Files
s3/weed/command/filer_remote_gateway.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

126 lines
4.7 KiB
Go

package command
import (
"context"
"fmt"
"os"
"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/pb/remote_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 RemoteGatewayOptions struct {
filerAddress *string
grpcDialOption grpc.DialOption
readChunkFromFiler *bool
timeAgo *time.Duration
createBucketAt *string
createBucketRandomSuffix *bool
include *string
exclude *string
mappings *remote_pb.RemoteStorageMapping
remoteConfs map[string]*remote_pb.RemoteConf
bucketsDir string
clientId int32
clientEpoch int32
}
var _ = filer_pb.FilerClient(&RemoteGatewayOptions{})
func (option *RemoteGatewayOptions) 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 *RemoteGatewayOptions) AdjustedUrl(location *filer_pb.Location) string {
return location.Url
}
func (option *RemoteGatewayOptions) GetDataCenter() string {
return ""
}
var (
remoteGatewayOptions RemoteGatewayOptions
)
func init() {
cmdFilerRemoteGateway.Run = runFilerRemoteGateway // break init cycle
remoteGatewayOptions.filerAddress = cmdFilerRemoteGateway.Flag.String("filer", "localhost:8888", "filer of the Hanzo S3 cluster")
remoteGatewayOptions.createBucketAt = cmdFilerRemoteGateway.Flag.String("createBucketAt", "", "one remote storage name to create new buckets in")
remoteGatewayOptions.createBucketRandomSuffix = cmdFilerRemoteGateway.Flag.Bool("createBucketWithRandomSuffix", true, "add randomized suffix to bucket name to avoid conflicts")
remoteGatewayOptions.readChunkFromFiler = cmdFilerRemoteGateway.Flag.Bool("filerProxy", false, "read file chunks from filer instead of volume servers")
remoteGatewayOptions.timeAgo = cmdFilerRemoteGateway.Flag.Duration("timeAgo", 0, "start time before now. \"300ms\", \"1.5h\" or \"2h45m\". Valid time units are \"ns\", \"us\" (or \"µs\"), \"ms\", \"s\", \"m\", \"h\"")
remoteGatewayOptions.include = cmdFilerRemoteGateway.Flag.String("include", "", "pattens of new bucket names, e.g., s3*")
remoteGatewayOptions.exclude = cmdFilerRemoteGateway.Flag.String("exclude", "", "pattens of new bucket names, e.g., local*")
remoteGatewayOptions.clientId = util.RandomInt32()
}
var cmdFilerRemoteGateway = &Command{
UsageLine: "filer.remote.gateway",
Short: "resumable continuously write back bucket creation, deletion, and other local updates to remote object store",
Long: `resumable continuously write back bucket creation, deletion, and other local updates to remote object store
filer.remote.gateway listens on filer local buckets update events.
If any bucket is created, deleted, or updated, it will mirror the changes to remote object store.
s3 filer.remote.gateway -createBucketAt=cloud1
`,
}
func runFilerRemoteGateway(cmd *Command, args []string) bool {
util.LoadSecurityConfiguration()
grpcDialOption := security.LoadClientTLS(util.GetViper(), "grpc.client")
remoteGatewayOptions.grpcDialOption = grpcDialOption
filerAddress := pb.ServerAddress(*remoteGatewayOptions.filerAddress)
filerSource := &source.FilerSource{}
filerSource.DoInitialize(
filerAddress.ToHttpAddress(),
filerAddress.ToGrpcAddress(),
"/", // does not matter
*remoteGatewayOptions.readChunkFromFiler,
)
remoteGatewayOptions.bucketsDir = "/buckets"
// check buckets again
remoteGatewayOptions.WithFilerClient(false, func(filerClient filer_pb.SeaweedFilerClient) error {
resp, err := filerClient.GetFilerConfiguration(context.Background(), &filer_pb.GetFilerConfigurationRequest{})
if err != nil {
return err
}
remoteGatewayOptions.bucketsDir = resp.DirBuckets
return nil
})
// read filer remote storage mount mappings
if detectErr := remoteGatewayOptions.collectRemoteStorageConf(); detectErr != nil {
fmt.Fprintf(os.Stderr, "read mount info: %v\n", detectErr)
return true
}
// synchronize /buckets folder
fmt.Printf("synchronize buckets in %s ...\n", remoteGatewayOptions.bucketsDir)
util.RetryUntil("filer.remote.sync buckets", func() error {
return remoteGatewayOptions.followBucketUpdatesAndUploadToRemote(filerSource)
}, func(err error) bool {
if err != nil {
glog.Errorf("synchronize %s: %v", remoteGatewayOptions.bucketsDir, err)
}
return true
})
return true
}