mirror of
https://github.com/hanzoai/s3.git
synced 2026-11-02 10:33:22 +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.
76 lines
2.4 KiB
Go
76 lines
2.4 KiB
Go
package weed_server
|
|
|
|
import (
|
|
"context"
|
|
"io"
|
|
"math"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/filer"
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/operation"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/stats"
|
|
)
|
|
|
|
const MergeChunkMinCount int = 1000
|
|
|
|
func (fs *FilerServer) maybeMergeChunks(ctx context.Context, so *operation.StorageOption, inputChunks []*filer_pb.FileChunk) (mergedChunks []*filer_pb.FileChunk, err error) {
|
|
// Don't merge SSE-encrypted chunks to preserve per-chunk metadata
|
|
for _, chunk := range inputChunks {
|
|
if chunk.GetSseType() != 0 { // Any SSE type (SSE-C or SSE-KMS)
|
|
glog.V(3).InfofCtx(ctx, "Skipping chunk merge for SSE-encrypted chunks")
|
|
return inputChunks, nil
|
|
}
|
|
}
|
|
|
|
// Only merge small chunks more than half of the file
|
|
var chunkSize = fs.option.MaxMB * 1024 * 1024
|
|
var smallChunk, sumChunk int
|
|
var minOffset int64 = math.MaxInt64
|
|
for _, chunk := range inputChunks {
|
|
if chunk.IsChunkManifest {
|
|
continue
|
|
}
|
|
if chunk.Size < uint64(chunkSize/2) {
|
|
smallChunk++
|
|
if chunk.Offset < minOffset {
|
|
minOffset = chunk.Offset
|
|
}
|
|
}
|
|
sumChunk++
|
|
}
|
|
if smallChunk < MergeChunkMinCount || smallChunk < sumChunk/2 {
|
|
return inputChunks, nil
|
|
}
|
|
|
|
return fs.mergeChunks(ctx, so, inputChunks, minOffset)
|
|
}
|
|
|
|
func (fs *FilerServer) mergeChunks(ctx context.Context, so *operation.StorageOption, inputChunks []*filer_pb.FileChunk, chunkOffset int64) (mergedChunks []*filer_pb.FileChunk, mergeErr error) {
|
|
chunkedFileReader := filer.NewChunkStreamReaderFromFiler(ctx, fs.filer.MasterClient, inputChunks)
|
|
_, mergeErr = chunkedFileReader.Seek(chunkOffset, io.SeekCurrent)
|
|
if mergeErr != nil {
|
|
return nil, mergeErr
|
|
}
|
|
mergedChunks, _, _, mergeErr, _ = fs.uploadReaderToChunks(ctx, nil, chunkedFileReader, chunkOffset, int32(fs.option.MaxMB*1024*1024), "", "", true, so)
|
|
if mergeErr != nil {
|
|
return
|
|
}
|
|
|
|
stats.FilerHandlerCounter.WithLabelValues(stats.ChunkMerge).Inc()
|
|
for _, chunk := range inputChunks {
|
|
if chunk.Offset < chunkOffset || chunk.IsChunkManifest {
|
|
mergedChunks = append(mergedChunks, chunk)
|
|
}
|
|
}
|
|
|
|
garbage, err := filer.MinusChunks(ctx, fs.lookupFileId, inputChunks, mergedChunks)
|
|
if err != nil {
|
|
glog.ErrorfCtx(ctx, "Failed to resolve old entry chunks when delete old entry chunks. new: %s, old: %s",
|
|
mergedChunks, inputChunks)
|
|
return mergedChunks, err
|
|
}
|
|
fs.filer.DeleteChunksNotRecursive(garbage)
|
|
return
|
|
}
|