mirror of
https://github.com/hanzoai/s3.git
synced 2026-10-30 14:59:09 +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.
117 lines
3.2 KiB
Go
117 lines
3.2 KiB
Go
package shell
|
|
|
|
import (
|
|
"context"
|
|
"flag"
|
|
"fmt"
|
|
"io"
|
|
"sort"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
|
|
)
|
|
|
|
func init() {
|
|
Commands = append(Commands, &commandVacuum{})
|
|
}
|
|
|
|
type commandVacuum struct {
|
|
}
|
|
|
|
func (c *commandVacuum) Name() string {
|
|
return "volume.vacuum"
|
|
}
|
|
|
|
func (c *commandVacuum) Help() string {
|
|
return `compact volumes if deleted entries are more than the limit
|
|
|
|
volume.vacuum [-garbageThreshold=0.3] [-collection=<collection name>] [-volumeId=<volume id>]
|
|
|
|
`
|
|
}
|
|
|
|
func (c *commandVacuum) HasTag(CommandTag) bool {
|
|
return false
|
|
}
|
|
|
|
func (c *commandVacuum) Do(args []string, commandEnv *CommandEnv, writer io.Writer) (err error) {
|
|
|
|
volumeVacuumCommand := flag.NewFlagSet(c.Name(), flag.ContinueOnError)
|
|
garbageThreshold := volumeVacuumCommand.Float64("garbageThreshold", 0.3, "vacuum when garbage is more than this limit")
|
|
collection := volumeVacuumCommand.String("collection", "", "vacuum this collection")
|
|
volumeIds := volumeVacuumCommand.String("volumeId", "", "comma-separated list of volume IDs")
|
|
if err = volumeVacuumCommand.Parse(args); err != nil {
|
|
return nil
|
|
}
|
|
|
|
if err = commandEnv.confirmIsLocked(args); err != nil {
|
|
return
|
|
}
|
|
|
|
var volumeIdInts []uint32
|
|
if *volumeIds != "" {
|
|
for _, volumeIdStr := range strings.Split(*volumeIds, ",") {
|
|
volumeIdStr = strings.TrimSpace(volumeIdStr)
|
|
if volumeIdInt, err := strconv.ParseUint(volumeIdStr, 10, 32); err == nil {
|
|
volumeIdInts = append(volumeIdInts, uint32(volumeIdInt))
|
|
} else {
|
|
return fmt.Errorf("parse volumeId string %s to int: %v", volumeIdStr, err)
|
|
}
|
|
}
|
|
} else {
|
|
volumeIdInts = append(volumeIdInts, 0)
|
|
}
|
|
|
|
// Reject unknown ids up front. The master's VacuumVolume RPC silently
|
|
// iterates matching volumes, so a typo or an already-deleted volume just
|
|
// returns success — making this command look like it worked when nothing
|
|
// happened.
|
|
if *volumeIds != "" {
|
|
topo, _, err := collectTopologyInfo(commandEnv, 0)
|
|
if err != nil {
|
|
return fmt.Errorf("collect topology: %w", err)
|
|
}
|
|
known := make(map[uint32]bool)
|
|
eachDataNode(topo, func(_ DataCenterId, _ RackId, dn *master_pb.DataNodeInfo) {
|
|
for _, disk := range dn.DiskInfos {
|
|
for _, vi := range disk.VolumeInfos {
|
|
known[vi.Id] = true
|
|
}
|
|
}
|
|
})
|
|
// Dedupe via a set so "volume.vacuum -volumeId 5,5,5" on a missing
|
|
// volume 5 reports [5] once instead of [5 5 5].
|
|
missingSet := make(map[uint32]bool)
|
|
for _, vid := range volumeIdInts {
|
|
if !known[vid] {
|
|
missingSet[vid] = true
|
|
}
|
|
}
|
|
if len(missingSet) > 0 {
|
|
missing := make([]uint32, 0, len(missingSet))
|
|
for vid := range missingSet {
|
|
missing = append(missing, vid)
|
|
}
|
|
sort.Slice(missing, func(i, j int) bool { return missing[i] < missing[j] })
|
|
return fmt.Errorf("volume(s) not found on master: %v", missing)
|
|
}
|
|
}
|
|
|
|
for _, volumeId := range volumeIdInts {
|
|
err = commandEnv.MasterClient.WithClient(false, func(client master_pb.SeaweedClient) error {
|
|
_, err = client.VacuumVolume(context.Background(), &master_pb.VacuumVolumeRequest{
|
|
GarbageThreshold: float32(*garbageThreshold),
|
|
VolumeId: volumeId,
|
|
Collection: *collection,
|
|
})
|
|
return err
|
|
})
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
return nil
|
|
}
|