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.
108 lines
3.6 KiB
Go
108 lines
3.6 KiB
Go
package command
|
|
|
|
import (
|
|
"fmt"
|
|
"time"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/replication/source"
|
|
"github.com/seaweedfs/seaweedfs/weed/security"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
"google.golang.org/grpc"
|
|
)
|
|
|
|
type RemoteSyncOptions struct {
|
|
filerAddress *string
|
|
storageClass *string
|
|
grpcDialOption grpc.DialOption
|
|
readChunkFromFiler *bool
|
|
timeAgo *time.Duration
|
|
dir *string
|
|
clientId int32
|
|
clientEpoch int32
|
|
}
|
|
|
|
var _ = filer_pb.FilerClient(&RemoteSyncOptions{})
|
|
|
|
func (option *RemoteSyncOptions) WithFilerClient(streamingMode bool, fn func(filer_pb.SeaweedFilerClient) error) error {
|
|
return pb.WithFilerClient(streamingMode, option.clientId, pb.ServerAddress(*option.filerAddress), option.grpcDialOption, func(client filer_pb.SeaweedFilerClient) error {
|
|
return fn(client)
|
|
})
|
|
}
|
|
func (option *RemoteSyncOptions) AdjustedUrl(location *filer_pb.Location) string {
|
|
return location.Url
|
|
}
|
|
|
|
func (option *RemoteSyncOptions) GetDataCenter() string {
|
|
return ""
|
|
}
|
|
|
|
var (
|
|
remoteSyncOptions RemoteSyncOptions
|
|
)
|
|
|
|
func init() {
|
|
cmdFilerRemoteSynchronize.Run = runFilerRemoteSynchronize // break init cycle
|
|
remoteSyncOptions.filerAddress = cmdFilerRemoteSynchronize.Flag.String("filer", "localhost:8888", "filer of the Hanzo S3 cluster")
|
|
remoteSyncOptions.dir = cmdFilerRemoteSynchronize.Flag.String("dir", "", "a mounted directory on filer")
|
|
remoteSyncOptions.storageClass = cmdFilerRemoteSynchronize.Flag.String("storageClass", "", "override amz storage class, empty to delete")
|
|
remoteSyncOptions.readChunkFromFiler = cmdFilerRemoteSynchronize.Flag.Bool("filerProxy", false, "read file chunks from filer instead of volume servers")
|
|
remoteSyncOptions.timeAgo = cmdFilerRemoteSynchronize.Flag.Duration("timeAgo", 0, "start time before now, skipping previous metadata changes. \"300ms\", \"1.5h\" or \"2h45m\". Valid time units are \"ns\", \"us\" (or \"µs\"), \"ms\", \"s\", \"m\", \"h\"")
|
|
remoteSyncOptions.clientId = util.RandomInt32()
|
|
}
|
|
|
|
var cmdFilerRemoteSynchronize = &Command{
|
|
UsageLine: "filer.remote.sync",
|
|
Short: "resumable continuously write back updates to remote storage",
|
|
Long: `resumable continuously write back updates to remote storage
|
|
|
|
filer.remote.sync listens on filer update events.
|
|
If any mounted remote file is updated, it will fetch the updated content,
|
|
and write to the remote storage.
|
|
|
|
s3 filer.remote.sync -dir=/mount/s3_on_cloud
|
|
|
|
The metadata sync starting time is determined with the following priority order:
|
|
1. specified by timeAgo
|
|
2. last sync timestamp for this directory
|
|
3. directory creation time
|
|
|
|
`,
|
|
}
|
|
|
|
func runFilerRemoteSynchronize(cmd *Command, args []string) bool {
|
|
|
|
util.LoadSecurityConfiguration()
|
|
grpcDialOption := security.LoadClientTLS(util.GetViper(), "grpc.client")
|
|
remoteSyncOptions.grpcDialOption = grpcDialOption
|
|
|
|
dir := *remoteSyncOptions.dir
|
|
filerAddress := pb.ServerAddress(*remoteSyncOptions.filerAddress)
|
|
|
|
filerSource := &source.FilerSource{}
|
|
filerSource.DoInitialize(
|
|
filerAddress.ToHttpAddress(),
|
|
filerAddress.ToGrpcAddress(),
|
|
"/", // does not matter
|
|
*remoteSyncOptions.readChunkFromFiler,
|
|
)
|
|
|
|
if dir != "" {
|
|
fmt.Printf("synchronize %s to remote storage...\n", dir)
|
|
util.RetryUntil("filer.remote.sync "+dir, func() error {
|
|
return followUpdatesAndUploadToRemote(&remoteSyncOptions, filerSource, dir)
|
|
}, func(err error) bool {
|
|
if err != nil {
|
|
glog.Errorf("synchronize %s: %v", dir, err)
|
|
}
|
|
return true
|
|
})
|
|
return true
|
|
}
|
|
|
|
return true
|
|
|
|
}
|