Files
s3/weed/topology/topology_ec.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

212 lines
6.1 KiB
Go

package topology
import (
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb"
"github.com/seaweedfs/seaweedfs/weed/pb/master_pb"
"github.com/seaweedfs/seaweedfs/weed/storage/erasure_coding"
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
)
type EcShardLocations struct {
Collection string
// Use MaxShardCount (32) to support custom EC ratios
Locations [erasure_coding.MaxShardCount][]*DataNode
}
func (t *Topology) SyncDataNodeEcShards(shardInfos []*master_pb.VolumeEcShardInformationMessage, dn *DataNode) (newShards, deletedShards []*erasure_coding.EcVolumeInfo) {
// convert into in memory struct storage.VolumeInfo
var shards []*erasure_coding.EcVolumeInfo
for _, shardInfo := range shardInfos {
// Create EcVolumeInfo directly with optimized format
ecVolumeInfo := &erasure_coding.EcVolumeInfo{
VolumeId: needle.VolumeId(shardInfo.Id),
Collection: shardInfo.Collection,
ShardsInfo: erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(shardInfo),
DiskType: shardInfo.DiskType,
DiskId: shardInfo.DiskId,
ExpireAtSec: shardInfo.ExpireAtSec,
FileCount: shardInfo.FileCount,
DeleteCount: shardInfo.DeleteCount,
EncodeTsNs: shardInfo.EncodeTsNs,
}
shards = append(shards, ecVolumeInfo)
}
// find out the delta volumes
newShards, deletedShards = dn.UpdateEcShards(shards)
for _, v := range newShards {
t.RegisterEcShards(v, dn)
}
for _, v := range deletedShards {
t.UnRegisterEcShards(v, dn)
}
return
}
func (t *Topology) IncrementalSyncDataNodeEcShards(newEcShards, deletedEcShards []*master_pb.VolumeEcShardInformationMessage, dn *DataNode) {
// convert into in memory struct storage.VolumeInfo
var newShards, deletedShards []*erasure_coding.EcVolumeInfo
for _, shardInfo := range newEcShards {
// Create EcVolumeInfo directly with optimized format
ecVolumeInfo := &erasure_coding.EcVolumeInfo{
VolumeId: needle.VolumeId(shardInfo.Id),
Collection: shardInfo.Collection,
ShardsInfo: erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(shardInfo),
DiskType: shardInfo.DiskType,
DiskId: shardInfo.DiskId,
ExpireAtSec: shardInfo.ExpireAtSec,
FileCount: shardInfo.FileCount,
DeleteCount: shardInfo.DeleteCount,
EncodeTsNs: shardInfo.EncodeTsNs,
}
newShards = append(newShards, ecVolumeInfo)
}
for _, shardInfo := range deletedEcShards {
// Create EcVolumeInfo directly with optimized format
ecVolumeInfo := &erasure_coding.EcVolumeInfo{
VolumeId: needle.VolumeId(shardInfo.Id),
Collection: shardInfo.Collection,
ShardsInfo: erasure_coding.ShardsInfoFromVolumeEcShardInformationMessage(shardInfo),
DiskType: shardInfo.DiskType,
DiskId: shardInfo.DiskId,
ExpireAtSec: shardInfo.ExpireAtSec,
FileCount: shardInfo.FileCount,
DeleteCount: shardInfo.DeleteCount,
EncodeTsNs: shardInfo.EncodeTsNs,
}
deletedShards = append(deletedShards, ecVolumeInfo)
}
dn.DeltaUpdateEcShards(newShards, deletedShards)
for _, v := range newShards {
t.RegisterEcShards(v, dn)
}
for _, v := range deletedShards {
t.UnRegisterEcShards(v, dn)
}
}
func NewEcShardLocations(collection string) *EcShardLocations {
return &EcShardLocations{
Collection: collection,
}
}
func (loc *EcShardLocations) AddShard(shardId erasure_coding.ShardId, dn *DataNode) (added bool) {
// Defensive bounds check to prevent panic with out-of-range shard IDs
if int(shardId) >= erasure_coding.MaxShardCount {
return false
}
dataNodes := loc.Locations[shardId]
for _, n := range dataNodes {
if n.Id() == dn.Id() {
return false
}
}
loc.Locations[shardId] = append(dataNodes, dn)
return true
}
func (loc *EcShardLocations) DeleteShard(shardId erasure_coding.ShardId, dn *DataNode) (deleted bool) {
// Defensive bounds check to prevent panic with out-of-range shard IDs
if int(shardId) >= erasure_coding.MaxShardCount {
return false
}
dataNodes := loc.Locations[shardId]
foundIndex := -1
for index, n := range dataNodes {
if n.Id() == dn.Id() {
foundIndex = index
}
}
if foundIndex < 0 {
return false
}
loc.Locations[shardId] = append(dataNodes[:foundIndex], dataNodes[foundIndex+1:]...)
return true
}
func (t *Topology) RegisterEcShards(ecvi *erasure_coding.EcVolumeInfo, dn *DataNode) {
// EC-only volumes (source volume deleted after encoding) must bump
// maxVolumeId too, or a heartbeat-rebuilt master could re-issue their id.
t.UpAdjustMaxVolumeId(ecvi.VolumeId)
t.ecShardMapLock.Lock()
defer t.ecShardMapLock.Unlock()
locations, found := t.ecShardMap[ecvi.VolumeId]
if !found {
locations = NewEcShardLocations(ecvi.Collection)
t.ecShardMap[ecvi.VolumeId] = locations
}
for _, shardId := range ecvi.ShardsInfo.Ids() {
locations.AddShard(shardId, dn)
}
}
func (t *Topology) UnRegisterEcShards(ecvi *erasure_coding.EcVolumeInfo, dn *DataNode) {
glog.Infof("removing ec shard info:%+v", ecvi)
t.ecShardMapLock.Lock()
defer t.ecShardMapLock.Unlock()
locations, found := t.ecShardMap[ecvi.VolumeId]
if !found {
return
}
for _, shardId := range ecvi.ShardsInfo.Ids() {
locations.DeleteShard(shardId, dn)
}
}
func (t *Topology) LookupEcShards(vid needle.VolumeId) (locations *EcShardLocations, found bool) {
t.ecShardMapLock.RLock()
defer t.ecShardMapLock.RUnlock()
locations, found = t.ecShardMap[vid]
return
}
func (t *Topology) ListEcServersByCollection(collection string) (dataNodes []pb.ServerAddress) {
t.ecShardMapLock.RLock()
defer t.ecShardMapLock.RUnlock()
dateNodeMap := make(map[pb.ServerAddress]bool)
for _, ecVolumeLocation := range t.ecShardMap {
if ecVolumeLocation.Collection == collection {
for _, locations := range ecVolumeLocation.Locations {
for _, loc := range locations {
dateNodeMap[loc.ServerAddress()] = true
}
}
}
}
for k, _ := range dateNodeMap {
dataNodes = append(dataNodes, k)
}
return
}
func (t *Topology) DeleteEcCollection(collection string) {
t.ecShardMapLock.Lock()
defer t.ecShardMapLock.Unlock()
var vids []needle.VolumeId
for vid, ecVolumeLocation := range t.ecShardMap {
if ecVolumeLocation.Collection == collection {
vids = append(vids, vid)
}
}
for _, vid := range vids {
delete(t.ecShardMap, vid)
}
}