mirror of
https://github.com/hanzoai/s3.git
synced 2026-11-03 03:07:41 +00:00
zooqueen
dd74d3e6d6
hanzoai/s3 was an AGPL-3.0 MinIO fork whose network-copyleft blocks embedding
and reselling as a managed service. Replace it wholesale with a fork of
SeaweedFS (github.com/seaweedfs/seaweedfs, Apache-2.0, Go) which ships a
built-in S3 gateway + Filer.
- License: AGPL-3.0 -> Apache-2.0 (upstream LICENSE kept verbatim, incl.
"Copyright 2025 Chris Lu"); NOTICE added crediting SeaweedFS. No AGPL/BUSL/
SSPL/GPL or enterprise ("ee") files remain.
- Module: go.mod path set to github.com/hanzoai/s3 with a self-replace
(replace github.com/seaweedfs/seaweedfs => ./) so the ~1800 internal Go files
keep their upstream import paths with zero churn. Internal identifiers and
import paths are intentionally NOT renamed.
- CLI rebrand: the binary is built as `s3` (was `weed`); root usage, per-command
help/usage/flag strings, shell autocomplete program name, and the product name
in CLI output now read "Hanzo S3" / `s3`. Users never see `weed`.
(e.g. `s3 server`, `s3 filer`, `s3 master`, `s3 volume`, `s3 s3`, `s3 mount`.)
- Build: `make` (or `go build -o s3 ./weed`) builds the `s3` binary green;
`cmd/weed-db` and `cmd/weed-sql` also build; `go vet ./weed/command/` clean.
- README/LLM.md rewritten for Hanzo S3; AGENTS.md/CLAUDE.md symlinks preserved.
- Dropped a 33MB prebuilt Mach-O `stress` binary upstream had committed; `.gitignore`
updated to ignore the `s3` build output.
105 lines
3.0 KiB
Go
105 lines
3.0 KiB
Go
package mount
|
|
|
|
import (
|
|
"fmt"
|
|
"io"
|
|
"sync"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/mount/page_writer"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
)
|
|
|
|
type ChunkedDirtyPages struct {
|
|
fh *FileHandle
|
|
writeWaitGroup sync.WaitGroup
|
|
lastErr error
|
|
collection string
|
|
replication string
|
|
uploadPipeline *page_writer.UploadPipeline
|
|
hasWrites bool
|
|
}
|
|
|
|
var (
|
|
_ = page_writer.DirtyPages(&ChunkedDirtyPages{})
|
|
)
|
|
|
|
func newMemoryChunkPages(fh *FileHandle, chunkSize int64) *ChunkedDirtyPages {
|
|
|
|
dirtyPages := &ChunkedDirtyPages{
|
|
fh: fh,
|
|
}
|
|
|
|
swapFileDir := fh.wfs.option.getUniqueCacheDirForWrite()
|
|
|
|
dirtyPages.uploadPipeline = page_writer.NewUploadPipeline(fh.wfs.concurrentWriters, chunkSize,
|
|
dirtyPages.saveChunkedFileIntervalToStorage, fh.wfs.option.ConcurrentWriters, swapFileDir,
|
|
fh.wfs.writeBufferAccountant)
|
|
|
|
return dirtyPages
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) AddPage(offset int64, data []byte, isSequential bool, tsNs int64) error {
|
|
pages.hasWrites = true
|
|
|
|
glog.V(4).Infof("%v memory AddPage [%d, %d)", pages.fh.fh, offset, offset+int64(len(data)))
|
|
_, err := pages.uploadPipeline.SaveDataAt(data, offset, isSequential, tsNs)
|
|
|
|
return err
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) FlushData() error {
|
|
if !pages.hasWrites {
|
|
return nil
|
|
}
|
|
pages.uploadPipeline.FlushAll()
|
|
if pages.lastErr != nil {
|
|
return fmt.Errorf("flush data: %v", pages.lastErr)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) ReadDirtyDataAt(data []byte, startOffset int64, tsNs int64) (maxStop int64) {
|
|
if !pages.hasWrites {
|
|
return
|
|
}
|
|
return pages.uploadPipeline.MaybeReadDataAt(data, startOffset, tsNs)
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) saveChunkedFileIntervalToStorage(reader io.Reader, offset int64, size int64, modifiedTsNs int64, cleanupFn func()) {
|
|
|
|
defer cleanupFn()
|
|
|
|
fileFullPath := pages.fh.FullPath()
|
|
fileName := fileFullPath.Name()
|
|
chunk, err := pages.fh.wfs.saveDataAsChunk(fileFullPath)(reader, fileName, offset, modifiedTsNs, uint64(size))
|
|
if err != nil {
|
|
glog.V(0).Infof("%v saveToStorage [%d,%d): %v", fileFullPath, offset, offset+size, err)
|
|
pages.lastErr = err
|
|
return
|
|
}
|
|
pages.fh.AddChunks([]*filer_pb.FileChunk{chunk})
|
|
pages.fh.entryChunkGroup.AddChunk(chunk)
|
|
glog.V(3).Infof("%v saveToStorage %s [%d,%d)", fileFullPath, chunk.FileId, offset, offset+size)
|
|
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) Destroy() {
|
|
pages.uploadPipeline.Shutdown()
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) EvictOneWritableChunk() bool {
|
|
return pages.uploadPipeline.EvictOneWritableChunk()
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) ProactiveFlush(nowNs, idleThresholdNs, maxHoldNs, fillRatio int64, frontierLag int, isSequential bool) bool {
|
|
return pages.uploadPipeline.ProactiveFlush(nowNs, idleThresholdNs, maxHoldNs, fillRatio, frontierLag, isSequential)
|
|
}
|
|
|
|
func (pages *ChunkedDirtyPages) LockForRead(startOffset, stopOffset int64) {
|
|
pages.uploadPipeline.LockForRead(startOffset, stopOffset)
|
|
}
|
|
func (pages *ChunkedDirtyPages) UnlockForRead(startOffset, stopOffset int64) {
|
|
pages.uploadPipeline.UnlockForRead(startOffset, stopOffset)
|
|
}
|