Files
s3/weed/command/compact.go
zooqueen dd74d3e6d6 Replace AGPL MinIO fork with Apache-2.0 SeaweedFS fork; rebrand CLI weed->s3
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.
2026-06-18 23:41:25 -07:00

72 lines
2.3 KiB
Go

package command
import (
"strings"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/storage"
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
"github.com/seaweedfs/seaweedfs/weed/util"
)
func init() {
cmdCompact.Run = runCompact // break init cycle
}
var cmdCompact = &Command{
UsageLine: "compact -dir=/tmp -volumeId=234",
Short: "run s3 tool compact on volume file",
Long: `Force an compaction to remove deleted files from volume files.
The compacted .dat file is stored as .cpd file.
The compacted .idx file is stored as .cpx file.
Supports two compaction methods:
* data: compacts based on the .dat file, works if .idx file is corrupted.
* index: compacts based on the .idx file, works if deletion happened but not written to .dat files.
`,
}
var (
compactVolumePath = cmdCompact.Flag.String("dir", ".", "data directory to store files")
compactVolumeCollection = cmdCompact.Flag.String("collection", "", "volume collection name")
compactVolumeId = cmdCompact.Flag.Int("volumeId", -1, "a volume id. The volume should already exist in the dir.")
compactMethod = cmdCompact.Flag.String("method", "data", "option to choose which compact method (data/index)")
compactVolumePreallocate = cmdCompact.Flag.Int64("preallocateMB", 0, "preallocate volume disk space")
)
func runCompact(cmd *Command, args []string) bool {
if *compactVolumeId == -1 {
return false
}
*compactVolumePath = util.ResolvePath(*compactVolumePath)
preallocateBytes := *compactVolumePreallocate * (1 << 20)
vid := needle.VolumeId(*compactVolumeId)
v, err := storage.NewVolume(*compactVolumePath, *compactVolumePath, *compactVolumeCollection, vid, storage.NeedleMapInMemory, nil, nil, preallocateBytes, needle.GetCurrentVersion(), 0, 0)
if err != nil {
glog.Fatalf("Load Volume [ERROR] %s\n", err)
}
opts := &storage.CompactOptions{
PreallocateBytes: preallocateBytes,
MaxBytesPerSecond: 0, // unlimited
}
switch strings.ToLower(*compactMethod) {
case "data":
if err = v.CompactByVolumeData(opts); err != nil {
glog.Fatalf("Compact Volume [ERROR] %s\n", err)
}
case "index":
if err = v.CompactByIndex(opts); err != nil {
glog.Fatalf("Compact Volume [ERROR] %s\n", err)
}
default:
glog.Fatalf("unsupported compaction method %q", *compactMethod)
}
return true
}