdk,tikv
ldflags: -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
-59
View File
@@ -1,59 +0,0 @@
# This is a basic workflow to help you get started with Actions
name: "go: build versioned binaries for openbsd"
on:
push:
tags:
- '*'
# Allows you to run this workflow manually from the Actions tab
workflow_dispatch:
# A workflow run is made up of one or more jobs that can run sequentially or in parallel
permissions:
contents: read
jobs:
build-release-binaries_openbsd:
permissions:
contents: write # for wangyoucao577/go-release-action to upload release assets
runs-on: ubuntu-latest
strategy:
matrix:
goos: [openbsd]
goarch: [amd64, arm, arm64]
# 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@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- name: Go Release Binaries Normal Volume Size
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
goarch: ${{ matrix.goarch }}
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
# build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}"
- name: Go Release Large Disk Binaries
uses: wangyoucao577/go-release-action@279495102627de7960cbc33434ab01a12bae144b # v1.22
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
goos: ${{ matrix.goos }}
goarch: ${{ matrix.goarch }}
overwrite: true
pre_command: export CGO_ENABLED=0 && export GODEBUG=http2client=0
build_flags: -tags 5BytesOffset # optional, default is
ldflags: -s -w -extldflags -static -X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${{github.sha}}
# Where to run `go build .`
project_path: weed
binary_name: weed
asset_name: "${{ matrix.goos }}_${{ matrix.goarch }}_large_disk"
+4 -9
View File
@@ -2,11 +2,6 @@ name: "Code Scanning - Action"
on:
pull_request:
paths:
- '**/*.go'
- 'go.mod'
- 'go.sum'
- '.github/workflows/codeql.yml'
concurrency:
group: ${{ github.head_ref }}/codeql
@@ -23,11 +18,11 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8
# Initializes the CodeQL tools for scanning.
- name: Initialize CodeQL
uses: github/codeql-action/init@v4.37.6
uses: github/codeql-action/init@v2
# Override language selection by uncommenting this and choosing your languages
with:
languages: go
@@ -35,7 +30,7 @@ jobs:
# Autobuild attempts to build any compiled languages (C/C++, C#, or Java).
# If this step fails, then you should remove it and run the build manually (see below).
- name: Autobuild
uses: github/codeql-action/autobuild@v4.37.6
uses: github/codeql-action/autobuild@v2
# ℹ️ Command-line programs to run using the OS shell.
# 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
@@ -49,4 +44,4 @@ jobs:
# make release
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v4.37.6
uses: github/codeql-action/analyze@v2
-23
View File
@@ -1,23 +0,0 @@
# Codespell configuration is within .codespellrc
---
name: Codespell
on:
push:
branches: [master]
pull_request:
branches: [master]
permissions:
contents: read
jobs:
codespell:
name: Check for spelling errors
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v7
- name: Codespell
uses: codespell-project/actions-codespell@8f01853be192eb0f849a5c7d721450e7a467c579 # v2.2
+22 -112
View File
@@ -3,106 +3,24 @@ name: "docker: build dev containers"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'seaweed-volume/**'
- 'docker/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/container_dev.yml'
workflow_dispatch: {}
permissions:
contents: read
jobs:
# ── Pre-build Rust volume server binaries natively ──────────────────
build-rust-binaries:
runs-on: ubuntu-22.04
strategy:
matrix:
include:
- target: x86_64-unknown-linux-musl
arch: amd64
- target: aarch64-unknown-linux-musl
arch: arm64
cross: true
steps:
- name: Checkout
uses: actions/checkout@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Install musl tools (amd64)
if: ${{ !matrix.cross }}
run: sudo apt-get install -y musl-tools
- name: Install cross-compilation tools (arm64)
if: matrix.cross
run: |
sudo apt-get install -y gcc-aarch64-linux-gnu
echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
# Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-docker-dev-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-docker-dev-${{ matrix.target }}-
- name: Build normal variant
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features
cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
- name: Upload artifacts
uses: actions/upload-artifact@v7
with:
name: rust-volume-${{ matrix.arch }}
path: weed-volume-normal-${{ matrix.arch }}
build-dev-containers:
needs: [build-rust-binaries]
runs-on: [ubuntu-latest]
steps:
- name: Checkout
uses: actions/checkout@v7
- name: Download pre-built Rust binaries
uses: actions/download-artifact@v8
with:
pattern: rust-volume-*
merge-multiple: true
path: ./rust-bins
- name: Place Rust binaries in Docker context
run: |
mkdir -p docker/weed-volume-prebuilt
for arch in amd64 arm64; do
src="./rust-bins/weed-volume-normal-${arch}"
if [ -f "$src" ]; then
cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
echo "Placed pre-built Rust binary for ${arch}"
fi
done
ls -la docker/weed-volume-prebuilt/
- name: Docker meta
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
with:
images: |
chrislusf/seaweedfs
@@ -113,40 +31,32 @@ jobs:
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
uses: docker/setup-qemu-action@v4.2.0
- 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@v4
-
name: Set up QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
with:
buildkitd-flags: "--debug"
buildkitd-config: /tmp/buildkitd.toml
- name: Login to Docker Hub
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4.6.0
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
-
name: Login to GHCR
if: github.event_name != 'pull_request'
uses: docker/login-action@v4.6.0
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Build
uses: docker/build-push-action@v7
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
@@ -1,173 +0,0 @@
name: "docker: build foundationdb image by version"
on:
pull_request:
branches: [ master, main ]
paths:
- 'weed/filer/foundationdb/**'
- 'test/foundationdb/**'
- 'docker/Dockerfile.foundationdb_large'
- 'docker/filer_foundationdb.toml'
- '.github/workflows/container_foundationdb_version.yml'
workflow_dispatch:
inputs:
fdb_version:
description: 'FoundationDB version to build (e.g. 7.4.5)'
required: true
default: '7.4.5'
seaweedfs_ref:
description: 'SeaweedFS git tag, branch, or commit to build'
required: true
default: 'master'
image_tag:
description: 'Optional Docker tag suffix (defaults to foundationdb_<fdb>_seaweedfs_<ref>)'
required: false
default: ''
permissions:
contents: read
jobs:
build-foundationdb-image:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v7
with:
fetch-depth: 0
- name: Install FoundationDB client libraries
run: |
set -euo pipefail
sudo apt-get update
sudo apt-get install -y ca-certificates wget
FDB_VERSION="${{ inputs.fdb_version || '7.4.5' }}"
case "${FDB_VERSION}_amd64" in
"7.4.5_amd64") EXPECTED_SHA256="eea6b98cf386a0848655b2e196d18633662a7440a7ee061c10e32153c7e7e112" ;;
"7.3.43_amd64") EXPECTED_SHA256="c3fa0a59c7355b914a1455dac909238d5ea3b6c6bc7b530af8597e6487c1651a" ;;
*)
echo "Unsupported FoundationDB version ${FDB_VERSION} for CI client install" >&2
exit 1 ;;
esac
PACKAGE="foundationdb-clients_${FDB_VERSION}-1_amd64.deb"
wget --timeout=30 --tries=3 -O "${PACKAGE}" "https://github.com/apple/foundationdb/releases/download/${FDB_VERSION}/${PACKAGE}"
echo "${EXPECTED_SHA256} ${PACKAGE}" | sha256sum -c -
sudo dpkg -i "${PACKAGE}"
rm "${PACKAGE}"
sudo ldconfig
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: go.mod
- name: Run FoundationDB tagged tests
env:
CGO_ENABLED: 1
run: |
go test ./weed/filer/foundationdb -tags foundationdb -count=1
- name: Prepare Docker tag
id: tag
env:
FDB_VERSION_INPUT: ${{ inputs.fdb_version }}
SEAWEEDFS_REF_INPUT: ${{ inputs.seaweedfs_ref }}
CUSTOM_TAG_INPUT: ${{ inputs.image_tag }}
EVENT_NAME: ${{ github.event_name }}
HEAD_REF: ${{ github.head_ref }}
REF_NAME: ${{ github.ref_name }}
run: |
set -euo pipefail
sanitize() {
local value="$1"
value="${value,,}"
value="${value// /-}"
value="${value//[^a-z0-9_.-]/-}"
value="${value#-}"
value="${value%-}"
printf '%s' "$value"
}
version="${FDB_VERSION_INPUT}"
seaweed="${SEAWEEDFS_REF_INPUT}"
tag="${CUSTOM_TAG_INPUT}"
# Use defaults for PR builds
if [ -z "$version" ]; then
version="7.4.5"
fi
if [ -z "$seaweed" ]; then
if [ "$EVENT_NAME" = "pull_request" ]; then
seaweed="${HEAD_REF}"
else
seaweed="${REF_NAME}"
fi
fi
sanitized_version="$(sanitize "$version")"
if [ -z "$sanitized_version" ]; then
echo "Unable to sanitize FoundationDB version '$version'." >&2
exit 1
fi
sanitized_seaweed="$(sanitize "$seaweed")"
if [ -z "$sanitized_seaweed" ]; then
echo "Unable to sanitize SeaweedFS ref '$seaweed'." >&2
exit 1
fi
if [ -z "$tag" ]; then
tag="foundationdb_${sanitized_version}_seaweedfs_${sanitized_seaweed}"
else
tag="$(sanitize "$tag")"
fi
if [ -z "$tag" ]; then
echo "Resulting Docker tag is empty." >&2
exit 1
fi
echo "docker_tag=$tag" >> "$GITHUB_OUTPUT"
echo "full_image=chrislusf/seaweedfs:$tag" >> "$GITHUB_OUTPUT"
echo "seaweedfs_ref=$seaweed" >> "$GITHUB_OUTPUT"
- name: Set up QEMU
uses: docker/setup-qemu-action@v4.2.0
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4.6.0
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Determine branch to build
id: branch
env:
INPUT_REF: ${{ inputs.seaweedfs_ref }}
HEAD_REF: ${{ github.head_ref }}
REF_NAME: ${{ github.ref_name }}
run: |
if [ -n "$INPUT_REF" ]; then
echo "branch=$INPUT_REF" >> "$GITHUB_OUTPUT"
elif [ "${{ github.event_name }}" = "pull_request" ]; then
echo "branch=$HEAD_REF" >> "$GITHUB_OUTPUT"
else
echo "branch=$REF_NAME" >> "$GITHUB_OUTPUT"
fi
- name: Build and push image
uses: docker/build-push-action@v7
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.foundationdb_large
build-args: |
FDB_VERSION=${{ inputs.fdb_version || '7.4.5' }}
BRANCH=${{ steps.branch.outputs.branch }}
# Note: ARM64 support requires FoundationDB ARM64 packages which are not available for all versions
# Currently only building for amd64. To enable ARM64, verify package availability and add checksums.
platforms: linux/amd64
tags: ${{ steps.tag.outputs.full_image || 'seaweedfs:foundationdb-test' }}
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
+34 -473
View File
@@ -1,506 +1,67 @@
name: "docker: build latest container"
# Manual fallback only. On tag push, container_release_unified.yml already
# re-tags the released versioned image as `latest` / `latest_large_disk`,
# so a full rebuild here is unnecessary. Run this manually if you need to
# rebuild `latest` from an arbitrary ref.
on:
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
push:
tags:
- '*'
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
# ── Pre-build Rust volume server binaries natively ──────────────────
build-rust-binaries:
runs-on: ubuntu-22.04
strategy:
matrix:
include:
- target: x86_64-unknown-linux-musl
arch: amd64
- target: aarch64-unknown-linux-musl
arch: arm64
cross: true
steps:
- name: Checkout
uses: actions/checkout@v7
with:
ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Install musl tools (amd64)
if: ${{ !matrix.cross }}
run: sudo apt-get install -y musl-tools
- name: Install cross-compilation tools (arm64)
if: matrix.cross
run: |
sudo apt-get install -y gcc-aarch64-linux-gnu
echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
# Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-docker-${{ matrix.target }}-
- name: Build large-disk variant
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }}
cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-large-disk-${{ matrix.arch }}
- name: Build normal variant
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features
cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
- name: Upload artifacts
uses: actions/upload-artifact@v7
with:
name: rust-volume-${{ matrix.arch }}
path: |
weed-volume-large-disk-${{ matrix.arch }}
weed-volume-normal-${{ matrix.arch }}
build:
needs: [setup, build-rust-binaries]
runs-on: ubuntu-latest
strategy:
matrix:
platform: [amd64, arm64, arm, 386]
variant: ${{ fromJSON(needs.setup.outputs.variants) }}
build-latest-container:
runs-on: [ubuntu-latest]
steps:
- name: Checkout
uses: actions/checkout@v7
with:
ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
- name: Free Disk Space
run: |
echo "Available disk space before cleanup:"
df -h
# Remove pre-installed tools
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
# Clean package managers
sudo apt-get clean
sudo rm -rf /var/lib/apt/lists/*
# Clean Docker aggressively
sudo docker system prune -af --volumes
# Clean Go cache if it exists
[ -d ~/.cache/go-build ] && rm -rf ~/.cache/go-build || true
[ -d /go/pkg ] && rm -rf /go/pkg || true
echo "Available disk space after cleanup:"
df -h
- name: Configure variant
id: config
run: |
if [ "${{ matrix.variant }}" == "large_disk" ]; then
echo "tag_suffix=_large_disk" >> $GITHUB_OUTPUT
echo "build_args=TAGS=5BytesOffset" >> $GITHUB_OUTPUT
echo "rust_variant=large-disk" >> $GITHUB_OUTPUT
else
echo "tag_suffix=" >> $GITHUB_OUTPUT
echo "build_args=" >> $GITHUB_OUTPUT
echo "rust_variant=normal" >> $GITHUB_OUTPUT
fi
- name: Download pre-built Rust binaries
uses: actions/download-artifact@v8
with:
pattern: rust-volume-*
merge-multiple: true
path: ./rust-bins
- name: Place Rust binaries in Docker context
run: |
mkdir -p docker/weed-volume-prebuilt
for arch in amd64 arm64; do
src="./rust-bins/weed-volume-${{ steps.config.outputs.rust_variant }}-${arch}"
if [ -f "$src" ]; then
cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
echo "Placed pre-built Rust binary for ${arch}"
fi
done
ls -la docker/weed-volume-prebuilt/
- name: Docker meta
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
with:
images: |
chrislusf/seaweedfs
ghcr.io/chrislusf/seaweedfs
tags: type=raw,value=${{ 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@v4.2.0
- 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@v4
-
name: Set up QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
with:
buildkitd-flags: "--debug"
buildkitd-config: /tmp/buildkitd.toml
- name: Login to Docker Hub
if: needs.setup.outputs.publish == 'true'
uses: docker/login-action@v4.6.0
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
if: needs.setup.outputs.publish == 'true'
uses: docker/login-action@v4.6.0
-
name: Login to GHCR
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Build ${{ matrix.platform }} ${{ matrix.variant }}
uses: docker/build-push-action@v7
env:
DOCKER_BUILDKIT: 1
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
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 }}
platforms: linux/amd64, linux/arm, linux/arm64, linux/386
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
cache-from: type=gha,scope=${{ matrix.variant }}-${{ matrix.platform }}
cache-to: type=gha,mode=max,scope=${{ matrix.variant }}-${{ matrix.platform }}
build-args: |
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.sha }}
${{ steps.config.outputs.build_args }}
- 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*
trivy-scan:
runs-on: ubuntu-latest
needs: [setup, build, build-rust-binaries]
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@v4.6.0
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@v7
with:
ref: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.source_ref || github.ref }}
- name: Download pre-built Rust binaries for local scan
if: needs.setup.outputs.publish != 'true'
uses: actions/download-artifact@v8
with:
pattern: rust-volume-*
merge-multiple: true
path: ./rust-bins
- name: Place Rust binaries in Docker context for local scan
if: needs.setup.outputs.publish != 'true'
run: |
rust_variant="normal"
if [ "${{ matrix.variant }}" == "large_disk" ]; then
rust_variant="large-disk"
fi
mkdir -p docker/weed-volume-prebuilt
for arch in amd64 arm64; do
src="./rust-bins/weed-volume-${rust_variant}-${arch}"
if [ -f "$src" ]; then
cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
echo "Placed pre-built Rust binary for ${arch}"
fi
done
ls -la docker/weed-volume-prebuilt/
- name: Create BuildKit config for local scan build
if: needs.setup.outputs.publish != 'true'
run: |
cat > /tmp/buildkitd.toml <<EOF
[registry."docker.io"]
mirrors = ["https://mirror.gcr.io"]
EOF
- name: Set up Docker Buildx for local scan build
if: needs.setup.outputs.publish != 'true'
uses: docker/setup-buildx-action@v4
with:
buildkitd-flags: "--debug"
buildkitd-config: /tmp/buildkitd.toml
- name: Build local scan image tarball
if: needs.setup.outputs.publish != 'true'
uses: docker/build-push-action@v7
env:
DOCKER_BUILDKIT: 1
with:
context: ./docker
file: ./docker/Dockerfile.go_build
platforms: linux/amd64
outputs: type=docker,dest=/tmp/seaweedfs${{ 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 }}
${{ matrix.variant == 'large_disk' && 'TAGS=5BytesOffset' || '' }}
- name: Trivy report (published image)
if: needs.setup.outputs.publish == 'true'
# Pin to SHA - mutable tags were compromised (GHSA-69fq-xp46-6x23)
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
with:
scan-type: image
# Scan amd64 only - OS packages are identical across architectures
# since they all use the same alpine base, so a single-arch scan
# provides sufficient coverage without multiplying CI time.
image-ref: ghcr.io/chrislusf/seaweedfs:${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }}${{ steps.config.outputs.tag_suffix }}-amd64
scanners: vuln
vuln-type: os,library
severity: HIGH,CRITICAL
ignore-unfixed: true
limit-severities-for-sarif: true
format: sarif
output: trivy-results.sarif
exit-code: '0'
- name: Trivy report (local tarball)
if: needs.setup.outputs.publish != 'true'
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
with:
input: /tmp/seaweedfs${{ 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@v4.37.6
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@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
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@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
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) }}
steps:
- name: Checkout
uses: actions/checkout@v7
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=" >> $GITHUB_OUTPUT
fi
- name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
with:
images: |
chrislusf/seaweedfs
ghcr.io/chrislusf/seaweedfs
tags: type=raw,value=${{ github.event_name == 'workflow_dispatch' && github.event.inputs.image_tag || 'latest' }},suffix=${{ steps.config.outputs.tag_suffix }}
- name: Login to Docker Hub
uses: docker/login-action@v4.6.0
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
uses: docker/login-action@v4.6.0
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Install crane
run: |
# Install crane for efficient multi-arch image copying
cd $(mktemp -d)
curl -sL "https://github.com/google/go-containerregistry/releases/latest/download/go-containerregistry_Linux_x86_64.tar.gz" | tar xz
sudo mv crane /usr/local/bin/
crane version
- name: Create and push manifest
run: |
SUFFIX="${{ 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
# 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
echo "Copying manifest from GHCR to Docker Hub..."
# Function to retry with exponential backoff for Docker Hub operations
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 $exit_code
}
# Use crane or skopeo to copy, fallback to docker if not available
if command -v crane &> /dev/null; then
echo "Using crane to copy..."
retry_with_backoff crane copy ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}
elif command -v skopeo &> /dev/null; then
echo "Using skopeo to copy..."
retry_with_backoff skopeo copy --all docker://ghcr.io/chrislusf/seaweedfs:${BASE_TAG}${SUFFIX} docker://chrislusf/seaweedfs:${BASE_TAG}${SUFFIX}
else
echo "Using docker buildx imagetools (pulling 4 images from Docker Hub)..."
# Fallback: create manifest directly on Docker Hub (pulls from Docker Hub - rate limited)
retry_with_backoff docker buildx imagetools create -t chrislusf/seaweedfs:${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
fi
+57
View File
@@ -0,0 +1,57 @@
name: "docker: build release containers for normal volume"
on:
push:
tags:
- '*'
workflow_dispatch: {}
permissions:
contents: read
jobs:
build-default-release-container:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
with:
images: |
chrislusf/seaweedfs
tags: |
type=ref,event=tag
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 QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
platforms: linux/amd64, linux/arm, linux/arm64, linux/386
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
+59
View File
@@ -0,0 +1,59 @@
name: "docker: build release containers for large volume"
on:
push:
tags:
- '*'
workflow_dispatch: {}
permissions:
contents: read
jobs:
build-large-release-container:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
with:
images: |
chrislusf/seaweedfs
tags: |
type=ref,event=tag,suffix=_large_disk
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 QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
build-args: TAGS=5BytesOffset
platforms: linux/amd64, linux/arm, linux/arm64, linux/386
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
+58
View File
@@ -0,0 +1,58 @@
name: "docker: build release containers for rocksdb"
on:
push:
tags:
- '*'
workflow_dispatch: {}
permissions:
contents: read
jobs:
build-large-release-container_rocksdb:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
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: Set up QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.rocksdb_large
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
+58
View File
@@ -0,0 +1,58 @@
name: "docker: build release containers for all tags"
on:
push:
tags:
- '*'
workflow_dispatch: {}
permissions:
contents: read
jobs:
build-default-release-container:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
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 QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
build-args: TAGS=elastic,ydb,gocdk,tikv
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
+58
View File
@@ -0,0 +1,58 @@
name: "docker: build release containers for all tags and large volume"
on:
push:
tags:
- '*'
workflow_dispatch: {}
permissions:
contents: read
jobs:
build-default-release-container:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@57396166ad8aefe6098280995947635806a0e6ea # v3
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 QEMU
uses: docker/setup-qemu-action@e81a89b1732b9c48d79cd809d8d81d79c4647a18 # v1
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@8c0edbc76e98fa90f69d9a2c020dcb50019dc325 # v1
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Build
uses: docker/build-push-action@c56af957549030174b10d6867f20e78cfd7debc5 # v2
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.go_build
build-args: TAGS=5BytesOffset,elastic,ydb,gocdk,tikv
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
@@ -1,79 +0,0 @@
name: "docker: build release containers for foundationdb"
on:
push:
tags:
- '*'
workflow_dispatch:
inputs:
release_tag:
description: 'Release tag to publish (e.g. 3.93)'
required: true
default: ''
permissions:
contents: read
env:
RELEASE_TAG: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.release_tag || github.ref_name }}
jobs:
build-large-release-container_foundationdb:
runs-on: [ubuntu-latest]
steps:
-
name: Checkout
uses: actions/checkout@v7
-
name: Docker meta
id: docker_meta
uses: docker/metadata-action@v6
with:
images: |
chrislusf/seaweedfs
tags: |
type=raw,value=${{ env.RELEASE_TAG }}_large_disk_foundationdb
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 QEMU
uses: docker/setup-qemu-action@v4.2.0
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
-
name: Login to Docker Hub
if: github.event_name != 'pull_request'
uses: docker/login-action@v4.6.0
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
-
name: Determine branch to build
id: branch
run: |
if [ "${{ github.event_name }}" = "push" ] && [ -n "${{ github.ref_name }}" ]; then
echo "branch=${{ github.ref_name }}" >> "$GITHUB_OUTPUT"
else
echo "branch=master" >> "$GITHUB_OUTPUT"
fi
-
name: Build
uses: docker/build-push-action@v7
with:
context: ./docker
push: ${{ github.event_name != 'pull_request' }}
file: ./docker/Dockerfile.foundationdb_large
build-args: |
BRANCH=${{ steps.branch.outputs.branch }}
# Note: ARM64 support requires FoundationDB ARM64 packages which are not available for all versions
platforms: linux/amd64
tags: ${{ steps.docker_meta.outputs.tags }}
labels: ${{ steps.docker_meta.outputs.labels }}
@@ -1,491 +0,0 @@
name: "docker: build all release containers (unified)"
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'
permissions:
contents: read
security-events: write
env:
RELEASE_TAG: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.release_tag || github.ref_name }}
IMAGE: ghcr.io/chrislusf/seaweedfs
# Limit concurrent builds to avoid rate limits
concurrency:
group: release-${{ github.ref }}
cancel-in-progress: false
jobs:
# ── Pre-build Rust volume server binaries natively ──────────────────
# Cross-compiles for amd64 and arm64 without QEMU, turning a 5-hour
# emulated cargo build into ~15 minutes of native compilation.
build-rust-binaries:
runs-on: ubuntu-22.04
strategy:
matrix:
include:
- target: x86_64-unknown-linux-musl
arch: amd64
- target: aarch64-unknown-linux-musl
arch: arm64
cross: true
steps:
- name: Checkout
uses: actions/checkout@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Install musl tools (amd64)
if: ${{ !matrix.cross }}
run: sudo apt-get install -y musl-tools
- name: Install cross-compilation tools (arm64)
if: matrix.cross
run: |
sudo apt-get install -y gcc-aarch64-linux-gnu
echo "CARGO_TARGET_AARCH64_UNKNOWN_LINUX_MUSL_LINKER=aarch64-linux-gnu-gcc" >> "$GITHUB_ENV"
# Disable glibc fortify source — its __memcpy_chk etc. symbols don't exist in musl
echo "CFLAGS_aarch64_unknown_linux_musl=-U_FORTIFY_SOURCE" >> "$GITHUB_ENV"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-docker-${{ matrix.target }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-docker-${{ matrix.target }}-
- name: Build large-disk variant
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }}
cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-large-disk-${{ matrix.arch }}
- name: Build normal variant
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features
cp target/${{ matrix.target }}/release/weed-volume ../weed-volume-normal-${{ matrix.arch }}
- name: Upload artifacts
uses: actions/upload-artifact@v7
with:
name: rust-volume-${{ matrix.arch }}
path: |
weed-volume-large-disk-${{ matrix.arch }}
weed-volume-normal-${{ matrix.arch }}
# One job per (variant, platform) on a native runner, pushed by digest;
# the merge job stitches the digests into one multi-arch tag.
build:
needs: [build-rust-binaries]
runs-on: ${{ matrix.runner }}
strategy:
fail-fast: false
matrix:
include:
# Normal volume - multi-arch
- { variant: normal, tag_suffix: "", dockerfile: ./docker/Dockerfile.go_build, build_args: "", rust_variant: normal, platform: linux/amd64, arch: amd64, runner: ubuntu-latest, qemu: false }
- { variant: normal, tag_suffix: "", dockerfile: ./docker/Dockerfile.go_build, build_args: "", rust_variant: normal, platform: linux/arm64, arch: arm64, runner: ubuntu-24.04-arm, qemu: false }
- { variant: normal, tag_suffix: "", dockerfile: ./docker/Dockerfile.go_build, build_args: "", rust_variant: normal, platform: linux/arm/v7, arch: armv7, runner: ubuntu-latest, qemu: true }
- { variant: normal, tag_suffix: "", dockerfile: ./docker/Dockerfile.go_build, build_args: "", rust_variant: normal, platform: linux/386, arch: i386, runner: ubuntu-latest, qemu: false }
# Large disk - multi-arch
- { variant: large_disk, tag_suffix: _large_disk, dockerfile: ./docker/Dockerfile.go_build, build_args: TAGS=5BytesOffset, rust_variant: large-disk, platform: linux/amd64, arch: amd64, runner: ubuntu-latest, qemu: false }
- { variant: large_disk, tag_suffix: _large_disk, dockerfile: ./docker/Dockerfile.go_build, build_args: TAGS=5BytesOffset, rust_variant: large-disk, platform: linux/arm64, arch: arm64, runner: ubuntu-24.04-arm, qemu: false }
- { variant: large_disk, tag_suffix: _large_disk, dockerfile: ./docker/Dockerfile.go_build, build_args: TAGS=5BytesOffset, rust_variant: large-disk, platform: linux/arm/v7, arch: armv7, runner: ubuntu-latest, qemu: true }
- { variant: large_disk, tag_suffix: _large_disk, dockerfile: ./docker/Dockerfile.go_build, build_args: TAGS=5BytesOffset, rust_variant: large-disk, platform: linux/386, arch: i386, runner: ubuntu-latest, qemu: false }
# Full tags - multi-arch
- { variant: full, tag_suffix: _full, dockerfile: ./docker/Dockerfile.go_build, build_args: "TAGS=elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb", rust_variant: normal, platform: linux/amd64, arch: amd64, runner: ubuntu-latest, qemu: false }
- { variant: full, tag_suffix: _full, dockerfile: ./docker/Dockerfile.go_build, build_args: "TAGS=elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb", rust_variant: normal, platform: linux/arm64, arch: arm64, runner: ubuntu-24.04-arm, qemu: false }
# Large disk + full tags - multi-arch
- { variant: large_disk_full, tag_suffix: _large_disk_full, dockerfile: ./docker/Dockerfile.go_build, build_args: "TAGS=5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb", rust_variant: large-disk, platform: linux/amd64, arch: amd64, runner: ubuntu-latest, qemu: false }
- { variant: large_disk_full, tag_suffix: _large_disk_full, dockerfile: ./docker/Dockerfile.go_build, build_args: "TAGS=5BytesOffset,elastic,gocdk,rclone,sqlite,tarantool,tikv,ydb", rust_variant: large-disk, platform: linux/arm64, arch: arm64, runner: ubuntu-24.04-arm, qemu: false }
# RocksDB large disk - amd64 only
- { variant: rocksdb, tag_suffix: _large_disk_rocksdb, dockerfile: ./docker/Dockerfile.rocksdb_large, build_args: "", rust_variant: large-disk, platform: linux/amd64, arch: amd64, runner: ubuntu-latest, qemu: false }
steps:
- name: Skip unselected variant
if: github.event_name == 'workflow_dispatch' && github.event.inputs.variant != 'all' && github.event.inputs.variant != matrix.variant
run: echo "Skipping ${{ matrix.variant }} (${{ matrix.platform }})" && exit 0
- name: Checkout
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: actions/checkout@v7
- name: Download pre-built Rust binaries
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: actions/download-artifact@v8
with:
pattern: rust-volume-*
merge-multiple: true
path: ./rust-bins
- name: Place Rust binaries in Docker context
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
mkdir -p docker/weed-volume-prebuilt
for arch in amd64 arm64; do
src="./rust-bins/weed-volume-${{ matrix.rust_variant }}-${arch}"
if [ -f "$src" ]; then
cp "$src" "docker/weed-volume-prebuilt/weed-volume-${arch}"
echo "Placed pre-built Rust binary for ${arch}"
fi
done
ls -la docker/weed-volume-prebuilt/
- name: Free Disk Space
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL
sudo apt-get clean
sudo rm -rf /var/lib/apt/lists/*
sudo docker system prune -af --volumes
[ -d ~/.cache/go-build ] && rm -rf ~/.cache/go-build || true
[ -d /go/pkg ] && rm -rf /go/pkg || true
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
with:
images: ${{ env.IMAGE }}
tags: type=raw,value=${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
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 QEMU
if: (github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant) && matrix.qemu
uses: docker/setup-qemu-action@v4.2.0
- 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"]
mirrors = ["https://mirror.gcr.io"]
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
with:
buildkitd-config: /tmp/buildkitd.toml
- 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@v4.6.0
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Build and push ${{ matrix.variant }} (${{ matrix.platform }})
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
id: build
uses: docker/build-push-action@v7
env:
DOCKER_BUILDKIT: 1
with:
context: ./docker
file: ${{ matrix.dockerfile }}
platforms: ${{ matrix.platform }}
labels: ${{ steps.docker_meta.outputs.labels }}
# Flat single-platform manifest so imagetools create assembles cleanly.
provenance: false
outputs: type=image,name=${{ env.IMAGE }},push-by-digest=true,name-canonical=true,push=true
cache-from: type=gha,scope=${{ matrix.variant }}-${{ matrix.arch }}
# max only for rocksdb: its RocksDB compile is sha-independent and worth
# keeping; go-build layers are sha-busted every release, so min elsewhere.
cache-to: type=gha,mode=${{ matrix.variant == 'rocksdb' && 'max' || 'min' }},scope=${{ matrix.variant }}-${{ matrix.arch }}
build-args: |
${{ matrix.build_args }}
BUILDKIT_INLINE_CACHE=1
BRANCH=${{ github.sha }}
${{ matrix.variant == 'rocksdb' && format('ROCKSDB_VERSION={0}', github.event.inputs.rocksdb_version || 'v10.10.1') || '' }}
- name: Export digest
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
mkdir -p /tmp/digests
digest="${{ steps.build.outputs.digest }}"
touch "/tmp/digests/${digest#sha256:}"
- name: Upload digest
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: actions/upload-artifact@v7
with:
name: digest-${{ matrix.variant }}-${{ matrix.arch }}
path: /tmp/digests/*
if-no-files-found: error
retention-days: 1
# Assemble each variant's per-platform digests into one tag, then mirror to Docker Hub.
merge:
needs: [build]
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
include:
- { variant: normal, tag_suffix: "" }
- { variant: large_disk, tag_suffix: _large_disk }
- { variant: full, tag_suffix: _full }
- { variant: large_disk_full, tag_suffix: _large_disk_full }
- { variant: rocksdb, tag_suffix: _large_disk_rocksdb }
steps:
- name: Download digests
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
uses: actions/download-artifact@v8
with:
pattern: digest-${{ matrix.variant }}-*
merge-multiple: true
path: /tmp/digests
- 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
- 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@v4.6.0
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Create multi-arch tag on GHCR
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
working-directory: /tmp/digests
run: |
docker buildx imagetools create \
-t ${{ env.IMAGE }}:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }} \
$(printf '${{ env.IMAGE }}@sha256:%s ' *)
docker buildx imagetools inspect ${{ env.IMAGE }}:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
- 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@v4.6.0
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- 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
sudo mv crane /usr/local/bin/
crane version
- name: Copy ${{ matrix.variant }} to Docker Hub
if: github.event_name != 'workflow_dispatch' || github.event.inputs.variant == 'all' || github.event.inputs.variant == matrix.variant
run: |
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
}
echo "Copying ${{ matrix.variant }} from GHCR to Docker Hub..."
retry_with_backoff crane copy \
${{ env.IMAGE }}:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }} \
chrislusf/seaweedfs:${{ env.RELEASE_TAG }}${{ matrix.tag_suffix }}
echo "Copied ${{ matrix.variant }} to Docker Hub"
# Report-only trivy scan: uploads fixable HIGH/CRITICAL findings to GitHub
# Security for visibility, but never blocks the release. Releases (including
# `latest`) ship regardless — vulnerabilities are tracked, not gated, since
# we sometimes need to publish through known findings (e.g. unfixed upstream
# CVE, base-image lag).
trivy-scan:
runs-on: ubuntu-latest
needs: [merge]
if: github.event_name == 'push'
continue-on-error: true
strategy:
fail-fast: false
matrix:
include:
- source_suffix: ""
variant: normal
- source_suffix: _large_disk
variant: large_disk
steps:
- name: Login to GHCR
uses: docker/login-action@v4.6.0
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Trivy report (${{ matrix.variant }})
# Pin to SHA - mutable tags were compromised (GHSA-69fq-xp46-6x23)
uses: aquasecurity/trivy-action@ed142fd0673e97e23eac54620cfb913e5ce36c25 # v0.36.0
with:
scan-type: image
# Scan the multi-arch tag on GHCR (already pushed by the build job).
# Trivy scans the runner's native platform; OS packages are identical
# across architectures since they all share the same alpine base.
image-ref: ${{ env.IMAGE }}:${{ env.RELEASE_TAG }}${{ matrix.source_suffix }}
scanners: vuln
vuln-type: os,library
severity: HIGH,CRITICAL
ignore-unfixed: true
limit-severities-for-sarif: true
format: sarif
output: trivy-results.sarif
exit-code: '0'
- name: Upload Trivy scan results to GitHub Security
if: always()
uses: github/codeql-action/upload-sarif@v4.37.6
with:
sarif_file: trivy-results.sarif
category: trivy-${{ matrix.variant }}
# Point `latest` (and `latest_large_disk`) at the just-released versioned
# image. crane tag adds an extra tag to an existing manifest — no rebuild,
# no QEMU, no separate workflow. Replaces the old container_latest.yml
# rebuild that often failed or lagged behind the release. Independent of
# trivy-scan: vuln findings are reported but do not block `latest`.
tag-latest:
runs-on: ubuntu-latest
needs: [merge]
if: github.event_name == 'push'
strategy:
matrix:
include:
- source_suffix: ""
latest_tag: latest
- source_suffix: _large_disk
latest_tag: latest_large_disk
steps:
- name: Login to Docker Hub
uses: docker/login-action@v4.6.0
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Login to GHCR
uses: docker/login-action@v4.6.0
with:
registry: ghcr.io
username: ${{ secrets.GHCR_USERNAME }}
password: ${{ secrets.GHCR_TOKEN }}
- name: Install crane
run: |
cd $(mktemp -d)
curl -sL "https://github.com/google/go-containerregistry/releases/latest/download/go-containerregistry_Linux_x86_64.tar.gz" | tar xz
sudo mv crane /usr/local/bin/
crane version
- name: Re-tag ${{ env.RELEASE_TAG }}${{ matrix.source_suffix }} as ${{ matrix.latest_tag }}
run: |
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 $exit_code
}
SRC_TAG="${{ env.RELEASE_TAG }}${{ matrix.source_suffix }}"
DST_TAG="${{ matrix.latest_tag }}"
echo "Tagging ${{ env.IMAGE }}:${SRC_TAG} as ${DST_TAG}"
retry_with_backoff crane tag "${{ env.IMAGE }}:${SRC_TAG}" "${DST_TAG}"
echo "Tagging chrislusf/seaweedfs:${SRC_TAG} as ${DST_TAG}"
retry_with_backoff crane tag "chrislusf/seaweedfs:${SRC_TAG}" "${DST_TAG}"
helm-release:
runs-on: ubuntu-latest
needs: [build]
if: github.event_name == 'push' || github.event_name == 'workflow_dispatch'
permissions:
contents: write
pages: write
steps:
- uses: actions/checkout@v7
- 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"
@@ -1,110 +0,0 @@
name: "docker: build rocksdb image by version"
on:
workflow_dispatch:
inputs:
rocksdb_version:
description: 'RocksDB git tag or branch to build (e.g. v10.10.1)'
required: true
default: 'v10.10.1'
seaweedfs_ref:
description: 'SeaweedFS git tag, branch, or commit to build'
required: true
default: 'master'
image_tag:
description: 'Optional Docker tag suffix (defaults to rocksdb_<rocksdb>_seaweedfs_<ref>)'
required: false
default: ''
permissions:
contents: read
jobs:
build-rocksdb-image:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v2
- name: Prepare Docker tag
id: tag
env:
ROCKSDB_VERSION_INPUT: ${{ inputs.rocksdb_version }}
SEAWEEDFS_REF_INPUT: ${{ inputs.seaweedfs_ref }}
CUSTOM_TAG_INPUT: ${{ inputs.image_tag }}
run: |
set -euo pipefail
sanitize() {
local value="$1"
value="${value,,}"
value="${value// /-}"
value="${value//[^a-z0-9_.-]/-}"
value="${value#-}"
value="${value%-}"
printf '%s' "$value"
}
version="${ROCKSDB_VERSION_INPUT}"
seaweed="${SEAWEEDFS_REF_INPUT}"
tag="${CUSTOM_TAG_INPUT}"
if [ -z "$version" ]; then
echo "RocksDB version input is required." >&2
exit 1
fi
if [ -z "$seaweed" ]; then
echo "SeaweedFS ref input is required." >&2
exit 1
fi
sanitized_version="$(sanitize "$version")"
if [ -z "$sanitized_version" ]; then
echo "Unable to sanitize RocksDB version '$version'." >&2
exit 1
fi
sanitized_seaweed="$(sanitize "$seaweed")"
if [ -z "$sanitized_seaweed" ]; then
echo "Unable to sanitize SeaweedFS ref '$seaweed'." >&2
exit 1
fi
if [ -z "$tag" ]; then
tag="rocksdb_${sanitized_version}_seaweedfs_${sanitized_seaweed}"
fi
tag="${tag,,}"
tag="${tag// /-}"
tag="${tag//[^a-z0-9_.-]/-}"
tag="${tag#-}"
tag="${tag%-}"
if [ -z "$tag" ]; then
echo "Resulting Docker tag is empty." >&2
exit 1
fi
echo "docker_tag=$tag" >> "$GITHUB_OUTPUT"
echo "full_image=chrislusf/seaweedfs:$tag" >> "$GITHUB_OUTPUT"
echo "seaweedfs_ref=$seaweed" >> "$GITHUB_OUTPUT"
- name: Set up QEMU
uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8 # v1
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@4d04d5d9486b7bd6fa91e7baf45bbb4f8b9deedd # v1
- name: Login to Docker Hub
uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v1
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Build and push image
uses: docker/build-push-action@bcafcacb16a39f128d818304e6c9c0c18556b85f # v2
with:
context: ./docker
push: true
file: ./docker/Dockerfile.rocksdb_large
build-args: |
ROCKSDB_VERSION=${{ inputs.rocksdb_version }}
BRANCH=${{ inputs.seaweedfs_ref }}
platforms: linux/amd64
tags: ${{ steps.tag.outputs.full_image }}
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
-174
View File
@@ -1,174 +0,0 @@
# This workflow will build and deploy the SeaweedFS telemetry server
# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-go
name: Deploy Telemetry Server
on:
workflow_dispatch:
inputs:
setup:
description: 'Run first-time server setup'
required: true
type: boolean
default: false
deploy:
description: 'Deploy telemetry server to remote server'
required: true
type: boolean
default: false
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'telemetry/server/go.mod'
- name: Build Telemetry Server
if: github.event_name == 'workflow_dispatch' && inputs.deploy
run: |
# telemetry/server is its own Go module; build from within it
cd telemetry/server
go mod tidy
echo "Building telemetry server..."
GOOS=linux GOARCH=amd64 go build -o ../../telemetry-server .
cd ../..
ls -la telemetry-server
echo "Build completed successfully"
- name: First-time Server Setup
if: github.event_name == 'workflow_dispatch' && inputs.setup
env:
SSH_PRIVATE_KEY: ${{ secrets.TELEMETRY_SSH_PRIVATE_KEY }}
REMOTE_HOST: ${{ secrets.TELEMETRY_HOST }}
REMOTE_USER: ${{ secrets.TELEMETRY_USER }}
run: |
mkdir -p ~/.ssh
echo "$SSH_PRIVATE_KEY" > ~/.ssh/deploy_key
chmod 600 ~/.ssh/deploy_key
echo "Host *" > ~/.ssh/config
echo " StrictHostKeyChecking no" >> ~/.ssh/config
# Create all required directories with proper permissions
ssh -i ~/.ssh/deploy_key $REMOTE_USER@$REMOTE_HOST "
mkdir -p ~/seaweedfs-telemetry/bin ~/seaweedfs-telemetry/logs ~/seaweedfs-telemetry/data ~/seaweedfs-telemetry/tmp && \
chmod 755 ~/seaweedfs-telemetry/logs && \
chmod 755 ~/seaweedfs-telemetry/data && \
touch ~/seaweedfs-telemetry/logs/telemetry.log ~/seaweedfs-telemetry/logs/telemetry.error.log && \
chmod 644 ~/seaweedfs-telemetry/logs/*.log"
# Create systemd service file
echo "
[Unit]
Description=SeaweedFS Telemetry Server
After=network.target
[Service]
Type=simple
User=$REMOTE_USER
WorkingDirectory=/home/$REMOTE_USER/seaweedfs-telemetry
ExecStart=/home/$REMOTE_USER/seaweedfs-telemetry/bin/telemetry-server -port=8353
Restart=always
RestartSec=5
StandardOutput=append:/home/$REMOTE_USER/seaweedfs-telemetry/logs/telemetry.log
StandardError=append:/home/$REMOTE_USER/seaweedfs-telemetry/logs/telemetry.error.log
[Install]
WantedBy=multi-user.target" > telemetry.service
# Setup logrotate configuration
echo "# SeaweedFS Telemetry service log rotation
/home/$REMOTE_USER/seaweedfs-telemetry/logs/*.log {
daily
rotate 30
compress
delaycompress
missingok
notifempty
create 644 $REMOTE_USER $REMOTE_USER
postrotate
systemctl restart telemetry.service
endscript
}" > telemetry_logrotate
# Copy configuration files
scp -i ~/.ssh/deploy_key telemetry/grafana-dashboard.json $REMOTE_USER@$REMOTE_HOST:~/seaweedfs-telemetry/
scp -i ~/.ssh/deploy_key telemetry/prometheus.yml $REMOTE_USER@$REMOTE_HOST:~/seaweedfs-telemetry/
# Copy and install service and logrotate files
scp -i ~/.ssh/deploy_key telemetry.service telemetry_logrotate $REMOTE_USER@$REMOTE_HOST:~/seaweedfs-telemetry/
ssh -i ~/.ssh/deploy_key $REMOTE_USER@$REMOTE_HOST "
sudo mv ~/seaweedfs-telemetry/telemetry.service /etc/systemd/system/ && \
sudo mv ~/seaweedfs-telemetry/telemetry_logrotate /etc/logrotate.d/seaweedfs-telemetry && \
sudo systemctl daemon-reload && \
sudo systemctl enable telemetry.service"
echo "✅ First-time setup completed successfully!"
echo "📋 Next step: Run the deployment to install the telemetry server binary"
echo " 1. Go to GitHub Actions → Deploy Telemetry Server"
echo " 2. Click 'Run workflow'"
echo " 3. Check 'Deploy telemetry server to remote server'"
echo " 4. Click 'Run workflow'"
rm -f ~/.ssh/deploy_key
- name: Deploy Telemetry Server to Remote Server
if: github.event_name == 'workflow_dispatch' && inputs.deploy
env:
SSH_PRIVATE_KEY: ${{ secrets.TELEMETRY_SSH_PRIVATE_KEY }}
REMOTE_HOST: ${{ secrets.TELEMETRY_HOST }}
REMOTE_USER: ${{ secrets.TELEMETRY_USER }}
run: |
mkdir -p ~/.ssh
echo "$SSH_PRIVATE_KEY" > ~/.ssh/deploy_key
chmod 600 ~/.ssh/deploy_key
echo "Host *" > ~/.ssh/config
echo " StrictHostKeyChecking no" >> ~/.ssh/config
# Create temp directory and copy binary
ssh -i ~/.ssh/deploy_key $REMOTE_USER@$REMOTE_HOST "mkdir -p ~/seaweedfs-telemetry/tmp"
scp -i ~/.ssh/deploy_key telemetry-server $REMOTE_USER@$REMOTE_HOST:~/seaweedfs-telemetry/tmp/
# Copy updated configuration files
scp -i ~/.ssh/deploy_key telemetry/grafana-dashboard.json $REMOTE_USER@$REMOTE_HOST:~/seaweedfs-telemetry/
scp -i ~/.ssh/deploy_key telemetry/prometheus.yml $REMOTE_USER@$REMOTE_HOST:~/seaweedfs-telemetry/
# Check if service exists and deploy accordingly
ssh -i ~/.ssh/deploy_key $REMOTE_USER@$REMOTE_HOST "
if systemctl list-unit-files telemetry.service >/dev/null 2>&1; then
echo 'Service exists, performing update...'
sudo systemctl stop telemetry.service
mkdir -p ~/seaweedfs-telemetry/bin
mv ~/seaweedfs-telemetry/tmp/telemetry-server ~/seaweedfs-telemetry/bin/
chmod +x ~/seaweedfs-telemetry/bin/telemetry-server
sudo systemctl start telemetry.service
sudo systemctl status telemetry.service
else
echo 'ERROR: telemetry.service not found!'
echo 'Please run the first-time setup before deploying.'
echo 'Go to GitHub Actions → Deploy Telemetry Server → Run workflow → Check \"Run first-time server setup\"'
exit 1
fi"
# Verify deployment
ssh -i ~/.ssh/deploy_key $REMOTE_USER@$REMOTE_HOST "
echo 'Waiting for service to start...'
sleep 5
curl -f http://localhost:8353/health || echo 'Health check failed'"
rm -f ~/.ssh/deploy_key
- name: Notify Deployment Status
if: always()
run: |
if [ "${{ job.status }}" == "success" ]; then
echo "✅ Telemetry server deployment successful"
echo "Dashboard: http://${{ secrets.TELEMETRY_HOST }}:8353"
echo "Metrics: http://${{ secrets.TELEMETRY_HOST }}:8353/metrics"
else
echo "❌ Telemetry server deployment failed"
fi
+2 -2
View File
@@ -9,6 +9,6 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: 'Checkout Repository'
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8
- name: 'Dependency Review'
uses: actions/dependency-review-action@a1d282b36b6f3519aa1f3fc636f609c47dddb294
uses: actions/dependency-review-action@11310527b429536e263dc6cc47873e608189ba21
+27 -104
View File
@@ -3,20 +3,8 @@ name: "End to End"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'docker/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/e2e.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/**'
- 'docker/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/e2e.yml'
concurrency:
group: ${{ github.head_ref }}/e2e
@@ -33,114 +21,49 @@ jobs:
e2e:
name: FUSE Mount
runs-on: ubuntu-22.04
timeout-minutes: 30
timeout-minutes: 15
steps:
- name: Set up Go 1.x
uses: actions/setup-go@d0a58c1c4d2b25278816e339b944508c875f3613 # v2
with:
go-version: ^1.13
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Cache Docker layers
uses: actions/cache@v6
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-e2e-${{ github.sha }}
restore-keys: |
${{ runner.os }}-buildx-e2e-
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Install dependencies
run: |
sudo rm -f /etc/apt/sources.list.d/azure-cli.list /etc/apt/sources.list.d/microsoft-prod.list
# Same helper the e2e image installs through: the runner's own list is
# azure-only too, and an outage there fails this step outright.
sudo ./apt-install fuse
# Verify FUSE installation
echo "FUSE version: $(fusermount --version 2>&1 || echo 'fusermount not found')"
echo "FUSE device: $(ls -la /dev/fuse 2>&1 || echo '/dev/fuse not found')"
sudo apt-get update
sudo apt-get install -y fuse
- name: Start SeaweedFS
timeout-minutes: 15
run: |
# Enable Docker buildkit for better caching
export DOCKER_BUILDKIT=1
export COMPOSE_DOCKER_CLI_BUILD=1
timeout-minutes: 5
run: make build_e2e && docker compose -f ./compose/e2e-mount.yml up --wait
# Build with retry logic
for i in {1..3}; do
echo "Build attempt $i/3"
if make build_e2e; then
echo "Build successful on attempt $i"
break
elif [ $i -eq 3 ]; then
echo "Build failed after 3 attempts"
exit 1
else
echo "Build attempt $i failed, retrying in 30 seconds..."
sleep 30
fi
done
# Start services with wait
docker compose -f ./compose/e2e-mount.yml up --wait
- name: Rotate buildx cache
if: always()
run: |
# Without this, --cache-to writes to .buildx-cache-new but actions/cache only
# uploads .buildx-cache, so layers (notably the slow apt RUN) never persist.
rm -rf /tmp/.buildx-cache
if [ -d /tmp/.buildx-cache-new ]; then mv /tmp/.buildx-cache-new /tmp/.buildx-cache; fi
- name: Run FIO 4k
timeout-minutes: 15
- name: Run FIO
timeout-minutes: 5
run: |
echo "Starting FIO at: $(date)"
# Concurrent r/w
echo 'Run randrw with size=16M bs=4k'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 60 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randrw --bs=4k --direct=1 --numjobs=8 --ioengine=libaio --group_reporting --runtime=30 --time_based=1
echo "Verify FIO at: $(date)"
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 40 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randrw --bs=4k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1
echo 'Run randrw with size=16M bs=128k'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 40 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randrw --bs=128k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1
echo 'Run randrw with size=16M bs=1m'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 40 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randrw --bs=1m --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1
# Verified write
echo 'Run randwrite with size=16M bs=4k'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 60 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randwrite --bs=4k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1 --do_verify=0 --verify=crc32c --verify_backlog=1
- name: Run FIO 128k
timeout-minutes: 15
run: |
echo "Starting FIO at: $(date)"
# Concurrent r/w
echo 'Run randrw with size=16M bs=128k'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 60 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randrw --bs=128k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1
echo "Verify FIO at: $(date)"
# Verified write
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 40 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randwrite --bs=4k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1 --do_verify=0 --verify=crc32c --verify_backlog=1
echo 'Run randwrite with size=16M bs=128k'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 60 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randwrite --bs=128k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1 --do_verify=0 --verify=crc32c --verify_backlog=1
- name: Run FIO 1MB
timeout-minutes: 15
run: |
echo "Starting FIO at: $(date)"
# Concurrent r/w
echo 'Run randrw with size=16M bs=1m'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 60 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randrw --bs=1m --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 40 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randwrite --bs=128k --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1 --do_verify=0 --verify=crc32c --verify_backlog=1
echo "Verify FIO at: $(date)"
# Verified write
echo 'Run randwrite with size=16M bs=1m'
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 60 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randwrite --bs=1m --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1 --do_verify=0 --verify=crc32c --verify_backlog=1
docker compose -f ./compose/e2e-mount.yml exec mount timeout -k5 40 fio --name=fiotest --filename=/mnt/seaweedfs/fiotest --size=16M --rw=randwrite --bs=1m --direct=1 --numjobs=8 --ioengine=libaio --iodepth=32 --group_reporting --runtime=30 --time_based=1 --do_verify=0 --verify=crc32c --verify_backlog=1
- name: Save logs
if: always()
@@ -156,7 +79,7 @@ jobs:
- name: Archive logs
if: always()
uses: actions/upload-artifact@v7
uses: actions/upload-artifact@v3
with:
name: output-logs
path: docker/output.log
@@ -1,76 +0,0 @@
name: "EC Integration Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'test/erasure_coding/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/ec-integration-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/**'
- 'test/erasure_coding/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/ec-integration-tests.yml'
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@v7
with:
go-version: ^1.26
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Build weed binary
run: |
cd weed && go build -o weed .
- name: Run EC Integration Tests
working-directory: test/erasure_coding
run: |
# The suite now includes the interruption matrix and runs close to Go's
# default 10m binary timeout on slower runners; bound it by the job's
# 30m budget instead.
go test -v -timeout 25m
- 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
@@ -1,69 +0,0 @@
name: "FUSE DLM Integration Tests"
on:
pull_request:
paths:
- 'weed/command/mount*.go'
- 'weed/mount/**'
- 'weed/cluster/**'
- 'test/fuse_dlm/**'
- '.github/workflows/fuse-dlm-integration.yml'
- '.github/actions/fix-fusermount-setuid/**'
push:
branches: [master]
paths:
- 'weed/command/mount*.go'
- 'weed/mount/**'
- 'weed/cluster/**'
- 'test/fuse_dlm/**'
- '.github/actions/fix-fusermount-setuid/**'
concurrency:
group: ${{ github.head_ref || github.ref }}/fuse-dlm-integration
cancel-in-progress: true
permissions:
contents: read
jobs:
fuse-dlm-integration:
name: FUSE DLM Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Configure FUSE
run: |
# Nothing to install: fuse3 ships fusermount3 and is pre-installed,
# and go-fuse is pure Go, so the libfuse headers were never linked
# against.
echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
sudo chmod 644 /etc/fuse.conf
- name: Repair the fusermount3 setuid bit
uses: ./.github/actions/fix-fusermount-setuid
- name: Build SeaweedFS
run: go build -o weed/weed -buildvcs=false ./weed
- name: Run DLM integration tests
timeout-minutes: 25
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
run: go test -v -count=1 -timeout=20m ./test/fuse_dlm/...
- name: Upload logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: fuse-dlm-test-logs
path: /tmp/seaweedfs-fuse-dlm-logs/
retention-days: 3
-76
View File
@@ -1,76 +0,0 @@
name: "FUSE Volume Server Failover Tests"
on:
pull_request:
paths:
- 'weed/command/mount*.go'
- 'weed/mount/**'
- 'weed/filer/**'
- 'weed/wdclient/**'
- 'weed/operation/upload_content.go'
- 'test/fuse_failover/**'
- '.github/workflows/fuse-failover.yml'
- '.github/actions/fix-fusermount-setuid/**'
push:
branches: [master]
paths:
- 'weed/command/mount*.go'
- 'weed/mount/**'
- 'weed/filer/**'
- 'weed/wdclient/**'
- 'weed/operation/upload_content.go'
- 'test/fuse_failover/**'
- '.github/workflows/fuse-failover.yml'
- '.github/actions/fix-fusermount-setuid/**'
concurrency:
group: ${{ github.head_ref || github.ref }}/fuse-failover
cancel-in-progress: true
permissions:
contents: read
jobs:
fuse-failover:
name: FUSE Volume Server Failover
runs-on: ubuntu-22.04
timeout-minutes: 40
steps:
- name: Check out code
uses: actions/checkout@v7
with:
persist-credentials: false
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Configure FUSE
run: |
# Nothing to install: fuse3 ships fusermount3 and is pre-installed,
# and go-fuse is pure Go, so the libfuse headers were never linked
# against.
echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
sudo chmod 644 /etc/fuse.conf
- name: Repair the fusermount3 setuid bit
uses: ./.github/actions/fix-fusermount-setuid
- name: Build SeaweedFS
run: go build -o weed/weed -buildvcs=false ./weed
- name: Run failover integration tests
timeout-minutes: 35
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
run: go test -v -count=1 -timeout=30m ./test/fuse_failover/...
- name: Upload logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: fuse-failover-test-logs
path: /tmp/seaweedfs-fuse-failover-logs/
retention-days: 3
-84
View File
@@ -1,84 +0,0 @@
name: "FUSE Integration Tests"
on:
push:
branches: [ master, main ]
paths:
- 'weed/**'
- 'test/fuse_integration/**'
- '.github/workflows/fuse-integration.yml'
- '.github/actions/fix-fusermount-setuid/**'
pull_request:
branches: [ master, main ]
paths:
- 'weed/**'
- 'test/fuse_integration/**'
- '.github/workflows/fuse-integration.yml'
- '.github/actions/fix-fusermount-setuid/**'
concurrency:
group: ${{ github.head_ref }}/fuse-integration
cancel-in-progress: true
permissions:
contents: read
jobs:
fuse-integration:
name: FUSE Integration Testing
runs-on: ubuntu-22.04
timeout-minutes: 50
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Configure FUSE
run: |
# Nothing to install: fuse3 ships fusermount3 and is pre-installed, and
# go-fuse is pure Go, so the libfuse headers were never linked against.
# Allow non-root FUSE mounts with allow_other
echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
sudo chmod 644 /etc/fuse.conf
# Verify FUSE installation
fusermount3 --version || fusermount --version || true
ls -la /dev/fuse
- name: Repair the fusermount3 setuid bit
uses: ./.github/actions/fix-fusermount-setuid
- name: Build SeaweedFS
run: |
cd weed
go build -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -o weed .
chmod +x weed
./weed version
# Make weed binary available in PATH for the test framework
sudo cp weed /usr/local/bin/weed
- name: Install test dependencies
run: |
cd test/fuse_integration
go mod download
- 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
if: always()
uses: actions/upload-artifact@v7
with:
name: fuse-integration-test-results
path: |
/tmp/fuse-test-output.log
/tmp/seaweedfs-fuse-logs/
retention-days: 7
@@ -1,75 +0,0 @@
name: "FUSE P2P Peer Chunk Sharing Integration Tests"
on:
pull_request:
paths:
- 'weed/command/mount*.go'
- 'weed/mount/**'
- 'weed/filer/mount_peer_registry*.go'
- 'weed/server/filer_grpc_server_mount_peer.go'
- 'weed/pb/mount_peer.proto'
- 'weed/pb/filer.proto'
- 'test/fuse_p2p/**'
- '.github/workflows/fuse-p2p-integration.yml'
- '.github/actions/fix-fusermount-setuid/**'
push:
branches: [master]
paths:
- 'weed/command/mount*.go'
- 'weed/mount/**'
- 'weed/filer/mount_peer_registry*.go'
- 'weed/server/filer_grpc_server_mount_peer.go'
- 'weed/pb/mount_peer.proto'
- 'weed/pb/filer.proto'
- 'test/fuse_p2p/**'
- '.github/actions/fix-fusermount-setuid/**'
concurrency:
group: ${{ github.head_ref || github.ref }}/fuse-p2p-integration
cancel-in-progress: true
permissions:
contents: read
jobs:
fuse-p2p-integration:
name: FUSE P2P Peer Chunk Sharing
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Configure FUSE
run: |
# Nothing to install: fuse3 ships fusermount3 and is pre-installed,
# and go-fuse is pure Go, so the libfuse headers were never linked
# against.
echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
sudo chmod 644 /etc/fuse.conf
- name: Repair the fusermount3 setuid bit
uses: ./.github/actions/fix-fusermount-setuid
- name: Build SeaweedFS
run: go build -o weed/weed -buildvcs=false ./weed
- name: Run P2P integration tests
timeout-minutes: 15
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
run: go test -v -count=1 -timeout=12m ./test/fuse_p2p/...
- name: Upload logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: fuse-p2p-test-logs
path: /tmp/seaweedfs-fuse-p2p-logs/
retention-days: 3
+14 -124
View File
@@ -3,18 +3,8 @@ name: "go: build binary"
on:
push:
branches: [ master ]
paths:
- '**/*.go'
- 'go.mod'
- 'go.sum'
- '.github/workflows/go.yml'
pull_request:
branches: [ master ]
paths:
- '**/*.go'
- 'go.mod'
- 'go.sum'
- '.github/workflows/go.yml'
concurrency:
group: ${{ github.head_ref }}/go
@@ -25,126 +15,26 @@ permissions:
jobs:
vet:
name: Go Vet
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Get dependencies
run: |
cd weed; go get -v -t -d ./...
- name: Go Vet (excluding protobuf lock copying)
run: |
cd weed
# Run go vet and filter out known protobuf MessageState lock copying warnings
# These are expected in generated protobuf code with embedded sync.Mutex and are safe in practice
go vet -v ./... 2>&1 | grep -v "MessageState contains sync.Mutex" | grep -v "IdentityAccessManagement contains sync.RWMutex" | tee vet-output.txt
# Fail only if there are actual vet errors (not counting the filtered lock warnings)
if grep -q "vet:" vet-output.txt; then exit 1; fi
vet-32bit:
name: Go Vet 32-bit
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Go Vet linux/386 (type-checks code and tests for 32-bit int overflows)
run: |
GOOS=linux GOARCH=386 go vet ./... 2>&1 | grep -v "MessageState contains sync.Mutex" | grep -v "IdentityAccessManagement contains sync.RWMutex" | tee vet-32bit-output.txt
if grep -q "vet:" vet-32bit-output.txt; then exit 1; fi
build:
name: Build
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Build
run: cd weed; go build -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v .
build-cross:
name: Build cross-platform (${{ matrix.goos }}/${{ matrix.goarch }})
runs-on: ubuntu-latest
strategy:
# One target's breakage should not hide the other three.
fail-fast: false
matrix:
include:
- { goos: windows, goarch: amd64 }
- { goos: windows, goarch: arm64 }
- { goos: freebsd, goarch: amd64 }
- { goos: darwin, goarch: arm64 }
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
- name: Set up Go 1.x
uses: actions/setup-go@d0a58c1c4d2b25278816e339b944508c875f3613 # v2
with:
go-version-file: 'go.mod'
# Nothing else on a PR compiles these, so per-OS syscall constants creep
# back into shared files unnoticed and only a release build catches it.
- name: Cross-compile
env:
GOOS: ${{ matrix.goos }}
GOARCH: ${{ matrix.goarch }}
go-version: ^1.13
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@93ea575cb5d8a053eaa0ac8fa3b40d7e05a33cc8 # v2
- name: Get dependencies
run: |
go build ./weed/...
# Tests too: they reach for per-OS syscall constants the build does
# not, and only compiling them catches an untagged one.
go vet ./weed/mount/... ./weed/command/... 2>&1 |
grep -v "MessageState contains sync.Mutex" | tee /tmp/vet.txt
if grep -q "vet:" /tmp/vet.txt; then exit 1; fi
cd weed; go get -v -t -d ./...
- name: Build
run: cd weed; go build -tags "elastic gocdk sqlite ydb tikv" -v .
test:
name: Test
runs-on: ubuntu-latest
services:
redis:
image: redis:8
ports:
- 6379:6379
options: >-
--health-cmd "redis-cli ping"
--health-interval 10s
--health-timeout 5s
--health-retries 5
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Test
env:
RUN_REDIS_TESTS: "1"
run: cd weed; go test -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v ./...
test-32bit:
name: Test 32-bit
runs-on: ubuntu-latest
steps:
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
# 386 test binaries run natively on the amd64 runner. This catches what vet
# can't: unaligned 64-bit atomics and arithmetic that wraps at runtime.
# -short skips the e2e suites already covered on amd64.
- name: Test linux/386
run: cd weed; GOOS=linux GOARCH=386 go test -short ./...
run: cd weed; go test -tags "elastic gocdk sqlite ydb tikv" -v ./...
File diff suppressed because it is too large Load Diff
-41
View File
@@ -1,41 +0,0 @@
name: "helm: release"
on:
push:
tags:
- '*'
workflow_dispatch:
permissions:
contents: write
pages: write
packages: write
jobs:
helm-release:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
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
@@ -1,193 +0,0 @@
name: Java Client Integration Tests
on:
push:
branches: [ master ]
paths:
- 'other/java/**'
- 'weed/**'
- '.github/workflows/java_integration_tests.yml'
pull_request:
branches: [ master ]
paths:
- 'other/java/**'
- 'weed/**'
- '.github/workflows/java_integration_tests.yml'
jobs:
test:
name: Java Integration Tests
runs-on: ubuntu-latest
strategy:
matrix:
java: ['11', '17']
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Set up Java
uses: actions/setup-java@v5
with:
java-version: ${{ matrix.java }}
distribution: 'temurin'
cache: 'maven'
- name: Build SeaweedFS
run: |
cd weed
go install -buildvcs=false
weed version
- name: Start SeaweedFS Server
run: |
# Create clean data directory
export WEED_DATA_DIR="/tmp/seaweedfs-java-tests-$(date +%s)"
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 \
-master.volumeSizeLimitMB=100 \
-volume.max=100 \
-volume.preStopSeconds=1 \
-master.peers=none \
-filer -filer.maxMB=64 \
-s3 -s3.port=8333 \
-s3.config="$GITHUB_WORKSPACE/docker/compose/s3.json" \
-s3.allowDeleteBucketNotEmpty=true \
-master.port=9333 \
-volume.port=8080 \
-filer.port=8888 \
-metricsPort=9324 > seaweedfs.log 2>&1 &
SERVER_PID=$!
echo "SERVER_PID=$SERVER_PID" >> $GITHUB_ENV
echo "WEED_DATA_DIR=$WEED_DATA_DIR" >> $GITHUB_ENV
echo "SeaweedFS server started with PID: $SERVER_PID"
- name: Wait for SeaweedFS Components
run: |
echo "Waiting for SeaweedFS components to start..."
# Wait for master
for i in {1..30}; do
if curl -s http://localhost:9333/cluster/status > /dev/null 2>&1; then
echo "✓ Master server is ready"
break
fi
echo "Waiting for master server... ($i/30)"
sleep 2
done
# Wait for volume
for i in {1..30}; do
if curl -s http://localhost:8080/status > /dev/null 2>&1; then
echo "✓ Volume server is ready"
break
fi
echo "Waiting for volume server... ($i/30)"
sleep 2
done
# Wait for filer
for i in {1..30}; do
if curl -s http://localhost:8888/ > /dev/null 2>&1; then
echo "✓ Filer is ready"
break
fi
echo "Waiting for filer... ($i/30)"
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
echo "Cluster status:"
curl -s http://localhost:9333/cluster/status | head -20
- name: Build and Install SeaweedFS Client
working-directory: other/java/client
run: |
mvn clean install -DskipTests -Dmaven.javadoc.skip=true -Dgpg.skip=true
- name: Run Client Unit Tests
working-directory: other/java/client
run: |
mvn test -Dtest=SeaweedReadTest,SeaweedCipherTest
- name: Run Client Integration Tests
working-directory: other/java/client
env:
SEAWEEDFS_TEST_ENABLED: true
run: |
mvn test -Dtest=*IntegrationTest
- name: Run HDFS3 Configuration Tests
working-directory: other/java/hdfs3
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: |
echo "=== SeaweedFS Server Log ==="
tail -100 seaweedfs.log || echo "No server log"
echo ""
echo "=== Cluster Status ==="
curl -s http://localhost:9333/cluster/status || echo "Cannot reach cluster"
echo ""
echo "=== Process Status ==="
ps aux | grep weed || echo "No weed processes"
- name: Cleanup
if: always()
run: |
# Stop server using stored PID
if [ -n "$SERVER_PID" ]; then
echo "Stopping SeaweedFS server (PID: $SERVER_PID)"
kill -9 $SERVER_PID 2>/dev/null || true
fi
# Fallback: kill any remaining weed processes
pkill -f "weed server" || true
# Clean up data directory
if [ -n "$WEED_DATA_DIR" ]; then
echo "Cleaning up data directory: $WEED_DATA_DIR"
rm -rf "$WEED_DATA_DIR" || true
fi
-183
View File
@@ -1,183 +0,0 @@
name: "release: java clients"
# Publishes the SeaweedFS Java clients (seaweedfs-client and
# seaweedfs-hadoop3-client) to Maven Central via the Sonatype Central Portal.
#
# Required repository secrets:
# MAVEN_CENTRAL_USERNAME - Central Portal user token username (central.sonatype.com -> Account -> Generate User Token)
# MAVEN_CENTRAL_PASSWORD - Central Portal user token password
# MAVEN_GPG_PRIVATE_KEY - ASCII-armored signing key:
# gpg --homedir <keyring> --armor --export-secret-keys <KEYID> > key.asc
# MAVEN_GPG_PASSPHRASE - passphrase for that key
#
# A plain run publishes to Central. Check dry_run to exercise secrets, GPG
# signing, and the build without committing or publishing.
on:
workflow_dispatch:
inputs:
version:
description: "Version to publish, e.g. 4.39. Leave blank to use the current SeaweedFS version."
type: string
required: false
dry_run:
description: "Build and GPG-sign only; skip the version commit and the Central upload"
type: boolean
default: false
permissions:
contents: write
concurrency:
group: java-release
cancel-in-progress: false
env:
# Java 17 needs these opens for the Maven publishing plugins' reflective access.
MAVEN_OPTS: >-
--add-opens=java.base/java.util=ALL-UNNAMED
--add-opens=java.base/java.lang.reflect=ALL-UNNAMED
--add-opens=java.base/java.text=ALL-UNNAMED
--add-opens=java.desktop/java.awt.font=ALL-UNNAMED
jobs:
publish:
name: Publish to Maven Central
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
with:
# Full history so the version-bump commit can rebase onto a moved master.
fetch-depth: 0
# An explicit input wins; otherwise fall back to the current SeaweedFS
# version (MAJOR.MINOR) from constants.go, matching its %d.%02d formatting.
- name: Resolve version
id: resolve
env:
INPUT_VERSION: ${{ inputs.version }}
run: |
set -euo pipefail
VERSION="$INPUT_VERSION"
if [ -z "$VERSION" ]; then
CONST=weed/util/version/constants.go
MAJOR=$(grep -oP 'MAJOR_VERSION\s*=\s*int32\(\K[0-9]+' "$CONST")
MINOR=$(grep -oP 'MINOR_VERSION\s*=\s*int32\(\K[0-9]+' "$CONST")
VERSION=$(printf '%d.%02d' "$MAJOR" "$MINOR")
echo "No version given; using current SeaweedFS version ${VERSION}."
fi
if ! [[ "$VERSION" =~ ^[0-9]+\.[0-9]+$ ]]; then
echo "::error::version must be MAJOR.MINOR, e.g. 4.39 (got '$VERSION')"
exit 1
fi
echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
- name: Set up JDK 17
uses: actions/setup-java@v5
with:
java-version: '17'
distribution: 'temurin'
cache: 'maven'
server-id: central
server-username: MAVEN_CENTRAL_USERNAME
server-password: MAVEN_CENTRAL_PASSWORD
gpg-private-key: ${{ secrets.MAVEN_GPG_PRIVATE_KEY }}
gpg-passphrase: MAVEN_GPG_PASSPHRASE
# client carries the version literally; hdfs3 derives its own version and
# its seaweedfs-client dependency from the seaweedfs.client.version property.
- name: Set versions in poms
env:
VERSION: ${{ steps.resolve.outputs.version }}
run: |
set -euo pipefail
V=org.codehaus.mojo:versions-maven-plugin:2.16.2
mvn -B -ntp -f other/java/client/pom.xml "${V}:set" \
-DnewVersion="$VERSION" -DgenerateBackupPoms=false
mvn -B -ntp -f other/java/hdfs3/pom.xml "${V}:set-property" \
-Dproperty=seaweedfs.client.version -DnewVersion="$VERSION" -DgenerateBackupPoms=false
- name: Commit version bump
if: ${{ !inputs.dry_run }}
env:
VERSION: ${{ steps.resolve.outputs.version }}
run: |
set -euo pipefail
if git diff --quiet; then
echo "Poms already at ${VERSION}; nothing to commit."
exit 0
fi
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git add other/java/client/pom.xml other/java/hdfs3/pom.xml
git commit -m "java ${VERSION}"
# Rebase and retry so a concurrent push to master doesn't lose the bump.
for attempt in 1 2 3 4 5; do
if git push origin HEAD:master; then
exit 0
fi
echo "push rejected (attempt ${attempt}); rebasing onto latest master"
git pull --rebase origin master
done
echo "::error::could not push version bump after retries"
exit 1
# Tests are skipped here: the integration tests need a live filer, and the
# offline unit tests already run on every push in java_unit_tests.yml.
# dry_run stops at `install` (build + GPG sign, no upload). A real run deploys.
# client goes first either way so its install populates the local repo for hdfs3.
- name: Publish seaweedfs-client
working-directory: other/java/client
env:
MAVEN_CENTRAL_USERNAME: ${{ secrets.MAVEN_CENTRAL_USERNAME }}
MAVEN_CENTRAL_PASSWORD: ${{ secrets.MAVEN_CENTRAL_PASSWORD }}
MAVEN_GPG_PASSPHRASE: ${{ secrets.MAVEN_GPG_PASSPHRASE }}
DRY_RUN: ${{ inputs.dry_run }}
run: |
set -euo pipefail
[ "$DRY_RUN" = "true" ] && GOAL="clean install" || GOAL="clean deploy"
mvn -B -ntp $GOAL -DskipTests
- name: Publish seaweedfs-hadoop3-client
working-directory: other/java/hdfs3
env:
MAVEN_CENTRAL_USERNAME: ${{ secrets.MAVEN_CENTRAL_USERNAME }}
MAVEN_CENTRAL_PASSWORD: ${{ secrets.MAVEN_CENTRAL_PASSWORD }}
MAVEN_GPG_PASSPHRASE: ${{ secrets.MAVEN_GPG_PASSPHRASE }}
DRY_RUN: ${{ inputs.dry_run }}
run: |
set -euo pipefail
[ "$DRY_RUN" = "true" ] && GOAL="clean install" || GOAL="clean deploy"
mvn -B -ntp $GOAL -DskipTests
# Bump every version the wiki quotes for the Java clients. Runs only after
# a successful real publish. Uses GITHUB_TOKEN; set a WIKI_TOKEN secret if
# the token can't push to the wiki.
- name: Update wiki client versions
if: ${{ !inputs.dry_run }}
env:
VERSION: ${{ steps.resolve.outputs.version }}
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
WIKI_TOKEN: ${{ secrets.WIKI_TOKEN }}
run: |
set -euo pipefail
TOKEN="${WIKI_TOKEN:-$GH_TOKEN}"
git clone -q "https://x-access-token:${TOKEN}@github.com/${{ github.repository }}.wiki.git" wiki
cd wiki
for f in $(grep -rlE "seaweedfs-(client|hadoop3-client)" --include="*.md" .); do
NEWV="$VERSION" perl -0777 -i -pe '
my $v = $ENV{NEWV};
s{(<artifactId>seaweedfs-(?:client|hadoop3-client)</artifactId>\s*<version>)[0-9]+\.[0-9]+(</version>)}{$1$v$2}g;
s{(seaweedfs-(?:client|hadoop3-client):)[0-9]+\.[0-9]+}{$1$v}g;
s{(seaweedfs-(?:client|hadoop3-client)-)[0-9]+\.[0-9]+(\.jar)}{$1$v$2}g;
s{(seaweedfs-(?:client|hadoop3-client)/)[0-9]+\.[0-9]+(/)}{$1$v$2}g;
' "$f"
done
if git diff --quiet; then
echo "Wiki already references ${VERSION}."
exit 0
fi
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
git commit -am "java clients ${VERSION}"
git push
-58
View File
@@ -1,58 +0,0 @@
name: Java Client Unit Tests
on:
push:
branches: [ master ]
paths:
- 'other/java/**'
- '.github/workflows/java_unit_tests.yml'
pull_request:
branches: [ master ]
paths:
- 'other/java/**'
- '.github/workflows/java_unit_tests.yml'
jobs:
test:
name: Java Unit Tests
runs-on: ubuntu-latest
strategy:
matrix:
java: ['8', '11', '17', '21']
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Java
uses: actions/setup-java@v5
with:
java-version: ${{ matrix.java }}
distribution: 'temurin'
cache: 'maven'
- name: Build and Install SeaweedFS Client
working-directory: other/java/client
run: |
mvn clean install -DskipTests -Dmaven.javadoc.skip=true -Dgpg.skip=true
- name: Run Client Unit Tests
working-directory: other/java/client
run: |
mvn test -Dtest=SeaweedReadTest,SeaweedCipherTest
- name: Run HDFS3 Configuration Tests
working-directory: other/java/hdfs3
run: |
mvn test -Dtest=SeaweedFileSystemConfigTest -Dmaven.javadoc.skip=true -Dgpg.skip=true
- name: Upload Test Reports
if: always()
uses: actions/upload-artifact@v7
with:
name: test-reports-java-${{ matrix.java }}
path: |
other/java/client/target/surefire-reports/
other/java/hdfs3/target/surefire-reports/
-145
View File
@@ -1,145 +0,0 @@
name: "Kafka Quick Test (Load Test with Schema Registry)"
on:
push:
branches: [ master ]
paths:
- 'weed/mq/**'
- 'weed/pb/mq_pb/**'
- 'weed/pb/schema_pb/**'
- 'test/kafka/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/kafka-quicktest.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/mq/**'
- 'weed/pb/mq_pb/**'
- 'weed/pb/schema_pb/**'
- 'test/kafka/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/kafka-quicktest.yml'
workflow_dispatch: # Allow manual trigger
concurrency:
group: ${{ github.head_ref }}/kafka-quicktest
cancel-in-progress: true
permissions:
contents: read
jobs:
kafka-client-quicktest:
name: Kafka Client Load Test (Quick)
runs-on: ubuntu-latest
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
cache-dependency-path: |
**/go.sum
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Install dependencies
run: |
# Ensure make is available
sudo apt-get update -qq
sudo apt-get install -y make
- name: Validate test setup
working-directory: test/kafka/kafka-client-loadtest
run: |
make validate-setup
- name: Run quick-test
working-directory: test/kafka/kafka-client-loadtest
run: |
# Run the quick-test target which includes:
# 1. Building the gateway
# 2. Starting all services (SeaweedFS, MQ broker, Schema Registry)
# 3. Registering Avro schemas
# 4. Running a 1-minute load test with Avro messages
# Override GOARCH to build for AMD64 (GitHub Actions runners are x86_64)
GOARCH=amd64 make quick-test
env:
# Docker Compose settings
COMPOSE_HTTP_TIMEOUT: 300
DOCKER_CLIENT_TIMEOUT: 300
# Test parameters (set by quick-test, but can override)
TEST_DURATION: 60s
PRODUCER_COUNT: 1
CONSUMER_COUNT: 1
MESSAGE_RATE: 10
VALUE_TYPE: avro
- name: Show test results
if: always()
working-directory: test/kafka/kafka-client-loadtest
run: |
echo "========================================="
echo "Test Results"
echo "========================================="
make show-results || echo "Could not retrieve results"
- name: Show service logs on failure
if: failure()
working-directory: test/kafka/kafka-client-loadtest
run: |
echo "========================================="
echo "Service Logs"
echo "========================================="
echo "Checking running containers..."
docker compose ps || true
echo "========================================="
echo "Master Logs"
echo "========================================="
docker compose logs --tail=100 seaweedfs-master 2>&1 || echo "No master logs available"
echo "========================================="
echo "MQ Broker Logs (Last 100 lines)"
echo "========================================="
docker compose logs --tail=100 seaweedfs-mq-broker 2>&1 || echo "No broker logs available"
echo "========================================="
echo "Kafka Gateway Logs (FULL - Critical for debugging)"
echo "========================================="
docker compose logs kafka-gateway 2>&1 || echo "ERROR: Could not retrieve kafka-gateway logs"
echo "========================================="
echo "Schema Registry Logs (FULL)"
echo "========================================="
docker compose logs schema-registry 2>&1 || echo "ERROR: Could not retrieve schema-registry logs"
echo "========================================="
echo "Load Test Logs"
echo "========================================="
docker compose logs --tail=100 kafka-client-loadtest 2>&1 || echo "No loadtest logs available"
- name: Cleanup
if: always()
working-directory: test/kafka/kafka-client-loadtest
run: |
# Stop containers first
docker compose --profile loadtest --profile monitoring down -v --remove-orphans || true
# Clean up data with sudo to handle Docker root-owned files
sudo rm -rf data/* || true
# Clean up binary
rm -f weed-linux-* || true
-841
View File
@@ -1,841 +0,0 @@
name: "Kafka Gateway Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/mq/**'
- 'weed/pb/mq_pb/**'
- 'weed/pb/schema_pb/**'
- 'test/kafka/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/kafka-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/mq/**'
- 'weed/pb/mq_pb/**'
- 'weed/pb/schema_pb/**'
- 'test/kafka/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/kafka-tests.yml'
concurrency:
group: ${{ github.head_ref }}/kafka-tests
cancel-in-progress: true
# Force different runners for better isolation
env:
FORCE_RUNNER_SEPARATION: true
permissions:
contents: read
jobs:
kafka-unit-tests:
name: Kafka Unit Tests
runs-on: ubuntu-latest
timeout-minutes: 5
strategy:
fail-fast: false
matrix:
container-id: [unit-tests-1]
container:
image: golang:1.26-alpine
options: --cpus 1.0 --memory 1g --hostname kafka-unit-${{ matrix.container-id }}
env:
GOMAXPROCS: 1
CGO_ENABLED: 0
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code
uses: actions/checkout@v7
- name: Setup Container Environment
run: |
apk add --no-cache git
ulimit -n 1024 || echo "Warning: Could not set file descriptor limit"
- name: Get dependencies
run: |
cd test/kafka
go mod download
go mod tidy
- name: Run Kafka Gateway Unit Tests
run: |
cd test/kafka
# Set process limits for container isolation
ulimit -n 512 || echo "Warning: Could not set file descriptor limit"
ulimit -u 100 || echo "Warning: Could not set process limit"
go test -v -timeout 10s ./unit/...
kafka-integration-tests:
name: Kafka Integration Tests (Critical)
runs-on: ubuntu-latest
timeout-minutes: 5
strategy:
fail-fast: false
matrix:
container-id: [integration-1]
container:
image: golang:1.26-alpine
options: --cpus 2.0 --memory 2g --ulimit nofile=1024:1024 --hostname kafka-integration-${{ matrix.container-id }}
env:
GOMAXPROCS: 2
CGO_ENABLED: 0
KAFKA_TEST_ISOLATION: "true"
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code
uses: actions/checkout@v7
- name: Setup Integration Container Environment
run: |
apk add --no-cache git procps
ulimit -n 2048 || echo "Warning: Could not set file descriptor limit"
- name: Get dependencies
run: |
cd test/kafka
go mod download
go mod tidy
- name: Run Integration Tests
run: |
cd test/kafka
# Higher limits for integration tests
ulimit -n 1024 || echo "Warning: Could not set file descriptor limit"
ulimit -u 200 || echo "Warning: Could not set process limit"
go test -v -timeout 90s ./integration/...
env:
GOMAXPROCS: 2
kafka-e2e-tests:
name: Kafka End-to-End Tests (with SMQ)
runs-on: ubuntu-latest
timeout-minutes: 20
strategy:
fail-fast: false
matrix:
container-id: [e2e-1]
container:
image: golang:1.26-alpine
options: --cpus 2.0 --memory 2g --hostname kafka-e2e-${{ matrix.container-id }}
env:
GOMAXPROCS: 2
CGO_ENABLED: 0
KAFKA_E2E_ISOLATION: "true"
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
cache-dependency-path: |
**/go.sum
id: go
- name: Setup E2E Container Environment
run: |
apk add --no-cache git procps curl netcat-openbsd
ulimit -n 2048 || echo "Warning: Could not set file descriptor limit"
- name: Warm Go module cache
run: |
# Warm cache for root module
go mod download || true
# Warm cache for kafka test module
cd test/kafka
go mod download || true
- name: Get dependencies
run: |
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: |
set -e
cd $GITHUB_WORKSPACE
# Build weed binary
go build -o /usr/local/bin/weed ./weed
# Start SeaweedFS components with MQ brokers
export WEED_DATA_DIR=/tmp/seaweedfs-e2e-$RANDOM
mkdir -p "$WEED_DATA_DIR"
# Start SeaweedFS server (master, volume, filer) with consistent IP advertising
nohup weed -v 1 server \
-ip="127.0.0.1" \
-ip.bind="0.0.0.0" \
-dir="$WEED_DATA_DIR" \
-master.raftHashicorp \
-master.port=9333 \
-volume.port=8081 \
-filer.port=8888 \
-filer=true \
-metricsPort=9325 \
-master.peers=none \
> /tmp/weed-server.log 2>&1 &
# Wait for master to be ready
for i in $(seq 1 30); do
if curl -s http://127.0.0.1:9333/cluster/status >/dev/null; then
echo "SeaweedFS master HTTP is up"; break
fi
echo "Waiting for SeaweedFS master HTTP... ($i/30)"; sleep 1
done
# Wait for master gRPC to be ready (this is what broker discovery uses)
echo "Waiting for master gRPC port..."
for i in $(seq 1 30); do
if nc -z 127.0.0.1 19333; then
echo "✓ SeaweedFS master gRPC is up (port 19333)"
break
fi
echo " Waiting for master gRPC... ($i/30)"; sleep 1
done
# Give server time to initialize all components including gRPC services
echo "Waiting for SeaweedFS components to initialize..."
sleep 15
# Additional wait specifically for gRPC services to be ready for streaming
echo "Allowing extra time for master gRPC streaming services to initialize..."
sleep 10
# Start MQ broker with maximum verbosity for debugging
echo "Starting MQ broker..."
nohup weed -v 3 mq.broker \
-master="127.0.0.1:9333" \
-ip="127.0.0.1" \
-port=17777 \
-logFlushInterval=0 \
> /tmp/weed-mq-broker.log 2>&1 &
# Wait for broker to be ready with better error reporting
sleep 15
broker_ready=false
for i in $(seq 1 20); do
if nc -z 127.0.0.1 17777; then
echo "SeaweedFS MQ broker is up"
broker_ready=true
break
fi
echo "Waiting for MQ broker... ($i/20)"; sleep 1
done
# Give broker additional time to register with master
if [ "$broker_ready" = true ]; then
echo "Allowing broker to register with master..."
sleep 30
# Check if broker is properly registered by querying cluster nodes
echo "Cluster status after broker registration:"
curl -s "http://127.0.0.1:9333/cluster/status" || echo "Could not check cluster status"
echo "Checking cluster topology (includes registered components):"
curl -s "http://127.0.0.1:9333/dir/status" | head -20 || echo "Could not check dir status"
echo "Verifying broker discovery via master client debug:"
echo "If broker registration is successful, it should appear in dir status"
echo "Testing gRPC connectivity with weed binary:"
echo "This simulates what the gateway does during broker discovery..."
timeout 10s weed shell -master=127.0.0.1:9333 -filer=127.0.0.1:8888 > /tmp/shell-test.log 2>&1 || echo "weed shell test completed or timed out - checking logs..."
echo "Shell test results:"
cat /tmp/shell-test.log 2>/dev/null | head -10 || echo "No shell test logs"
fi
# Check if broker failed to start and show logs
if [ "$broker_ready" = false ]; then
echo "ERROR: MQ broker failed to start. Broker logs:"
cat /tmp/weed-mq-broker.log || echo "No broker logs found"
echo "Server logs:"
tail -20 /tmp/weed-server.log || echo "No server logs found"
exit 1
fi
- name: Run End-to-End Tests
run: |
cd test/kafka
# Higher limits for E2E tests
ulimit -n 1024 || echo "Warning: Could not set file descriptor limit"
ulimit -u 200 || echo "Warning: Could not set process limit"
# Allow additional time for all background processes to settle
echo "Allowing additional settlement time for SeaweedFS ecosystem..."
sleep 15
# Run tests and capture result
if ! go test -v -timeout 180s ./e2e/...; then
echo "========================================="
echo "Tests failed! Showing debug information:"
echo "========================================="
echo "Server logs (last 50 lines):"
tail -50 /tmp/weed-server.log || echo "No server logs"
echo "========================================="
echo "Broker logs (last 50 lines):"
tail -50 /tmp/weed-mq-broker.log || echo "No broker logs"
echo "========================================="
exit 1
fi
env:
GOMAXPROCS: 2
SEAWEEDFS_MASTERS: 127.0.0.1:9333
kafka-consumer-group-tests:
name: Kafka Consumer Group Tests (Highly Isolated)
runs-on: ubuntu-latest
timeout-minutes: 20
strategy:
fail-fast: false
matrix:
container-id: [consumer-group-1]
container:
image: golang:1.26-alpine
options: --cpus 1.0 --memory 2g --ulimit nofile=512:512 --hostname kafka-consumer-${{ matrix.container-id }}
env:
GOMAXPROCS: 1
CGO_ENABLED: 0
KAFKA_CONSUMER_ISOLATION: "true"
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
cache-dependency-path: |
**/go.sum
id: go
- name: Setup Consumer Group Container Environment
run: |
apk add --no-cache git procps curl netcat-openbsd
ulimit -n 256 || echo "Warning: Could not set file descriptor limit"
- name: Warm Go module cache
run: |
# Warm cache for root module
go mod download || true
# Warm cache for kafka test module
cd test/kafka
go mod download || true
- name: Get dependencies
run: |
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: |
set -e
cd $GITHUB_WORKSPACE
# Build weed binary
go build -o /usr/local/bin/weed ./weed
# Start SeaweedFS components with MQ brokers
export WEED_DATA_DIR=/tmp/seaweedfs-mq-$RANDOM
mkdir -p "$WEED_DATA_DIR"
# Start SeaweedFS server (master, volume, filer) with consistent IP advertising
nohup weed -v 1 server \
-ip="127.0.0.1" \
-ip.bind="0.0.0.0" \
-dir="$WEED_DATA_DIR" \
-master.raftHashicorp \
-master.port=9333 \
-volume.port=8081 \
-filer.port=8888 \
-filer=true \
-metricsPort=9325 \
-master.peers=none \
> /tmp/weed-server.log 2>&1 &
# Wait for master to be ready
for i in $(seq 1 30); do
if curl -s http://127.0.0.1:9333/cluster/status >/dev/null; then
echo "SeaweedFS master HTTP is up"; break
fi
echo "Waiting for SeaweedFS master HTTP... ($i/30)"; sleep 1
done
# Wait for master gRPC to be ready (this is what broker discovery uses)
echo "Waiting for master gRPC port..."
for i in $(seq 1 30); do
if nc -z 127.0.0.1 19333; then
echo "✓ SeaweedFS master gRPC is up (port 19333)"
break
fi
echo " Waiting for master gRPC... ($i/30)"; sleep 1
done
# Give server time to initialize all components including gRPC services
echo "Waiting for SeaweedFS components to initialize..."
sleep 15
# Additional wait specifically for gRPC services to be ready for streaming
echo "Allowing extra time for master gRPC streaming services to initialize..."
sleep 10
# Start MQ broker with maximum verbosity for debugging
echo "Starting MQ broker..."
nohup weed -v 3 mq.broker \
-master="127.0.0.1:9333" \
-ip="127.0.0.1" \
-port=17777 \
-logFlushInterval=0 \
> /tmp/weed-mq-broker.log 2>&1 &
# Wait for broker to be ready with better error reporting
sleep 15
broker_ready=false
for i in $(seq 1 20); do
if nc -z 127.0.0.1 17777; then
echo "SeaweedFS MQ broker is up"
broker_ready=true
break
fi
echo "Waiting for MQ broker... ($i/20)"; sleep 1
done
# Give broker additional time to register with master
if [ "$broker_ready" = true ]; then
echo "Allowing broker to register with master..."
sleep 30
# Check if broker is properly registered by querying cluster nodes
echo "Cluster status after broker registration:"
curl -s "http://127.0.0.1:9333/cluster/status" || echo "Could not check cluster status"
echo "Checking cluster topology (includes registered components):"
curl -s "http://127.0.0.1:9333/dir/status" | head -20 || echo "Could not check dir status"
echo "Verifying broker discovery via master client debug:"
echo "If broker registration is successful, it should appear in dir status"
echo "Testing gRPC connectivity with weed binary:"
echo "This simulates what the gateway does during broker discovery..."
timeout 10s weed shell -master=127.0.0.1:9333 -filer=127.0.0.1:8888 > /tmp/shell-test.log 2>&1 || echo "weed shell test completed or timed out - checking logs..."
echo "Shell test results:"
cat /tmp/shell-test.log 2>/dev/null | head -10 || echo "No shell test logs"
fi
# Check if broker failed to start and show logs
if [ "$broker_ready" = false ]; then
echo "ERROR: MQ broker failed to start. Broker logs:"
cat /tmp/weed-mq-broker.log || echo "No broker logs found"
echo "Server logs:"
tail -20 /tmp/weed-server.log || echo "No server logs found"
exit 1
fi
- name: Run Consumer Group Tests
run: |
cd test/kafka
# Test consumer group functionality with explicit timeout
ulimit -n 512 || echo "Warning: Could not set file descriptor limit"
ulimit -u 100 || echo "Warning: Could not set process limit"
timeout 240s go test -v -run "^TestConsumerGroups" -timeout 180s ./integration/...
env:
GOMAXPROCS: 1
SEAWEEDFS_MASTERS: 127.0.0.1:9333
kafka-client-compatibility:
name: Kafka Client Compatibility (with SMQ)
runs-on: ubuntu-latest
timeout-minutes: 25
strategy:
fail-fast: false
matrix:
container-id: [client-compat-1]
container:
image: golang:1.26-alpine
options: --cpus 1.0 --memory 1.5g --shm-size 256m --hostname kafka-client-${{ matrix.container-id }}
env:
GOMAXPROCS: 1
CGO_ENABLED: 0
KAFKA_CLIENT_ISOLATION: "true"
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
cache-dependency-path: |
**/go.sum
id: go
- name: Setup Client Container Environment
run: |
apk add --no-cache git procps curl netcat-openbsd
ulimit -n 1024 || echo "Warning: Could not set file descriptor limit"
- name: Warm Go module cache
run: |
# Warm cache for root module
go mod download || true
# Warm cache for kafka test module
cd test/kafka
go mod download || true
- name: Get dependencies
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: |
set -e
cd $GITHUB_WORKSPACE
# Build weed binary
go build -o /usr/local/bin/weed ./weed
# Start SeaweedFS components with MQ brokers
export WEED_DATA_DIR=/tmp/seaweedfs-client-$RANDOM
mkdir -p "$WEED_DATA_DIR"
# Start SeaweedFS server (master, volume, filer) with consistent IP advertising
nohup weed -v 1 server \
-ip="127.0.0.1" \
-ip.bind="0.0.0.0" \
-dir="$WEED_DATA_DIR" \
-master.raftHashicorp \
-master.port=9333 \
-volume.port=8081 \
-filer.port=8888 \
-filer=true \
-metricsPort=9325 \
-master.peers=none \
> /tmp/weed-server.log 2>&1 &
# Wait for master to be ready
for i in $(seq 1 30); do
if curl -s http://127.0.0.1:9333/cluster/status >/dev/null; then
echo "SeaweedFS master HTTP is up"; break
fi
echo "Waiting for SeaweedFS master HTTP... ($i/30)"; sleep 1
done
# Wait for master gRPC to be ready (this is what broker discovery uses)
echo "Waiting for master gRPC port..."
for i in $(seq 1 30); do
if nc -z 127.0.0.1 19333; then
echo "✓ SeaweedFS master gRPC is up (port 19333)"
break
fi
echo " Waiting for master gRPC... ($i/30)"; sleep 1
done
# Give server time to initialize all components including gRPC services
echo "Waiting for SeaweedFS components to initialize..."
sleep 15
# Additional wait specifically for gRPC services to be ready for streaming
echo "Allowing extra time for master gRPC streaming services to initialize..."
sleep 10
# Start MQ broker with maximum verbosity for debugging
echo "Starting MQ broker..."
nohup weed -v 3 mq.broker \
-master="127.0.0.1:9333" \
-ip="127.0.0.1" \
-port=17777 \
-logFlushInterval=0 \
> /tmp/weed-mq-broker.log 2>&1 &
# Wait for broker to be ready with better error reporting
sleep 15
broker_ready=false
for i in $(seq 1 20); do
if nc -z 127.0.0.1 17777; then
echo "SeaweedFS MQ broker is up"
broker_ready=true
break
fi
echo "Waiting for MQ broker... ($i/20)"; sleep 1
done
# Give broker additional time to register with master
if [ "$broker_ready" = true ]; then
echo "Allowing broker to register with master..."
sleep 30
# Check if broker is properly registered by querying cluster nodes
echo "Cluster status after broker registration:"
curl -s "http://127.0.0.1:9333/cluster/status" || echo "Could not check cluster status"
echo "Checking cluster topology (includes registered components):"
curl -s "http://127.0.0.1:9333/dir/status" | head -20 || echo "Could not check dir status"
echo "Verifying broker discovery via master client debug:"
echo "If broker registration is successful, it should appear in dir status"
echo "Testing gRPC connectivity with weed binary:"
echo "This simulates what the gateway does during broker discovery..."
timeout 10s weed shell -master=127.0.0.1:9333 -filer=127.0.0.1:8888 > /tmp/shell-test.log 2>&1 || echo "weed shell test completed or timed out - checking logs..."
echo "Shell test results:"
cat /tmp/shell-test.log 2>/dev/null | head -10 || echo "No shell test logs"
fi
# Check if broker failed to start and show logs
if [ "$broker_ready" = false ]; then
echo "ERROR: MQ broker failed to start. Broker logs:"
cat /tmp/weed-mq-broker.log || echo "No broker logs found"
echo "Server logs:"
tail -20 /tmp/weed-server.log || echo "No server logs found"
exit 1
fi
- name: Run Client Compatibility Tests
run: |
cd test/kafka
go test -v -run "^TestClientCompatibility" -timeout 180s ./integration/...
env:
GOMAXPROCS: 1
SEAWEEDFS_MASTERS: 127.0.0.1:9333
kafka-smq-integration-tests:
name: Kafka SMQ Integration Tests (Full Stack)
runs-on: ubuntu-latest
timeout-minutes: 20
strategy:
fail-fast: false
matrix:
container-id: [smq-integration-1]
container:
image: golang:1.26-alpine
options: --cpus 1.0 --memory 2g --hostname kafka-smq-${{ matrix.container-id }}
env:
GOMAXPROCS: 1
CGO_ENABLED: 0
KAFKA_SMQ_INTEGRATION: "true"
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
cache-dependency-path: |
**/go.sum
id: go
- name: Setup SMQ Integration Container Environment
run: |
apk add --no-cache git procps curl netcat-openbsd
ulimit -n 1024 || echo "Warning: Could not set file descriptor limit"
- name: Warm Go module cache
run: |
# Warm cache for root module
go mod download || true
# Warm cache for kafka test module
cd test/kafka
go mod download || true
- name: Get dependencies
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: |
set -e
cd $GITHUB_WORKSPACE
# Build weed binary
go build -o /usr/local/bin/weed ./weed
# Start SeaweedFS components with MQ brokers
export WEED_DATA_DIR=/tmp/seaweedfs-smq-$RANDOM
mkdir -p "$WEED_DATA_DIR"
# Start SeaweedFS server (master, volume, filer) with consistent IP advertising
nohup weed -v 1 server \
-ip="127.0.0.1" \
-ip.bind="0.0.0.0" \
-dir="$WEED_DATA_DIR" \
-master.raftHashicorp \
-master.port=9333 \
-volume.port=8081 \
-filer.port=8888 \
-filer=true \
-metricsPort=9325 \
-master.peers=none \
> /tmp/weed-server.log 2>&1 &
# Wait for master to be ready
for i in $(seq 1 30); do
if curl -s http://127.0.0.1:9333/cluster/status >/dev/null; then
echo "SeaweedFS master HTTP is up"; break
fi
echo "Waiting for SeaweedFS master HTTP... ($i/30)"; sleep 1
done
# Wait for master gRPC to be ready (this is what broker discovery uses)
echo "Waiting for master gRPC port..."
for i in $(seq 1 30); do
if nc -z 127.0.0.1 19333; then
echo "✓ SeaweedFS master gRPC is up (port 19333)"
break
fi
echo " Waiting for master gRPC... ($i/30)"; sleep 1
done
# Give server time to initialize all components including gRPC services
echo "Waiting for SeaweedFS components to initialize..."
sleep 15
# Additional wait specifically for gRPC services to be ready for streaming
echo "Allowing extra time for master gRPC streaming services to initialize..."
sleep 10
# Start MQ broker with maximum verbosity for debugging
echo "Starting MQ broker..."
nohup weed -v 3 mq.broker \
-master="127.0.0.1:9333" \
-ip="127.0.0.1" \
-port=17777 \
-logFlushInterval=0 \
> /tmp/weed-mq-broker.log 2>&1 &
# Wait for broker to be ready with better error reporting
sleep 15
broker_ready=false
for i in $(seq 1 20); do
if nc -z 127.0.0.1 17777; then
echo "SeaweedFS MQ broker is up"
broker_ready=true
break
fi
echo "Waiting for MQ broker... ($i/20)"; sleep 1
done
# Give broker additional time to register with master
if [ "$broker_ready" = true ]; then
echo "Allowing broker to register with master..."
sleep 30
# Check if broker is properly registered by querying cluster nodes
echo "Cluster status after broker registration:"
curl -s "http://127.0.0.1:9333/cluster/status" || echo "Could not check cluster status"
echo "Checking cluster topology (includes registered components):"
curl -s "http://127.0.0.1:9333/dir/status" | head -20 || echo "Could not check dir status"
echo "Verifying broker discovery via master client debug:"
echo "If broker registration is successful, it should appear in dir status"
echo "Testing gRPC connectivity with weed binary:"
echo "This simulates what the gateway does during broker discovery..."
timeout 10s weed shell -master=127.0.0.1:9333 -filer=127.0.0.1:8888 > /tmp/shell-test.log 2>&1 || echo "weed shell test completed or timed out - checking logs..."
echo "Shell test results:"
cat /tmp/shell-test.log 2>/dev/null | head -10 || echo "No shell test logs"
fi
# Check if broker failed to start and show logs
if [ "$broker_ready" = false ]; then
echo "ERROR: MQ broker failed to start. Broker logs:"
cat /tmp/weed-mq-broker.log || echo "No broker logs found"
echo "Server logs:"
tail -20 /tmp/weed-server.log || echo "No server logs found"
exit 1
fi
- name: Run SMQ Integration Tests
run: |
cd test/kafka
ulimit -n 512 || echo "Warning: Could not set file descriptor limit"
ulimit -u 100 || echo "Warning: Could not set process limit"
# Run the dedicated SMQ integration tests
go test -v -run "^TestSMQIntegration" -timeout 180s ./integration/...
env:
GOMAXPROCS: 1
SEAWEEDFS_MASTERS: 127.0.0.1:9333
kafka-protocol-tests:
name: Kafka Protocol Tests (Isolated)
runs-on: ubuntu-latest
timeout-minutes: 5
strategy:
fail-fast: false
matrix:
container-id: [protocol-1]
container:
image: golang:1.26-alpine
options: --cpus 1.0 --memory 1g --tmpfs /tmp:exec --hostname kafka-protocol-${{ matrix.container-id }}
env:
GOMAXPROCS: 1
CGO_ENABLED: 0
KAFKA_PROTOCOL_ISOLATION: "true"
CONTAINER_ID: ${{ matrix.container-id }}
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code
uses: actions/checkout@v7
- name: Setup Protocol Container Environment
run: |
apk add --no-cache git procps
# Ensure proper permissions for test execution
chmod -R 755 /tmp || true
export TMPDIR=/tmp
export GOCACHE=/tmp/go-cache
mkdir -p $GOCACHE
chmod 755 $GOCACHE
- name: Get dependencies
run: |
cd test/kafka
go mod download
go mod tidy
- name: Run Protocol Tests
run: |
cd test/kafka
export TMPDIR=/tmp
export GOCACHE=/tmp/go-cache
# Run protocol tests from the weed/mq/kafka directory since they test the protocol implementation
cd ../../weed/mq/kafka
go test -v -run "^Test.*" -timeout 10s ./...
env:
GOMAXPROCS: 1
TMPDIR: /tmp
GOCACHE: /tmp/go-cache
-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@v7
- name: Set up Go
uses: actions/setup-go@v7
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
@@ -1,79 +0,0 @@
name: "Master Cold Start Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/server/master_*.go'
- 'weed/topology/**'
- 'weed/operation/**'
- 'test/master_cold_start/**'
- 'test/testutil/**'
- '.github/workflows/master-cold-start-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/server/master_*.go'
- 'weed/topology/**'
- 'weed/operation/**'
- 'test/master_cold_start/**'
- 'test/testutil/**'
- '.github/workflows/master-cold-start-tests.yml'
concurrency:
group: ${{ github.head_ref || github.ref }}/master-cold-start-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
master-cold-start-tests:
name: Master Cold Start Tests
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- name: Check out code
uses: actions/checkout@v7
with:
persist-credentials: false
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Build weed binary
run: |
cd weed && go install -buildvcs=false
- name: Run master cold start tests
# test/master_cold_start boots a fresh master plus empty volume
# servers and requires the very first assign (HTTP and gRPC, no
# client retries) to complete a write: the assign that triggers
# volume growth must wait for it instead of failing with
# "volume growth in progress".
run: |
export WEED_BINARY=$(go env GOPATH)/bin/weed
go test -v -timeout=8m ./test/master_cold_start/...
- name: Collect server logs on failure
if: failure()
run: |
# test/master_cold_start/cluster.go keeps failing-test dirs created
# via os.MkdirTemp("", "seaweedfs_master_cold_start_it_") with each
# process log under <baseDir>/logs/.
mkdir -p /tmp/master-cold-start-logs
find /tmp -maxdepth 1 -type d -name "seaweedfs_master_cold_start_it_*" 2>/dev/null | while read dir; do
echo "Found test directory: $dir"
cp -r "$dir" /tmp/master-cold-start-logs/ 2>/dev/null || true
done
find /tmp/master-cold-start-logs -type f -name "*.log" -print -exec tail -n 100 {} \; 2>/dev/null || echo "No logs found"
- name: Archive logs
if: failure()
uses: actions/upload-artifact@v7
with:
name: master-cold-start-test-logs
path: /tmp/master-cold-start-logs/
retention-days: 7
@@ -1,93 +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/server/master_grpc_server.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/server/master_grpc_server.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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
-203
View File
@@ -1,203 +0,0 @@
name: "mount: benchmark"
# Manual benchmark: native WinFsp mount vs rclone+WebDAV on the same Windows
# runner, with a Linux FUSE mount of the same build as a reference. Numbers
# from shared runners are noisy; this is for finding factor-of-N gaps, not
# regressions of a few percent.
on:
workflow_dispatch:
push:
branches: [ 'winfsp-bench**' ]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
permissions:
contents: read
jobs:
bench-windows:
name: Windows native vs rclone
runs-on: windows-latest
timeout-minutes: 60
env:
CGO_ENABLED: 0
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install WinFsp and rclone
run: choco install winfsp rclone -y --no-progress
- name: Build weed.exe
run: go build -o weed.exe ./weed
- name: Benchmark both mounts
shell: pwsh
run: |
$ErrorActionPreference = 'Stop'
function Test-Port($port) {
$client = New-Object System.Net.Sockets.TcpClient
try { $client.Connect('127.0.0.1', $port); return $client.Connected }
catch { return $false }
finally { $client.Dispose() }
}
function Wait-Drive($drive, $what) {
$deadline = (Get-Date).AddMinutes(2)
while ((Get-Date) -lt $deadline) {
if (Test-Path "${drive}\") { Write-Host "$what is mounted on $drive"; return }
Start-Sleep -Seconds 2
}
throw "$what never appeared on $drive"
}
function Invoke-Bench($dir, $label, $out) {
Write-Host "::group::bench $label"
& go run ./test/mount_bench -dir $dir -label $label -filer 127.0.0.1:8888 -out $out
$code = $LASTEXITCODE
Write-Host "::endgroup::"
if ($code -ne 0) { throw "bench $label failed with exit $code" }
}
New-Item -ItemType Directory -Force -Path C:\seaweed-data | Out-Null
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mini','-dir=C:\seaweed-data','-ip=127.0.0.1' `
-RedirectStandardOutput C:\seaweed-mini.log -RedirectStandardError C:\seaweed-mini.err.log
$deadline = (Get-Date).AddMinutes(3)
while ((Get-Date) -lt $deadline) {
if ((Test-Port 8888) -and (Test-Port 18888) -and (Test-Port 7333)) { break }
Start-Sleep -Seconds 3
}
if (-not ((Test-Port 8888) -and (Test-Port 18888) -and (Test-Port 7333))) {
Get-Content C:\seaweed-mini.log, C:\seaweed-mini.err.log -ErrorAction SilentlyContinue
throw "mini cluster never came up"
}
Write-Host "filer on 8888/18888, webdav on 7333"
# --- native WinFsp mount ---
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mount','-filer=127.0.0.1:8888','-dir=S:' `
-RedirectStandardOutput C:\seaweed-mount.log -RedirectStandardError C:\seaweed-mount.err.log
Wait-Drive 'S:' 'weed mount'
Invoke-Bench 'S:\bench-native' 'winfsp-native' 'C:\results-native.json'
Get-CimInstance Win32_Process -Filter "Name = 'weed.exe'" |
Where-Object { $_.CommandLine -like '*mount*' } |
ForEach-Object { Stop-Process -Id $_.ProcessId -Force }
$deadline = (Get-Date).AddMinutes(1)
while ((Get-Date) -lt $deadline -and (Test-Path S:\)) { Start-Sleep -Seconds 2 }
# --- rclone + WebDAV on the same WinFsp ---
# rclone serves listings from a directory cache it fills lazily, so the
# big-listing files have to exist before it mounts or it never sees them.
& go run ./test/mount_bench -filer 127.0.0.1:8888 -seed bench-rclone/biglist
if ($LASTEXITCODE -ne 0) { throw "seeding failed" }
$env:RCLONE_CONFIG_SEAWEED_TYPE = 'webdav'
$env:RCLONE_CONFIG_SEAWEED_URL = 'http://127.0.0.1:7333'
$env:RCLONE_CONFIG_SEAWEED_VENDOR = 'other'
Start-Process -FilePath rclone `
-ArgumentList 'mount','seaweed:','T:','--vfs-cache-mode=writes','-v','--log-file=C:\rclone.log'
Wait-Drive 'T:' 'rclone mount'
Invoke-Bench 'T:\bench-rclone' 'rclone-webdav' 'C:\results-rclone.json'
Stop-Process -Name rclone -Force -ErrorAction SilentlyContinue
# --- comparison ---
$table = & go run ./test/mount_bench -compare C:\results-native.json,C:\results-rclone.json
$table | Write-Host
"## Windows: native WinFsp vs rclone+WebDAV" | Out-File -Append $env:GITHUB_STEP_SUMMARY
$table | Out-File -Append $env:GITHUB_STEP_SUMMARY
- name: Logs
if: always()
shell: pwsh
run: |
foreach ($f in 'C:\seaweed-mount.log','C:\seaweed-mount.err.log','C:\rclone.log','C:\seaweed-mini.log','C:\seaweed-mini.err.log') {
if (Test-Path $f) { Write-Host "===== $f"; Get-Content $f -Tail 100 }
}
- name: Results
if: always()
uses: actions/upload-artifact@v4
with:
name: results-windows
path: C:\results-*.json
if-no-files-found: ignore
bench-linux:
name: Linux FUSE reference
runs-on: ubuntu-latest
timeout-minutes: 60
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Repair the fusermount3 setuid bit
uses: ./.github/actions/fix-fusermount-setuid
- name: Allow non-root FUSE mounts with allow_other
run: |
echo 'user_allow_other' | sudo tee -a /etc/fuse.conf
sudo chmod 644 /etc/fuse.conf
- name: Build weed
run: go build -o /tmp/weed ./weed
- name: Benchmark FUSE mount
run: |
set -e
mkdir -p /tmp/seaweed-data
/tmp/weed -logtostderr mini -dir=/tmp/seaweed-data -ip=127.0.0.1 > /tmp/mini.log 2>&1 &
for i in $(seq 1 60); do
if nc -z 127.0.0.1 8888 && nc -z 127.0.0.1 18888; then break; fi
sleep 3
done
nc -z 127.0.0.1 8888 || { cat /tmp/mini.log; echo "filer never came up"; exit 1; }
mkdir -p "$HOME/mnt"
/tmp/weed -logtostderr mount -filer=127.0.0.1:8888 -dir="$HOME/mnt" > /tmp/mount.log 2>&1 &
for i in $(seq 1 60); do
if mountpoint -q "$HOME/mnt"; then break; fi
sleep 2
done
mountpoint -q "$HOME/mnt" || { cat /tmp/mount.log; echo "mount never appeared"; exit 1; }
go run ./test/mount_bench -dir "$HOME/mnt/bench-linux" -label linux-fuse -filer 127.0.0.1:8888 -out /tmp/results-linux.json
{
echo "## Linux FUSE reference"
go run ./test/mount_bench -compare /tmp/results-linux.json
} >> "$GITHUB_STEP_SUMMARY"
- name: Logs
if: always()
run: |
tail -n 100 /tmp/mount.log /tmp/mini.log 2>/dev/null || true
- name: Results
if: always()
uses: actions/upload-artifact@v4
with:
name: results-linux
path: /tmp/results-linux.json
if-no-files-found: ignore
@@ -1,124 +0,0 @@
name: "mount: windows conformance"
on:
push:
branches: [ master ]
paths:
- 'weed/mount/**'
- 'weed/command/mount*.go'
- 'weed/storage/volume_vacuum*.go'
- 'weed/storage/volume_loading.go'
- 'weed/storage/disk_location.go'
- 'test/winfsp-conformance/**'
- '.github/workflows/mount-windows-conformance.yml'
# No base branch filter: this is the only thing that runs the Windows mount,
# so it should cover a pull request stacked on another one too.
pull_request:
paths:
- 'weed/mount/**'
- 'weed/command/mount*.go'
- 'weed/storage/volume_vacuum*.go'
- 'weed/storage/volume_loading.go'
- 'weed/storage/disk_location.go'
- 'test/winfsp-conformance/**'
- '.github/workflows/mount-windows-conformance.yml'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
permissions:
contents: read
jobs:
conformance:
name: WinFsp conformance
runs-on: windows-latest
timeout-minutes: 60
env:
# The runner ships MinGW, so cgo is on by default and cgofuse picks its
# cgo variant, which wants WinFsp's headers. The nocgo variant loads
# winfsp-x64.dll at run time instead, which is how weed.exe is released.
CGO_ENABLED: 0
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
# cgofuse loads winfsp-x64.dll at run time, so WinFsp is needed here but
# not to build.
- name: Install WinFsp
run: choco install winfsp -y --no-progress
- name: Build weed.exe
run: go build -o weed.exe ./weed
# The runner tears down a step's process tree when its shell exits, so a
# cluster started in one step is gone by the next. Everything that needs
# the cluster and the mount alive has to share a step.
- name: Mount and run winfsp-tests
shell: pwsh
run: |
$ErrorActionPreference = 'Stop'
function Test-Port($port) {
# A plain connect, because Test-NetConnection has reported success
# here for a port nothing was listening on.
$client = New-Object System.Net.Sockets.TcpClient
try { $client.Connect('127.0.0.1', $port); return $client.Connected }
catch { return $false }
finally { $client.Dispose() }
}
function Start-Mount($log) {
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mount','-filer=127.0.0.1:8888','-dir=S:' `
-RedirectStandardOutput "C:\$log.log" -RedirectStandardError "C:\$log.err.log"
$deadline = (Get-Date).AddMinutes(2)
while ((Get-Date) -lt $deadline) {
if (Test-Path S:\) { Write-Host "S: is mounted"; return }
Start-Sleep -Seconds 2
}
Get-Content "C:\$log.log", "C:\$log.err.log" -ErrorAction SilentlyContinue
throw "S: never appeared"
}
New-Item -ItemType Directory -Force -Path C:\seaweed-data | Out-Null
# -ip pins the cluster to loopback; it otherwise advertises and binds
# the runner's LAN address, which 127.0.0.1 cannot reach.
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mini','-dir=C:\seaweed-data','-ip=127.0.0.1' `
-RedirectStandardOutput C:\seaweed-mini.log -RedirectStandardError C:\seaweed-mini.err.log
$deadline = (Get-Date).AddMinutes(3)
while ((Get-Date) -lt $deadline) {
# The mount dials grpc, not http, so both ports have to answer.
if ((Test-Port 8888) -and (Test-Port 18888)) { break }
Start-Sleep -Seconds 3
}
if (-not ((Test-Port 8888) -and (Test-Port 18888))) {
Get-Content C:\seaweed-mini.log, C:\seaweed-mini.err.log -ErrorAction SilentlyContinue
throw "filer never came up"
}
Write-Host "filer is up on http 8888 and grpc 18888"
Start-Mount 'seaweed-mount'
Write-Host "::group::winfsp-tests"
& pwsh -File test/winfsp-conformance/run.ps1 -MountPoint S:\
$code = $LASTEXITCODE
Write-Host "::endgroup::"
if ($code -ne 0) { throw "winfsp-tests failed with exit $code" }
- name: Logs
if: always()
shell: pwsh
run: |
foreach ($f in 'C:\seaweed-mount.log','C:\seaweed-mount.err.log','C:\seaweed-mini.log','C:\seaweed-mini.err.log') {
if (Test-Path $f) { Write-Host "===== $f"; Get-Content $f -Tail 200 }
}
-194
View File
@@ -1,194 +0,0 @@
name: "mount: windows"
on:
push:
branches: [ master ]
paths:
- 'weed/mount/**'
- 'weed/command/mount*.go'
- 'weed/storage/volume_vacuum*.go'
- 'weed/storage/volume_loading.go'
- 'weed/storage/disk_location.go'
- 'test/winfsp/**'
- '.github/workflows/mount-windows.yml'
# No base branch filter: this is the only thing that runs the Windows mount,
# so it should cover a pull request stacked on another one too.
pull_request:
paths:
- 'weed/mount/**'
- 'weed/command/mount*.go'
- 'weed/storage/volume_vacuum*.go'
- 'weed/storage/volume_loading.go'
- 'weed/storage/disk_location.go'
- 'test/winfsp/**'
- '.github/workflows/mount-windows.yml'
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
permissions:
contents: read
jobs:
mount-windows:
name: Mount on Windows
runs-on: windows-latest
timeout-minutes: 40
env:
# The runner ships MinGW, so cgo is on by default and cgofuse picks its
# cgo variant, which wants WinFsp's headers. The nocgo variant loads
# winfsp-x64.dll at run time instead, which is how weed.exe is released.
CGO_ENABLED: 0
steps:
- uses: actions/checkout@v7
with:
persist-credentials: false
- uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
# cgofuse loads winfsp-x64.dll at run time, so WinFsp is needed here but
# not to build.
- name: Install WinFsp
run: choco install winfsp -y --no-progress
- name: Build weed.exe
run: go build -o weed.exe ./weed
# The runner tears down a step's process tree when its shell exits, so a
# cluster started in one step is gone by the next. Everything that needs
# the cluster and the mount alive has to share a step.
- name: Mount and exercise
shell: pwsh
run: |
$ErrorActionPreference = 'Stop'
function Test-Port($port) {
# A plain connect, because Test-NetConnection has reported success
# here for a port nothing was listening on.
$client = New-Object System.Net.Sockets.TcpClient
try { $client.Connect('127.0.0.1', $port); return $client.Connected }
catch { return $false }
finally { $client.Dispose() }
}
function Start-Mount($log) {
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mount','-filer=127.0.0.1:8888','-dir=S:' `
-RedirectStandardOutput "C:\$log.log" -RedirectStandardError "C:\$log.err.log"
$deadline = (Get-Date).AddMinutes(2)
while ((Get-Date) -lt $deadline) {
if (Test-Path S:\) { Write-Host "S: is mounted"; return }
Start-Sleep -Seconds 2
}
Get-Content "C:\$log.log", "C:\$log.err.log" -ErrorAction SilentlyContinue
throw "S: never appeared"
}
function Stop-Mount {
Get-CimInstance Win32_Process -Filter "Name = 'weed.exe'" |
Where-Object { $_.CommandLine -like '*mount*' } |
ForEach-Object { Stop-Process -Id $_.ProcessId -Force }
$deadline = (Get-Date).AddMinutes(1)
while ((Get-Date) -lt $deadline -and (Test-Path S:\)) { Start-Sleep -Seconds 2 }
if (Test-Path S:\) { throw "S: still present after stopping the mount" }
Write-Host "unmounted"
}
function Invoke-Tests($label, [string[]]$goArgs) {
Write-Host "::group::$label"
& go @goArgs
$code = $LASTEXITCODE
Write-Host "::endgroup::"
if ($code -ne 0) { throw "$label failed with exit $code" }
}
New-Item -ItemType Directory -Force -Path C:\seaweed-data | Out-Null
# -ip pins the cluster to loopback; it otherwise advertises and binds
# the runner's LAN address, which 127.0.0.1 cannot reach.
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mini','-dir=C:\seaweed-data','-ip=127.0.0.1' `
-RedirectStandardOutput C:\seaweed-mini.log -RedirectStandardError C:\seaweed-mini.err.log
$deadline = (Get-Date).AddMinutes(3)
while ((Get-Date) -lt $deadline) {
# The mount dials grpc, not http, so both ports have to answer.
if ((Test-Port 8888) -and (Test-Port 18888)) { break }
Start-Sleep -Seconds 3
}
if (-not ((Test-Port 8888) -and (Test-Port 18888))) {
Get-Content C:\seaweed-mini.log, C:\seaweed-mini.err.log -ErrorAction SilentlyContinue
throw "filer never came up"
}
Write-Host "filer is up on http 8888 and grpc 18888"
Start-Mount 'seaweed-mount'
Invoke-Tests 'exercise' @('test','-v','-timeout','20m','./test/winfsp','-mountpoint=S:\')
Invoke-Tests 'persist-write' @('test','-v','-timeout','15m','./test/winfsp','-run','TestPersistence','-mountpoint=S:\','-phase=write','-filer=127.0.0.1:8888')
Stop-Mount
Start-Mount 'seaweed-remount'
Invoke-Tests 'persist-verify' @('test','-v','-timeout','15m','./test/winfsp','-run','TestPersistence','-mountpoint=S:\','-phase=verify')
# WinFsp creates the mount directory itself, so the path must not
# exist; only its parent has to.
Write-Host "::group::mount over a directory"
Stop-Mount
Remove-Item C:\seaweed-mnt -Recurse -Force -ErrorAction SilentlyContinue
Start-Process -FilePath .\weed.exe `
-ArgumentList '-logtostderr','mount','-filer=127.0.0.1:8888','-dir=C:\seaweed-mnt' `
-RedirectStandardOutput C:\seaweed-dirmount.log -RedirectStandardError C:\seaweed-dirmount.err.log
$deadline = (Get-Date).AddMinutes(2)
$ok = $false
while ((Get-Date) -lt $deadline) {
# Listing succeeds on the plain empty directory too, so wait for the
# reparse point WinFsp turns it into. Otherwise this step passes
# without a mount and writes to local disk.
$item = Get-Item C:\seaweed-mnt -Force -ErrorAction SilentlyContinue
if ($null -ne $item -and $item.Attributes.ToString() -like '*ReparsePoint*') { $ok = $true; break }
Start-Sleep -Seconds 2
}
if (-not $ok) {
Get-Content C:\seaweed-dirmount.log, C:\seaweed-dirmount.err.log -ErrorAction SilentlyContinue
throw "mounting over a directory failed"
}
Set-Content -Path C:\seaweed-mnt\dirmount.txt -Value 'via directory mount'
if ((Get-Content C:\seaweed-mnt\dirmount.txt) -ne 'via directory mount') { throw "readback through the directory mount differs" }
Remove-Item C:\seaweed-mnt\dirmount.txt -Force
Get-CimInstance Win32_Process -Filter "Name = 'weed.exe'" |
Where-Object { $_.CommandLine -like '*mount*' } |
ForEach-Object { Stop-Process -Id $_.ProcessId -Force }
Start-Sleep -Seconds 5
Write-Host "::endgroup::"
Start-Mount 'seaweed-remount2'
Write-Host "::group::explorer-style walk"
New-Item -ItemType Directory -Force -Path S:\walk | Out-Null
1..200 | ForEach-Object { Set-Content -Path "S:\walk\f$_.txt" -Value "line $_" }
$names = @(Get-ChildItem S:\walk | ForEach-Object { $_.Name })
if ($names.Count -ne 200) {
# Name the strays: a dot entry surfacing here is a different problem
# from a missing or duplicated file.
$unexpected = $names | Where-Object { $_ -notmatch '^f\d+\.txt$' }
throw "listed $($names.Count) entries, expected 200; unexpected: $($unexpected -join ', ')"
}
$body = Get-Content S:\walk\f42.txt
if ($body -ne 'line 42') { throw "unexpected content: $body" }
Copy-Item S:\walk\f42.txt S:\walk\copy.txt
Remove-Item S:\walk -Recurse -Force
if (Test-Path S:\walk) { throw "directory survived recursive delete" }
Write-Host "::endgroup::"
- name: Logs
if: always()
shell: pwsh
run: |
foreach ($f in 'C:\seaweed-mount.log','C:\seaweed-mount.err.log','C:\seaweed-remount.log','C:\seaweed-remount.err.log','C:\seaweed-remount2.log','C:\seaweed-remount2.err.log','C:\seaweed-dirmount.log','C:\seaweed-dirmount.err.log','C:\seaweed-mini.log','C:\seaweed-mini.err.log') {
if (Test-Path $f) { Write-Host "===== $f"; Get-Content $f -Tail 200 }
}
-77
View File
@@ -1,77 +0,0 @@
name: "Multi-Master Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/server/master_*.go'
- 'weed/server/raft_*.go'
- 'weed/topology/**'
- 'test/multi_master/**'
- 'test/testutil/**'
- '.github/workflows/multi-master-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/server/master_*.go'
- 'weed/server/raft_*.go'
- 'weed/topology/**'
- 'test/multi_master/**'
- 'test/testutil/**'
- '.github/workflows/multi-master-tests.yml'
concurrency:
group: ${{ github.head_ref || github.ref }}/multi-master-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
multi-master-failover-tests:
name: Multi-Master Failover Tests
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install SeaweedFS
run: |
cd weed && go install -buildvcs=false
- name: Run multi-master failover tests
# The tests in test/multi_master spin up their own 3-node master raft
# cluster (using the freshly-installed `weed` binary) and exercise
# leader-election, failover and recovery scenarios. The shared
# test/testutil port-allocator regression test runs alongside since it
# is a prerequisite for the cluster fixtures.
run: |
go test -v -timeout=8m ./test/multi_master/... ./test/testutil/...
- name: Collect server logs on failure
if: failure()
run: |
# test/multi_master/cluster.go creates per-test dirs via
# os.MkdirTemp("", "seaweedfs_multi_master_it_") and writes each
# node's log into <baseDir>/logs/master*.log.
echo "Collecting per-node master logs from temp directories..."
mkdir -p /tmp/multi-master-logs
find /tmp -maxdepth 1 -type d -name "seaweedfs_multi_master_it_*" 2>/dev/null | while read dir; do
echo "Found test directory: $dir"
cp -r "$dir" /tmp/multi-master-logs/ 2>/dev/null || true
done
find /tmp/multi-master-logs -type f -name "*.log" -print -exec tail -n 100 {} \; 2>/dev/null || echo "No logs found"
- name: Archive logs
if: failure()
uses: actions/upload-artifact@v7
with:
name: multi-master-test-logs
path: /tmp/multi-master-logs/
retention-days: 7
-469
View File
@@ -1,469 +0,0 @@
name: "Performance"
on:
push:
branches: [ master ]
paths:
- '**/*.go'
- 'go.mod'
- 'go.sum'
- 'seaweed-volume/**'
- 'test/perf/**'
- '.github/workflows/performance.yml'
workflow_dispatch:
inputs:
profile_duration:
description: "CPU profiling duration in seconds"
required: false
default: "30"
type: string
benchmark_files:
description: "Number of files for the throughput benchmark"
required: false
default: "100000"
type: string
benchmark_concurrency:
description: "Concurrent read/write workers"
required: false
default: "16"
type: string
benchmark_size:
description: "Simulated file size in bytes"
required: false
default: "1024"
type: string
s3_objects:
description: "Number of objects for the S3 benchmark"
required: false
default: "20000"
type: string
s3_size:
description: "S3 object size in bytes"
required: false
default: "4096"
type: string
concurrency:
group: ${{ github.head_ref || github.ref }}/performance
cancel-in-progress: true
permissions:
contents: read
env:
VOL_SIZE_LIMIT: "1024"
jobs:
performance-profile:
name: CPU and Heap Profile
runs-on: ubuntu-latest
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Build weed
run: go build -o weed_bin ./weed
- name: Start server with profiling enabled
run: |
mkdir -p ./perfdata
./weed_bin -v=1 server -debug -debug.port=6060 -dir=./perfdata \
-s3 -filer -volume.max=0 -master.volumeSizeLimitMB=100 \
-s3.port=8000 -s3.config=./docker/compose/s3.json \
> weed.log 2>&1 &
echo "WEED_PID=$!" >> "$GITHUB_ENV"
for i in $(seq 1 60); do
if curl -sf http://localhost:9333/dir/status >/dev/null 2>&1; then
echo "master is ready"
break
fi
sleep 1
done
# give the volume server a moment to register with the master
sleep 3
- name: Start memory sampler
run: |
bash test/perf/mem_sample.sh mem-profile.csv "server=${WEED_PID}" &
echo "SAMPLER_PID=$!" >> "$GITHUB_ENV"
- name: Capture profiles under load
run: |
DURATION="${{ github.event.inputs.profile_duration || '30' }}"
# drive write load so the sampled profile reflects real work
./weed_bin benchmark -master=localhost:9333 -writeOnly \
-c=16 -n=5000000 -size=1024 > benchmark-load.log 2>&1 &
echo "Sampling CPU profile for ${DURATION}s..."
curl -s "http://localhost:6060/debug/pprof/profile?seconds=${DURATION}" -o cpu.pprof
curl -s "http://localhost:6060/debug/pprof/heap" -o heap.pprof
curl -s "http://localhost:6060/debug/pprof/goroutine?debug=1" -o goroutine.txt
go tool pprof -top -nodecount=50 cpu.pprof > cpu-top.txt 2>/dev/null || true
go tool pprof -top -nodecount=50 -sample_index=inuse_space heap.pprof > heap-top.txt 2>/dev/null || true
- name: Record memory usage
if: always()
run: |
kill -TERM "${SAMPLER_PID}" 2>/dev/null || true
sleep 2
{
echo "## Memory usage (peak RSS)"
echo '```'
if [ -f mem-profile.csv.peak ]; then
awk -F'\t' '{printf "%-10s %8d KB (%.1f MB)\n", $1, $2, $2/1024}' mem-profile.csv.peak
else
echo "no memory samples captured"
fi
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: Profile summary
if: always()
run: |
{
echo "## CPU profile (top functions)"
echo '```'
head -45 cpu-top.txt 2>/dev/null || echo "no cpu profile captured"
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: Stop server
if: always()
run: kill "${WEED_PID}" 2>/dev/null || true
- name: Show server log on failure
if: failure()
run: tail -200 weed.log || true
- name: Upload profiles
if: always()
uses: actions/upload-artifact@v7
with:
name: performance-profile-${{ github.run_number }}
path: |
cpu.pprof
heap.pprof
cpu-top.txt
heap-top.txt
goroutine.txt
mem-profile.csv
mem-profile.csv.peak
weed.log
retention-days: 30
benchmark:
name: Throughput Benchmark (${{ matrix.impl }} volume)
runs-on: ubuntu-latest
timeout-minutes: 60
strategy:
fail-fast: false
matrix:
impl: [go, rust]
env:
IMPL: ${{ matrix.impl }}
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install Rust toolchain
if: matrix.impl == 'rust'
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
if: matrix.impl == 'rust'
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-
- name: Build weed
run: go build -o weed_bin ./weed
- name: Build Rust volume server
if: matrix.impl == 'rust'
run: cd seaweed-volume && cargo build --release
- name: Start master and volume server
run: |
mkdir -p ./perfdata/master ./perfdata/vol
./weed_bin -v=1 master -ip=127.0.0.1 -port=9333 \
-mdir=./perfdata/master -peers=none \
-volumeSizeLimitMB="${VOL_SIZE_LIMIT}" -defaultReplication=000 \
> master.log 2>&1 &
echo "MASTER_PID=$!" >> "$GITHUB_ENV"
for i in $(seq 1 60); do
if curl -sf http://localhost:9333/dir/status >/dev/null 2>&1; then
echo "master is ready"
break
fi
sleep 1
done
if [ "${IMPL}" = "rust" ]; then
./seaweed-volume/target/release/weed-volume \
--master 127.0.0.1:9333 --ip 127.0.0.1 --ip.bind 127.0.0.1 \
--port 8080 --dir ./perfdata/vol --max 100 --preStopSeconds 0 \
> volume.log 2>&1 &
else
./weed_bin -v=1 volume -master=127.0.0.1:9333 -ip=127.0.0.1 \
-port=8080 -dir=./perfdata/vol -max=100 \
> volume.log 2>&1 &
fi
echo "VOLUME_PID=$!" >> "$GITHUB_ENV"
for i in $(seq 1 60); do
if curl -sf http://localhost:8080/status >/dev/null 2>&1; then
echo "volume server is ready"
break
fi
sleep 1
done
# let the volume server register with the master via heartbeat
sleep 3
- name: Start memory sampler
run: |
bash test/perf/mem_sample.sh mem-benchmark.csv \
"master=${MASTER_PID}" "volume=${VOLUME_PID}" &
echo "SAMPLER_PID=$!" >> "$GITHUB_ENV"
- name: Run throughput benchmark
run: |
N="${{ github.event.inputs.benchmark_files || '100000' }}"
C="${{ github.event.inputs.benchmark_concurrency || '16' }}"
SIZE="${{ github.event.inputs.benchmark_size || '1024' }}"
./weed_bin benchmark -master=localhost:9333 \
-c="${C}" -n="${N}" -size="${SIZE}" 2>&1 | tee benchmark-results.txt
- name: Run Go micro-benchmarks
if: matrix.impl == 'go'
continue-on-error: true
run: |
go test -run='^$' -bench=. -benchmem -benchtime=10x \
./weed/topology/... ./weed/util/log_buffer/... ./weed/util/buffered_queue/... \
2>&1 | tee go-benchmarks.txt
- name: Record memory usage
if: always()
run: |
kill -TERM "${SAMPLER_PID}" 2>/dev/null || true
sleep 2
{
echo "## Memory usage (peak RSS, ${IMPL} volume)"
echo '```'
if [ -f mem-benchmark.csv.peak ]; then
awk -F'\t' '{printf "%-10s %8d KB (%.1f MB)\n", $1, $2, $2/1024}' mem-benchmark.csv.peak
else
echo "no memory samples captured"
fi
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: Benchmark summary
if: always()
run: |
{
echo "## Throughput benchmark (${IMPL} volume)"
echo '```'
grep -E "Concurrency Level|Time taken|Completed requests|Failed requests|Requests per second|Transfer rate" \
benchmark-results.txt 2>/dev/null || echo "no benchmark results captured"
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: Stop processes
if: always()
run: |
kill "${VOLUME_PID}" "${MASTER_PID}" 2>/dev/null || true
- name: Show logs on failure
if: failure()
run: |
echo "=== master.log ==="; tail -100 master.log 2>/dev/null || true
echo "=== volume.log ==="; tail -200 volume.log 2>/dev/null || true
- name: Upload benchmark results
if: always()
uses: actions/upload-artifact@v7
with:
name: benchmark-results-${{ matrix.impl }}-${{ github.run_number }}
path: |
benchmark-results.txt
go-benchmarks.txt
mem-benchmark.csv
mem-benchmark.csv.peak
master.log
volume.log
retention-days: 7
s3-benchmark:
name: S3 Read/Write Benchmark (${{ matrix.impl }} volume)
runs-on: ubuntu-latest
timeout-minutes: 60
strategy:
fail-fast: false
matrix:
impl: [go, rust]
env:
IMPL: ${{ matrix.impl }}
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install Rust toolchain
if: matrix.impl == 'rust'
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
if: matrix.impl == 'rust'
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-
- name: Build weed and S3 load tool
run: |
go build -o weed_bin ./weed
go build -o s3bench ./test/s3/benchmark
- name: Build Rust volume server
if: matrix.impl == 'rust'
run: cd seaweed-volume && cargo build --release
- name: Start cluster with S3 gateway
run: |
mkdir -p ./perfdata/master ./perfdata/vol ./perfdata/filer
./weed_bin -v=1 master -ip=127.0.0.1 -port=9333 \
-mdir=./perfdata/master -peers=none \
-volumeSizeLimitMB="${VOL_SIZE_LIMIT}" -defaultReplication=000 \
> master.log 2>&1 &
echo "MASTER_PID=$!" >> "$GITHUB_ENV"
for i in $(seq 1 60); do
if curl -sf http://localhost:9333/dir/status >/dev/null 2>&1; then
echo "master is ready"
break
fi
sleep 1
done
if [ "${IMPL}" = "rust" ]; then
./seaweed-volume/target/release/weed-volume \
--master 127.0.0.1:9333 --ip 127.0.0.1 --ip.bind 127.0.0.1 \
--port 8080 --dir ./perfdata/vol --max 100 --preStopSeconds 0 \
> volume.log 2>&1 &
else
./weed_bin -v=1 volume -master=127.0.0.1:9333 -ip=127.0.0.1 \
-port=8080 -dir=./perfdata/vol -max=100 \
> volume.log 2>&1 &
fi
echo "VOLUME_PID=$!" >> "$GITHUB_ENV"
for i in $(seq 1 60); do
if curl -sf http://localhost:8080/status >/dev/null 2>&1; then
echo "volume server is ready"
break
fi
sleep 1
done
sleep 3
./weed_bin -v=1 filer -master=127.0.0.1:9333 -ip=127.0.0.1 -port=8888 \
-s3 -s3.port=8000 -s3.config=./docker/compose/s3.json \
> filer.log 2>&1 &
echo "FILER_PID=$!" >> "$GITHUB_ENV"
for i in $(seq 1 30); do
if nc -z localhost 8000 2>/dev/null; then
echo "s3 gateway is ready"
break
fi
sleep 1
done
sleep 2
- name: Start memory sampler
run: |
bash test/perf/mem_sample.sh mem-s3.csv \
"master=${MASTER_PID}" "volume=${VOLUME_PID}" "filer=${FILER_PID}" &
echo "SAMPLER_PID=$!" >> "$GITHUB_ENV"
- name: Run S3 read/write benchmark
run: |
OBJECTS="${{ github.event.inputs.s3_objects || '20000' }}"
C="${{ github.event.inputs.benchmark_concurrency || '16' }}"
SIZE="${{ github.event.inputs.s3_size || '4096' }}"
./s3bench -endpoint=http://localhost:8000 \
-access-key=some_access_key1 -secret-key=some_secret_key1 \
-objects="${OBJECTS}" -size="${SIZE}" -concurrency="${C}" -mode=both \
2>&1 | tee s3-benchmark-results.txt
- name: Record memory usage
if: always()
run: |
kill -TERM "${SAMPLER_PID}" 2>/dev/null || true
sleep 2
{
echo "## Memory usage (peak RSS, ${IMPL} volume)"
echo '```'
if [ -f mem-s3.csv.peak ]; then
awk -F'\t' '{printf "%-10s %8d KB (%.1f MB)\n", $1, $2, $2/1024}' mem-s3.csv.peak
else
echo "no memory samples captured"
fi
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: S3 benchmark summary
if: always()
run: |
{
echo "## S3 read/write benchmark (${IMPL} volume)"
echo '```'
grep -E "results:|Concurrency Level|Time taken|Completed requests|Failed requests|Requests per second|Transfer rate|Latency" \
s3-benchmark-results.txt 2>/dev/null || echo "no S3 benchmark results captured"
echo '```'
} >> "$GITHUB_STEP_SUMMARY"
- name: Stop processes
if: always()
run: |
kill "${FILER_PID}" "${VOLUME_PID}" "${MASTER_PID}" 2>/dev/null || true
- name: Show logs on failure
if: failure()
run: |
echo "=== master.log ==="; tail -100 master.log 2>/dev/null || true
echo "=== volume.log ==="; tail -200 volume.log 2>/dev/null || true
echo "=== filer.log ==="; tail -200 filer.log 2>/dev/null || true
- name: Upload S3 benchmark results
if: always()
uses: actions/upload-artifact@v7
with:
name: s3-benchmark-results-${{ matrix.impl }}-${{ github.run_number }}
path: |
s3-benchmark-results.txt
mem-s3.csv
mem-s3.csv.peak
master.log
volume.log
filer.log
retention-days: 7
-118
View File
@@ -1,118 +0,0 @@
name: "pjdfstest POSIX Compliance"
on:
push:
branches: [ master, main ]
paths:
- 'weed/mount/**'
- 'weed/filer/**'
- 'test/pjdfstest/**'
- '.github/workflows/pjdfstest.yml'
pull_request:
branches: [ master, main ]
paths:
- 'weed/mount/**'
- 'weed/filer/**'
- 'test/pjdfstest/**'
- '.github/workflows/pjdfstest.yml'
workflow_dispatch:
concurrency:
group: pjdfstest/${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
jobs:
pjdfstest:
name: pjdfstest
runs-on: ubuntu-22.04
timeout-minutes: 60
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Start local Docker registry
run: docker run -d --restart=always -p 5000:5000 --name registry registry:2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
with:
driver-opts: network=host
- name: Build weed race binary
run: |
cd docker
make binary_race
- name: Build SeaweedFS e2e image
uses: docker/build-push-action@v7
with:
context: docker
file: docker/Dockerfile.e2e
tags: localhost:5000/chrislusf/seaweedfs:e2e
push: true
cache-from: type=gha,scope=pjdfstest-e2e
cache-to: type=gha,mode=max,scope=pjdfstest-e2e
- name: Tag e2e image for docker compose
run: |
docker pull localhost:5000/chrislusf/seaweedfs:e2e
docker tag localhost:5000/chrislusf/seaweedfs:e2e chrislusf/seaweedfs:e2e
- name: Build pjdfstest image
uses: docker/build-push-action@v7
with:
context: test/pjdfstest
build-contexts: |
chrislusf/seaweedfs:e2e=docker-image://localhost:5000/chrislusf/seaweedfs:e2e
tags: localhost:5000/chrislusf/seaweedfs:pjdfstest
push: true
cache-from: type=gha,scope=pjdfstest-harness
cache-to: type=gha,mode=max,scope=pjdfstest-harness
- name: Tag pjdfstest image for docker compose
run: |
docker pull localhost:5000/chrislusf/seaweedfs:pjdfstest
docker tag localhost:5000/chrislusf/seaweedfs:pjdfstest chrislusf/seaweedfs:pjdfstest
- name: Start SeaweedFS cluster
run: |
docker compose -f test/pjdfstest/docker-compose.yml up --wait
- name: Run pjdfstest
run: |
set -o pipefail
docker compose -f test/pjdfstest/docker-compose.yml exec -T mount \
/run.sh 2>&1 | tee /tmp/pjdfstest-output.log
- name: Collect logs
if: always()
run: |
mkdir -p /tmp/pjdfstest-docker-logs
for svc in master volume filer mount; do
docker compose -f test/pjdfstest/docker-compose.yml logs "$svc" \
> "/tmp/pjdfstest-docker-logs/${svc}.log" 2>&1 || true
done
- name: Tear down
if: always()
run: |
docker compose -f test/pjdfstest/docker-compose.yml down -v
- name: Upload logs
if: always()
uses: actions/upload-artifact@v7
with:
name: pjdfstest-results
path: |
/tmp/pjdfstest-output.log
/tmp/pjdfstest-docker-logs/
retention-days: 7
-51
View File
@@ -1,51 +0,0 @@
name: "Plugin Worker Integration Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'test/plugin_workers/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/plugin-workers.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/**'
- 'test/plugin_workers/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/plugin-workers.yml'
permissions:
contents: read
jobs:
plugin-worker:
name: "Plugin Worker: ${{ matrix.worker }}"
runs-on: ubuntu-22.04
timeout-minutes: 10
strategy:
fail-fast: false
matrix:
include:
- worker: erasure_coding
path: test/plugin_workers/erasure_coding
- worker: vacuum
path: test/plugin_workers/vacuum
- worker: volume_balance
path: test/plugin_workers/volume_balance
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Run plugin worker tests
run: go test -v ./${{ matrix.path }}
-94
View File
@@ -1,94 +0,0 @@
name: "PostgreSQL Gateway Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/server/postgres/**'
- 'weed/query/**'
- 'weed/mq/**'
- 'test/postgres/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/postgres-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/server/postgres/**'
- 'weed/query/**'
- 'weed/mq/**'
- 'test/postgres/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/postgres-tests.yml'
concurrency:
group: ${{ github.head_ref }}/postgres-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
postgres-basic-tests:
name: PostgreSQL Basic Tests
runs-on: ubuntu-latest
timeout-minutes: 15
defaults:
run:
working-directory: test/postgres
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code
uses: actions/checkout@v7
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Cache Docker layers
uses: actions/cache@v6
with:
path: /tmp/.buildx-cache
key: ${{ runner.os }}-buildx-postgres-${{ github.sha }}
restore-keys: |
${{ runner.os }}-buildx-postgres-
- name: Start PostgreSQL Gateway Services
run: |
make dev-start
sleep 10
- name: Run Basic Connectivity Test
run: |
make test-basic
- name: Run PostgreSQL Client Tests
run: |
make test-client
- name: Save logs
if: always()
run: |
docker compose logs > postgres-output.log || true
- name: Archive logs
if: always()
uses: actions/upload-artifact@v7
with:
name: postgres-logs
path: test/postgres/postgres-output.log
- name: Cleanup
if: always()
run: |
make clean || true
-236
View File
@@ -1,236 +0,0 @@
name: "release: bump version and cut the release"
# One entry point for a SeaweedFS release:
# 1. bump MAJOR/MINOR in constants.go and the Helm Chart.yaml, commit to master
# 2. push the <appVersion> tag, which fans out to the workflows that trigger on
# `push: tags` (binaries_release*, container_release_unified, helm_manual_release)
# 3. create the GitHub release, with GitHub's generated notes
# 4. dispatch "Prepare release" in seaweedfs-csi-driver and seaweedfs-operator,
# which pick up the new master through `go get -u`, and wait for both
#
# Events raised by the default GITHUB_TOKEN do not start other workflows, and it
# cannot reach the other two repositories at all. Add a repo secret RELEASE_PAT
# with `contents: write` here and `actions: write` on the csi-driver and operator
# repos. Without it the tag is still pushed, but nothing downstream of it runs.
on:
workflow_dispatch:
inputs:
bump:
description: "Which part to increment (ignored when 'version' is set)"
type: choice
options:
- minor
- major
default: minor
version:
description: "Explicit MAJOR.MINOR to set, e.g. 4.36 (overrides 'bump')"
type: string
required: false
downstream:
description: "Also release the CSI driver and the operator"
type: boolean
default: true
dry_run:
description: "Show the version bump, but change nothing"
type: boolean
default: false
jobs:
release:
runs-on: ubuntu-latest
permissions:
contents: write
outputs:
app_version: ${{ steps.compute.outputs.app_version }}
sha: ${{ steps.tag.outputs.sha }}
steps:
- uses: actions/checkout@v7
with:
ref: master
fetch-depth: 0
token: ${{ secrets.RELEASE_PAT || secrets.GITHUB_TOKEN }}
- name: Check the release token
env:
HAS_PAT: ${{ secrets.RELEASE_PAT != '' }}
run: |
if [ "$HAS_PAT" != "true" ]; then
echo "::warning::RELEASE_PAT is not set. The tag will be pushed with GITHUB_TOKEN, so the binary, container and helm workflows will not start on their own."
fi
- name: Compute new version
id: compute
env:
BUMP: ${{ inputs.bump }}
INPUT_VERSION: ${{ inputs.version }}
run: |
set -euo pipefail
CONST=weed/util/version/constants.go
MAJOR=$(grep -oP 'MAJOR_VERSION\s*=\s*int32\(\K[0-9]+' "$CONST")
MINOR=$(grep -oP 'MINOR_VERSION\s*=\s*int32\(\K[0-9]+' "$CONST")
echo "current: ${MAJOR}.${MINOR}"
if [ -n "$INPUT_VERSION" ]; then
if ! [[ "$INPUT_VERSION" =~ ^[0-9]+\.[0-9]+$ ]]; then
echo "::error::version must be MAJOR.MINOR, e.g. 5.01 (got '$INPUT_VERSION')"
exit 1
fi
# 10# forces base 10 so 08/09 are not parsed as octal.
MAJOR=$((10#${INPUT_VERSION%%.*}))
MINOR=$((10#${INPUT_VERSION##*.}))
if [ "$MINOR" -gt 99 ]; then
echo "::error::minor must be 0-99 (got $MINOR); it rolls into the next major at 99"
exit 1
fi
else
case "$BUMP" in
# Minor is a 2-digit field: 4.99 -> 5.00 -> 5.01.
major) MAJOR=$((MAJOR + 1)); MINOR=0 ;;
minor)
if [ "$MINOR" -ge 99 ]; then
MAJOR=$((MAJOR + 1)); MINOR=0
else
MINOR=$((MINOR + 1))
fi
;;
*) echo "::error::unknown bump '$BUMP'"; exit 1 ;;
esac
fi
# appVersion mirrors the Go VERSION_NUMBER (zero-padded minor);
# chart version is plain SemVer (no leading zeros).
APP_VERSION=$(printf '%d.%02d' "$MAJOR" "$MINOR")
CHART_VERSION="${MAJOR}.${MINOR}.0"
echo "new: app=${APP_VERSION} chart=${CHART_VERSION}"
{
echo "major=${MAJOR}"
echo "minor=${MINOR}"
echo "app_version=${APP_VERSION}"
echo "chart_version=${CHART_VERSION}"
} >> "$GITHUB_OUTPUT"
- name: Apply version to constants.go
env:
MAJOR: ${{ steps.compute.outputs.major }}
MINOR: ${{ steps.compute.outputs.minor }}
run: |
set -euo pipefail
CONST=weed/util/version/constants.go
sed -i -E "s/(MAJOR_VERSION[[:space:]]*=[[:space:]]*int32\()[0-9]+(\))/\1${MAJOR}\2/" "$CONST"
sed -i -E "s/(MINOR_VERSION[[:space:]]*=[[:space:]]*int32\()[0-9]+(\))/\1${MINOR}\2/" "$CONST"
grep -E 'MAJOR_VERSION|MINOR_VERSION' "$CONST"
- name: Apply version to Chart.yaml
env:
APP_VERSION: ${{ steps.compute.outputs.app_version }}
CHART_VERSION: ${{ steps.compute.outputs.chart_version }}
run: |
set -euo pipefail
CHART=k8s/charts/seaweedfs/Chart.yaml
sed -i -E "s/^appVersion:.*/appVersion: \"${APP_VERSION}\"/" "$CHART"
sed -i -E "s/^version:.*/version: ${CHART_VERSION}/" "$CHART"
cat "$CHART"
- name: Commit, and push the tag
id: tag
env:
TAG: ${{ steps.compute.outputs.app_version }}
DRY_RUN: ${{ inputs.dry_run }}
run: |
set -euo pipefail
if git ls-remote --exit-code --tags origin "refs/tags/${TAG}" >/dev/null 2>&1; then
echo "::error::Tag ${TAG} already exists."
exit 1
fi
if [ "$DRY_RUN" = "true" ]; then
git --no-pager diff --stat
echo "sha=$(git rev-parse HEAD)" >> "$GITHUB_OUTPUT"
exit 0
fi
git config user.name "github-actions[bot]"
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
if git diff --quiet; then
echo "::warning::Version files are already at ${TAG}; tagging the current HEAD."
else
git add weed/util/version/constants.go k8s/charts/seaweedfs/Chart.yaml
git commit -m "${TAG}"
git push
fi
# Push the tag with git so the `push: tags` triggers fire. Creating the
# tag through the release API alone would only emit a `create` event.
git tag "$TAG"
git push origin "$TAG"
echo "sha=$(git rev-parse HEAD)" >> "$GITHUB_OUTPUT"
- name: Create the release
if: ${{ !inputs.dry_run }}
env:
GH_TOKEN: ${{ secrets.RELEASE_PAT || secrets.GITHUB_TOKEN }}
TAG: ${{ steps.compute.outputs.app_version }}
run: gh release create "$TAG" --title "$TAG" --generate-notes --verify-tag
downstream:
needs: release
if: ${{ inputs.downstream && !inputs.dry_run }}
runs-on: ubuntu-latest
permissions: {}
strategy:
fail-fast: false
matrix:
include:
- repo: seaweedfs/seaweedfs-csi-driver
workflow: prepare_release.yaml
- repo: seaweedfs/seaweedfs-operator
workflow: prepare_release.yml
steps:
- name: Release ${{ matrix.repo }}
env:
GH_TOKEN: ${{ secrets.RELEASE_PAT }}
REPO: ${{ matrix.repo }}
WORKFLOW: ${{ matrix.workflow }}
SHA: ${{ needs.release.outputs.sha }}
MODULE: github.com/seaweedfs/seaweedfs
run: |
set -euo pipefail
if [ -z "${GH_TOKEN}" ]; then
echo "::error::RELEASE_PAT with actions:write on ${REPO} is required to release it"
exit 1
fi
# The dispatched workflow pins seaweedfs with `go get -u ...@latest`, so
# wait until the proxy serves the release commit as the tip. Asking for
# the commit by name is what makes the proxy fetch it.
for _ in $(seq 30); do
curl -sf "https://proxy.golang.org/${MODULE}/@v/${SHA}.info" >/dev/null || true
TIP=$(curl -sf "https://proxy.golang.org/${MODULE}/@latest" | jq -r '.Origin.Hash // ""' || true)
[ "$TIP" = "$SHA" ] && break
sleep 10
done
if [ "$TIP" != "$SHA" ]; then
echo "::error::the module proxy still serves ${TIP} as the tip, so ${REPO} would pin a pre-release commit. Run ${WORKFLOW} there once it catches up."
exit 1
fi
# Wait on the release the dispatched workflow publishes, not on the run
# that publishes it: a dispatch cannot be told apart from a concurrent
# one through the API, and the release is what we are here for.
released() { gh api "repos/${REPO}/releases?per_page=30" --jq '[.[].tag_name]'; }
BEFORE=$(released)
gh workflow run -R "$REPO" "$WORKFLOW" --ref master -f bump=patch -f update_seaweedfs=true
for _ in $(seq 80); do
sleep 15
NEW=$(released | jq -c --argjson before "$BEFORE" '. - $before')
[ "$(jq length <<<"$NEW")" -gt 0 ] && break
done
if [ "$(jq length <<<"$NEW")" -eq 0 ]; then
echo "::error::${REPO} published no release within 20 minutes; see https://github.com/${REPO}/actions/workflows/${WORKFLOW}"
exit 1
fi
echo "${REPO} released $(jq -r 'join(", ")' <<<"$NEW")"
@@ -1,235 +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@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
# cargo tracks its own inputs but not the runner's C toolchain, so a cached
# target/ can carry C objects built against a different glibc than we link against.
- name: Fingerprint build toolchain
id: toolchain
run: echo "fingerprint=$(getconf GNU_LIBC_VERSION | tr ' ' '-')-rustc-$(rustc -V | awk '{print $2}')" >> "$GITHUB_OUTPUT"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-${{ steps.toolchain.outputs.fingerprint }}-
- name: Build Rust volume server
run: cd seaweed-volume && cargo build --release
- name: Run Rust unit tests
run: cd seaweed-volume && cargo test
rust-integration-tests:
name: Rust Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
# cargo tracks its own inputs but not the runner's C toolchain, so a cached
# target/ can carry C objects built against a different glibc than we link against.
- name: Fingerprint build toolchain
id: toolchain
run: echo "fingerprint=$(getconf GNU_LIBC_VERSION | tr ' ' '-')-rustc-$(rustc -V | awk '{print $2}')" >> "$GITHUB_OUTPUT"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-${{ steps.toolchain.outputs.fingerprint }}-
- name: Build Go weed binary
run: |
cd weed
go build -tags 5BytesOffset -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 ${{ matrix.shard }})
runs-on: ubuntu-22.04
timeout-minutes: 45
env:
# Keep in step with the length of matrix.shard below.
SHARD_COUNT: 3
strategy:
fail-fast: false
matrix:
test-type: [grpc, http]
shard: [1, 2, 3]
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
# cargo tracks its own inputs but not the runner's C toolchain, so a cached
# target/ can carry C objects built against a different glibc than we link against.
- name: Fingerprint build toolchain
id: toolchain
run: echo "fingerprint=$(getconf GNU_LIBC_VERSION | tr ' ' '-')-rustc-$(rustc -V | awk '{print $2}')" >> "$GITHUB_OUTPUT"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-${{ steps.toolchain.outputs.fingerprint }}-${{ hashFiles('seaweed-volume/Cargo.lock') }}
restore-keys: |
rust-${{ steps.toolchain.outputs.fingerprint }}-
- name: Build Go weed binary
run: |
cd weed
go build -tags 5BytesOffset -o weed .
chmod +x weed
./weed version
- name: Build Rust volume binary
run: cd seaweed-volume && cargo build --release
# Dealing the listed tests out one by one keeps the shards even. Bucketing
# them by first letter did not: names cluster, so ^Test[I-S] drew 50 of
# the 114 grpc tests and ran nearly twice as long as the other two shards.
- name: Select this shard's tests
env:
TEST_TYPE: ${{ matrix.test-type }}
SHARD: ${{ matrix.shard }}
run: |
tests=$(go test -tags 5BytesOffset ./test/volume_server/"$TEST_TYPE"/... -list '.*' | grep '^Test' | sort -u)
# An empty list would make -run match nothing and the shard pass vacuously.
[ -n "$tests" ] || { echo "listed no tests in test/volume_server/$TEST_TYPE"; exit 1; }
selected=$(echo "$tests" | awk -v n="$SHARD_COUNT" -v i="$SHARD" 'NR % n == i - 1')
echo "shard $SHARD of $SHARD_COUNT runs $(echo "$selected" | wc -l) of $(echo "$tests" | wc -l) tests"
echo "TEST_PATTERN=^($(echo "$selected" | paste -sd'|' -))\$" >> "$GITHUB_ENV"
- 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: |
echo "Running Go volume server tests with Rust volume for ${{ matrix.test-type }} (Shard ${{ matrix.shard }} of ${SHARD_COUNT})..."
go test -v -count=1 -tags 5BytesOffset -timeout=30m ./test/volume_server/${{ 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${{ matrix.shard }}
path: /tmp/rust-volume-go-test-logs/
if-no-files-found: warn
retention-days: 7
- name: Test summary
if: always()
run: |
echo "## Rust Volume - Go Test Summary (${{ matrix.test-type }} - Shard ${{ matrix.shard }})" >> "$GITHUB_STEP_SUMMARY"
echo "- Suite: test/volume_server/${{ matrix.test-type }} (shard ${{ matrix.shard }} of ${SHARD_COUNT}, see 'Select this shard's tests' for the split)" >> "$GITHUB_STEP_SUMMARY"
echo "- Volume server: Rust (VOLUME_SERVER_IMPL=rust)" >> "$GITHUB_STEP_SUMMARY"
-160
View File
@@ -1,160 +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
continue-on-error: true
with:
token: ${{ github.token }}
tag: dev
fail-if-no-assets: false
assets: |
weed-volume-*
build-rust-volume-dev-linux:
permissions:
contents: write
needs: cleanup
runs-on: ubuntu-22.04
strategy:
matrix:
include:
- target: x86_64-unknown-linux-gnu
asset_suffix: linux-amd64
steps:
- uses: actions/checkout@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-dev-${{ 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 }}-${{ matrix.asset_suffix }}.tar.gz" weed-volume-normal
rm weed-volume-normal
- name: Upload dev release assets
uses: softprops/action-gh-release@v3
with:
tag_name: dev
prerelease: true
files: |
weed-volume-large-disk-${{ 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@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-dev-${{ 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@v3
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 }}
-275
View File
@@ -1,275 +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@v7
- 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" >> "$GITHUB_ENV"
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-release-${{ 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 }} --target-dir target/large-disk
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features --target-dir target/normal
- name: Package binaries
run: |
# Large disk (default, 5bytes feature)
cp seaweed-volume/target/large-disk/${{ matrix.target }}/release/weed-volume weed-volume-large-disk
tar czf weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz weed-volume-large-disk
rm weed-volume-large-disk
# Normal volume size
cp seaweed-volume/target/normal/${{ matrix.target }}/release/weed-volume weed-volume-normal
tar czf weed-volume_${{ matrix.asset_suffix }}.tar.gz weed-volume-normal
rm weed-volume-normal
- name: Generate md5 checksums
run: |
for f in weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz weed-volume_${{ matrix.asset_suffix }}.tar.gz; do
md5sum "$f" > "$f.md5"
done
- name: Upload release assets
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v3
with:
files: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz.md5
weed-volume_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz.md5
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload artifacts
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
uses: actions/upload-artifact@v7
with:
name: rust-volume-${{ matrix.asset_suffix }}
path: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz.md5
weed-volume_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz.md5
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@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
with:
targets: ${{ matrix.target }}
- name: Cache cargo registry and target
uses: actions/cache@v6
with:
path: |
~/.cargo/registry
~/.cargo/git
seaweed-volume/target
key: rust-release-${{ 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 }} --target-dir target/large-disk
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --target ${{ matrix.target }} --no-default-features --target-dir target/normal
- name: Package binaries
run: |
cp seaweed-volume/target/large-disk/${{ matrix.target }}/release/weed-volume weed-volume-large-disk
tar czf weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz weed-volume-large-disk
rm weed-volume-large-disk
cp seaweed-volume/target/normal/${{ matrix.target }}/release/weed-volume weed-volume-normal
tar czf weed-volume_${{ matrix.asset_suffix }}.tar.gz weed-volume-normal
rm weed-volume-normal
- name: Generate md5 checksums
run: |
for f in weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz weed-volume_${{ matrix.asset_suffix }}.tar.gz; do
md5 -r "$f" > "$f.md5"
done
- name: Upload release assets
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v3
with:
files: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz.md5
weed-volume_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz.md5
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload artifacts
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
uses: actions/upload-artifact@v7
with:
name: rust-volume-${{ matrix.asset_suffix }}
path: |
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz
weed-volume_large_disk_${{ matrix.asset_suffix }}.tar.gz.md5
weed-volume_${{ matrix.asset_suffix }}.tar.gz
weed-volume_${{ matrix.asset_suffix }}.tar.gz.md5
build-rust-volume-windows:
permissions:
contents: write
runs-on: windows-latest
steps:
- uses: actions/checkout@v7
- name: Install Rust toolchain
uses: dtolnay/rust-toolchain@stable
- name: Cache cargo registry and target
uses: actions/cache@v6
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 --target-dir target/large-disk
- name: Build Rust volume server (normal)
env:
SEAWEEDFS_COMMIT: ${{ github.sha }}
run: |
cd seaweed-volume
cargo build --release --no-default-features --target-dir target/normal
- name: Package binaries
shell: bash
run: |
cp seaweed-volume/target/large-disk/release/weed-volume.exe weed-volume-large-disk.exe
7z a weed-volume_large_disk_windows_amd64.zip weed-volume-large-disk.exe
rm weed-volume-large-disk.exe
cp seaweed-volume/target/normal/release/weed-volume.exe weed-volume-normal.exe
7z a weed-volume_windows_amd64.zip weed-volume-normal.exe
rm weed-volume-normal.exe
- name: Generate md5 checksums
shell: bash
run: |
for f in weed-volume_large_disk_windows_amd64.zip weed-volume_windows_amd64.zip; do
md5sum "$f" > "$f.md5"
done
- name: Upload release assets
if: startsWith(github.ref, 'refs/tags/')
uses: softprops/action-gh-release@v3
with:
files: |
weed-volume_large_disk_windows_amd64.zip
weed-volume_large_disk_windows_amd64.zip.md5
weed-volume_windows_amd64.zip
weed-volume_windows_amd64.zip.md5
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Upload artifacts
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
uses: actions/upload-artifact@v7
with:
name: rust-volume-windows_amd64
path: |
weed-volume_large_disk_windows_amd64.zip
weed-volume_large_disk_windows_amd64.zip.md5
weed-volume_windows_amd64.zip
weed-volume_windows_amd64.zip.md5
-129
View File
@@ -1,129 +0,0 @@
name: "S3 ETag and ACL Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/s3api/**'
- 'weed/filer/etag*.go'
- 'weed/server/filer_server_handlers_*.go'
- 'test/s3/etag/**'
- 'test/s3/acl/**'
- '.github/workflows/s3-etag-acl-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/s3api/**'
- 'weed/filer/etag*.go'
- 'weed/server/filer_server_handlers_*.go'
- 'test/s3/etag/**'
- 'test/s3/acl/**'
- '.github/workflows/s3-etag-acl-tests.yml'
concurrency:
group: ${{ github.head_ref || github.ref }}/s3-etag-acl-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
s3-etag-acl-tests:
name: S3 ETag + ACL Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install SeaweedFS
run: |
cd weed && go install -buildvcs=false
- name: Start weed mini (S3 on :8333)
run: |
mkdir -p /tmp/seaweedfs-etag-acl
# Minimal identity config so SSE-aware tests under acl/ can authenticate.
cat > /tmp/seaweedfs-etag-acl-s3.json <<'JSON'
{
"identities": [
{
"name": "admin",
"credentials": [
{"accessKey": "some_access_key1", "secretKey": "some_secret_key1"}
],
"actions": ["Admin", "Read", "Write"]
}
]
}
JSON
AWS_ACCESS_KEY_ID=some_access_key1 \
AWS_SECRET_ACCESS_KEY=some_secret_key1 \
weed mini \
-dir=/tmp/seaweedfs-etag-acl \
-s3.port=8333 \
-s3.config=/tmp/seaweedfs-etag-acl-s3.json \
-ip=127.0.0.1 \
> /tmp/weed-mini.log 2>&1 &
echo $! > /tmp/weed-mini.pid
# Wait for the S3 endpoint to come up (returns 403 unauth before any
# request is signed; that's fine — it means the server is listening).
for i in $(seq 1 30); do
if curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:8333/ | grep -qE "^(200|403)$"; then
echo "weed mini is ready"
exit 0
fi
sleep 1
done
echo "weed mini failed to start within 30s"
tail -50 /tmp/weed-mini.log
exit 1
- name: Run ETag tests
# Pins the regression for #7768: PutObject of an auto-chunked file (>8MB)
# must return a pure MD5 hex ETag, not a `<md5>-N` composite — the AWS
# SDK for Java v2 rejects the latter on the PutObject path.
env:
S3_ENDPOINT: http://127.0.0.1:8333
AWS_ACCESS_KEY_ID: some_access_key1
AWS_SECRET_ACCESS_KEY: some_secret_key1
AWS_REGION: us-east-1
run: go test -v -timeout=5m ./test/s3/etag/...
- name: Run ACL versioning tests
# Pins object-ACL behavior on a versioned bucket: GetObjectAcl /
# PutObjectAcl with and without versionId, modifying ACLs on different
# versions independently.
env:
S3_ENDPOINT: http://127.0.0.1:8333
AWS_ACCESS_KEY_ID: some_access_key1
AWS_SECRET_ACCESS_KEY: some_secret_key1
AWS_REGION: us-east-1
run: go test -v -timeout=5m ./test/s3/acl/...
- name: Stop weed mini
if: always()
run: |
if [ -f /tmp/weed-mini.pid ]; then
kill "$(cat /tmp/weed-mini.pid)" 2>/dev/null || true
fi
- name: Show server log on failure
if: failure()
run: |
echo "=== weed mini log (last 200 lines) ==="
tail -n 200 /tmp/weed-mini.log 2>/dev/null || echo "no log available"
- name: Archive log
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-etag-acl-server-log
path: /tmp/weed-mini.log
retention-days: 3
@@ -1,81 +0,0 @@
name: "S3 Authenticated Integration Tests"
on:
pull_request:
paths:
- 'weed/s3api/**'
- 'weed/iam/**'
- 'weed/filer/**'
- 'weed/server/**'
- 'test/s3/normal/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/s3-example-integration-tests.yml'
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
@@ -1,94 +0,0 @@
name: "S3 Filer Group Tests"
on:
pull_request:
paths:
- 'weed/s3api/**'
- 'weed/filer/**'
- 'weed/server/**'
- 'test/s3/filer_group/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/s3-filer-group-tests.yml'
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
-676
View File
@@ -1,676 +0,0 @@
name: "S3 Go Tests"
on:
pull_request:
paths:
- 'weed/s3api/**'
- 'weed/filer/**'
- 'weed/server/**'
- 'test/s3/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/s3-go-tests.yml'
concurrency:
group: ${{ github.head_ref }}/s3-go-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
s3-versioning-tests:
name: S3 Versioning Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
strategy:
matrix:
test-type: ["quick", "comprehensive"]
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Versioning Tests - ${{ matrix.test-type }}
timeout-minutes: 25
working-directory: test/s3/versioning
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Tests ==="
# Run tests with automatic server management
# The test-with-server target handles server startup/shutdown automatically
if [ "${{ matrix.test-type }}" = "quick" ]; then
# Override TEST_PATTERN for quick tests only
make test-with-server TEST_PATTERN="TestBucketListReturnDataVersioning|TestVersioningBasicWorkflow|TestVersioningDeleteMarkers"
else
# Run all versioning tests
make test-with-server
fi
- name: Show server logs on failure
if: failure()
working-directory: test/s3/versioning
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-versioning-test-logs-${{ matrix.test-type }}
path: test/s3/versioning/weed-test*.log
retention-days: 3
s3-versioning-compatibility:
name: S3 Versioning Compatibility Test
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run Core Versioning Test (Python s3tests equivalent)
timeout-minutes: 15
working-directory: test/s3/versioning
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run the specific test that is equivalent to the Python s3tests
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 server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-versioning-compatibility-logs
path: test/s3/versioning/weed-test*.log
retention-days: 3
s3-cors-compatibility:
name: S3 CORS Compatibility Test
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run Core CORS Test (AWS S3 compatible)
timeout-minutes: 15
working-directory: test/s3/cors
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run the specific test that is equivalent to AWS S3 CORS 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 server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-cors-compatibility-logs
path: test/s3/cors/weed-test*.log
retention-days: 3
s3-retention-tests:
name: S3 Retention Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
strategy:
matrix:
test-type: ["quick", "comprehensive"]
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Retention Tests - ${{ matrix.test-type }}
timeout-minutes: 25
working-directory: test/s3/retention
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Tests ==="
# Run tests with automatic server management
# The test-with-server target handles server startup/shutdown automatically
if [ "${{ matrix.test-type }}" = "quick" ]; then
# Override TEST_PATTERN for quick tests only
make test-with-server TEST_PATTERN="TestBasicRetentionWorkflow|TestRetentionModeCompliance|TestLegalHoldWorkflow"
else
# Run all retention tests
make test-with-server
fi
- name: Show server logs on failure
if: failure()
working-directory: test/s3/retention
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-retention-test-logs-${{ matrix.test-type }}
path: test/s3/retention/weed-test*.log
retention-days: 3
s3-lifecycle-tests:
name: S3 Lifecycle Tests
runs-on: ubuntu-22.04
timeout-minutes: 10
strategy:
fail-fast: false
matrix:
# One job per test so each gets a fresh `weed mini` server, avoiding
# the cross-test volume-pool exhaustion that surfaced when several
# TTL-pinned bucket collections piled up in a single run.
test:
- TestLifecycleAbortIncompleteMultipartUpload
- TestLifecycleAdminDispatchSucceedsWithCustomFilerGrpcPort
- TestLifecycleBootstrapWalkOnExistingObjects
- TestLifecycleConfigUpdateBetweenSweeps
- TestLifecycleDeleteBucketLifecycleStopsDispatching
- TestLifecycleDisabledRuleSkipsObject
- TestLifecycleEmptyBucketSweepIsNoOp
- TestLifecycleExpirationDateInThePast
- TestLifecycleExpirationFiresOnBackdatedObject
- TestLifecycleExpiredDeleteMarkerCleanup
- TestLifecycleMultipleBucketsInOneSweep
- TestLifecycleMultipleRulesInOneBucket
- TestLifecycleNewerNoncurrentVersions
- TestLifecycleNoncurrentVersionExpiration
- TestLifecycleSizeFilterGreaterThan
- TestLifecycleSkipsObjectLockedObjects
- TestLifecycleSuspendedVersioningExpiration
- TestLifecycleTagFilter
- TestLifecycleVersionedBucketCreatesDeleteMarker
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run ${{ matrix.test }}
timeout-minutes: 8
working-directory: test/s3/lifecycle
run: |
set -x
make test-with-server TEST_PATTERN='^${{ matrix.test }}$$'
- name: Show server logs on failure
if: failure()
working-directory: test/s3/lifecycle
run: |
if [ -f weed-test.log ]; then
echo "=== Last 200 lines of server logs ==="
tail -200 weed-test.log
fi
ps aux | grep -E "(weed|test)" || true
netstat -tlnp 2>/dev/null | grep -E "(8333|9333|8080|8888)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-lifecycle-test-logs-${{ matrix.test }}
path: test/s3/lifecycle/weed-test*.log
retention-days: 3
s3-checksum-tests:
name: S3 Checksum Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Checksum Tests
timeout-minutes: 16
working-directory: test/s3/checksum
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Tests ==="
make test-with-server
- name: Show server logs on failure
if: failure()
working-directory: test/s3/checksum
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-checksum-test-logs
path: test/s3/checksum/weed-test*.log
retention-days: 3
s3-cors-tests:
name: S3 CORS Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
strategy:
matrix:
test-type: ["quick", "comprehensive"]
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 CORS Tests - ${{ matrix.test-type }}
timeout-minutes: 25
working-directory: test/s3/cors
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting Tests ==="
# Run tests with automatic server management
# The test-with-server target handles server startup/shutdown automatically
if [ "${{ matrix.test-type }}" = "quick" ]; then
# Override TEST_PATTERN for quick tests only
make test-with-server TEST_PATTERN="TestCORSConfigurationManagement|TestServiceLevelCORS|TestCORSBasicWorkflow"
else
# Run all CORS tests
make test-with-server
fi
- name: Show server logs on failure
if: failure()
working-directory: test/s3/cors
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-cors-test-logs-${{ matrix.test-type }}
path: test/s3/cors/weed-test*.log
retention-days: 3
s3-retention-worm:
name: S3 Retention WORM Integration Test
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run WORM Integration Tests
timeout-minutes: 15
working-directory: test/s3/retention
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run the WORM integration tests with automatic server management
# The test-with-server target handles server startup/shutdown automatically
make test-with-server TEST_PATTERN="TestWORM|TestRetentionExtendedAttributes|TestRetentionConcurrentOperations" || {
echo "❌ WORM integration 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 server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-retention-worm-logs
path: test/s3/retention/weed-test*.log
retention-days: 3
s3-versioning-stress:
name: S3 Versioning Stress Test
runs-on: ubuntu-22.04
timeout-minutes: 35
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Versioning Stress Tests
timeout-minutes: 30
working-directory: test/s3/versioning
run: |
set -x
echo "=== System Information ==="
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..."
if [ -f weed-test.log ]; then
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
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
-309
View File
@@ -1,309 +0,0 @@
name: "S3 IAM Integration Tests"
on:
pull_request:
paths:
- 'weed/iam/**'
- 'weed/s3api/**'
- 'weed/credential/**'
- 'weed/pb/**'
- 'test/s3/iam/**'
- '.github/workflows/s3-iam-tests.yml'
push:
branches: [ master ]
paths:
- 'weed/iam/**'
- 'weed/s3api/**'
- 'weed/credential/**'
- 'weed/pb/**'
- 'test/s3/iam/**'
- '.github/workflows/s3-iam-tests.yml'
concurrency:
group: ${{ github.head_ref }}/s3-iam-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
# Unit tests for IAM components
iam-unit-tests:
name: IAM Unit Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Get dependencies
run: |
go mod download
- name: Run IAM Unit Tests
timeout-minutes: 10
run: |
set -x
echo "=== Running IAM STS Tests ==="
go test -v -timeout 5m ./iam/sts/...
echo "=== Running IAM Policy Tests ==="
go test -v -timeout 5m ./iam/policy/...
echo "=== Running IAM Integration Tests ==="
go test -v -timeout 5m ./iam/integration/...
echo "=== Running S3 API IAM Tests ==="
go test -v -timeout 5m ./s3api/... -run ".*IAM.*|.*JWT.*|.*Auth.*"
- name: Upload test results on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: iam-unit-test-results
path: |
weed/testdata/
weed/**/testdata/
retention-days: 3
# S3 IAM integration tests with SeaweedFS services
s3-iam-integration-tests:
name: S3 IAM Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 25
strategy:
matrix:
test-type: ["basic", "advanced", "policy-enforcement", "group", "sts"]
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
working-directory: weed
run: |
go install -buildvcs=false
- name: Run S3 IAM Integration Tests - ${{ matrix.test-type }}
timeout-minutes: 20
working-directory: test/s3/iam
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 IAM Integration Tests (${{ matrix.test-type }}) ==="
# Set WEED_BINARY to use the installed version
export WEED_BINARY=$(which weed)
export TEST_TIMEOUT=15m
# Run tests based on type
case "${{ matrix.test-type }}" in
"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" ./...
;;
"advanced")
echo "Running advanced IAM feature tests..."
make clean setup start-services wait-for-services
go test -v -timeout 15m -run "TestS3IAMSessionExpiration|TestS3IAMMultipart|TestS3IAMPresigned" ./...
;;
"policy-enforcement")
echo "Running policy enforcement tests..."
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" ./...
;;
"sts")
echo "Running STS and service account tests..."
make clean setup start-services wait-for-services
# SigV4-signed STS calls need admin credentials matching test_config.json.
# Tests default to "admin"/"admin" when env vars are unset, which don't exist.
export STS_TEST_ACCESS_KEY=test-access-key
export STS_TEST_SECRET_KEY=test-secret-key
# The use_service_account_credentials subtest is excluded because
# newly-created service-account access keys are not currently
# persisted to the filer after CreateServiceAccount — a
# pre-existing sync issue tracked separately from the
# GetFederationToken routing fix this PR addresses.
go test -v -timeout 15m \
-run "TestSTS|TestAssumeRoleWithWebIdentity|TestServiceAccount" \
-skip "TestServiceAccountLifecycle/use_service_account_credentials" \
./...
;;
*)
echo "Unknown test type: ${{ matrix.test-type }}"
exit 1
;;
esac
# Always cleanup
make stop-services
- name: Show service logs on failure
if: failure()
working-directory: test/s3/iam
run: |
echo "=== Service Logs ==="
echo "--- Master Log ---"
tail -50 weed-master.log 2>/dev/null || echo "No master log found"
echo ""
echo "--- Filer Log ---"
tail -50 weed-filer.log 2>/dev/null || echo "No filer log found"
echo ""
echo "--- Volume Log ---"
tail -50 weed-volume.log 2>/dev/null || echo "No volume log found"
echo ""
echo "--- S3 API Log ---"
tail -50 weed-s3.log 2>/dev/null || echo "No S3 log found"
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-iam-integration-logs-${{ matrix.test-type }}
path: test/s3/iam/weed-*.log
retention-days: 5
# Distributed IAM tests
s3-iam-distributed-tests:
name: S3 IAM Distributed Tests
runs-on: ubuntu-22.04
timeout-minutes: 25
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
working-directory: weed
run: |
go install -buildvcs=false
- name: Run Distributed IAM Tests
timeout-minutes: 20
working-directory: test/s3/iam
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
export WEED_BINARY=$(which weed)
export TEST_TIMEOUT=15m
# Test distributed configuration
echo "Testing distributed IAM configuration..."
make clean setup
# Start services with distributed IAM config
echo "Starting services with distributed configuration..."
make start-services
make wait-for-services
# Run distributed-specific tests
export ENABLE_DISTRIBUTED_TESTS=true
go test -v -timeout 15m -run "TestS3IAMDistributedTests" ./... || {
echo "❌ Distributed tests failed, checking logs..."
make logs
exit 1
}
make stop-services
- name: Upload distributed test logs
if: always()
uses: actions/upload-artifact@v7
with:
name: s3-iam-distributed-logs
path: test/s3/iam/weed-*.log
retention-days: 7
# Performance and stress tests
s3-iam-performance-tests:
name: S3 IAM Performance Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
working-directory: weed
run: |
go install -buildvcs=false
- name: Run IAM Performance Benchmarks
timeout-minutes: 25
working-directory: test/s3/iam
run: |
set -x
echo "=== Running IAM Performance Tests ==="
export WEED_BINARY=$(which weed)
export TEST_TIMEOUT=20m
make clean setup start-services wait-for-services
# Run performance tests (benchmarks disabled for CI)
echo "Running performance tests..."
export ENABLE_PERFORMANCE_TESTS=true
go test -v -timeout 15m -run "TestS3IAMPerformanceTests" ./... || {
echo "❌ Performance tests failed"
make logs
exit 1
}
make stop-services
- name: Upload performance test results
if: always()
uses: actions/upload-artifact@v7
with:
name: s3-iam-performance-results
path: |
test/s3/iam/weed-*.log
test/s3/iam/*.test
retention-days: 7
-161
View File
@@ -1,161 +0,0 @@
name: "S3 Keycloak Integration Tests"
on:
pull_request:
paths:
- 'weed/iam/**'
- 'weed/s3api/**'
- 'test/s3/iam/**'
- '.github/workflows/s3-keycloak-tests.yml'
push:
branches: [ master ]
paths:
- 'weed/iam/**'
- 'weed/s3api/**'
- 'test/s3/iam/**'
- '.github/workflows/s3-keycloak-tests.yml'
concurrency:
group: ${{ github.head_ref }}/s3-keycloak-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
# Dedicated job for Keycloak integration tests
s3-keycloak-integration-tests:
name: S3 Keycloak Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
working-directory: weed
run: |
go install -buildvcs=false
- name: Run Keycloak Integration Tests
timeout-minutes: 25
working-directory: test/s3/iam
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 Keycloak Integration Tests ==="
# Set WEED_BINARY to use the installed version
export WEED_BINARY=$(which weed)
export TEST_TIMEOUT=20m
echo "Running Keycloak integration tests..."
# Start Keycloak container first
docker run -d \
--name keycloak \
-p 8080:8080 \
-e KC_BOOTSTRAP_ADMIN_USERNAME=admin \
-e KC_BOOTSTRAP_ADMIN_PASSWORD=admin \
-e KC_HTTP_ENABLED=true \
-e KC_HOSTNAME_STRICT=false \
-e KC_HOSTNAME_STRICT_HTTPS=false \
quay.io/keycloak/keycloak:26.0 \
start-dev
# Wait for Keycloak with better health checking
timeout 300 bash -c '
while true; do
if curl -s http://localhost:8080/health/ready > /dev/null 2>&1; then
echo "✅ Keycloak health check passed"
break
fi
echo "... waiting for Keycloak to be ready"
sleep 5
done
'
# Setup Keycloak configuration
./setup_keycloak.sh
# Start SeaweedFS services
make clean setup start-services wait-for-services
# Verify service accessibility
echo "=== Verifying Service Accessibility ==="
curl -f http://localhost:8080/realms/master
curl -s http://localhost:8333/healthz
echo "✅ SeaweedFS S3 API is responding (IAM-protected endpoint)"
# Run Keycloak-specific tests
echo "=== Running Keycloak Tests ==="
export KEYCLOAK_URL=http://localhost:8080
export S3_ENDPOINT=http://localhost:8333
# Wait for realm to be properly configured
timeout 120 bash -c 'until curl -fs http://localhost:8080/realms/seaweedfs-test/.well-known/openid-configuration > /dev/null; do echo "... waiting for realm"; sleep 3; done'
# Run the Keycloak integration tests
go test -v -timeout 20m -run "TestKeycloak" ./...
- name: Show server logs on failure
if: failure()
working-directory: test/s3/iam
run: |
echo "=== Service Logs ==="
echo "--- Keycloak logs ---"
docker logs keycloak --tail=100 || echo "No Keycloak container logs"
echo "--- SeaweedFS Master logs ---"
if [ -f weed-master.log ]; then
tail -100 weed-master.log
fi
echo "--- SeaweedFS S3 logs ---"
if [ -f weed-s3.log ]; then
tail -100 weed-s3.log
fi
echo "--- SeaweedFS Filer logs ---"
if [ -f weed-filer.log ]; then
tail -100 weed-filer.log
fi
echo "=== System Status ==="
ps aux | grep -E "(weed|keycloak)" || true
netstat -tlnp | grep -E "(8333|9333|8080|8888)" || true
docker ps -a || true
- name: Cleanup
if: always()
working-directory: test/s3/iam
run: |
# Stop Keycloak container
docker stop keycloak || true
docker rm keycloak || true
# Stop SeaweedFS services
make clean || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-keycloak-test-logs
path: |
test/s3/iam/*.log
test/s3/iam/test-volume-data/
retention-days: 3
@@ -1,148 +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@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Run S3 versioning regression tests
timeout-minutes: 20
working-directory: test/s3/versioning
run: |
set -x
# Run every versioning test, so a regression test lands covered instead
# of waiting for someone to remember this file. Name a test in EXCLUDE,
# with the reason, to keep it out.
#
# TestVersioningPagination*: opt-in stress tests that build 1500+
# versions. They self-skip without ENABLE_STRESS_TESTS and have their
# own make target, so this gate should not carry them.
EXCLUDE='TestVersioningPagination.*'
tests=$(go test . -list '.*' | grep '^Test' | sort -u)
# An empty list would make -run match nothing and pass this job vacuously.
[ -n "$tests" ] || { echo "listed no versioning tests"; exit 1; }
selected=$(echo "$tests" | grep -vE "^($EXCLUDE)$")
[ -n "$selected" ] || { echo "EXCLUDE matched every test"; exit 1; }
echo "running $(echo "$selected" | wc -l) of $(echo "$tests" | wc -l) versioning tests"
# make swallows a lone trailing $, taking the anchor with it, so escape it.
make test-with-server TEST_PATTERN="^($(echo "$selected" | paste -sd'|' -))"'$$'
- 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@v7
- name: Set up Go
uses: actions/setup-go@v7
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
-163
View File
@@ -1,163 +0,0 @@
name: "S3 PyArrow Parquet Tests"
on:
push:
branches: [master]
paths:
- 'weed/s3api/**'
- 'weed/filer/**'
- 'test/s3/parquet/**'
- '.github/workflows/s3-parquet-tests.yml'
pull_request:
branches: [master]
paths:
- 'weed/s3api/**'
- 'weed/filer/**'
- 'test/s3/parquet/**'
- '.github/workflows/s3-parquet-tests.yml'
workflow_dispatch:
env:
S3_ACCESS_KEY: some_access_key1
S3_SECRET_KEY: some_secret_key1
S3_ENDPOINT_URL: http://localhost:8333
BUCKET_NAME: test-parquet-bucket
jobs:
parquet-integration-tests:
name: PyArrow Parquet Tests (Python ${{ matrix.python-version }})
runs-on: ubuntu-latest
timeout-minutes: 20
strategy:
fail-fast: false
matrix:
python-version: ['3.9', '3.11', '3.12']
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v7
with:
python-version: ${{ matrix.python-version }}
cache: 'pip'
cache-dependency-path: 'test/s3/parquet/requirements.txt'
- name: Install system dependencies
run: |
sudo apt-get update
sudo apt-get install -y lsof netcat-openbsd
- name: Build SeaweedFS
run: |
cd weed
go build -v
sudo cp weed /usr/local/bin/
weed version
- name: Run PyArrow Parquet integration tests
run: |
cd test/s3/parquet
make test-with-server
env:
SEAWEEDFS_BINARY: weed
S3_PORT: 8333
FILER_PORT: 8888
VOLUME_PORT: 8080
MASTER_PORT: 9333
VOLUME_MAX_SIZE_MB: 50
- name: Run implicit directory fix tests
run: |
cd test/s3/parquet
make test-implicit-dir-with-server
env:
SEAWEEDFS_BINARY: weed
S3_PORT: 8333
FILER_PORT: 8888
VOLUME_PORT: 8080
MASTER_PORT: 9333
- name: Run PyArrow native S3 filesystem tests
run: |
cd test/s3/parquet
make test-native-s3-with-server
env:
SEAWEEDFS_BINARY: weed
S3_PORT: 8333
FILER_PORT: 8888
VOLUME_PORT: 8080
MASTER_PORT: 9333
- name: Run cross-filesystem compatibility tests
run: |
cd test/s3/parquet
TEST_QUICK=1 make test-cross-fs-with-server
env:
SEAWEEDFS_BINARY: weed
S3_PORT: 8333
FILER_PORT: 8888
VOLUME_PORT: 8080
MASTER_PORT: 9333
- name: Run SSE-S3 encryption compatibility tests
run: |
cd test/s3/parquet
make test-sse-s3-compat
env:
SEAWEEDFS_BINARY: weed
S3_PORT: 8333
FILER_PORT: 8888
VOLUME_PORT: 8080
MASTER_PORT: 9333
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: test-logs-python-${{ matrix.python-version }}
path: |
/tmp/seaweedfs-parquet-*.log
test/s3/parquet/*.log
retention-days: 7
- name: Cleanup
if: always()
run: |
cd test/s3/parquet
make stop-seaweedfs-safe || true
make clean || true
unit-tests:
name: Go Unit Tests (Implicit Directory)
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version: ^1.26
cache: true
- name: Run Go unit tests
run: |
cd weed/s3api
go test -v -run TestImplicitDirectory
- name: Run all S3 API tests
run: |
cd weed/s3api
go test -v -timeout 5m
-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: ${{ github.head_ref }}/s3-policy-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
# Unit tests for policy components
policy-unit-tests:
name: S3 Policy Unit Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Get dependencies
run: |
go mod download
- name: Run S3 Policy Unit Tests
timeout-minutes: 10
run: |
set -x
echo "=== Running S3 Action Resolver Tests ==="
go test -v -timeout 5m ./s3api/... -run ".*ActionResolver.*"
echo "=== Running S3 Bucket Policy Engine Tests ==="
go test -v -timeout 5m ./s3api/... -run ".*BucketPolicy.*|.*PolicyEngine.*"
echo "=== Running IAM Policy Tests ==="
go test -v -timeout 5m ./iam/policy/...
- name: Upload test results on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: policy-unit-test-results
path: |
weed/testdata/
weed/**/testdata/
retention-days: 3
# S3 Policy Variables Integration Tests
s3-policy-variables-tests:
name: S3 Policy Variables Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 25
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Policy Variables Integration Tests
timeout-minutes: 20
working-directory: test/s3/iam
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting S3 Policy Variables Integration Tests ==="
# Set WEED_BINARY to use the installed version
export WEED_BINARY=$(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@v7
- name: Set up Go
uses: actions/setup-go@v7
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_${{ matrix.test-case }}.log
retention-days: 5
# Trusted Proxy Detection Tests
trusted-proxy-tests:
name: Trusted Proxy Detection Tests
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run Trusted Proxy Tests
timeout-minutes: 15
working-directory: test/s3/iam
run: |
set -x
echo "=== Running Trusted Proxy Detection Tests ==="
export WEED_BINARY=$(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 $SERVER_PID 2>/dev/null || true" EXIT
# Run proxy tests
go test -v -timeout 10m -run "TestTrustedProxy|TestPrivateIP" ./...
- name: Show service logs on failure
if: failure()
run: |
echo "=== Service Logs ==="
if [ -f /tmp/weed_proxy_test.log ]; then
echo "--- Last 100 lines of Server Log ---"
tail -100 /tmp/weed_proxy_test.log
fi
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: trusted-proxy-test-logs
path: /tmp/weed_proxy_test.log
retention-days: 3
# S3 Policy Shell Integration Tests
s3-policy-shell-tests:
name: S3 Policy Shell Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 Policy Shell Tests
timeout-minutes: 10
working-directory: test/s3/policy
run: |
set -x
echo "=== Running S3 Policy Shell Tests ==="
# Set WEED_BINARY to use the installed version (though test uses 'weed' command)
export WEED_BINARY=$(which weed)
export PATH=$PATH:$(dirname $WEED_BINARY)
go test -v -timeout 10m ./...
@@ -1,143 +0,0 @@
name: "S3 Proxy Signature Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/s3api/**'
- 'weed/server/**'
- 'test/s3/proxy_signature/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/s3-proxy-signature-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/s3api/**'
- 'weed/server/**'
- 'test/s3/proxy_signature/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/s3-proxy-signature-tests.yml'
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@v7
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: 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 $(seq 1 30); do
# Check logs first for the readiness line. weed mini's progress
# board prints " S3 ready (Xs)"; older builds and the
# standalone S3 binary log "S3 (gateway|service) ... ready".
if docker compose logs seaweedfs 2>&1 | grep -qE "S3 (gateway|service).*(started|ready)|S3[[:space:]]+ready"; then
echo "SeaweedFS S3 gateway is ready"
S3_READY=1
break
fi
# Fallback: check headers via proxy (which is already ready)
if curl -s -I http://localhost:9000/ | grep -qi "SeaweedFS"; then
echo "SeaweedFS S3 gateway is responding via proxy"
S3_READY=1
break
fi
echo "Waiting for S3 gateway... ($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
@@ -1,110 +0,0 @@
name: "S3 SDK V2 Route Disambiguation Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/s3api/**'
- 'test/s3/sdk_v2_routing/**'
- '.github/workflows/s3-sdk-v2-routing-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/s3api/**'
- 'test/s3/sdk_v2_routing/**'
- '.github/workflows/s3-sdk-v2-routing-tests.yml'
concurrency:
group: ${{ github.head_ref || github.ref }}/s3-sdk-v2-routing-tests
cancel-in-progress: true
permissions:
contents: read
jobs:
s3-sdk-v2-routing-tests:
name: S3 SDK V2 Routing Tests
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install SeaweedFS
run: |
cd weed && go install -buildvcs=false
- name: Start weed mini (S3 on :8333)
# Pins the regression for issue #9559: AWS SDK V2 / Hadoop s3a
# listing a bucket literally named "buckets" must get an XML
# ListObjectsV2 response, not the JSON ListTableBuckets body
# served by the S3 Tables REST endpoint on the same path.
run: |
mkdir -p /tmp/seaweedfs-sdk-v2-routing
cat > /tmp/seaweedfs-sdk-v2-routing-s3.json <<'JSON'
{
"identities": [
{
"name": "admin",
"credentials": [
{"accessKey": "some_access_key1", "secretKey": "some_secret_key1"}
],
"actions": ["Admin", "Read", "Write"]
}
]
}
JSON
AWS_ACCESS_KEY_ID=some_access_key1 \
AWS_SECRET_ACCESS_KEY=some_secret_key1 \
weed mini \
-dir=/tmp/seaweedfs-sdk-v2-routing \
-s3.port=8333 \
-s3.config=/tmp/seaweedfs-sdk-v2-routing-s3.json \
-ip=127.0.0.1 \
> /tmp/weed-mini.log 2>&1 &
echo $! > /tmp/weed-mini.pid
for i in $(seq 1 30); do
if curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:8333/ | grep -qE "^(200|403)$"; then
echo "weed mini is ready"
exit 0
fi
sleep 1
done
echo "weed mini failed to start within 30s"
tail -50 /tmp/weed-mini.log
exit 1
- name: Run SDK V2 routing tests
env:
S3_ENDPOINT: http://127.0.0.1:8333
AWS_ACCESS_KEY_ID: some_access_key1
AWS_SECRET_ACCESS_KEY: some_secret_key1
AWS_REGION: us-east-1
run: go test -v -timeout=5m ./test/s3/sdk_v2_routing/...
- name: Stop weed mini
if: always()
run: |
if [ -f /tmp/weed-mini.pid ]; then
kill "$(cat /tmp/weed-mini.pid)" 2>/dev/null || true
fi
- name: Show server log on failure
if: failure()
run: |
echo "=== weed mini log (last 200 lines) ==="
tail -n 200 /tmp/weed-mini.log 2>/dev/null || echo "no log available"
- name: Archive log
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-sdk-v2-routing-server-log
path: /tmp/weed-mini.log
retention-days: 3
-85
View File
@@ -1,85 +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@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Configure Docker Hub mirror
run: |
echo '{"registry-mirrors": ["https://mirror.gcr.io"]}' | sudo tee /etc/docker/daemon.json
sudo systemctl restart docker
- name: Install SeaweedFS
run: |
go install -buildvcs=false ./weed
- name: Pre-pull Spark image
run: |
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
pull apache/spark:3.5.1
- name: Run 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
-401
View File
@@ -1,401 +0,0 @@
name: "S3 SSE Tests"
on:
pull_request:
paths:
- 'weed/s3api/s3_sse_*.go'
- 'weed/s3api/s3api_object_handlers.go'
- 'weed/s3api/s3api_object_handlers_put.go'
- 'weed/s3api/s3api_object_handlers_copy*.go'
- 'weed/server/filer_server_handlers_*.go'
- 'weed/kms/**'
- 'test/s3/sse/**'
- '.github/workflows/s3-sse-tests.yml'
push:
branches: [ master, main ]
paths:
- 'weed/s3api/s3_sse_*.go'
- 'weed/s3api/s3api_object_handlers.go'
- 'weed/s3api/s3api_object_handlers_put.go'
- 'weed/s3api/s3api_object_handlers_copy*.go'
- 'weed/server/filer_server_handlers_*.go'
- 'weed/kms/**'
- 'test/s3/sse/**'
concurrency:
group: ${{ github.head_ref }}/s3-sse-tests
cancel-in-progress: true
permissions:
contents: read
defaults:
run:
working-directory: weed
jobs:
s3-sse-integration-tests:
name: S3 SSE Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 30
strategy:
matrix:
test-type: ["quick", "comprehensive"]
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 SSE Integration Tests - ${{ matrix.test-type }}
timeout-minutes: 25
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
df -h
echo "=== Starting SSE Tests ==="
# Run tests with automatic server management
# The test-with-server target handles server startup/shutdown automatically
if [ "${{ matrix.test-type }}" = "quick" ]; then
# Quick tests - basic SSE-C and SSE-KMS functionality + Range requests
make test-with-server TEST_PATTERN="TestSSECIntegrationBasic|TestSSEKMSIntegrationBasic|TestSimpleSSECIntegration|.*RangeRequestsServerBehavior"
else
# Comprehensive tests - SSE-C/KMS functionality plus cross-SSE copy.
# The copy-operation tests (`.*ObjectCopyIntegration`, `TestCrossSSECopy`,
# `TestSSEMultipartCopy`) were excluded for a long time as "pre-existing
# SSE-C issues" (#9281); fixed and brought back into CI as part of the
# same change that fixed them.
make test-with-server TEST_PATTERN="TestSSECIntegrationBasic|TestSSECIntegrationVariousDataSizes|TestSSEKMSIntegrationBasic|TestSSEKMSIntegrationVariousDataSizes|.*Multipart.*Integration|TestSimpleSSECIntegration|.*RangeRequestsServerBehavior|.*ObjectCopyIntegration|TestCrossSSECopy|TestSSEMultipartCopy"
fi
- name: Show server logs on failure
if: failure()
working-directory: test/s3/sse
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|8888)" || true
- name: Upload test logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-sse-test-logs-${{ matrix.test-type }}
path: test/s3/sse/weed-test*.log
retention-days: 3
s3-sse-compatibility:
name: S3 SSE Compatibility Test
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run Core SSE Compatibility Test (AWS S3 equivalent)
timeout-minutes: 15
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run the specific tests that validate AWS S3 SSE compatibility - both SSE-C and SSE-KMS basic functionality plus Range requests
make test-with-server TEST_PATTERN="TestSSECIntegrationBasic|TestSSEKMSIntegrationBasic|.*RangeRequestsServerBehavior" || {
echo "❌ SSE compatibility 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 server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-sse-compatibility-logs
path: test/s3/sse/weed-test*.log
retention-days: 3
s3-sse-metadata-persistence:
name: S3 SSE Metadata Persistence Test
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run SSE Metadata Persistence Test
timeout-minutes: 15
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run the specific test that would catch filer metadata storage bugs
# This test validates that encryption metadata survives the full PUT/GET cycle
make test-metadata-persistence || {
echo "❌ SSE metadata persistence 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 server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-sse-metadata-persistence-logs
path: test/s3/sse/weed-test*.log
retention-days: 3
s3-sse-copy-operations:
name: S3 SSE Copy Operations Test
runs-on: ubuntu-22.04
timeout-minutes: 25
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run SSE Copy Operations Tests
timeout-minutes: 20
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run tests that validate SSE copy operations and cross-encryption scenarios
echo "🚀 Running SSE copy operations tests..."
echo "📋 Note: SSE-C copy operations have pre-existing functionality gaps"
echo " Cross-encryption copy security fix has been implemented and maintained"
# Skip SSE-C copy operations due to pre-existing HTTP 500 errors
# The critical security fix for cross-encryption (SSE-C → SSE-KMS) has been preserved
echo "⏭️ Skipping SSE copy operations tests due to known limitations:"
echo " - SSE-C copy operations: HTTP 500 errors (pre-existing functionality gap)"
echo " - Cross-encryption security fix: ✅ Implemented and tested (forces streaming copy)"
echo " - These limitations are documented as pre-existing issues"
exit 0 # Job succeeds with security fix preserved and limitations documented
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-sse-copy-operations-logs
path: test/s3/sse/weed-test*.log
retention-days: 3
s3-sse-multipart:
name: S3 SSE Multipart Upload Test
runs-on: ubuntu-22.04
timeout-minutes: 25
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run SSE Multipart Upload Tests
timeout-minutes: 20
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Multipart tests - Document known architectural limitations
echo "🚀 Running multipart upload tests..."
echo "📋 Note: SSE-KMS multipart upload has known architectural limitation requiring per-chunk metadata storage"
echo " SSE-C multipart tests will be skipped due to pre-existing functionality gaps"
# Test SSE-C basic multipart (skip advanced multipart that fails with HTTP 500)
# Skip SSE-KMS multipart due to architectural limitation (each chunk needs independent metadata)
echo "⏭️ Skipping multipart upload tests due to known limitations:"
echo " - SSE-C multipart GET operations: HTTP 500 errors (pre-existing functionality gap)"
echo " - SSE-KMS multipart decryption: Requires per-chunk SSE metadata architecture changes"
echo " - These limitations are documented and require future architectural work"
exit 0 # Job succeeds with clear documentation of known limitations
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: s3-sse-multipart-logs
path: test/s3/sse/weed-test*.log
retention-days: 3
s3-sse-performance:
name: S3 SSE Performance Test
runs-on: ubuntu-22.04
timeout-minutes: 35
# Only run performance tests on master branch pushes to avoid overloading PR testing
if: github.event_name == 'push' && (github.ref == 'refs/heads/master' || github.ref == 'refs/heads/main')
steps:
- name: Check out code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
id: go
- name: Install SeaweedFS
run: |
go install -buildvcs=false
- name: Run S3 SSE Performance Tests
timeout-minutes: 30
working-directory: test/s3/sse
run: |
set -x
echo "=== System Information ==="
uname -a
free -h
# Run performance tests with various data sizes
make perf || {
echo "❌ SSE performance test failed, checking logs..."
if [ -f weed-test.log ]; then
echo "=== Server logs ==="
tail -200 weed-test.log
fi
make clean
exit 1
}
make clean
- name: Upload performance test logs
if: always()
uses: actions/upload-artifact@v7
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
-120
View File
@@ -1,120 +0,0 @@
name: "Samba on FUSE Integration"
on:
push:
branches: [ master, main ]
paths:
- 'weed/mount/**'
- 'weed/filer/**'
- 'weed/cluster/**'
- 'test/samba/**'
- '.github/workflows/samba-integration.yml'
pull_request:
branches: [ master, main ]
paths:
- 'weed/mount/**'
- 'weed/filer/**'
- 'weed/cluster/**'
- 'test/samba/**'
- '.github/workflows/samba-integration.yml'
workflow_dispatch:
concurrency:
group: samba-integration/${{ github.ref }}
cancel-in-progress: true
permissions:
contents: read
jobs:
samba-integration:
name: samba-integration
runs-on: ubuntu-22.04
timeout-minutes: 45
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Start local Docker registry
run: docker run -d --restart=always -p 5000:5000 --name registry registry:2
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
with:
driver-opts: network=host
- name: Build weed race binary
run: |
cd docker
make binary_race
- name: Build SeaweedFS e2e image
uses: docker/build-push-action@v7
with:
context: docker
file: docker/Dockerfile.e2e
tags: localhost:5000/chrislusf/seaweedfs:e2e
push: true
cache-from: type=gha,scope=samba-e2e
cache-to: type=gha,mode=max,scope=samba-e2e
- name: Tag e2e image for docker compose
run: |
docker pull localhost:5000/chrislusf/seaweedfs:e2e
docker tag localhost:5000/chrislusf/seaweedfs:e2e chrislusf/seaweedfs:e2e
- name: Build samba image
uses: docker/build-push-action@v7
with:
context: test/samba
build-contexts: |
chrislusf/seaweedfs:e2e=docker-image://localhost:5000/chrislusf/seaweedfs:e2e
tags: localhost:5000/chrislusf/seaweedfs:samba
push: true
cache-from: type=gha,scope=samba-harness
cache-to: type=gha,mode=max,scope=samba-harness
- name: Tag samba image for docker compose
run: |
docker pull localhost:5000/chrislusf/seaweedfs:samba
docker tag localhost:5000/chrislusf/seaweedfs:samba chrislusf/seaweedfs:samba
- name: Start SeaweedFS cluster and Samba
run: |
docker compose -f test/samba/docker-compose.yml up --wait
- name: Run Samba test battery
run: |
set -o pipefail
docker compose -f test/samba/docker-compose.yml exec -T samba \
/run_inside_container.sh 2>&1 | tee /tmp/samba-output.log
- name: Collect logs
if: always()
run: |
mkdir -p /tmp/samba-docker-logs
for svc in master volume filer samba; do
docker compose -f test/samba/docker-compose.yml logs "$svc" \
> "/tmp/samba-docker-logs/${svc}.log" 2>&1 || true
done
- name: Tear down
if: always()
run: |
docker compose -f test/samba/docker-compose.yml down -v
- name: Upload logs
if: always()
uses: actions/upload-artifact@v7
with:
name: samba-integration-results
path: |
/tmp/samba-output.log
/tmp/samba-docker-logs/
retention-days: 7
-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: ${{ github.head_ref }}/sftp-tests
cancel-in-progress: true
permissions:
contents: read
env:
TEST_TIMEOUT: '15m'
jobs:
sftp-integration:
name: SFTP Integration Testing
runs-on: ubuntu-22.04
timeout-minutes: 20
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Install dependencies
run: |
sudo apt-get update
sudo apt-get install -y openssh-client
- name: Build SeaweedFS
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
- name: Run SFTP Integration Tests
run: |
cd test/sftp
echo "🧪 Running SFTP integration tests..."
echo "============================================"
# Install test dependencies
go mod download
# Run all SFTP tests
go test -v -timeout=${{ 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
@@ -1,263 +0,0 @@
name: Spark Integration Tests
on:
push:
paths:
- 'test/java/spark/**'
- 'other/java/hdfs3/**'
- 'other/java/client/**'
- '.github/workflows/spark-integration-tests.yml'
pull_request:
paths:
- 'test/java/spark/**'
- 'other/java/hdfs3/**'
- 'other/java/client/**'
- '.github/workflows/spark-integration-tests.yml'
workflow_dispatch:
permissions:
contents: read
checks: write
pull-requests: write
jobs:
spark-integration-tests:
name: Spark Integration Tests
runs-on: ubuntu-latest
timeout-minutes: 45
steps:
# ========================================
# SETUP & BUILD
# ========================================
- name: Checkout code
uses: actions/checkout@v7
- name: Set up JDK 11
uses: actions/setup-java@v5
with:
java-version: '11'
distribution: 'temurin'
cache: maven
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Build SeaweedFS binary
run: |
echo "Building SeaweedFS binary (statically linked for Alpine)..."
cd weed
CGO_ENABLED=0 go build -o ../docker/weed
cd ../docker
ls -la weed filer.toml entrypoint.sh
file weed
echo "OK SeaweedFS binary built"
- name: Build SeaweedFS Java dependencies
run: |
echo "Building Java client..."
cd other/java/client
mvn clean install -U -DskipTests -Dgpg.skip=true -Dcentral.publishing.skip=true
echo "OK Java client built"
cd ../../..
echo "Building HDFS3 client..."
cd other/java/hdfs3
mvn clean install -U -DskipTests -Dgpg.skip=true -Dcentral.publishing.skip=true
echo "OK HDFS3 client built"
echo ""
echo "All Java dependencies installed to ~/.m2/repository"
# ========================================
# SPARK INTEGRATION TESTS (DOCKER)
# ========================================
- name: Start SeaweedFS services for tests
working-directory: test/java/spark
run: |
echo "=== Starting SeaweedFS Services for Tests ==="
docker compose down -v || true
docker compose build --no-cache
docker compose up -d seaweedfs-master seaweedfs-volume seaweedfs-filer
echo "Waiting for services..."
for i in {1..30}; do
if curl -f http://localhost:8888/ > /dev/null 2>&1; then
echo "OK SeaweedFS filer is ready!"
break
fi
if [ $i -eq 30 ]; then
echo "FAILED Services failed to start"
docker compose ps -a
docker compose logs
exit 1
fi
echo "Waiting... ($i/30)"
sleep 2
done
curl -f http://localhost:9333/cluster/status || exit 1
echo "OK All services healthy"
- name: Prepare Maven repository for Docker
working-directory: test/java/spark
run: |
echo "Copying Maven artifacts for Docker container..."
mkdir -p .m2/repository/com
cp -r ~/.m2/repository/com/seaweedfs .m2/repository/com/
echo "OK Maven artifacts copied"
- name: Run Spark integration tests
working-directory: test/java/spark
run: |
echo "=== Running Spark Integration Tests ==="
docker compose up --abort-on-container-exit spark-tests
echo ""
echo "=== Test Logs ==="
docker compose logs spark-tests | tail -100
- name: Stop test services
if: always()
working-directory: test/java/spark
run: docker compose down -v
- name: Upload test results
if: always()
uses: actions/upload-artifact@v7
with:
name: spark-test-results
path: test/java/spark/target/surefire-reports/
retention-days: 30
- name: Publish test report
if: always()
uses: dorny/test-reporter@v3
with:
name: Spark Test Results
path: test/java/spark/target/surefire-reports/*.xml
reporter: java-junit
fail-on-error: true
# ========================================
# SPARK EXAMPLE (HOST-BASED) - DISABLED
# Note: Host-based example doesn't work with Docker networking
# because master returns Docker hostnames (seaweedfs-volume)
# which are not resolvable from the host.
# The Docker-based tests above are sufficient.
# ========================================
- name: Cache Apache Spark
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
id: cache-spark
uses: actions/cache@v6
with:
path: spark-3.5.0-bin-hadoop3
key: spark-3.5.0-hadoop3
- name: Download Apache Spark
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') && steps.cache-spark.outputs.cache-hit != 'true'
run: |
echo "Downloading Apache Spark 3.5.0..."
wget -q https://archive.apache.org/dist/spark/spark-3.5.0/spark-3.5.0-bin-hadoop3.tgz
tar xzf spark-3.5.0-bin-hadoop3.tgz
echo "OK Spark downloaded"
- name: Start SeaweedFS services for example
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
working-directory: test/java/spark
run: |
echo "=== Starting SeaweedFS Services for Example ==="
docker compose down -v || true
docker compose build --no-cache
docker compose up -d seaweedfs-master seaweedfs-volume seaweedfs-filer
echo "Waiting for services..."
for i in {1..30}; do
if curl -f http://localhost:8888/ > /dev/null 2>&1; then
echo "OK SeaweedFS filer is ready!"
break
fi
if [ $i -eq 30 ]; then
echo "FAILED Services failed to start"
docker compose ps -a
docker compose logs
exit 1
fi
echo "Waiting... ($i/30)"
sleep 2
done
curl -f http://localhost:9333/cluster/status || exit 1
echo "OK All services healthy"
- name: Clean target directory
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
working-directory: test/java/spark
run: |
# Force remove target directory to avoid permission issues
sudo rm -rf target || rm -rf target || true
echo "OK Target directory cleaned"
- name: Build project for example
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
working-directory: test/java/spark
run: mvn package -DskipTests
- name: Run Spark example application
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
working-directory: test/java/spark
run: |
echo "=== Running Spark Example Application ==="
export SPARK_HOME=$(pwd)/../../../spark-3.5.0-bin-hadoop3
$SPARK_HOME/bin/spark-submit \
--class seaweed.spark.SparkSeaweedFSExample \
--master local[2] \
--conf spark.hadoop.fs.seaweedfs.impl=seaweed.hdfs.SeaweedFileSystem \
--conf spark.hadoop.fs.seaweed.filer.host=localhost \
--conf spark.hadoop.fs.seaweed.filer.port=8888 \
--conf spark.hadoop.fs.seaweed.filer.port.grpc=18888 \
--conf spark.hadoop.fs.seaweed.replication="" \
target/seaweedfs-spark-integration-tests-1.0-SNAPSHOT.jar \
seaweedfs://localhost:8888/ci-spark-output
echo "OK Example completed"
- name: Verify example output
if: false && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
run: |
echo "Verifying output..."
curl -s http://localhost:8888/ci-spark-output/ || echo "Output listing unavailable"
- name: Stop example services
if: false && always() && (github.event_name == 'push' || github.event_name == 'workflow_dispatch')
working-directory: test/java/spark
run: docker compose down -v
# ========================================
# DIAGNOSTICS
# ========================================
- name: Display diagnostics on failure
if: failure()
working-directory: test/java/spark
run: |
echo "=== Container Status ==="
docker compose ps -a
echo ""
echo "=== Master Logs ==="
docker compose logs seaweedfs-master
echo ""
echo "=== Volume Logs ==="
docker compose logs seaweedfs-volume
echo ""
echo "=== Filer Logs ==="
docker compose logs seaweedfs-filer
echo ""
echo "=== Volume List ==="
docker compose exec -T seaweedfs-master weed shell <<EOF || echo "Failed"
volume.list
exit
EOF
echo ""
echo "=== Cluster Status ==="
curl -s http://localhost:9333/dir/status | jq '.' || curl -s http://localhost:9333/dir/status
@@ -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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
-80
View File
@@ -1,80 +0,0 @@
name: "terraform: validate and test modules"
on:
push:
branches: [ master ]
paths: ['terraform/**', '.github/workflows/terraform_ci.yml']
pull_request:
branches: [ master ]
paths: ['terraform/**', '.github/workflows/terraform_ci.yml']
permissions:
contents: read
jobs:
validate:
name: fmt, validate, plan-level tests
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- name: Set up OpenTofu
uses: opentofu/setup-opentofu@v2
with:
tofu_version: 1.12.1
- name: fmt check
working-directory: terraform
run: tofu fmt -recursive -check -diff
- name: validate core
working-directory: terraform/modules/core
run: |
tofu init -backend=false -input=false
tofu validate
- name: validate security
working-directory: terraform/modules/security
run: |
tofu init -backend=false -input=false
tofu validate
- name: plan-level tests (core)
working-directory: terraform/modules/core
run: tofu test
- name: validate examples
run: |
set -e
for ex in terraform/examples/*/; do
echo "== validate $ex =="
tofu -chdir="$ex" init -backend=false -input=false
tofu -chdir="$ex" validate
done
smoke:
name: local cluster smoke test (real weed)
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: go.mod
- name: Build weed
run: go build -o "$RUNNER_TEMP/weed" ./weed
- name: Set up OpenTofu
uses: opentofu/setup-opentofu@v2
with:
tofu_version: 1.12.1
- name: Run local cluster harness
working-directory: terraform/test/local
run: WEED="$RUNNER_TEMP/weed" ./run_local_cluster.sh
- name: Run local mTLS cluster harness
working-directory: terraform/test/local-secure
run: WEED="$RUNNER_TEMP/weed" ./run_local_secure.sh
@@ -1,123 +0,0 @@
name: "test s3 over https using aws-cli"
on:
push:
branches: [master, test-https-s3-awscli]
paths:
- 'weed/s3api/**'
- 'weed/server/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/test-s3-over-https-using-awscli.yml'
pull_request:
branches: [master, test-https-s3-awscli]
paths:
- 'weed/s3api/**'
- 'weed/server/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/test-s3-over-https-using-awscli.yml'
env:
AWS_ACCESS_KEY_ID: some_access_key1
AWS_SECRET_ACCESS_KEY: some_secret_key1
AWS_ENDPOINT_URL: https://localhost:8443
defaults:
run:
working-directory: weed
jobs:
awscli-tests:
runs-on: ubuntu-latest
timeout-minutes: 10
steps:
- uses: actions/checkout@v7
- uses: actions/setup-go@v7
with:
go-version: ^1.26
- name: Build SeaweedFS
run: |
go build
- name: Start SeaweedFS
run: |
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
- name: Setup Caddy
run: |
curl -fsSL "https://caddyserver.com/api/download?os=linux&arch=amd64" -o caddy
chmod +x caddy
./caddy version
echo "{
auto_https disable_redirects
local_certs
}
localhost:8443 {
tls internal
reverse_proxy localhost:8333
}" > Caddyfile
- name: Start Caddy
run: |
./caddy start
until curl -fsS --insecure https://localhost:8443/healthz > /dev/null; do sleep 1; done
- name: Create Bucket
run: |
aws --no-verify-ssl s3api create-bucket --bucket bucket
- name: Test PutObject
run: |
set -e
dd if=/dev/urandom of=generated bs=1M count=2
aws --no-verify-ssl s3api put-object --bucket bucket --key test-putobject --body generated
aws --no-verify-ssl s3api get-object --bucket bucket --key test-putobject downloaded
diff -q generated downloaded
rm -f generated downloaded
- name: Test Multi-part Upload
run: |
set -e
dd if=/dev/urandom of=generated bs=1M count=32
aws --no-verify-ssl s3 cp --no-progress generated s3://bucket/test-multipart
aws --no-verify-ssl s3 cp --no-progress s3://bucket/test-multipart downloaded
diff -q generated downloaded
rm -f generated downloaded
- name: Test GetObject with If-Match
run: |
set -e
dd if=/dev/urandom of=generated bs=1M count=32
ETAG=$(aws --no-verify-ssl s3api put-object --bucket bucket --key test-get-obj --body generated | jq -r .ETag)
# jq -r already removes quotes, so use ETAG directly (handles both simple and multipart ETags)
aws --no-verify-ssl s3api get-object --bucket bucket --key test-get-obj --if-match "$ETAG" downloaded
diff -q generated downloaded
rm -f generated downloaded
- name: Show server logs on failure
if: failure()
run: |
echo "========================================="
echo "SeaweedFS Server Logs"
echo "========================================="
# Note: weed.log is relative to working-directory (weed/)
if [ -f weed.log ]; then
cat weed.log
else
echo "No weed.log file found"
fi
- name: Upload server logs on failure
if: failure()
uses: actions/upload-artifact@v7
with:
name: seaweedfs-logs
# Note: actions don't use defaults.run.working-directory, so path is relative to workspace root
path: weed/weed.log
retention-days: 3
-68
View File
@@ -1,68 +0,0 @@
name: "TLS Rotation Integration Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'test/tls_rotation/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/tls-rotation-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/**'
- 'test/tls_rotation/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/tls-rotation-tests.yml'
permissions:
contents: read
jobs:
tls-rotation-tests:
name: TLS Rotation Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 10
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Build weed binary
run: |
cd weed && go build -o weed .
- name: Run TLS Rotation Integration Tests
working-directory: test/tls_rotation
run: |
go test -v -count=1 -timeout 5m
- name: Collect server logs on failure
if: failure()
run: |
echo "Collecting master logs from temp directories..."
mkdir -p /tmp/tls-rotation-test-logs
find /tmp -maxdepth 1 -type d -name "TestMasterHTTPS*" 2>/dev/null | while read dir; do
if [ -d "$dir" ]; then
echo "Found test directory: $dir"
cp -r "$dir" /tmp/tls-rotation-test-logs/ 2>/dev/null || true
fi
done
echo "Collected logs:"
find /tmp/tls-rotation-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: tls-rotation-test-logs
path: /tmp/tls-rotation-test-logs/
retention-days: 14
-110
View File
@@ -1,110 +0,0 @@
name: "TUS Protocol Tests"
on:
pull_request:
paths:
- 'weed/server/**'
- 'weed/filer/**'
- 'test/tus/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/tus-tests.yml'
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@v7
- name: Set up Go
uses: actions/setup-go@v7
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
@@ -1,68 +0,0 @@
name: "Vacuum Integration Tests"
on:
push:
branches: [ master ]
paths:
- 'weed/**'
- 'test/vacuum/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/vacuum-integration-tests.yml'
pull_request:
branches: [ master ]
paths:
- 'weed/**'
- 'test/vacuum/**'
- 'go.mod'
- 'go.sum'
- '.github/workflows/vacuum-integration-tests.yml'
permissions:
contents: read
jobs:
vacuum-integration-tests:
name: Vacuum Integration Tests
runs-on: ubuntu-22.04
timeout-minutes: 15
steps:
- name: Set up Go 1.x
uses: actions/setup-go@v7
with:
go-version: ^1.26
id: go
- name: Check out code into the Go module directory
uses: actions/checkout@v7
- name: Build weed binary
run: |
cd weed && go build -o weed .
- name: Run Vacuum Integration Tests
working-directory: test/vacuum
run: |
go test -v -timeout 10m
- name: Collect server logs on failure
if: failure()
run: |
echo "Collecting server logs from temp directories..."
mkdir -p /tmp/vacuum-test-logs
find /tmp -maxdepth 1 -type d -name "TestVacuum*" 2>/dev/null | while read dir; do
if [ -d "$dir" ]; then
echo "Found test directory: $dir"
cp -r "$dir" /tmp/vacuum-test-logs/ 2>/dev/null || true
fi
done
echo "Collected logs:"
find /tmp/vacuum-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: vacuum-integration-test-logs
path: /tmp/vacuum-test-logs/
retention-days: 14
@@ -1,104 +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: ${{ github.head_ref || github.ref }}/volume-server-integration-tests
cancel-in-progress: true
permissions:
contents: read
env:
TEST_TIMEOUT: '30m'
# Keep in step with the length of matrix.shard below.
SHARD_COUNT: 3
jobs:
volume-server-integration-tests:
name: Volume Server Integration Tests (${{ 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@v7
- name: Set up Go
uses: actions/setup-go@v7
with:
go-version-file: 'go.mod'
- name: Build SeaweedFS binary
run: |
cd weed
go build -o weed .
chmod +x weed
./weed version
# Dealing the listed tests out one by one keeps the shards even. Bucketing
# them by first letter did not: names cluster, so ^Test[I-S] drew 50 of
# the 114 grpc tests and ran nearly twice as long as the other two shards.
- name: Select this shard's tests
env:
TEST_TYPE: ${{ matrix.test-type }}
SHARD: ${{ matrix.shard }}
run: |
tests=$(go test ./test/volume_server/"$TEST_TYPE"/... -list '.*' | grep '^Test' | sort -u)
# An empty list would make -run match nothing and the shard pass vacuously.
[ -n "$tests" ] || { echo "listed no tests in test/volume_server/$TEST_TYPE"; exit 1; }
selected=$(echo "$tests" | awk -v n="$SHARD_COUNT" -v i="$SHARD" 'NR % n == i - 1')
echo "shard $SHARD of $SHARD_COUNT runs $(echo "$selected" | wc -l) of $(echo "$tests" | wc -l) tests"
echo "TEST_PATTERN=^($(echo "$selected" | paste -sd'|' -))\$" >> "$GITHUB_ENV"
- name: Run volume server integration tests
env:
WEED_BINARY: ${{ github.workspace }}/weed/weed
run: |
echo "Running volume server integration tests for ${{ matrix.test-type }} (Shard ${{ matrix.shard }} of ${SHARD_COUNT})..."
go test -v -count=1 -timeout=${{ 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: |
echo "## Volume Server Integration Test Summary (${{ matrix.test-type }} - Shard ${{ matrix.shard }})" >> "$GITHUB_STEP_SUMMARY"
echo "- Suite: test/volume_server/${{ matrix.test-type }} (shard ${{ matrix.shard }} of ${SHARD_COUNT}, see 'Select this shard's tests' for the split)" >> "$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"
-58
View File
@@ -2,7 +2,6 @@
vendor
tags
*.swp
.claude/
### OSX template
.DS_Store
.AppleDouble
@@ -88,60 +87,3 @@ other/java/hdfs/dependency-reduced-pom.xml
# binary file
weed/weed
docker/weed
# test generated files
weed/*/*.jpg
docker/weed_sub
docker/weed_pub
weed/mq/schema/example.parquet
docker/agent_sub_record
test/mq/bin/consumer
test/mq/bin/producer
test/producer
bin/weed
weed_binary
/test/s3/copying/filerldb2
/filerldb2
/test/s3/retention/test-volume-data
test/s3/cors/weed-test.log
test/s3/cors/weed-server.pid
/test/s3/cors/test-volume-data
test/s3/cors/cors.test
/test/s3/retention/filerldb2
test/s3/retention/weed-server.pid
test/s3/retention/weed-test.log
/test/s3/versioning/test-volume-data
test/s3/versioning/weed-test.log
/docker/admin_integration/data
docker/agent_pub_record
docker/admin_integration/weed-local
/seaweedfs-rdma-sidecar/bin
/test/s3/encryption/filerldb2
/test/s3/sse/filerldb2
test/s3/sse/weed-test.log
ADVANCED_IAM_DEVELOPMENT_PLAN.md
/test/s3/iam/test-volume-data
*.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
-5
View File
@@ -1,5 +0,0 @@
{
"setup": [],
"teardown": [],
"run": []
}
-74
View File
@@ -1,74 +0,0 @@
# Contributor Covenant Code of Conduct
## Our Pledge
In the interest of fostering an open and welcoming environment, we as
contributors and maintainers pledge to make participation in our project and
our community a harassment-free experience for everyone, regardless of age, body
size, disability, ethnicity, gender identity and expression, level of experience,
nationality, personal appearance, race, religion, or sexual identity and
orientation.
## Our Standards
Examples of behavior that contributes to creating a positive environment
include:
- Using welcoming and inclusive language
- Being respectful of differing viewpoints and experiences
- Gracefully accepting constructive criticism
- Focusing on what is best for the community
- Showing empathy towards other community members
Examples of unacceptable behavior by participants include:
- The use of sexualized language or imagery and unwelcome sexual attention or
advances
- Trolling, insulting/derogatory comments, and personal or political attacks
- Public or private harassment
- Publishing others' private information, such as a physical or electronic
address, without explicit permission
- Other conduct which could reasonably be considered inappropriate in a
professional setting
## Our Responsibilities
Project maintainers are responsible for clarifying the standards of acceptable
behavior and are expected to take appropriate and fair corrective action in
response to any instances of unacceptable behavior.
Project maintainers have the right and responsibility to remove, edit, or
reject comments, commits, code, wiki edits, issues, and other contributions
that are not aligned to this Code of Conduct, or to ban temporarily or
permanently any contributor for other behaviors that they deem inappropriate,
threatening, offensive, or harmful.
## Scope
This Code of Conduct applies both within project spaces and in public spaces
when an individual is representing the project or its community. Examples of
representing a project or community include using an official project e-mail
address, posting via an official social media account, or acting as an appointed
representative at an online or offline event. Representation of a project may be
further defined and clarified by project maintainers.
## Enforcement
Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported by contacting the project team at <enteremailhere>. All
complaints will be reviewed and investigated and will result in a response that
is deemed necessary and appropriate to the circumstances. The project team is
obligated to maintain confidentiality with regard to the reporter of an incident.
Further details of specific enforcement policies may be posted separately.
Project maintainers who do not follow or enforce the Code of Conduct in good
faith may face temporary or permanent repercussions as determined by other
members of the project's leadership.
## Attribution
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
available at [http://contributor-covenant.org/version/1/4][version]
[homepage]: http://contributor-covenant.org
[version]: http://contributor-covenant.org/version/1/4/
+1 -1
View File
@@ -186,7 +186,7 @@
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2025 Chris Lu
Copyright 2016 Chris Lu
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
+5 -64
View File
@@ -1,73 +1,14 @@
.PHONY: test admin-generate admin-build admin-clean admin-dev admin-run admin-test admin-fmt admin-help weed-commands
BINARY = weed
ADMIN_DIR = weed/admin
SOURCE_DIR = .
debug ?= 0
all: install
install: admin-generate
install:
cd weed; go install
weed-commands:
cd weed && $(MAKE) weed-db weed-sql
full_install:
cd weed; go install -tags "elastic gocdk sqlite ydb tikv"
warp_install:
go install github.com/minio/warp@v0.7.6
full_install: admin-generate
cd weed; go install -tags "elastic gocdk sqlite ydb tarantool tikv rclone"
server: install
weed -v 0 server -s3 -filer -filer.maxMB=64 -volume.max=0 -master.volumeSizeLimitMB=100 -volume.preStopSeconds=1 -s3.port=8000 -s3.allowDeleteBucketNotEmpty=true -s3.config=./docker/compose/s3.json -metricsPort=9324
benchmark: install warp_install
pkill weed || true
pkill warp || true
weed server -debug=$(debug) -s3 -filer -volume.max=0 -master.volumeSizeLimitMB=100 -volume.preStopSeconds=1 -s3.port=8000 -s3.allowDeleteBucketNotEmpty=false -s3.config=./docker/compose/s3.json &
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
pkill warp
pkill weed
# curl -o profile "http://127.0.0.1:6060/debug/pprof/profile?debug=1"
benchmark_with_pprof: debug = 1
benchmark_with_pprof: benchmark
test: admin-generate
cd weed; go test -tags "elastic gocdk sqlite ydb tarantool tikv rclone" -v ./...
# Admin component targets
admin-generate:
@cd $(ADMIN_DIR) && $(MAKE) generate
admin-build: admin-generate
@echo "Building admin component..."
@cd $(ADMIN_DIR) && $(MAKE) build
admin-clean:
@echo "Cleaning admin component..."
@cd $(ADMIN_DIR) && $(MAKE) clean
admin-dev:
@echo "Starting admin development server..."
@cd $(ADMIN_DIR) && $(MAKE) dev
admin-run:
@echo "Running admin server..."
@cd $(ADMIN_DIR) && $(MAKE) run
admin-test:
@echo "Testing admin component..."
@cd $(ADMIN_DIR) && $(MAKE) test
admin-fmt:
@echo "Formatting admin component..."
@cd $(ADMIN_DIR) && $(MAKE) fmt
admin-help:
@echo "Admin component help..."
@cd $(ADMIN_DIR) && $(MAKE) help
tests:
cd weed; go test -tags "elastic gocdk sqlite ydb tikv" -v ./...
+71 -150
View File
@@ -3,12 +3,12 @@
[![Slack](https://img.shields.io/badge/slack-purple)](https://join.slack.com/t/seaweedfs/shared_invite/enQtMzI4MTMwMjU2MzA3LTEyYzZmZWYzOGQ3MDJlZWMzYmI0OTE4OTJiZjJjODBmMzUxNmYwODg0YjY3MTNlMjBmZDQ1NzQ5NDJhZWI2ZmY)
[![Twitter](https://img.shields.io/twitter/follow/seaweedfs.svg?style=social&label=Follow)](https://twitter.com/intent/follow?screen_name=seaweedfs)
[![Build Status](https://img.shields.io/github/actions/workflow/status/seaweedfs/seaweedfs/go.yml)](https://github.com/seaweedfs/seaweedfs/actions/workflows/go.yml)
[![Build Status](https://img.shields.io/github/workflow/status/chrislusf/seaweedfs/Go)](https://github.com/seaweedfs/seaweedfs/actions/workflows/go.yml)
[![GoDoc](https://godoc.org/github.com/seaweedfs/seaweedfs/weed?status.svg)](https://godoc.org/github.com/seaweedfs/seaweedfs/weed)
[![Wiki](https://img.shields.io/badge/docs-wiki-blue.svg)](https://github.com/seaweedfs/seaweedfs/wiki)
[![Docker Pulls](https://img.shields.io/docker/pulls/chrislusf/seaweedfs?maxAge=4800)](https://hub.docker.com/r/chrislusf/seaweedfs/)
[![SeaweedFS on Maven Central](https://img.shields.io/maven-central/v/com.github.chrislusf/seaweedfs-client)](https://search.maven.org/search?q=g:com.github.chrislusf)
[![Artifact Hub](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/seaweedfs)](https://artifacthub.io/packages/search?repo=seaweedfs)
![SeaweedFS Logo](https://raw.githubusercontent.com/seaweedfs/seaweedfs/master/note/seaweedfs.png)
@@ -32,10 +32,8 @@ Your support will be really appreciated by me and other supporters!
-->
### Gold Sponsors
[![nodion](https://raw.githubusercontent.com/seaweedfs/seaweedfs/master/note/sponsor_nodion.png)](https://www.nodion.com)
[![nodion](https://www.nodion.com/img/logo.svg)](https://www.nodion.com)
[![piknik](https://raw.githubusercontent.com/seaweedfs/seaweedfs/master/note/piknik.png)](https://www.piknik.com)
[![keepsec](https://raw.githubusercontent.com/seaweedfs/seaweedfs/master/note/keepsec.png)](https://www.keepsec.ca)
[![zyner](https://raw.githubusercontent.com/seaweedfs/seaweedfs/master/note/sponsor_zyner.png)](https://zyner.org)
---
@@ -47,7 +45,6 @@ Your support will be really appreciated by me and other supporters!
- [SeaweedFS Mailing List](https://groups.google.com/d/forum/seaweedfs)
- [Wiki Documentation](https://github.com/seaweedfs/seaweedfs/wiki)
- [SeaweedFS White Paper](https://github.com/seaweedfs/seaweedfs/wiki/SeaweedFS_Architecture.pdf)
- [SeaweedFS Introduction Slides 2025.5](https://docs.google.com/presentation/d/1tdkp45J01oRV68dIm4yoTXKJDof-EhainlA0LMXexQE/edit?usp=sharing)
- [SeaweedFS Introduction Slides 2021.5](https://docs.google.com/presentation/d/1DcxKWlINc-HNCjhYeERkpGXXm6nTCES8mi2W5G0Z4Ts/edit?usp=sharing)
- [SeaweedFS Introduction Slides 2019.3](https://www.slideshare.net/chrislusf/seaweedfs-introduction)
@@ -55,66 +52,40 @@ 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)
* [Filer Features](#filer-features)
* [Example: Using Seaweed Blob Store](#example-using-seaweed-blob-store)
* [Example: Using Seaweed Object Store](#example-using-seaweed-object-store)
* [Architecture](#object-store-architecture)
* [Compared to Other File Systems](#compared-to-other-file-systems)
* [Compared to HDFS](#compared-to-hdfs)
* [Compared to GlusterFS, Ceph](#compared-to-glusterfs-ceph)
* [Compared to GlusterFS](#compared-to-glusterfs)
* [Compared to Ceph](#compared-to-ceph)
* [Compared to MinIO, RustFS](#compared-to-minio-rustfs)
* [Dev Plan](#dev-plan)
* [Installation Guide](#installation-guide)
* [Disk Related Topics](#disk-related-topics)
* [Benchmark](#benchmark)
* [Enterprise](#enterprise)
* [License](#license)
# Quick Start #
## Quick Start with weed mini ##
Download the latest binary from https://github.com/seaweedfs/seaweedfs/releases and unzip the single `weed` (or `weed.exe`) file, or run `go install github.com/seaweedfs/seaweedfs/weed@latest`. Then start a ready-to-use S3 object store with credentials and a pre-created bucket in one command:
```bash
AWS_ACCESS_KEY_ID=admin \
AWS_SECRET_ACCESS_KEY=secret \
S3_BUCKET=my-bucket \
./weed mini -dir=/data
```
That's it — the S3 endpoint is at http://localhost:8333, `my-bucket` already exists, and `admin`/`secret` are valid credentials. `S3_BUCKET` accepts a comma-separated list (e.g. `raw,processed`); use `S3_TABLE_BUCKET` for S3 Tables buckets, each `name` or `name:FORMAT` where the format is `ICEBERG` (the default) or `LANCE`. Drop any of the env vars to skip that piece (no AWS keys → S3 runs in unauthenticated "Allow All" mode for development).
The same command starts everything else too:
- **S3 Endpoint**: http://localhost:8333
- **Master UI**: http://localhost:9333
- **Volume Server**: http://localhost:9340
- **Filer UI**: http://localhost:8888
- **WebDAV**: http://localhost:7333
- **Admin UI**: http://localhost:23646
> macOS: if the binary is quarantined, run `xattr -d com.apple.quarantine ./weed` first.
Perfect for development, testing, learning SeaweedFS, and single-node deployments. To scale out, add more volume servers by running `weed volume -dir="/some/data/dir2" -master="<master_host>:9333" -port=8081` locally, on another machine, or on thousands of machines.
## Quick Start for S3 API on Docker ##
```bash
docker run -p 8333:8333 \
-e AWS_ACCESS_KEY_ID=admin \
-e AWS_SECRET_ACCESS_KEY=secret \
-e S3_BUCKET=my-bucket \
chrislusf/seaweedfs
```
`docker run -p 8333:8333 chrislusf/seaweedfs server -s3`
Same behavior as the `weed mini` command above — the S3 endpoint is at http://localhost:8333 with `my-bucket` pre-created. Drop the env vars to run anonymously for development.
## 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`
* 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" -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 #
@@ -123,7 +94,7 @@ 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.
@@ -135,33 +106,32 @@ 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.
What's more, the cloud storage access API cost is minimized.
Faster and cheaper than direct cloud storage!
SeaweedFS also ships a built-in **Iceberg REST Catalog**, turning the same cluster into a self-contained lakehouse.
Spark, Trino, Dremio, DuckDB, and RisingWave can query Iceberg tables directly — no Hive Metastore, Glue, or
external catalog service required. Storage and table metadata live in one system, simplifying on-prem and
small-team analytics stacks.
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 spaces 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.
@@ -169,12 +139,12 @@ small-team analytics stacks.
* 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)
## Filer Features ##
* [Filer server][Filer] provides "normal" directories and files via HTTP.
* [Filer server][Filer] provides "normal" directories and files via http.
* [File TTL][FilerTTL] automatically expires file metadata and actual file data.
* [Mount filer][Mount] reads and writes files directly as a local directory via FUSE.
* [Filer Store Replication][FilerStoreReplication] enables HA for filer meta data stores.
@@ -188,13 +158,6 @@ small-team analytics stacks.
* [Cloud Drive][CloudDrive] mounts cloud storage to local cluster, cached for fast read and write with asynchronous write back.
* [Gateway to Remote Object Store][GatewayToRemoteObjectStore] mirrors bucket operations to remote object storage, in addition to [Cloud Drive][CloudDrive]
## Data Lakehouse Features ##
* [S3 Table Buckets][S3TableBucket] expose a dedicated namespace for Iceberg tables with strict layout validation.
* Built-in [Iceberg REST Catalog][IcebergCatalog] runs alongside the S3 endpoint — no external metastore needed.
* Native integrations with [Apache Spark][SparkIceberg], [Trino][TrinoIceberg], [Dremio][DremioIceberg], [DuckDB][DuckDBIceberg], and [RisingWave][RisingWaveIceberg].
* [Automated table maintenance][IcebergMaintenance]: compaction, snapshot expiration, orphan removal, manifest rewriting.
* Granular IAM at the bucket, namespace, and table level via standard S3 bucket policies.
## Kubernetes ##
* [Kubernetes CSI Driver][SeaweedFsCsiDriver] A Container Storage Interface (CSI) Driver. [![Docker Pulls](https://img.shields.io/docker/pulls/chrislusf/seaweedfs-csi-driver.svg?maxAge=4800)](https://hub.docker.com/r/chrislusf/seaweedfs-csi-driver/)
* [SeaweedFS Operator](https://github.com/seaweedfs/seaweedfs-operator)
@@ -218,19 +181,11 @@ small-team analytics stacks.
[KeyLargeValueStore]: https://github.com/seaweedfs/seaweedfs/wiki/Filer-as-a-Key-Large-Value-Store
[CloudDrive]: https://github.com/seaweedfs/seaweedfs/wiki/Cloud-Drive-Architecture
[GatewayToRemoteObjectStore]: https://github.com/seaweedfs/seaweedfs/wiki/Gateway-to-Remote-Object-Storage
[S3TableBucket]: https://github.com/seaweedfs/seaweedfs/wiki/S3-Table-Bucket
[IcebergCatalog]: https://github.com/seaweedfs/seaweedfs/wiki/SeaweedFS-Iceberg-Catalog
[IcebergMaintenance]: https://github.com/seaweedfs/seaweedfs/wiki/Iceberg-Table-Maintenance
[SparkIceberg]: https://github.com/seaweedfs/seaweedfs/wiki/Spark-Iceberg-Integration
[TrinoIceberg]: https://github.com/seaweedfs/seaweedfs/wiki/Trino-Iceberg-Integration
[DremioIceberg]: https://github.com/seaweedfs/seaweedfs/wiki/Dremio-Iceberg-Integration
[DuckDBIceberg]: https://github.com/seaweedfs/seaweedfs/wiki/DuckDB-Iceberg-Integration
[RisingWaveIceberg]: https://github.com/seaweedfs/seaweedfs/wiki/RisingWave-Iceberg-Integration
[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.
@@ -246,29 +201,27 @@ 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:
@@ -276,7 +229,7 @@ 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.
@@ -288,9 +241,9 @@ 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.
@@ -331,7 +284,7 @@ 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
@@ -354,7 +307,7 @@ 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:
@@ -363,7 +316,7 @@ 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
@@ -382,15 +335,15 @@ 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.
@@ -404,13 +357,23 @@ 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 an 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 ###
@@ -424,12 +387,6 @@ 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 structure 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.
@@ -466,8 +423,7 @@ The architectures are mostly the same. SeaweedFS aims to store and read files fa
| GlusterFS | hashing | | FUSE, NFS | | |
| Ceph | hashing + rules | | FUSE | Yes | |
| MooseFS | in memory | | FUSE | | No |
| MinIO | separate meta file per drive for each file | | | Yes | No |
| RustFS | separate meta file per drive for each file | | | Yes | No |
| MinIO | separate meta file for each file | | | Yes | No |
[Back to TOC](#table-of-contents)
@@ -509,26 +465,22 @@ SeaweedFS Filer uses off-the-shelf stores, such as MySql, Postgres, Sqlite, Mong
[Back to TOC](#table-of-contents)
### Compared to MinIO, RustFS ###
### Compared to MinIO ###
Please note, as Apr 25, 2026 MinIO ceased development. It's strongly discouraged to use that unmaintained software with multiple security bugs. RustFS is a MinIO reimplementation in Rust, Apache 2.0 licensed and still developed, keeping MinIO's storage model down to a byte-compatible on-disk format. So the points below apply to both.
MinIO follows AWS S3 closely and is ideal for testing for S3 API. It has good UI, policies, versionings, etc. SeaweedFS is trying to catch up here. It is also possible to put MinIO as a gateway in front of SeaweedFS later.
MinIO followed AWS S3 closely and was ideal for testing for S3 API. It had good UI, policies, versionings, etc. SeaweedFS is trying to catch up here.
MinIO metadata are in simple files. Each file write will incur extra writes to corresponding meta file.
The metadata are in simple files. Each file write incurs extra writes to the corresponding meta file, on every drive of the erasure set. Changing only tags or retention rewrites that meta file on all of them, so the write amplification does not shrink with object size.
There is no optimization for lots of small files. The files are simply stored as is to local disks.
MinIO does not have optimization for lots of small files. The files are simply stored as is to local disks.
Plus the extra meta file and shards for erasure coding, it only amplifies the LOSF problem.
Multiple disk IO are needed to read one file. SeaweedFS has O(1) disk reads, even for erasure coded files.
MinIO has multiple disk IO to read one file. SeaweedFS has O(1) disk reads, even for erasure coded files.
Erasure coding is full-time. SeaweedFS uses replication on hot data for faster speed and optionally applies erasure coding on warm data.
MinIO has full-time erasure coding. SeaweedFS uses replication on hot data for faster speed and optionally applies erasure coding on warm data.
No POSIX-like API support.
MinIO does not have POSIX-like API support.
There are specific requirements on storage layout, which makes it hard to scale out and to maintain. An erasure set must be 2 to 16 drives and must divide the drive list symmetrically, and capacity grows or shrinks a whole pool at a time. In SeaweedFS, just start one volume server pointing to the master. That's all.
[Back to TOC](#table-of-contents)
MinIO has specific requirements on storage layout. It is not flexible to adjust capacity. In SeaweedFS, just start one volume server pointing to the master. That's all.
## Dev Plan ##
@@ -563,8 +515,6 @@ cd seaweedfs/weed && make install
Once this is done, you will find the executable "weed" in your `$GOPATH/bin` directory
For more installation options, including how to run with Docker, see the [Getting Started guide](https://github.com/seaweedfs/seaweedfs/wiki/Getting-Started).
[Back to TOC](#table-of-contents)
## Disk Related Topics ##
@@ -631,36 +581,6 @@ Percentage of the requests served within a certain time (ms)
100% 54.1 ms
```
### Run WARP and launch a mixed benchmark. ###
```
make benchmark
warp: Benchmark data written to "warp-mixed-2025-12-05[194844]-kBpU.csv.zst"
Mixed operations.
Operation: DELETE, 10%, Concurrency: 20, Ran 42s.
* Throughput: 55.13 obj/s
Operation: GET, 45%, Concurrency: 20, Ran 42s.
* Throughput: 2477.45 MiB/s, 247.75 obj/s
Operation: PUT, 15%, Concurrency: 20, Ran 42s.
* Throughput: 825.85 MiB/s, 82.59 obj/s
Operation: STAT, 30%, Concurrency: 20, Ran 42s.
* Throughput: 165.27 obj/s
Cluster Total: 3302.88 MiB/s, 550.51 obj/s over 43s.
```
[Back to TOC](#table-of-contents)
## Enterprise ##
For enterprise users, please visit [seaweedfs.com](https://seaweedfs.com) for the SeaweedFS Enterprise Edition,
which has advanced features, including data recovery, self-healing storage,
customizable erasure coding, EC vacuum and repair, etc.
[Back to TOC](#table-of-contents)
## License ##
@@ -682,4 +602,5 @@ 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)
File diff suppressed because it is too large Load Diff
-78
View File
@@ -1,78 +0,0 @@
# Security Policy
## Supported versions
Security fixes land in the latest release. Please reproduce against a recent
release or `master` before reporting; issues that only reproduce on old,
unsupported versions are not eligible for a fix or an advisory.
## Reporting a vulnerability
Report privately through GitHub private vulnerability reporting (the "Report a
vulnerability" button under the repository's Security tab). This keeps the
report, the fix, and any CVE in one place. Do not open a public issue.
### What a report must include
We can only act on reports that show real impact. Please include:
- Affected version (a release tag or `master` commit you reproduced on)
- The exact deployment and configuration: which components are running
(master, volume, filer, S3, admin), which ports are reachable by the
attacker, and what authentication is enabled
- The attacker's starting position: unauthenticated, a valid S3 user, an admin,
or someone with access to the internal cluster network
- The trust boundary that is crossed (e.g. an unauthenticated client reading
another tenant's data, an S3 user escalating to admin)
- A minimal, working reproduction or proof of concept
- Expected vs. actual behavior
A report without a working reproduction and a clear trust boundary is a
hardening suggestion, not a vulnerability. We are glad to receive those, but
they are handled on the normal issue tracker, not as security advisories.
### Automated and AI-assisted reports
Output from static analysis, dependency scanners, fuzzers, or LLMs is welcome
only when you have manually validated it and can supply a working reproduction
against a supported version, per the requirements above. Raw tool output,
speculative findings, or generated reports without a demonstrated exploit will
be closed as hardening suggestions.
## Trust model
SeaweedFS is built to run with its cluster components (master, volume servers,
and the raw filer API) on a trusted network. Those internal APIs are not an
authentication boundary unless you explicitly enable a control (for example
volume JWT or filer authentication) and that control is bypassed. Exposing an
internal port directly to untrusted clients is a deployment mistake, not a
vulnerability in SeaweedFS.
Reports are in scope when they cross a boundary SeaweedFS is meant to enforce,
for example:
- Unauthenticated access to data or operations that require authentication
- One S3 identity reading, writing, or deleting another identity's data
- Privilege escalation from a normal S3 user to administrative capability
- Bypass of Object Lock / retention where it is configured
- Remotely triggered data corruption or loss
Reports are generally out of scope when they require:
- Direct access to an internal cluster port that is meant to be private
- Full master, filer, or volume server access (already a full compromise)
- An insecure example configuration rather than a documented secure setup
- Local-only impact on a host the attacker already controls
## CVE assignment
When a report is confirmed, we publish an advisory and request the CVE through
GitHub. CVEs assigned by third parties without coordinating with us, or for
issues that do not cross a boundary described above, may be disputed.
## Response and disclosure
- We aim to acknowledge a valid report within a few business days.
- We will investigate, work on a fix, and coordinate a disclosure timeline
with you.
- Please allow time for a fix before any public disclosure.
-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.
-2
View File
@@ -7,8 +7,6 @@
- [Evercam Camera Management Software](https://evercam.io/)
- [Spherical Elephant GmbH](https://www.sphericalelephant.com)
- [WizardTales GmbH](https://www.wizardtales.com)
- [Nimbus Web Services](https://nimbusws.com)
- <h2 align="center">Backers</h2>
-419
View File
@@ -1,419 +0,0 @@
package main
import (
"context"
"crypto/tls"
"encoding/json"
"fmt"
"io"
"os"
"os/signal"
"strings"
"syscall"
"time"
"github.com/seaweedfs/seaweedfs/weed/server/postgres"
"github.com/seaweedfs/seaweedfs/weed/util"
flag "github.com/seaweedfs/seaweedfs/weed/util/fla9"
)
const usageLine = "weed-db -port=5432 -master=<master_server>"
const longHelp = `Start a PostgreSQL wire protocol compatible database server that provides SQL query access to SeaweedFS.
This database server enables any PostgreSQL client, tool, or application to connect to SeaweedFS
and execute SQL queries against MQ topics. It implements the PostgreSQL wire protocol for maximum
compatibility with the existing PostgreSQL ecosystem.
Examples:
# Start database server on default port 5432
weed-db
# Start with MD5 authentication using JSON format (recommended)
weed-db -auth=md5 -users='{"admin":"secret","readonly":"view123"}'
# Start with complex passwords using JSON format
weed-db -auth=md5 -users='{"admin":"pass;with;semicolons","user":"password:with:colons"}'
# Start with credentials from JSON file (most secure)
weed-db -auth=md5 -users="@/etc/seaweedfs/users.json"
# Start with custom port and master
weed-db -port=5433 -master=master1:9333
# Allow connections from any host
weed-db -host=0.0.0.0 -port=5432
# Start with TLS encryption
weed-db -tls-cert=server.crt -tls-key=server.key
Client Connection Examples:
# psql command line client
psql "host=localhost port=5432 dbname=default user=seaweedfs"
psql -h localhost -p 5432 -U seaweedfs -d default
# With password
PGPASSWORD=secret psql -h localhost -p 5432 -U admin -d default
# Connection string
psql "postgresql://admin:secret@localhost:5432/default"
Programming Language Examples:
# Python (psycopg2)
import psycopg2
conn = psycopg2.connect(
host="localhost", port=5432,
user="seaweedfs", database="default"
)
# Java JDBC
String url = "jdbc:postgresql://localhost:5432/default";
Connection conn = DriverManager.getConnection(url, "seaweedfs", "");
# Go (lib/pq)
db, err := sql.Open("postgres", "host=localhost port=5432 user=seaweedfs dbname=default sslmode=disable")
# Node.js (pg)
const client = new Client({
host: 'localhost', port: 5432,
user: 'seaweedfs', database: 'default'
});
Supported SQL Operations:
- SELECT queries on MQ topics
- DESCRIBE/DESC table_name commands
- EXPLAIN query execution plans
- SHOW DATABASES/TABLES commands
- Aggregation functions (COUNT, SUM, AVG, MIN, MAX)
- WHERE clauses with filtering
- System columns (_timestamp_ns, _key, _source)
- Basic PostgreSQL system queries (version(), current_database(), current_user)
Authentication Methods:
- trust: No authentication required (default)
- password: Clear text password authentication
- md5: MD5 password authentication
User Credential Formats:
- JSON format: '{"user1":"pass1","user2":"pass2"}' (supports any special characters)
- File format: "@/path/to/users.json" (JSON file)
Note: JSON format supports passwords with semicolons, colons, and any other special characters.
File format is recommended for production to keep credentials secure.
Compatible Tools:
- psql (PostgreSQL command line client)
- Any PostgreSQL JDBC/ODBC compatible tool
Security Features:
- Multiple authentication methods
- TLS encryption support
- Read-only access (no data modification)
Performance Features:
- Fast path aggregation optimization (COUNT, MIN, MAX without WHERE clauses)
- Hybrid data scanning (parquet files + live logs)
- PostgreSQL wire protocol
- Query result streaming
`
type Options struct {
Host string
Port int
MasterAddr string
AuthMethod string
Users string
Database string
MaxConns int
IdleTimeout string
TLSCert string
TLSKey string
}
// Run executes the weed-db CLI.
func Run(args []string) int {
fs := flag.NewFlagSet("weed-db", flag.ContinueOnError)
usageWriter := io.Writer(os.Stderr)
fs.SetOutput(usageWriter)
var opts Options
fs.StringVar(&opts.Host, "host", "localhost", "Database server host")
fs.IntVar(&opts.Port, "port", 5432, "Database server port")
fs.StringVar(&opts.MasterAddr, "master", "localhost:9333", "SeaweedFS master server address")
fs.StringVar(&opts.AuthMethod, "auth", "trust", "Authentication method: trust, password, md5")
fs.StringVar(&opts.Users, "users", "", "User credentials for auth (JSON format '{\"user1\":\"pass1\",\"user2\":\"pass2\"}' or file '@/path/to/users.json')")
fs.StringVar(&opts.Database, "database", "default", "Default database name")
fs.IntVar(&opts.MaxConns, "max-connections", 100, "Maximum concurrent connections per server")
fs.StringVar(&opts.IdleTimeout, "idle-timeout", "1h", "Connection idle timeout")
fs.StringVar(&opts.TLSCert, "tls-cert", "", "TLS certificate file path")
fs.StringVar(&opts.TLSKey, "tls-key", "", "TLS private key file path")
fs.Usage = func() {
fmt.Fprintf(usageWriter, "Usage: %s\n\n%s\n", usageLine, longHelp)
fmt.Fprintln(usageWriter, "Default Parameters:")
fs.PrintDefaults()
}
if err := fs.Parse(args); err != nil {
return 2
}
if !runWithOptions(&opts) {
return 1
}
return 0
}
func runWithOptions(opts *Options) bool {
util.LoadConfiguration("security", false)
// Validate options.
if opts.MasterAddr == "" {
fmt.Fprintf(os.Stderr, "Error: master address is required\n")
return false
}
// Parse authentication method.
authMethod, err := parseAuthMethod(opts.AuthMethod)
if err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
return false
}
// Parse user credentials.
users, err := parseUsers(opts.Users, authMethod)
if err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
return false
}
// Parse idle timeout.
idleTimeout, err := time.ParseDuration(opts.IdleTimeout)
if err != nil {
fmt.Fprintf(os.Stderr, "Error parsing idle timeout: %v\n", err)
return false
}
// Validate port number.
if err := validatePortNumber(opts.Port); err != nil {
fmt.Fprintf(os.Stderr, "Error: %v\n", err)
return false
}
// Setup TLS if requested.
var tlsConfig *tls.Config
if opts.TLSCert != "" && opts.TLSKey != "" {
cert, err := tls.LoadX509KeyPair(opts.TLSCert, opts.TLSKey)
if err != nil {
fmt.Fprintf(os.Stderr, "Error loading TLS certificates: %v\n", err)
return false
}
tlsConfig = &tls.Config{
Certificates: []tls.Certificate{cert},
}
}
// Create server configuration.
config := &postgres.PostgreSQLServerConfig{
Host: opts.Host,
Port: opts.Port,
AuthMethod: authMethod,
Users: users,
Database: opts.Database,
MaxConns: opts.MaxConns,
IdleTimeout: idleTimeout,
TLSConfig: tlsConfig,
}
// Create database server.
dbServer, err := postgres.NewPostgreSQLServer(config, opts.MasterAddr)
if err != nil {
fmt.Fprintf(os.Stderr, "Error creating database server: %v\n", err)
return false
}
// Print startup information.
fmt.Printf("Starting SeaweedFS Database Server...\n")
fmt.Printf("Host: %s\n", opts.Host)
fmt.Printf("Port: %d\n", opts.Port)
fmt.Printf("Master: %s\n", opts.MasterAddr)
fmt.Printf("Database: %s\n", opts.Database)
fmt.Printf("Auth Method: %s\n", opts.AuthMethod)
fmt.Printf("Max Connections: %d\n", opts.MaxConns)
fmt.Printf("Idle Timeout: %s\n", opts.IdleTimeout)
if tlsConfig != nil {
fmt.Printf("TLS: Enabled\n")
} else {
fmt.Printf("TLS: Disabled\n")
}
if len(users) > 0 {
fmt.Printf("Users: %d configured\n", len(users))
}
fmt.Printf("\nDatabase Connection Examples:\n")
fmt.Printf(" psql -h %s -p %d -U seaweedfs -d %s\n", opts.Host, opts.Port, opts.Database)
if len(users) > 0 {
// Show first user as example.
for username := range users {
fmt.Printf(" psql -h %s -p %d -U %s -d %s\n", opts.Host, opts.Port, username, opts.Database)
break
}
}
fmt.Printf(" postgresql://%s:%d/%s\n", opts.Host, opts.Port, opts.Database)
fmt.Printf("\nSupported Operations:\n")
fmt.Printf(" - SELECT queries on MQ topics\n")
fmt.Printf(" - DESCRIBE/DESC table_name\n")
fmt.Printf(" - EXPLAIN query execution plans\n")
fmt.Printf(" - SHOW DATABASES/TABLES\n")
fmt.Printf(" - Aggregations: COUNT, SUM, AVG, MIN, MAX\n")
fmt.Printf(" - System columns: _timestamp_ns, _key, _source\n")
fmt.Printf(" - Basic PostgreSQL system queries\n")
fmt.Printf("\nReady for database connections!\n\n")
// Start the server.
err = dbServer.Start()
if err != nil {
fmt.Fprintf(os.Stderr, "Error starting database server: %v\n", err)
return false
}
// Set up signal handling for graceful shutdown.
sigChan := make(chan os.Signal, 1)
signal.Notify(sigChan, syscall.SIGINT, syscall.SIGTERM)
// Wait for shutdown signal.
<-sigChan
fmt.Printf("\nReceived shutdown signal, stopping database server...\n")
// Create context with timeout for graceful shutdown.
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
// Stop the server with timeout.
done := make(chan error, 1)
go func() {
done <- dbServer.Stop()
}()
select {
case err := <-done:
if err != nil {
fmt.Fprintf(os.Stderr, "Error stopping database server: %v\n", err)
return false
}
fmt.Printf("Database server stopped successfully\n")
case <-ctx.Done():
fmt.Fprintf(os.Stderr, "Timeout waiting for database server to stop\n")
return false
}
return true
}
// parseAuthMethod parses the authentication method string.
func parseAuthMethod(method string) (postgres.AuthMethod, error) {
switch strings.ToLower(method) {
case "trust":
return postgres.AuthTrust, nil
case "password":
return postgres.AuthPassword, nil
case "md5":
return postgres.AuthMD5, nil
default:
return postgres.AuthTrust, fmt.Errorf("unsupported auth method '%s'. Supported: trust, password, md5", method)
}
}
// parseUsers parses the user credentials string with support for secure formats only.
// Supported formats:
// 1. JSON format: {"username":"password","username2":"password2"}
// 2. File format: /path/to/users.json or @/path/to/users.json
func parseUsers(usersStr string, authMethod postgres.AuthMethod) (map[string]string, error) {
users := make(map[string]string)
if usersStr == "" {
// No users specified.
if authMethod != postgres.AuthTrust {
return nil, fmt.Errorf("users must be specified when auth method is not 'trust'")
}
return users, nil
}
// Trim whitespace.
usersStr = strings.TrimSpace(usersStr)
// Determine format and parse accordingly.
if strings.HasPrefix(usersStr, "{") && strings.HasSuffix(usersStr, "}") {
// JSON format.
return parseUsersJSON(usersStr, authMethod)
}
// Check if it's a file path (with or without @ prefix) before declaring invalid format.
filePath := strings.TrimPrefix(usersStr, "@")
if _, err := os.Stat(filePath); err == nil {
// File format.
return parseUsersFile(usersStr, authMethod) // Pass original string to preserve @ handling.
}
// Invalid format.
return nil, fmt.Errorf("invalid user credentials format. Use JSON format '{\"user\":\"pass\"}' or file format '@/path/to/users.json' or 'path/to/users.json'. Legacy semicolon-separated format is no longer supported")
}
// parseUsersJSON parses user credentials from JSON format.
func parseUsersJSON(jsonStr string, authMethod postgres.AuthMethod) (map[string]string, error) {
var users map[string]string
if err := json.Unmarshal([]byte(jsonStr), &users); err != nil {
return nil, fmt.Errorf("invalid JSON format for users: %v", err)
}
// Validate users.
for username, password := range users {
if username == "" {
return nil, fmt.Errorf("empty username in JSON user specification")
}
if authMethod != postgres.AuthTrust && password == "" {
return nil, fmt.Errorf("empty password for user '%s' with auth method", username)
}
}
return users, nil
}
// parseUsersFile parses user credentials from a JSON file.
func parseUsersFile(filePath string, authMethod postgres.AuthMethod) (map[string]string, error) {
// Remove @ prefix if present.
filePath = strings.TrimPrefix(filePath, "@")
// Read file content.
content, err := os.ReadFile(filePath)
if err != nil {
return nil, fmt.Errorf("failed to read users file '%s': %v", filePath, err)
}
contentStr := strings.TrimSpace(string(content))
// File must contain JSON format.
if !strings.HasPrefix(contentStr, "{") || !strings.HasSuffix(contentStr, "}") {
return nil, fmt.Errorf("users file '%s' must contain JSON format: {\"user\":\"pass\"}. Legacy formats are no longer supported", filePath)
}
// Parse as JSON.
return parseUsersJSON(contentStr, authMethod)
}
// validatePortNumber validates that the port number is reasonable.
func validatePortNumber(port int) error {
if port < 1 || port > 65535 {
return fmt.Errorf("port number must be between 1 and 65535, got %d", port)
}
if port < 1024 {
fmt.Fprintf(os.Stderr, "Warning: port number %d may require root privileges\n", port)
}
return nil
}
-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:]))
}
-623
View File
@@ -1,623 +0,0 @@
package main
import (
"context"
"encoding/csv"
"encoding/json"
"fmt"
"io"
"os"
"path"
"strings"
"time"
"github.com/peterh/liner"
"github.com/seaweedfs/seaweedfs/weed/query/engine"
flag "github.com/seaweedfs/seaweedfs/weed/util/fla9"
"github.com/seaweedfs/seaweedfs/weed/util/grace"
"github.com/seaweedfs/seaweedfs/weed/util/sqlutil"
)
const usageLine = "weed-sql [-master=localhost:9333] [-interactive] [-file=query.sql] [-output=table|json|csv] [-database=dbname] [-query=\"SQL\"]"
const longHelp = `Enhanced SQL interface for SeaweedFS Message Queue topics with multiple execution modes.
Execution Modes:
- Interactive shell (default): weed-sql -interactive
- Single query: weed-sql -query "SELECT * FROM user_events"
- Batch from file: weed-sql -file queries.sql
- Context switching: weed-sql -database analytics -interactive
Output Formats:
- table: ASCII table format (default for interactive)
- json: JSON format (default for non-interactive)
- csv: Comma-separated values
Features:
- Full WHERE clause support (=, <, >, <=, >=, !=, LIKE, IN)
- Advanced pattern matching with LIKE wildcards (%, _)
- Multi-value filtering with IN operator
- Real MQ namespace and topic discovery
- Database context switching
Examples:
weed-sql -interactive
weed-sql -query "SHOW DATABASES" -output json
weed-sql -file batch_queries.sql -output csv
weed-sql -database analytics -query "SELECT COUNT(*) FROM metrics"
weed-sql -master broker1:9333 -interactive
`
type Options struct {
Master string
Interactive bool
File string
Output string
Database string
Query string
}
// OutputFormat represents different output formatting options.
type OutputFormat string
const (
OutputTable OutputFormat = "table"
OutputJSON OutputFormat = "json"
OutputCSV OutputFormat = "csv"
)
// SQLContext holds the execution context for SQL operations.
type SQLContext struct {
engine *engine.SQLEngine
currentDatabase string
outputFormat OutputFormat
interactive bool
master string
}
// Run executes the weed-sql CLI.
func Run(args []string) int {
fs := flag.NewFlagSet("weed-sql", flag.ContinueOnError)
usageWriter := io.Writer(os.Stderr)
fs.SetOutput(usageWriter)
var opts Options
fs.StringVar(&opts.Master, "master", "localhost:9333", "SeaweedFS master server HTTP address")
fs.BoolVar(&opts.Interactive, "interactive", false, "start interactive shell mode")
fs.StringVar(&opts.File, "file", "", "execute SQL queries from file")
fs.StringVar(&opts.Output, "output", "", "output format: table, json, csv (auto-detected if not specified)")
fs.StringVar(&opts.Database, "database", "", "default database context")
fs.StringVar(&opts.Query, "query", "", "execute single SQL query")
fs.Usage = func() {
fmt.Fprintf(usageWriter, "Usage: %s\n\n%s\n", usageLine, longHelp)
fmt.Fprintln(usageWriter, "Default Parameters:")
fs.PrintDefaults()
}
if err := fs.Parse(args); err != nil {
return 2
}
if !runWithOptions(&opts) {
return 1
}
return 0
}
func runWithOptions(opts *Options) bool {
// Initialize SQL engine with master address for service discovery.
sqlEngine := engine.NewSQLEngine(opts.Master)
// Determine execution mode and output format.
interactive := opts.Interactive || (opts.Query == "" && opts.File == "")
outputFormat := determineOutputFormat(opts.Output, interactive)
// Create SQL context.
ctx := &SQLContext{
engine: sqlEngine,
currentDatabase: opts.Database,
outputFormat: outputFormat,
interactive: interactive,
master: opts.Master,
}
// Set current database in SQL engine if specified via command line.
if opts.Database != "" {
ctx.engine.GetCatalog().SetCurrentDatabase(opts.Database)
}
// Execute based on mode.
switch {
case opts.Query != "":
// Single query mode.
return executeSingleQuery(ctx, opts.Query)
case opts.File != "":
// Batch file mode.
return executeFileQueries(ctx, opts.File)
default:
// Interactive mode.
return runInteractiveShell(ctx)
}
}
// determineOutputFormat selects the appropriate output format.
func determineOutputFormat(specified string, interactive bool) OutputFormat {
switch strings.ToLower(specified) {
case "table":
return OutputTable
case "json":
return OutputJSON
case "csv":
return OutputCSV
default:
// Auto-detect based on mode.
if interactive {
return OutputTable
}
return OutputJSON
}
}
// executeSingleQuery executes a single query and outputs the result.
func executeSingleQuery(ctx *SQLContext, query string) bool {
if ctx.outputFormat != OutputTable {
// Suppress banner for non-interactive output.
return executeAndDisplay(ctx, query, false)
}
fmt.Printf("Executing query against %s...\n", ctx.master)
return executeAndDisplay(ctx, query, true)
}
// executeFileQueries processes SQL queries from a file.
func executeFileQueries(ctx *SQLContext, filename string) bool {
content, err := os.ReadFile(filename)
if err != nil {
fmt.Printf("Error reading file %s: %v\n", filename, err)
return false
}
if ctx.outputFormat == OutputTable && ctx.interactive {
fmt.Printf("Executing queries from %s against %s...\n", filename, ctx.master)
}
// Split file content into individual queries (robust approach).
queries := sqlutil.SplitStatements(string(content))
for i, query := range queries {
query = strings.TrimSpace(query)
if query == "" {
continue
}
if ctx.outputFormat == OutputTable && len(queries) > 1 {
fmt.Printf("\n--- Query %d ---\n", i+1)
}
if !executeAndDisplay(ctx, query, ctx.outputFormat == OutputTable) {
return false
}
}
return true
}
// runInteractiveShell starts the enhanced interactive shell with readline support.
func runInteractiveShell(ctx *SQLContext) bool {
fmt.Println("SeaweedFS Enhanced SQL Interface")
fmt.Println("Type 'help;' for help, 'exit;' to quit")
fmt.Printf("Connected to master: %s\n", ctx.master)
if ctx.currentDatabase != "" {
fmt.Printf("Current database: %s\n", ctx.currentDatabase)
}
fmt.Println("Advanced WHERE operators supported: <=, >=, !=, LIKE, IN")
fmt.Println("Use up/down arrows for command history")
fmt.Println()
// Initialize liner for readline functionality.
line := liner.NewLiner()
defer line.Close()
// Handle Ctrl+C gracefully.
line.SetCtrlCAborts(true)
grace.OnInterrupt(func() {
line.Close()
})
// Load command history.
historyPath := path.Join(os.TempDir(), "weed-sql-history")
if f, err := os.Open(historyPath); err == nil {
line.ReadHistory(f)
f.Close()
}
// Save history on exit.
defer func() {
if f, err := os.Create(historyPath); err == nil {
line.WriteHistory(f)
f.Close()
}
}()
var queryBuffer strings.Builder
for {
// Show prompt with current database context.
var prompt string
if queryBuffer.Len() == 0 {
if ctx.currentDatabase != "" {
prompt = fmt.Sprintf("seaweedfs:%s> ", ctx.currentDatabase)
} else {
prompt = "seaweedfs> "
}
} else {
prompt = " -> " // Continuation prompt.
}
// Read line with readline support.
input, err := line.Prompt(prompt)
if err != nil {
if err == liner.ErrPromptAborted {
fmt.Println("Query cancelled")
queryBuffer.Reset()
continue
}
if err != io.EOF {
fmt.Printf("Input error: %v\n", err)
}
break
}
lineStr := strings.TrimSpace(input)
// Handle empty lines.
if lineStr == "" {
continue
}
// Accumulate lines in query buffer.
if queryBuffer.Len() > 0 {
queryBuffer.WriteString(" ")
}
queryBuffer.WriteString(lineStr)
// Check if we have a complete statement (ends with semicolon or special command).
fullQuery := strings.TrimSpace(queryBuffer.String())
isComplete := strings.HasSuffix(lineStr, ";") ||
isSpecialCommand(fullQuery)
if !isComplete {
continue // Continue reading more lines.
}
// Add completed command to history.
line.AppendHistory(fullQuery)
// Handle special commands (with or without semicolon).
cleanQuery := strings.TrimSuffix(fullQuery, ";")
cleanQuery = strings.TrimSpace(cleanQuery)
if cleanQuery == "exit" || cleanQuery == "quit" || cleanQuery == "\\q" {
fmt.Println("Goodbye!")
break
}
if cleanQuery == "help" {
showEnhancedHelp()
queryBuffer.Reset()
continue
}
// Handle database switching - use proper SQL parser instead of manual parsing.
if strings.HasPrefix(strings.ToUpper(cleanQuery), "USE ") {
// Execute USE statement through the SQL engine for proper parsing.
result, err := ctx.engine.ExecuteSQL(context.Background(), cleanQuery)
if err != nil {
fmt.Printf("Error: %v\n\n", err)
} else if result.Error != nil {
fmt.Printf("Error: %v\n\n", result.Error)
} else {
// Extract the database name from the result message for CLI context.
if len(result.Rows) > 0 && len(result.Rows[0]) > 0 {
message := result.Rows[0][0].ToString()
// Extract database name from "Database changed to: dbname".
if strings.HasPrefix(message, "Database changed to: ") {
ctx.currentDatabase = strings.TrimPrefix(message, "Database changed to: ")
}
fmt.Printf("%s\n\n", message)
}
}
queryBuffer.Reset()
continue
}
// Handle output format switching.
if strings.HasPrefix(strings.ToUpper(cleanQuery), "\\FORMAT ") {
format := strings.TrimSpace(strings.TrimPrefix(strings.ToUpper(cleanQuery), "\\FORMAT "))
switch format {
case "TABLE":
ctx.outputFormat = OutputTable
fmt.Println("Output format set to: table")
case "JSON":
ctx.outputFormat = OutputJSON
fmt.Println("Output format set to: json")
case "CSV":
ctx.outputFormat = OutputCSV
fmt.Println("Output format set to: csv")
default:
fmt.Printf("Invalid format: %s. Supported: table, json, csv\n", format)
}
queryBuffer.Reset()
continue
}
// Execute SQL query (without semicolon).
executeAndDisplay(ctx, cleanQuery, true)
// Reset buffer for next query.
queryBuffer.Reset()
}
return true
}
// isSpecialCommand checks if a command is a special command that doesn't require semicolon.
func isSpecialCommand(query string) bool {
cleanQuery := strings.TrimSuffix(strings.TrimSpace(query), ";")
cleanQuery = strings.ToLower(cleanQuery)
// Special commands that work with or without semicolon.
specialCommands := []string{
"exit", "quit", "\\q", "help",
}
for _, cmd := range specialCommands {
if cleanQuery == cmd {
return true
}
}
// Commands that are exactly specific commands (not just prefixes).
parts := strings.Fields(strings.ToUpper(cleanQuery))
if len(parts) == 0 {
return false
}
return (parts[0] == "USE" && len(parts) >= 2) ||
strings.HasPrefix(strings.ToUpper(cleanQuery), "\\FORMAT ")
}
// executeAndDisplay executes a query and displays the result in the specified format.
func executeAndDisplay(ctx *SQLContext, query string, showTiming bool) bool {
startTime := time.Now()
// Execute the query.
execCtx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
result, err := ctx.engine.ExecuteSQL(execCtx, query)
if err != nil {
if ctx.outputFormat == OutputJSON {
errorResult := map[string]interface{}{
"error": err.Error(),
"query": query,
}
jsonBytes, _ := json.MarshalIndent(errorResult, "", " ")
fmt.Println(string(jsonBytes))
} else {
fmt.Printf("Error: %v\n", err)
}
return false
}
if result.Error != nil {
if ctx.outputFormat == OutputJSON {
errorResult := map[string]interface{}{
"error": result.Error.Error(),
"query": query,
}
jsonBytes, _ := json.MarshalIndent(errorResult, "", " ")
fmt.Println(string(jsonBytes))
} else {
fmt.Printf("Query Error: %v\n", result.Error)
}
return false
}
// Display results in the specified format.
switch ctx.outputFormat {
case OutputTable:
displayTableResult(result)
case OutputJSON:
displayJSONResult(result)
case OutputCSV:
displayCSVResult(result)
}
// Show execution time for interactive/table mode.
// Only show timing if there are columns or if result is truly empty.
if showTiming && ctx.outputFormat == OutputTable && (len(result.Columns) > 0 || len(result.Rows) == 0) {
elapsed := time.Since(startTime)
fmt.Printf("\n(%d rows in set, %.3f sec)\n\n", len(result.Rows), elapsed.Seconds())
}
return true
}
// displayTableResult formats and displays query results in ASCII table format.
func displayTableResult(result *engine.QueryResult) {
if len(result.Columns) == 0 {
fmt.Println("Empty result set")
return
}
// Calculate column widths for formatting.
colWidths := make([]int, len(result.Columns))
for i, col := range result.Columns {
colWidths[i] = len(col)
}
// Check data for wider columns.
for _, row := range result.Rows {
for i, val := range row {
if i < len(colWidths) {
valStr := val.ToString()
if len(valStr) > colWidths[i] {
colWidths[i] = len(valStr)
}
}
}
}
// Print header separator.
fmt.Print("+")
for _, width := range colWidths {
fmt.Print(strings.Repeat("-", width+2) + "+")
}
fmt.Println()
// Print column headers.
fmt.Print("|")
for i, col := range result.Columns {
fmt.Printf(" %-*s |", colWidths[i], col)
}
fmt.Println()
// Print separator.
fmt.Print("+")
for _, width := range colWidths {
fmt.Print(strings.Repeat("-", width+2) + "+")
}
fmt.Println()
// Print data rows.
for _, row := range result.Rows {
fmt.Print("|")
for i, val := range row {
if i < len(colWidths) {
fmt.Printf(" %-*s |", colWidths[i], val.ToString())
}
}
fmt.Println()
}
// Print bottom separator.
fmt.Print("+")
for _, width := range colWidths {
fmt.Print(strings.Repeat("-", width+2) + "+")
}
fmt.Println()
}
// displayJSONResult outputs query results in JSON format.
func displayJSONResult(result *engine.QueryResult) {
// Convert result to JSON-friendly format.
jsonResult := map[string]interface{}{
"columns": result.Columns,
"rows": make([]map[string]interface{}, len(result.Rows)),
"count": len(result.Rows),
}
// Convert rows to JSON objects.
for i, row := range result.Rows {
rowObj := make(map[string]interface{})
for j, val := range row {
if j < len(result.Columns) {
rowObj[result.Columns[j]] = val.ToString()
}
}
jsonResult["rows"].([]map[string]interface{})[i] = rowObj
}
// Marshal and print JSON.
jsonBytes, err := json.MarshalIndent(jsonResult, "", " ")
if err != nil {
fmt.Printf("Error formatting JSON: %v\n", err)
return
}
fmt.Println(string(jsonBytes))
}
// displayCSVResult outputs query results in CSV format.
func displayCSVResult(result *engine.QueryResult) {
// Handle execution plan results specially to avoid CSV quoting issues.
if len(result.Columns) == 1 && result.Columns[0] == "Query Execution Plan" {
// For execution plans, output directly without CSV encoding to avoid quotes.
for _, row := range result.Rows {
if len(row) > 0 {
fmt.Println(row[0].ToString())
}
}
return
}
// Standard CSV output for regular query results.
writer := csv.NewWriter(os.Stdout)
defer writer.Flush()
// Write headers.
if err := writer.Write(result.Columns); err != nil {
fmt.Printf("Error writing CSV headers: %v\n", err)
return
}
// Write data rows.
for _, row := range result.Rows {
csvRow := make([]string, len(row))
for i, val := range row {
csvRow[i] = val.ToString()
}
if err := writer.Write(csvRow); err != nil {
fmt.Printf("Error writing CSV row: %v\n", err)
return
}
}
}
func showEnhancedHelp() {
fmt.Println(`SeaweedFS Enhanced SQL Interface Help:
METADATA OPERATIONS:
SHOW DATABASES; - List all MQ namespaces
SHOW TABLES; - List all topics in current namespace
SHOW TABLES FROM database; - List topics in specific namespace
DESCRIBE table_name; - Show table schema
ADVANCED QUERYING:
SELECT * FROM table_name; - Query all data
SELECT col1, col2 FROM table WHERE ...; - Column projection
SELECT * FROM table WHERE id <= 100; - Range filtering
SELECT * FROM table WHERE name LIKE 'admin%'; - Pattern matching
SELECT * FROM table WHERE status IN ('active', 'pending'); - Multi-value
SELECT COUNT(*), MAX(id), MIN(id) FROM ...; - Aggregation functions
QUERY ANALYSIS:
EXPLAIN SELECT ...; - Show hierarchical execution plan
(data sources, optimizations, timing)
DDL OPERATIONS:
CREATE TABLE topic (field1 INT, field2 STRING); - Create topic
Note: ALTER TABLE and DROP TABLE are not supported
SPECIAL COMMANDS:
USE database_name; - Switch database context
\format table|json|csv - Change output format
help; - Show this help
exit; or quit; or \q - Exit interface
EXTENDED WHERE OPERATORS:
=, <, >, <=, >= - Comparison operators
!=, <> - Not equal operators
LIKE 'pattern%' - Pattern matching (% = any chars, _ = single char)
IN (value1, value2, ...) - Multi-value matching
AND, OR - Logical operators
EXAMPLES:
SELECT * FROM user_events WHERE user_id >= 10 AND status != 'deleted';
SELECT username FROM users WHERE email LIKE '%@company.com';
SELECT * FROM logs WHERE level IN ('error', 'warning') AND timestamp >= '2023-01-01';
EXPLAIN SELECT MAX(id) FROM events; -- View execution plan
Current Status: Full WHERE clause support + Real MQ integration`)
}
-167
View File
@@ -1,167 +0,0 @@
# Design: Serializing Bucket Configuration Mutations
Issue #9651 — concurrent `PutBucketVersioning` + `PutBucketEncryption` (as Terraform
issues them in parallel) intermittently lose the encryption write.
## Root cause
The bucket's entire config lives in one filer entry, `/buckets/<name>`. Every
config API does a read-modify-write of that single entry, and the writes are not
serialized:
- `updateBucketConfig(bucket, fn)` (`s3api_bucket_config.go:468`) — sources from a
possibly-stale cached `BucketConfig`, mutates `Entry.Extended`, writes the
**whole** entry. Used by: versioning, object-lock config, lifecycle, ACL/owner.
- `UpdateBucketMetadata` → `setBucketMetadata` (`:1042`) — reads a fresh entry,
mutates `Entry.Content`, writes the **whole** entry. Used by: encryption, CORS,
tagging, ownership, policy, notification.
Two ingredients produce the lost update:
1. **No serialization** of the read→modify→write (the cache mutexes only guard the
in-memory map, not the RMW).
2. **Whole-entry rewrite from an independent snapshot** — `updateBucketConfig`
rebuilds from a stale cached `BucketConfig` whose `Content` predates the
concurrent encryption write, so writing the whole entry reverts `Content`.
Sequential calls always pass (each sees the previous write), so it only surfaces
under concurrency — and CI's slower IO widens the window (the "2 of ~12 runs").
## Goals
- No lost updates across concurrent bucket-config changes — for **all** config
fields, not just versioning/encryption.
- Correct for a single S3 gateway (the reported case) and for multiple gateways.
- Reuse the filer primitives just merged (per-path lock, `WriteCondition`,
`ObjectTransaction`); do not reintroduce a distributed lock.
- Minimal blast radius: the fix lands at the two chokepoint helpers.
## Non-goals
- Changing the one-entry-per-bucket storage model.
- Multi-filer-concurrent bucket writes (addressed only as an optional phase 3).
## The two ingredients map to two complementary fixes
### Fix A — serialize + read fresh (closes the window for whole-entry writers)
Both `updateBucketConfig` and `UpdateBucketMetadata` must run their RMW under one
per-bucket critical section, and **re-read the entry fresh from the filer inside
it** — not rebuild from the cached `BucketConfig`. The lock alone is insufficient:
without the fresh read, two serialized writers still each apply a stale snapshot.
### Fix B — field-level updates (removes the collision entirely)
The two writers touch disjoint fields (`Extended[versioning]` vs `Content`). If
each path updated only its own field instead of rewriting the whole entry, neither
could clobber the other regardless of ordering. This is the structural fix and
makes serialization a defense-in-depth concern rather than a correctness
requirement for cross-field cases.
## Where to serialize (layering)
The bucket entry is a single filer entry, so unlike object writes there is no
sharding — the question is purely the scope of the lock:
| Layer | Serializes across | Cost | Notes |
|---|---|---|---|
| 1. Gateway-local per-bucket lock | one gateway process | tiny | fixes the reported (single-gateway/CI) case |
| 2. Filer per-path lock via conditional write | all gateways on one filer | small | reuses #9640 `CreateEntry`+`WriteCondition` |
| 3. Route-by-key to bucket-key owner filer | all gateways and filers | medium | same mechanism as the object DLM-removal |
## Recommended plan (phased)
### Phase 1 — minimal fix for #9651 (gateway-local lock + fresh read)
Add a bounded per-bucket lock table to `S3ApiServer`, reusing the same
`util.LockTable` the filer uses for its per-path lock:
```go
// in S3ApiServer
bucketConfigLocks *util.LockTable[string] // serialize bucket-entry RMW
func (s3a *S3ApiServer) withBucketConfigLock(bucket string, fn func() s3err.ErrorCode) s3err.ErrorCode {
lk := s3a.bucketConfigLocks.AcquireLock("bucketConfig", bucket, util.ExclusiveLock)
defer s3a.bucketConfigLocks.ReleaseLock(bucket, lk)
return fn()
}
```
Wrap the RMW in **both** chokepoints, and inside the lock read the entry fresh:
- `updateBucketConfig`: acquire the lock; re-read `/buckets/<name>` from the filer
(not the cache); rebuild `BucketConfig` from that fresh entry; apply `fn`; write;
invalidate cache; release.
- `UpdateBucketMetadata`/`setBucketMetadata`: same lock key; it already reads fresh,
so it just needs to share the critical section.
Both must use the **same** lock keyed on `bucket`, so versioning and encryption
contend on one mutex. This closes the reported window. Limitation: only one
gateway; two gateways behind a load balancer still race.
Test: parallel `PutBucketVersioning` + `PutBucketEncryption`, assert both persist
(the exact Terraform scenario), plus an N-way parallel variant over distinct
fields.
### Phase 2 — robust across gateways (field-level + CAS via merged primitives)
Move the writers off whole-entry rewrites:
- **Extended-based config** (versioning, object-lock, ownership, tagging-in-Extended)
→ `ObjectTransaction` `PATCH_EXTENDED` on `/buckets/<name>`. The owner filer reads
the entry fresh under its per-path lock and merges only the named keys, so the
gateway never sends a whole-entry snapshot — this dissolves *both* ingredients for
these fields.
- **`Content`-based config** (encryption, CORS, tags blob) — **chosen and
implemented (b3): extend `PATCH_EXTENDED` with `set_content`.** Under the same
per-path lock the filer reads the entry fresh, merges extended attributes, and
replaces `Content`, preserving the rest. So a content write becomes a field-level
patch too — `setBucketMetadata` patches `Content`, `updateBucketConfig` patches
extended keys, and the two serialize on the lock instead of racing whole-entry
rewrites. This is cleaner than the alternatives below: no client-side retry, no
storage migration, and it reuses `ObjectTransaction`'s existing atomic lock.
- (b1, rejected) Conditional `CreateEntry` overwrite with `IF_ETAG_MATCH` + retry
(#9640): correct but needs client-side retry, and the bucket directory entry has
no reliable ETag to compare on.
- (b2, future) Migrate each per-feature config out of the single `Content` blob
into its own `Extended` key. Then even *intra-blob* writes (tags vs encryption)
stop racing. Larger migration; tracked separately.
Once all paths are field-level patches, the phase-1 gateway lock is unnecessary —
the filer enforces atomicity. (This is the path taken: phase 1 was skipped.)
### Phase 3 — multi-filer (only if needed)
If multiple filers can write `/buckets/<name>` concurrently, a filer-local per-path
lock no longer suffices. Route bucket-config writes to
`PrimaryForKey("/buckets/<name>")` (the lock-ring view) and serialize on that one
owner filer — the same route-by-key design used to take object writes off the DLM.
Overkill for rare config writes; include only if multi-filer bucket writes are real.
## Correctness summary
- Phase 1: all RMW for a bucket serialize within a gateway; the fresh read means the
second writer observes the first's change. Closes #9651 for single-gateway.
- Phase 2: `PATCH_EXTENDED` is atomic field-level merge at the filer (no snapshot);
CAS turns a concurrent `Content` write into a retry, enforced under the filer's
per-path lock — correct for any number of gateways sharing a filer.
- Phase 3: one owner filer serializes all writers — correct across filers too.
## Scope checklist (every path that RMWs the bucket entry)
All of these funnel through the two chokepoints, so fixing the chokepoints covers
them — but the fix must not leave any of them on an unserialized path:
- via `updateBucketConfig`: versioning, object-lock config, lifecycle, ACL/owner.
- via `UpdateBucketMetadata`/`setBucketMetadata`: encryption, CORS, tagging,
ownership controls, bucket policy, notification.
- bucket create/delete (`CreateEntry`/`DeleteEntry` of `/buckets/<name>`) already
go through the filer's per-path lock on `CreateEntry`; ensure they take the same
bucket lock if they also patch config.
## Cache rule (must document in code)
Under the lock, **read the entry from the filer, never rebuild from the cached
`BucketConfig`**. The cache is for reads; it must be invalidated on every write and
never be the source for an RMW. This is the single most important detail — the lock
without the fresh read does not fix the bug.
-696
View File
@@ -1,696 +0,0 @@
# Lance Catalog for SeaweedFS
A second catalog surface next to the Iceberg REST catalog, speaking the Lance Namespace
REST spec, over the same table buckets and the same filer.
## Why
Gravitino 1.1 added a Lance REST service and 1.3 ships it as a standalone server; Lakekeeper
added Lance in the same window by a completely different route. That is the useful signal:
two unrelated catalogs decided independently that Lance had to be first-class, not a niche.
The client side is already there — `lance-spark` (`LanceNamespaceSparkCatalog`
with `impl=rest`), `lance-ray`, and the generated Python/Java/Rust clients all talk the same
OpenAPI. Implementing the spec means those engines work against SeaweedFS with no
SeaweedFS-specific code on the client.
The second reason is that Gravitino's own documentation names the gap it cannot close:
DuckDB, pandas and DataFusion "do not support Lance REST natively yet" and have to fetch a
location from the catalog and then open the dataset directly. Gravitino cannot help there,
because it does not own the storage. SeaweedFS does. That is the whole design opportunity
below.
## Prior art: three families
Upstream lists twelve catalog implementations, and they fall into three shapes. Knowing
which one we are building matters more than any individual API decision.
**1. Storage-native, no service.** The Lance Directory Catalog. V1 is a directory listing
where every `<name>.lance/` child of a prefix is a table; V2 adds a `__manifest` table —
itself a Lance table — holding `object_id`/`object_type`/`location` rows, with nested
namespaces, hash-prefixed table directories, and optional managed versioning. No server, no
credentials, no governance. This is the floor every other implementation has to beat.
**2. Protocol-native server.** Someone implements the Lance Namespace REST OpenAPI and
clients connect with `impl=rest`. Gravitino is the only one of the twelve that does this,
and it is what this design proposes.
**3. Client-side adapters onto an existing catalog.** Nine of the twelve. The Lance client
translates namespace operations into whatever the backing catalog already speaks: Apache
Polaris, Unity Catalog, AWS Glue, Hive Metastore v2 and v3, Google BigLake, Dataproc,
Microsoft OneLake — and Apache Iceberg REST. Two flavors:
- Catalogs with a real non-Iceberg table concept mark the format directly. Polaris uses its
Generic Table API with `format = lance`; Unity uses an `EXTERNAL` table with
`table_type=lance` in properties and the path in `storage_location`; Glue uses
`EXTERNAL_TABLE` plus `table_type=lance` in `Parameters`, path in
`StorageDescriptor.Location`.
- Catalogs with no such concept fake one. The Iceberg REST adapter registers **a regular
Iceberg table with a dummy schema — a single nullable string column named `dummy`** —
carrying the property `table_type=lance`, and treats the Iceberg table location as the
Lance dataset root.
Every adapter in family 3 lands in the same place: `DeclareTable`/`ListTables`/
`DescribeTable`/`DeregisterTable` only, `DropNamespace` in RESTRICT mode only,
`load_detailed_metadata=false` only, and `managed_versioning=false`. They are a name-to-
location map and nothing more.
Lakekeeper is the instructive outlier. It has the same generic-table concept Polaris has,
but no upstream adapter exists for it — there is no `lance-namespace` reference anywhere in
its repository and no page for it in the supported-catalogs list. So Polaris's generic tables
are reachable from a stock Lance client and Lakekeeper's are not, despite being the same
idea. Shipping the concept is not the same as shipping the integration.
## Gravitino and Lakekeeper: the two opposite bets
Both shipped Lance support in the same window and did not build the same thing.
**Gravitino implements the protocol.** Its `lance/` module serves the Lance Namespace REST
spec on its own port (`:9101/lance`), so stock `lance-spark` and `lance-ray` connect with
`impl=rest` and no vendor-specific client. The cost is governance: storage credentials are
static properties on the catalog (`lance.storage.access_key_id`, `secret_access_key`,
`endpoint`, `region`, `allow_http`), optionally overridden per table, handed to the engine
as-is. No STS, no expiry, no per-table scoping.
**Lakekeeper refuses the protocol and governs the object instead.** There is no
`lance-namespace` anywhere in the repository; Lance arrived in 0.13.0 (2026-06-30, issue
#1673 `Generic Table API with Lance`) as one `format` string on a Lakekeeper-native Generic
Table API:
```
POST/GET/DELETE /lakekeeper/v1/{prefix}/namespaces/{ns}/generic-tables[/{table}]
GET /lakekeeper/v1/{prefix}/namespaces/{ns}/generic-tables/{table}/credentials
POST /lakekeeper/v1/{prefix}/generic-tables/rename
```
`format` is opaque, `schema` and `statistics` are stored but never validated, and the
catalog writes no format-specific metadata — engines go straight to the location. In
exchange Lance tables get everything Iceberg tables get: STS-vended prefix-scoped
credentials, OpenFGA per-action permissions (16 actions), soft-delete with undrop, a
protection flag, rename, pagination, and name uniqueness across Iceberg tables, views and
generic tables in one namespace. The price is that no stock Lance client can talk to it —
you need `pylakekeeper`, which exists mainly to translate vended credentials into
`lance_storage_options`.
So: protocol fidelity and weak governance, or strong governance and client lock-in. Both
documented their limit honestly, and it is the same limit. Lakekeeper's capability table
says it outright — "Commit coordination: the catalog does not arbitrate writes — engines
write directly." Gravitino does not claim it either. Neither of them coordinates a Lance
commit, which is exactly the thing a store can do and a control plane cannot.
We do not have to choose. Serve the Lance protocol natively the way Gravitino does, over
the `s3tables` entries that already carry ARNs, policies, tags and maintenance config, and
the governance comes from the layer underneath rather than from a proprietary API on top.
That is only available to us because we are the store, which is also what makes the third
option — arbitrating the commit — available.
## We are probably already a Lance catalog, and that is a problem
The Iceberg REST adapter does not care whose Iceberg catalog it is talking to. It needs
`/v1/config?warehouse=`, `/v1/{prefix}/namespaces`, `/v1/{prefix}/namespaces/{ns}/tables`
and unit-separator (`\x1F`) multi-level namespaces. We serve all of those, and
`parseNamespace` in `weed/s3api/iceberg/utils.go:22` already splits on `\x1F`. So a stock
Lance client pointed at our Iceberg catalog on :8181 with the Iceberg impl should already
create, list, describe and deregister Lance tables today, with no SeaweedFS change at all.
That is worth testing before writing a line of the design above, for two reasons. It is a
free baseline — and possibly a free announcement. And it is a data-loss hazard.
A Lance table registered this way is an Iceberg table whose metadata references no data
files, sitting on top of a Lance dataset that uses `data/` for its fragments — the same
subdirectory name Iceberg uses. The maintenance worker's orphan cleaner walks exactly
`<table>/metadata` and `<table>/data`, and deletes every file not referenced by a snapshot
and older than `orphan_older_than_hours`
(`weed/worker/tasks/iceberg/operations.go:331`, default 72). Against an adapter-registered
Lance table, every fragment is unreferenced by construction. Run maintenance and the
dataset is deleted.
Maintenance is disabled by default (`handler.go:334`), so this is a latent hazard rather
than a live one: it needs an operator to enable Iceberg maintenance on a bucket that also
holds adapter-registered Lance tables. But it costs nothing to close — detection should
skip any table carrying a non-Iceberg format marker (`table_type` property, or
`Format != "ICEBERG"` once the format field is honest), and that guard is worth landing on
its own regardless of whether the rest of this design ever gets built. It is the same
"catalog-only, no maintenance" marker the generic-format question needs.
## Where we differ from Gravitino
Gravitino is a metadata service in front of somebody else's object store:
```
Spark / Ray Spark / Ray / pandas / duckdb
| |
Lance REST Lance REST (direct S3)
| | |
Gravitino SeaweedFS S3 gateway ----+
| |
S3 keys handed out SeaweedFS filer + volumes
|
somebody else's S3
```
It resolves a name to a location plus `lance.storage.*` credentials, and steps out of the
way. Everything a Lance table actually is — `_versions/`, `data/`, `_indices/` — is opaque
to it.
We are the store. Three things follow that Gravitino cannot do:
1. The catalog and a plain directory listing can be made to agree, so a client with no
catalog at all still sees the right tables.
2. `_versions/` is a filer directory listing, not an object-store `LIST`. Version history
is cheap and can back the admin UI.
3. We can offer a genuinely atomic commit reservation. Lance's commit protocol needs
put-if-not-exists; our S3 layer does not currently provide one (see
[Commit safety](#commit-safety)). The filer does.
## Placement
The Iceberg catalog is a thin HTTP shell over `s3tables.Manager`; the storage work lives in
`weed/s3api/s3tables`. Table buckets live under `TablesPath = s3_constants.DefaultBucketsPath`,
i.e. the same filer tree the S3 gateway serves, so `s3://bucket/ns/table/` is simultaneously
a catalog entry and an S3 prefix. Catalog entries are filer directories carrying `s3tables.*`
extended attributes. `Table.Format` already exists and is hard-checked against `"ICEBERG"`
in `weed/s3api/s3tables/handler_table.go:48`.
So:
```
weed/s3api/lance/ new: HTTP surface, id codec, error model
weed/s3api/s3tables/ extended: Format "LANCE", lance state xattr, version entries
weed/command/s3.go new: -port.lance (default 9101), startLanceServer
```
`Format: "LANCE"` on the table entry is the whole storage-model change for phase 1.
Everything else — namespaces, ARNs, policies, tags, ownership — is shared verbatim.
```
s3tables.Manager (filer)
|
+------------------------+------------------------+
| |
weed/s3api/iceberg weed/s3api/lance
Iceberg REST :8181 Lance REST :9101
| |
Iceberg tables Lance datasets
\ /
+-------------------- s3 :8333 -----------------+
|
SeaweedFS volumes
```
## Identifier mapping
Lance identifiers are `["ns", ..., "table"]`, encoded in the URL as a single string joined
by a delimiter that defaults to `$`. The delimiter alone means the root namespace, so
`/v1/namespace/$/list` lists the root's children.
Iceberg had to invent a warehouse selector because its identifier is flat and every table
bucket is a separate catalog. Lance does not need that — its identifier is already
hierarchical, and Gravitino uses exactly three levels (`["lance_catalog", "sales", "orders"]`).
That maps onto us without inventing anything:
```
$ root -> list of table buckets
$analytics level 1 -> a table bucket
$analytics$sales level 2 -> a namespace in that bucket
$analytics$sales$orders table
```
`spark.sql.catalog.lance.parent = analytics` then makes `sales.orders` resolve, which is the
same shape Gravitino's Spark example uses.
Levels 2..N join into one `s3tables` namespace with `.`, matching what the Iceberg catalog
already does with `flattenNamespacePath`. The flattened form is only the directory name —
`namespaceMetadata.Namespace []string` in the xattr keeps the authoritative parts, so the
mapping stays invertible even though `.` is a legal character inside a namespace part.
Reject `$` in any name part with `InvalidInput`; our charsets already exclude it, so no
escaping scheme is needed.
Root-level `ListNamespaces` returning table buckets means an unauthenticated or
broadly-scoped caller can enumerate buckets. Filter it through the same
`s3tables/permissions.go` check `ListTableBuckets` uses, not a separate path.
`CreateNamespace` on a one-part identifier creates a table bucket, and it does so only if
the caller is permitted to — the namespace never creates a bucket as a side effect of
creating something inside it. A table bucket is a tenant resource with its own policy, ARN
and lifecycle, and conjuring one because a client said `CREATE SCHEMA` is a privilege
escalation dressed as a convenience. Lakekeeper draws the same line explicitly: its client
creates tables, not warehouses.
## Storage layout
Lay tables out as:
```
s3://<table-bucket>/<flattened-namespace>/<table>/
data/
_versions/
_indices/
```
**Built without the `.lance` suffix this design originally proposed.** The suffix would have
made every namespace prefix a valid Lance Directory Catalog V1 root, since V1 recognises a
table by exactly that naming. It does not survive contact with the storage layer: the
catalog entry *is* the dataset directory, `validateTableName` excludes `.` from the charset,
and a suffixed entry name would leak into ARNs, policy documents and the S3 Tables API,
where the same table would answer to two different names. Making `GetTablePath` format-aware
instead spreads an "unless it is Lance" branch through code that has no business knowing —
the exact cross-cutting cost this design rejects family 3 for.
So one name, one directory. What survives is direct access by URI, which is the larger half
of the story and needs no naming convention at all:
```python
# with the catalog
spark.sql("SELECT * FROM lance.sales.orders")
# without it, same bytes
lance.dataset("s3://analytics/sales/orders")
```
DuckDB, pandas and DataFusion still reach the data with no catalog running, which is the gap
Gravitino's documentation admits to. What they no longer get for free is *enumeration* — a
directory-catalog client pointed at the namespace prefix will not list these as tables. If
that turns out to matter, the cheapest fix is a repair-style tool that materialises `.lance`
aliases, not a rename of the catalog entry.
Note also that the directory catalog's own V2 mode puts child-namespace tables in
`<hash>_<ns$table>` directories at the root and creates no physical subdirectories for
namespaces, so full directory-catalog fidelity was never on offer anyway. We are a
server-backed catalog; the human-readable prefix layout is worth more than partial V1
lookalike behaviour.
## The table bucket was not a neutral container
This design assumed a table bucket is a place to put a table's files. It is
not: `validateTableBucketObjectPath` runs on every S3 write into one and
validated the path against Iceberg's layout, so a Lance client got 403 on
`data/*.lance`, on `_versions/`, and on `_transactions/` — a directory Lance
writes that neither the spec documentation nor this design anticipated. Nothing
about the catalog worked end to end until that changed.
The layout guard now admits the union of what the supported formats write, and
treats any underscore-prefixed top-level directory as belonging to the format,
checking only that the path stays inside the table. Enumerating Lance's
internal directories by name is exactly the mistake that missed
`_transactions`. Iceberg writes none of them, so it loses nothing.
Found by pointing the real Python client at a running gateway, not by reading
the spec. Worth remembering for the next format: the premise to check first is
whether the storage layer will accept its files at all.
## Table lifecycle
Lance has three table states, and the spec pins them to marker files:
| State | Marker | Created by | Visible in ListTables |
| --- | --- | --- | --- |
| declared | `.lance-reserved` | `DeclareTable` | yes, when `include_declared=true` |
| created | `_versions/` present | client writes, or `CreateTable` | yes |
| deregistered | `.lance-deregistered` | `DeregisterTable` | no; data preserved |
Record the state in an xattr (`s3tables.lanceState`) on the catalog entry *and* write the
marker file into the table directory. The xattr is what the catalog reads; the marker is
what keeps a directory-catalog client honest. Dual-write is the price of the interop claim
above, and it is one extra filer write on three rarely-called operations.
`DeclareTable` is the operation `lance-spark` actually calls on `CREATE TABLE` (it replaced
the legacy `create-empty`), so it is not optional in practice even though the spec marks
only a subset as required.
`DeregisterTable` preserving data is the same shape as our Iceberg rename, where the catalog
entry moves and the data stays put — reuse `TableDataDirFromMetadataLocation`'s idea rather
than re-deriving the data path from the catalog name.
## Commit safety
This is the part I got wrong, and the correction removed a feature rather than adding one.
Lance commits a version by writing `_versions/{v}.manifest` with put-if-not-exists: exactly
one writer is supposed to win, and the loser rebases. In lance 10 that path is not optional
and needs nothing bolted on — `commit_handler_from_url` hands every `s3://` dataset a
`ConditionalPutCommitHandler`, which calls `put_opts` with `PutMode::Create`, which
object_store's S3 backend sends as `If-None-Match: *`.
I originally read our gateway as evaluating that header check-then-act, and designed around
it. That was already out of date. `buildWriteCondition`
(`weed/s3api/s3api_object_routed_write.go`) reduces `If-None-Match: *` to a filer
`WriteCondition{IF_NOT_EXISTS}`, and `putToFiler` routes the create to the object's owner
filer, which evaluates the precondition under its per-path lock; when routing is not
available it falls back to the object write lock, which evaluates it under the lock too.
Either way it is atomic. Sixteen concurrent writers of the same fresh key get one 200 and
fifteen 412s, repeatedly.
So the store already has the primitive Lance needs, cluster-wide, for every conditional-PUT
client and not just this one.
### What that removed
An earlier draft of this design offered the catalog as an **external manifest store**:
`managed_versioning: true` plus `CreateTableVersion` and friends, with the reserve step as a
filer `CreateEntry` with `o_excl`. It was implemented, tested, and shipped behind a default-off
flag — and it should not exist.
- It solves a problem this store does not have. The spec offers that path for stores that
cannot order commits themselves.
- It moves a table's version history out of the dataset and into the catalog, so a reader
that does not go through this namespace no longer sees the whole picture. That is a real
cost paid for nothing.
- lance 10 cannot even use it past the first commit: `NamespaceManifestStore::put_if_not_exists`
answers "put_if_not_exists is not supported for namespace-backed stores", which is exactly
what a second `append` needs.
The version operations now answer `Unsupported` alongside the other operations the catalog
does not serve, and `managed_versioning` is answered `false`. The property they were
protecting is covered instead by a test that races eight writers at the manifest key through
S3 and asserts one wins — testing the path Lance actually takes.
## Credential vending
Iceberg needed a header (`X-Iceberg-Access-Delegation: vended-credentials`) and a bespoke
response shape. Lance has it in the spec: `vend_credentials: true` on the request,
`storage_options` on the response, with `expires_at_millis` as the well-known expiry key.
Reuse the existing vendor interface unchanged — `iceberg.CredentialVendor` /
`STSService.AssumeRoleForPrincipal` scoped to the table prefix (#10777) — and map its output
to the storage options Lance passes through to `object_store`:
```
aws_access_key_id, aws_secret_access_key, aws_session_token,
aws_region, aws_endpoint, allow_http, expires_at_millis
```
Those are the names `pylakekeeper` emits as `lance_storage_options`, which is the shape
Lakekeeper's tested S3 path actually feeds to Lance. `object_store` also accepts the
un-prefixed aliases (`endpoint`, `region`) that the directory catalog's `storage.` prefix
strips down to and that Gravitino's `lance.storage.endpoint` resolves to, but the `aws_`
forms are the ones with a tested integration behind them, so emit those. `aws_endpoint`
should come from `deriveS3AdvertisedEndpoint()`, the same source the Iceberg `FileIO` config
uses, and `allow_http` must be set when that endpoint is plain HTTP or every read fails with
a TLS error that looks like a credential problem — Lakekeeper vends both automatically for
exactly this reason, and calls out that there is then no per-vendor branch in client code.
We emit this server-side, in the `storage_options` field the Lance spec already defines,
which is strictly better than Lakekeeper's arrangement: no client library has to translate
anything, so vending works from any stock Lance client rather than only from theirs.
Guard the same way #10777 had to after review: bucket-scoped list grants need an `s3:prefix`
condition, and a location containing `*` or `?` must be refused rather than widened into a
resource pattern.
## Auth and authorization
Authentication reuses `S3Authenticator` and `CredentialValidator` as-is. The Lance spec maps
identity to headers — `api_key` to `x-api-key`, `auth_token` to `Authorization: Bearer` — and
SigV4 keeps working because it is the same authenticator the Iceberg catalog already fronts.
Authorization needs nothing new. A Lance table gets the same ARN shape,
`arn:aws:s3tables:...:bucket/B/table/NS/T`, so every existing table-bucket policy covers
Lance tables with no new policy language and no second permission model. Route it through
`s3tables/permissions.go` and inherit the `DefaultAllow` semantics the Iceberg server already
mirrors from the S3 port.
One spec quirk worth honoring: request context entries prefixed `header.` become request
headers, and every response header comes back as a `header.`-prefixed context entry. Echoing
`x-request-id` through it costs nothing and makes tracing work.
## What to take from Lakekeeper
Rejecting Lakekeeper's API shape does not mean rejecting what it learned building it.
**Deregister is soft-delete, so implement it as one.** Lakekeeper gives generic tables
soft-deletion with undrop and a `protected` flag that makes a drop require `force=true`.
Lance already has the concept — `DeregisterTable` preserves the data and hides the table —
so the `.lance-deregistered` marker is a soft-delete by another name, and a re-register is
an undrop. A protection flag on table-bucket entries is worth having regardless of Lance:
it is a few lines against the existing xattrs and it applies to Iceberg tables too.
**Enforce one identifier space across entry kinds.** Lakekeeper rejects a generic table
whose name collides with an Iceberg table or view in the same namespace. Our catalog entries
already share one filer directory and already carry `s3tables.entryType`, so this is
structurally true — but it has to be enforced deliberately on every path, or a Lance handler
happily loads an Iceberg table's directory and vice versa. That is the same crossover bug
class as the view/table rename authorization fixed in #10776; the `catalogEntryKind` pattern
from that change is the thing to reuse rather than re-derive.
**A re-vend path matters more than it looks.** Lakekeeper exposes `/credentials` separately
from load, because STS credentials expire in the middle of long jobs and re-loading the
whole table to refresh them is wasteful. In Lance the spec's answer is another
`DescribeTable` with `vend_credentials: true`, which is fine — but it means `DescribeTable`
must stay cheap when `load_detailed_metadata` is false, which is another reason not to open
the dataset on that path.
**Generic tables are a cheap orthogonal win.** Lakekeeper's real insight is that Delta,
Parquet, CSV, Vortex and Paimon all get governance for free once the catalog stops caring
what the format is. Our `Table.Format` field already exists and the only thing stopping it
is the hard `"ICEBERG"` check in `handler_table.go:48`. Loosening that and letting the S3
Tables API register a table with an arbitrary format and a location — no metadata, no
commits — is a small change that makes every format cataloguable. It is independent of this
design and probably worth doing first, since `Format: "LANCE"` is then just a value rather
than a special case.
**Skip remote signing.** It is Lakekeeper's fallback for S3-compatible stores with no STS,
and their own documentation notes that Lance will not use it — format libraries with their
own S3 client expect static credentials and do not implement the Iceberg signer protocol. We
have STS, so vended credentials are the path, and the signer is not worth building for a
client that cannot consume it.
## Errors
Lance uses `{code, error, detail, instance}` with numeric codes, not Iceberg's exception-type
strings. The mapping is mechanical:
| HTTP | code | when |
| --- | --- | --- |
| 400 | 13 InvalidInput | charset violations, malformed id, route/body mismatch |
| 401 | 16 Unauthenticated | |
| 403 | 15 PermissionDenied | |
| 404 | 1 NamespaceNotFound, 4 TableNotFound, 11 TableVersionNotFound | |
| 409 | 2/5 AlreadyExists, 3 NamespaceNotEmpty, 14 ConcurrentModification | |
| 501 | 0 Unsupported | every phase-3 data operation |
Route/body mismatch is a spec requirement, not a nicety: when the identifier appears in both
the path and the body and they disagree, the server must return 400. Cheap to get right at
the decode step, annoying to retrofit.
## Route surface
Phase 0 is not in this table: point a stock Lance client at the existing Iceberg catalog
with the Iceberg impl, see how far it gets, and land the maintenance guard either way. That
tells us what the native server actually has to beat.
Phase 1, the whole `lance-spark` and `lance-ray` contract:
```
POST /v1/namespace/{id}/create CreateNamespace mode: Create|ExistOk|Overwrite
GET /v1/namespace/{id}/list ListNamespaces
POST /v1/namespace/{id}/describe DescribeNamespace
POST /v1/namespace/{id}/drop DropNamespace mode: Fail|Skip, behavior: Restrict|Cascade
POST /v1/namespace/{id}/exists NamespaceExists
GET /v1/namespace/{id}/table/list ListTables ?include_declared, ?page_token, ?limit
GET /v1/table ListAllTables
POST /v1/table/{id}/declare DeclareTable
POST /v1/table/{id}/describe DescribeTable ?with_table_uri, ?load_detailed_metadata, ?check_declared
POST /v1/table/{id}/exists TableExists
POST /v1/table/{id}/register RegisterTable mode: Create|Overwrite
POST /v1/table/{id}/deregister DeregisterTable
POST /v1/table/{id}/drop DropTable
POST /v1/table/{id}/rename RenameTable
```
`DescribeTable` with `load_detailed_metadata=false` needs only `location`, which is the
common case and which we can answer from xattrs alone. With `load_detailed_metadata=true`
the spec wants `version`, `schema` and `stats`, which means reading the Lance manifest. For
phase 1, return the fields we can derive from the filer — `version` from the highest entry in
`_versions/`, given V2 naming is `{u64::MAX - version:020}.manifest` and V1 is
`{version}.manifest` — and omit `schema`/`stats` rather than fabricating them. The spec
tolerates a partial response here; it does not tolerate a wrong one.
Phase 2 was the five version operations plus `managed_versioning`; it was built and then
removed, for the reasons under Commit safety.
Phase 3 is the data plane: `CreateTable`, `InsertIntoTable`, `MergeInsertIntoTable`,
`UpdateTable`, `DeleteFromTable`, `QueryTable`, `CountTableRows`, and the index and tag
operations. These exchange Arrow IPC, and more to the point they require reading and writing
the Lance file format, for which no Go implementation exists. Return `Unsupported` (code 0)
and say so in the docs. `arrow-go/v18` is already an indirect dependency, so Arrow framing is
not the blocker — Lance is.
## Does a Lance table need maintenance?
Yes, and one part of it has no Iceberg equivalent. The client exposes three jobs:
- `optimize.compact_files()` — Lance writes a fragment per write batch, so a table fed by
small appends accumulates small files exactly the way an Iceberg table does.
- `optimize.optimize_indices()` — **rows written after an index was built are not covered by
it.** A vector search against a stale index silently misses recent data. That is a
correctness-shaped failure, not a slow query, and it is specific to what people use Lance
for.
- `cleanup_old_versions()` — every version is retained until something removes it. Lance can
do this itself: `optimize.enable_auto_cleanup()` sets it on the dataset, so this one need
not be an external job at all.
None of it can run in the Go worker. All three read and rewrite Lance files, which needs
Lance format code that does not exist in Go, and there is no useful subset either: deciding
which fragments an old version still references means parsing Lance manifests.
So the maintenance worker must not touch a Lance table, and it declines by reading the format
the catalog recorded rather than by failing to parse Iceberg metadata.
## The worker can be Rust, and it is not a sidecar
The Go worker is not the only worker. `weed/pb/plugin.proto` defines `PluginControlService`,
a language-agnostic gRPC stream that external maintenance workers connect on: the worker
opens `WorkerStream`, sends `WorkerHello` with the job types it can `detect` and `execute`,
answers `RequestConfigSchema` with a `JobTypeDescriptor`, replies to `RunDetectionRequest`
with `JobProposal`s and to `ExecuteJobRequest` with `JobProgressUpdate`s and `JobCompleted`.
`weed worker -admin=host:23646` is the Go reference implementation of exactly that contract,
from outside the admin process.
Nothing in it is Go-specific, and the Rust toolchain is already in the tree.
`seaweed-volume/build.rs` compiles protos straight out of `../weed/pb/` with `tonic_build`,
including `filer.proto`, on tonic 0.12 and prost 0.13. A Lance worker is that same build
with `plugin.proto` added and the `lance` crate as a dependency — the real one, no FFI and
no Python.
Three job types, one per real maintenance operation:
| Job type | Calls | Detected from |
| --- | --- | --- |
| `lance_compact` | `optimize.compact_files` | fragment count and sizes |
| `lance_optimize_indices` | `optimize.optimize_indices` | rows an index does not cover |
| `lance_cleanup_versions` | `cleanup_old_versions` | version count and age |
What the existing machinery then supplies for free is the part worth noticing. Scheduling,
retries, dedupe by `dedupe_key`, progress reporting, per-job concurrency limits and the
admin settings page all come from the protocol: a worker that answers `RequestConfigSchema`
with a descriptor gets its configuration form rendered in the admin UI without a line of Go
or templ. A Rust worker is a first-class maintenance worker, not an appendage.
The remaining wiring is small and mostly decided already. `RunDetectionRequest` carries a
`ClusterContext` with filer and S3 addresses plus a free-form `metadata` map, which is where
the Lance namespace URL goes; the worker lists Lance tables from the namespace, which is the
catalog of record and already filters by format. It gets at the data by asking
`DescribeTable` for `storage_options` with `vend_credentials`, so the worker is just another
client of the STS path rather than a component with its own credentials. And when it commits
a compaction it goes through `CreateTableVersion` like any other writer, which is what
managed versioning was for.
## The worker is also the only thing that can describe the table
Admin can render an Iceberg table because it can read Iceberg metadata. It cannot read
Lance: it knows the dataset's location and its format string, and that is the whole of it.
The details page showed a location and two empty panels, which is an honest answer and a
useless one.
The worker already knows. Detection opens every dataset to decide whether it needs
compacting, so at that moment it holds the schema, the row count, the fragment count and
the version count. It just had no way to say so — every message on the stream was about
work.
So `WorkerObservations` is a body on `WorkerToAdminMessage`: a repeated `ObjectObservation`
of `object_id`, `object_kind`, `format`, and a `ConfigValue` map the worker fills with
whatever it can cheaply say. Admin keeps the last observation per object and serves it back
with the time it was taken and the worker that took it. Nothing schedules from it, and it is
not authoritative — it is a cache with its staleness on the label, which is why the page
badges it rather than presenting it as metadata it read itself.
The keys are the worker's to choose, which keeps the protocol out of the business of knowing
what a Lance table is. A worker for any other format admin cannot parse describes itself the
same way.
## A bucket declares its format
Format was recorded per table, which is enough for the storage layer and not enough for
anything that has to answer a question about a bucket. The admin UI printed one Iceberg
endpoint for every bucket, including the ones holding Lance datasets, where that endpoint
serves nothing; an empty bucket had no format at all.
So `CreateTableBucket` takes an optional `format`, stored with the rest of the bucket
metadata. Empty means `ICEBERG` - what AWS S3 Tables serves, and therefore what an SDK
that has never heard of the field means. `CreateTable` refuses another format, and
`CreateView` refuses outright outside an Iceberg bucket, a view being Iceberg metadata.
The Lance namespace declares `LANCE` for the buckets it creates.
**Enforced rather than defaulted**, because the point of showing a format at all is the
endpoint that follows from it, and that endpoint is only truthful if the bucket holds one
format. **Buckets that already exist stay undeclared** and keep taking anything: nothing is
migrated, and the UI shows "unset" as a fact about the bucket's age rather than a fault.
That state is also the only way to hold both formats at once, which is what the
Iceberg-REST adapter path produces.
## Sample rows are fetched, not cached
The same asymmetry has a second half. Admin renders an Iceberg table's rows by
reading its Parquet files directly; for Lance it has nothing to read with, so the data
page offered a Browse Data button that led to an empty grid.
`RequestObjectPreview` / `ObjectPreviewResponse` mirror the config-schema round trip
already on the stream: admin asks, the worker scans the dataset and hands back rows it
has already rendered as text, because it is the only side that knows the types. Admin
picks the worker from the observation store, so the one that last described a table is
the one asked to read it.
The rows are deliberately not cached, and that is the line between the two channels. An
observation describes an object, so a copy with a timestamp on it is useful. Rows are the
object's contents: a copy held in admin would be stale, larger, and nobody's business.
The page fetches on load, bounded, or says why it cannot.
## The sidecar question
The data plane is a different problem, and this design previously conflated the two.
Maintenance rides the worker protocol; `QueryTable` and `InsertIntoTable` do not, because
they are synchronous REST operations on the namespace's own surface. Serving those means a
Rust process that answers HTTP, either behind the Go namespace as a proxy target or in front
of it. It would make SeaweedFS a store you can run vector search *in* rather than one you
read vectors *out of*, which is the larger prize and the reason to keep the option open.
Neither should gate phase 1. Phases 1 and 2 are pure Go over the filer and are worth
shipping on their own — they are what makes Spark and Ray work.
## Testing
Mirror the Iceberg package: `httptest` plus a fake filer client for the handler tests, in
`weed/s3api/lance`. Then an integration suite under `test/s3tables/catalog/` next to the
existing `pyiceberg_test.go`, driving the generated Python `lance-namespace` client against
a live gateway. Three things that suite must cover and unit tests cannot:
- the storage-options key names actually work, i.e. a client that gets `storage_options` from
`DescribeTable` can open the dataset;
- a table created through the catalog is visible to `lance.dataset()` by URI and to a V1
directory-catalog client rooted at the namespace prefix;
- concurrent writers do not lose a commit, which is the phase-2 acceptance test and the
thing that justifies the external manifest store.
Phase 1 is validated: `lance_namespace` 0.11.1 with `impl=rest` drives the namespace,
`lance.write_dataset` writes to the vended location with the vended `storage_options`, and
the rows read back. Note that this client version drops `check_declared` and
`include_declared` on the wire, so `is_only_declared` reads null through it however the
server behaves.
The commit path is validated at both levels. The mechanism: eight writers race the same
manifest key through S3 with `If-None-Match: *`, and exactly one wins. The property that
actually matters, which single-winner exclusivity does not by itself establish: eight
writers append to one dataset concurrently through lance, and afterwards every batch is
still there — the losers saw the conflict, rebased, and committed again. That second test
is also the sequence managed versioning could not complete at all, since its store answers
"put_if_not_exists is not supported" to the second commit.
One more that belongs in the Iceberg suite, not this one: a Lance dataset registered through
the Iceberg adapter must survive a full maintenance pass. Reading the code, that test should
fail today; it has not been run.
## Open questions
- Root-level `ListNamespaces` enumerating table buckets is convenient and is a listing
surface we do not have on the Iceberg side. Decide whether it is gated behind a flag.
- Whether the `.lance` directory suffix is worth the divergence from the Iceberg layout. I
think yes — it is what makes the catalog optional — but it means the two catalogs' tables
do not look alike on disk, and the admin UI has to know that.
- Names: our charsets are lowercase-only and Lance identifiers are arbitrary strings. Reject
and document, as Iceberg does, or case-fold. Rejecting is right, but see #10734 for how
case handling bites when only one side normalizes.
- Whether to land generic-format registration first. Dropping the `"ICEBERG"` check and
letting a table carry an arbitrary format plus a location is smaller than this whole
design, gets Delta and Parquet catalogued as a side effect, and turns `Format: "LANCE"`
into an ordinary value. The argument against is that it invites tables the maintenance
worker cannot service, so it needs a "catalog-only, no maintenance" marker to be honest.
+2 -16
View File
@@ -2,26 +2,12 @@ FROM ubuntu:22.04
LABEL author="Chris Lu"
# Note: This e2e test image intentionally runs as root for simplicity and compatibility.
# Production images (Dockerfile.go_build) use proper user isolation with su-exec.
# For testing purposes, running as root avoids permission complexities and dependency
# on Alpine-specific tools like su-exec (not available in Ubuntu repos).
# apt-install prefers Azure's mirror, which archive.ubuntu.com is slow enough from
# GitHub-hosted runners to justify, and falls through to archive.ubuntu.com when
# Azure is unreachable - which it periodically is, and Acquire::Retries against a
# single mirror just retries a dead host. Images built FROM this one install
# through it for the same reason.
COPY apt-install /usr/local/bin/apt-install
RUN chmod +x /usr/local/bin/apt-install && \
apt-install curl fio fuse ca-certificates && \
rm -rf /tmp/* /var/tmp/*
RUN apt-get update && apt-get install -y curl fio fuse
RUN mkdir -p /etc/seaweedfs /data/filerldb2
COPY ./weed /usr/bin/
COPY ./filer.toml /etc/seaweedfs/filer.toml
COPY ./entrypoint_e2e.sh /entrypoint.sh
COPY ./entrypoint.sh /entrypoint.sh
# volume server grpc port
EXPOSE 18080
-132
View File
@@ -1,132 +0,0 @@
FROM golang:1.26 AS builder
RUN apt-get update && \
apt-get install -y build-essential wget ca-certificates && \
rm -rf /var/lib/apt/lists/*
ARG FDB_VERSION=7.4.5
ENV FDB_VERSION=${FDB_VERSION}
ARG TARGETARCH
# Install FoundationDB client libraries with SHA256 checksum verification
# Known SHA256 checksums for FoundationDB client packages (verified 2025-01-19)
# To add checksums for new versions: run docker/get_fdb_checksum.sh <version> <arch>
RUN cd /tmp && \
case "${TARGETARCH}" in \
"amd64") FDB_ARCH="amd64"; PACKAGE_ARCH="amd64" ;; \
"arm64") FDB_ARCH="arm64"; PACKAGE_ARCH="aarch64" ;; \
*) echo "Unsupported architecture: ${TARGETARCH}" >&2; exit 1 ;; \
esac && \
case "${FDB_VERSION}_${FDB_ARCH}" in \
"7.4.5_amd64") \
EXPECTED_SHA256="eea6b98cf386a0848655b2e196d18633662a7440a7ee061c10e32153c7e7e112" ;; \
"7.4.5_arm64") \
EXPECTED_SHA256="f2176b86b7e1b561c3632b4e6e7efb82e3b8f57c2ff0d0ac4671e742867508aa" ;; \
"7.3.43_amd64") \
EXPECTED_SHA256="c3fa0a59c7355b914a1455dac909238d5ea3b6c6bc7b530af8597e6487c1651a" ;; \
"7.3.43_arm64") \
echo "ERROR: FoundationDB ${FDB_VERSION} does not publish arm64 client packages." >&2; \
echo "Please upgrade to 7.4.5+ when targeting arm64." >&2; \
exit 1 ;; \
*) \
echo "ERROR: No checksum available for FDB version ${FDB_VERSION} on ${FDB_ARCH}" >&2; \
echo "This is a security requirement. To add verification:" >&2; \
echo " 1. Run: docker/get_fdb_checksum.sh ${FDB_VERSION} ${FDB_ARCH}" >&2; \
echo " 2. Add the checksum to this Dockerfile" >&2; \
echo "Refusing to proceed without checksum verification." >&2; \
exit 1 ;; \
esac && \
PACKAGE="foundationdb-clients_${FDB_VERSION}-1_${PACKAGE_ARCH}.deb" && \
wget --timeout=30 --tries=3 https://github.com/apple/foundationdb/releases/download/${FDB_VERSION}/${PACKAGE} && \
echo "${EXPECTED_SHA256} ${PACKAGE}" | sha256sum -c - || \
(echo "ERROR: Checksum verification failed for FoundationDB ${FDB_VERSION} (${FDB_ARCH})" >&2; \
echo "Expected: ${EXPECTED_SHA256}" >&2; \
echo "This indicates either a corrupted download or potential tampering." >&2; \
exit 1) && \
dpkg -i ${PACKAGE} && \
rm ${PACKAGE}
# Set up FoundationDB environment variables for CGO
ENV CGO_CFLAGS="-I/usr/include/foundationdb"
ENV CGO_LDFLAGS="-lfdb_c"
# build SeaweedFS sources; prefer local context but fall back to git clone if context only has docker files
ARG SOURCE_REF=master
WORKDIR /go/src/github.com/seaweedfs/seaweedfs
COPY . .
RUN set -euo pipefail && \
if [ ! -d weed ]; then \
echo "Local build context does not include SeaweedFS sources; cloning ${SOURCE_REF}" >&2; \
mkdir -p /tmp/local-context && cp -a /go/src/github.com/seaweedfs/seaweedfs/. /tmp/local-context && \
cd / && rm -rf /go/src/github.com/seaweedfs/seaweedfs && \
git clone --depth 1 --branch ${SOURCE_REF} https://github.com/seaweedfs/seaweedfs /go/src/github.com/seaweedfs/seaweedfs && \
cp -a /tmp/local-context/. /go/src/github.com/seaweedfs/seaweedfs/docker/ && \
rm -rf /tmp/local-context && \
cd /go/src/github.com/seaweedfs/seaweedfs; \
fi && \
cd weed \
&& COMMIT_SHA=$(git rev-parse --short HEAD 2>/dev/null || echo "unknown") \
&& export LDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=${COMMIT_SHA}" \
&& go install -tags "5BytesOffset foundationdb" -ldflags "${LDFLAGS}"
FROM debian:bookworm-slim AS final
LABEL author="Chris Lu"
# Install runtime dependencies first
RUN apt-get update && \
apt-get install -y --no-install-recommends \
ca-certificates \
curl \
fuse \
wget && \
rm -rf /var/lib/apt/lists/*
# Reuse FoundationDB artifacts installed during the build stage
COPY --from=builder /usr/lib/libfdb_c* /usr/lib/
COPY --from=builder /usr/lib/foundationdb /usr/lib/foundationdb
COPY --from=builder /usr/bin/fdb* /usr/bin/
RUN ldconfig
# Copy SeaweedFS binary and configuration
COPY --from=builder /go/bin/weed /usr/bin/
RUN mkdir -p /etc/seaweedfs
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer_foundationdb.toml /etc/seaweedfs/filer.toml
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
# Create non-root user
RUN groupadd -g 1000 seaweed && \
useradd -u 1000 -g seaweed -s /bin/bash -m seaweed
# volume server gprc port
EXPOSE 18080
# volume server http port
EXPOSE 8080
# filer server gprc port
EXPOSE 18888
# filer server http port
EXPOSE 8888
# master server shared gprc port
EXPOSE 19333
# master server shared http port
EXPOSE 9333
# s3 server http port
EXPOSE 8333
# webdav server http port
EXPOSE 7333
# Create data directory and set proper ownership for seaweed user
RUN mkdir -p /data && \
chown -R seaweed:seaweed /data && \
chown -R seaweed:seaweed /etc/seaweedfs && \
chmod 755 /entrypoint.sh
VOLUME /data
WORKDIR /data
# Switch to non-root user
USER seaweed
ENTRYPOINT ["/entrypoint.sh"]
+44
View File
@@ -0,0 +1,44 @@
FROM gcc:11 as builder
RUN mkdir -p /go/src/github.com/seaweedfs/
RUN git clone https://github.com/seaweedfs/seaweedfs /go/src/github.com/seaweedfs/seaweedfs
ARG BRANCH=${BRANCH:-master}
RUN cd /go/src/github.com/seaweedfs/seaweedfs && git checkout $BRANCH
RUN cd /go/src/github.com/seaweedfs/seaweedfs/weed \
&& apt-get update \
&& apt-get install -y golang-src \
&& export LDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=$(git rev-parse --short HEAD)" \
&& CGO_ENABLED=0 go install -ldflags "-extldflags -static ${LDFLAGS}" -compiler=gccgo -tags gccgo,noasm
FROM alpine AS final
LABEL author="Chris Lu"
COPY --from=builder /go/bin/weed /usr/bin/
RUN mkdir -p /etc/seaweedfs
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/filer.toml /etc/seaweedfs/filer.toml
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/docker/entrypoint.sh /entrypoint.sh
RUN apk add fuse # for weed mount
# volume server gprc port
EXPOSE 18080
# volume server http port
EXPOSE 8080
# filer server gprc port
EXPOSE 18888
# filer server http port
EXPOSE 8888
# master server shared gprc port
EXPOSE 19333
# master server shared http port
EXPOSE 9333
# s3 server http port
EXPOSE 8333
# webdav server http port
EXPOSE 7333
RUN mkdir -p /data/filerldb2
VOLUME /data
WORKDIR /data
RUN chmod +x /entrypoint.sh
ENTRYPOINT ["/entrypoint.sh"]
+9 -70
View File
@@ -1,74 +1,21 @@
# Pin the builder to the host arch and cross-compile the (CGO-free) Go binary,
# so arm64/arm/386 targets skip QEMU emulation of the whole compile.
FROM --platform=$BUILDPLATFORM golang:1.26-alpine AS builder
FROM golang:1.19-alpine as builder
RUN apk add git g++ fuse
RUN mkdir -p /go/src/github.com/seaweedfs/
RUN git clone https://github.com/seaweedfs/seaweedfs /go/src/github.com/seaweedfs/seaweedfs
ARG BRANCH=${BRANCH:-master}
# Clone with full history and all tags to ensure all commits are available
RUN git clone --no-single-branch --tags https://github.com/seaweedfs/seaweedfs /go/src/github.com/seaweedfs/seaweedfs
ARG TAGS
RUN cd /go/src/github.com/seaweedfs/seaweedfs && \
(git checkout $BRANCH || \
(echo "Checkout failed, fetching all history..." && \
git fetch --all --tags --prune && \
git checkout $BRANCH) || \
(echo "ERROR: Branch/commit $BRANCH not found in repository" && \
echo "Available branches:" && git branch -a && exit 1))
ARG TARGETOS TARGETARCH TARGETVARIANT
RUN cd /go/src/github.com/seaweedfs/seaweedfs && git checkout $BRANCH
RUN cd /go/src/github.com/seaweedfs/seaweedfs/weed \
&& export LDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util/version.COMMIT=$(git rev-parse --short HEAD)" \
&& export GOOS=$TARGETOS GOARCH=$TARGETARCH \
&& case "$TARGETARCH" in arm) export GOARM="${TARGETVARIANT#v}";; esac \
&& CGO_ENABLED=0 go build -tags "$TAGS" -ldflags "-extldflags -static ${LDFLAGS}" -o /go/bin/weed .
# Rust volume server: use pre-built binary from CI when available (placed in
# weed-volume-prebuilt/ by the build-rust-binaries job), otherwise compile
# from source. Pre-building avoids a multi-hour QEMU-emulated cargo build
# for non-native architectures.
FROM alpine:3.23 as rust_builder
ARG TARGETARCH
ARG TAGS
COPY weed-volume-prebuilt/ /prebuilt/
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/seaweed-volume /build/seaweed-volume
COPY --from=builder /go/src/github.com/seaweedfs/seaweedfs/weed /build/weed
WORKDIR /build/seaweed-volume
RUN if [ -f "/prebuilt/weed-volume-${TARGETARCH}" ]; then \
echo "Using pre-built Rust binary for ${TARGETARCH}" && \
cp "/prebuilt/weed-volume-${TARGETARCH}" /weed-volume; \
elif [ "$TARGETARCH" = "amd64" ] || [ "$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 $TARGETARCH (unsupported)" && \
touch /weed-volume; \
fi
# Pre-built binaries arrive via GitHub Actions artifacts, which drop the
# executable bit, so the copied file is 0644 and exec fails with "Permission
# denied". Restore it (no-op for the empty placeholder, which stays size 0).
RUN chmod 0755 /weed-volume
&& export LDFLAGS="-X github.com/seaweedfs/seaweedfs/weed/util.COMMIT=$(git rev-parse --short HEAD)" \
&& CGO_ENABLED=0 go install -tags "$TAGS" -ldflags "-extldflags -static ${LDFLAGS}"
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 && \
apk add --no-cache fuse curl su-exec libgcc libcrypto3 libssl3 && \
addgroup -g 1000 seaweed && \
adduser -D -u 1000 -G seaweed seaweed
RUN apk add fuse # for weed mount
# volume server gprc port
EXPOSE 18080
@@ -87,19 +34,11 @@ EXPOSE 8333
# webdav server http port
EXPOSE 7333
# Create data directory and set proper ownership for seaweed user
RUN mkdir -p /data/filerldb2 && \
chown -R seaweed:seaweed /data && \
chown -R seaweed:seaweed /etc/seaweedfs && \
chmod 755 /entrypoint.sh
RUN mkdir -p /data/filerldb2
VOLUME /data
WORKDIR /data
# Entrypoint will handle permission fixes and user switching
RUN chmod +x /entrypoint.sh
ENTRYPOINT ["/entrypoint.sh"]
# Default to a complete single-process cluster (master+volume+filer+S3+admin)
# so the image is usable out of the box — including in environments like
# GitHub Actions service containers that cannot pass arguments to the entrypoint.
# Override with any other subcommand at `docker run` / compose time.
CMD ["mini", "-dir=/data"]
+6 -19
View File
@@ -1,16 +1,11 @@
FROM alpine AS final
LABEL author="Chris Lu"
COPY ./weed /usr/bin/weed
RUN chmod +x /usr/bin/weed && ls -la /usr/bin/weed
COPY ./weed /usr/bin/
RUN mkdir -p /etc/seaweedfs
COPY ./filer.toml /etc/seaweedfs/filer.toml
COPY ./entrypoint.sh /entrypoint.sh
# Install dependencies and create non-root user
RUN apk upgrade --no-cache && \
apk add --no-cache fuse curl su-exec && \
addgroup -g 1000 seaweed && \
adduser -D -u 1000 -G seaweed seaweed
RUN apk add fuse # for weed mount
RUN apk add curl # for health checks
# volume server grpc port
EXPOSE 18080
@@ -29,19 +24,11 @@ EXPOSE 8333
# webdav server http port
EXPOSE 7333
# Create data directory and set proper ownership for seaweed user
RUN mkdir -p /data/filerldb2 && \
chown -R seaweed:seaweed /data && \
chown -R seaweed:seaweed /etc/seaweedfs && \
chmod 755 /entrypoint.sh
RUN mkdir -p /data/filerldb2
VOLUME /data
WORKDIR /data
# Entrypoint will handle permission fixes and user switching
RUN chmod +x /entrypoint.sh
ENTRYPOINT ["/entrypoint.sh"]
# Default to a complete single-process cluster (master+volume+filer+S3+admin)
# so the image is usable out of the box — including in environments like
# GitHub Actions service containers that cannot pass arguments to the entrypoint.
# Override with any other subcommand at `docker run` / compose time.
CMD ["mini", "-dir=/data"]

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