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.
111 lines
2.9 KiB
Go
111 lines
2.9 KiB
Go
package weed_server
|
|
|
|
import (
|
|
"context"
|
|
"sync"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
util_http "github.com/seaweedfs/seaweedfs/weed/util/http"
|
|
"github.com/seaweedfs/seaweedfs/weed/util/mem"
|
|
"github.com/seaweedfs/seaweedfs/weed/util/request_id"
|
|
|
|
"io"
|
|
"math/rand/v2"
|
|
"net/http"
|
|
)
|
|
|
|
// proxyReadConcurrencyPerVolumeServer limits how many concurrent proxy read
|
|
// requests the filer will issue to any single volume server. Without this,
|
|
// replication bursts can open hundreds of connections to one volume server,
|
|
// causing it to drop connections with "unexpected EOF".
|
|
const proxyReadConcurrencyPerVolumeServer = 16
|
|
|
|
var (
|
|
proxySemaphores sync.Map // host -> chan struct{}
|
|
)
|
|
|
|
func acquireProxySemaphore(ctx context.Context, host string) error {
|
|
v, _ := proxySemaphores.LoadOrStore(host, make(chan struct{}, proxyReadConcurrencyPerVolumeServer))
|
|
sem := v.(chan struct{})
|
|
select {
|
|
case sem <- struct{}{}:
|
|
return nil
|
|
case <-ctx.Done():
|
|
return ctx.Err()
|
|
}
|
|
}
|
|
|
|
func releaseProxySemaphore(host string) {
|
|
v, ok := proxySemaphores.Load(host)
|
|
if !ok {
|
|
return
|
|
}
|
|
select {
|
|
case <-v.(chan struct{}):
|
|
default:
|
|
glog.Warningf("proxy semaphore for %s was already empty on release", host)
|
|
}
|
|
}
|
|
|
|
func (fs *FilerServer) proxyToVolumeServer(w http.ResponseWriter, r *http.Request, fileId string) {
|
|
ctx := r.Context()
|
|
urlStrings, err := fs.filer.MasterClient.GetLookupFileIdFunction()(ctx, fileId)
|
|
if err != nil {
|
|
glog.ErrorfCtx(ctx, "locate %s: %v", fileId, err)
|
|
w.WriteHeader(http.StatusInternalServerError)
|
|
return
|
|
}
|
|
|
|
if len(urlStrings) == 0 {
|
|
w.WriteHeader(http.StatusNotFound)
|
|
return
|
|
}
|
|
|
|
proxyReq, err := http.NewRequest(r.Method, urlStrings[rand.IntN(len(urlStrings))], r.Body)
|
|
if err != nil {
|
|
glog.ErrorfCtx(ctx, "NewRequest %s: %v", urlStrings[0], err)
|
|
w.WriteHeader(http.StatusInternalServerError)
|
|
return
|
|
}
|
|
|
|
// Limit concurrent requests per volume server to prevent overload
|
|
volumeHost := proxyReq.URL.Host
|
|
if err := acquireProxySemaphore(ctx, volumeHost); err != nil {
|
|
glog.V(0).InfofCtx(ctx, "proxy to %s cancelled while waiting: %v", volumeHost, err)
|
|
w.WriteHeader(http.StatusServiceUnavailable)
|
|
return
|
|
}
|
|
defer releaseProxySemaphore(volumeHost)
|
|
|
|
proxyReq.Header.Set("Host", r.Host)
|
|
proxyReq.Header.Set("X-Forwarded-For", r.RemoteAddr)
|
|
request_id.InjectToRequest(ctx, proxyReq)
|
|
|
|
for header, values := range r.Header {
|
|
for _, value := range values {
|
|
proxyReq.Header.Add(header, value)
|
|
}
|
|
}
|
|
|
|
proxyResponse, postErr := util_http.GetGlobalHttpClient().Do(proxyReq)
|
|
|
|
if postErr != nil {
|
|
glog.ErrorfCtx(ctx, "post to filer: %v", postErr)
|
|
w.WriteHeader(http.StatusInternalServerError)
|
|
return
|
|
}
|
|
defer util_http.CloseResponse(proxyResponse)
|
|
|
|
for k, v := range proxyResponse.Header {
|
|
w.Header()[k] = v
|
|
}
|
|
w.WriteHeader(proxyResponse.StatusCode)
|
|
|
|
buf := mem.Allocate(128 * 1024)
|
|
defer mem.Free(buf)
|
|
if _, copyErr := io.CopyBuffer(w, proxyResponse.Body, buf); copyErr != nil {
|
|
glog.V(0).InfofCtx(ctx, "proxy copy %s: %v", fileId, copyErr)
|
|
}
|
|
|
|
}
|