mirror of
https://github.com/hanzoai/s3.git
synced 2026-11-03 03:07:41 +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.
122 lines
3.4 KiB
Go
122 lines
3.4 KiB
Go
package mount
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"fmt"
|
|
"io"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
|
|
"github.com/seaweedfs/go-fuse/v2/fuse"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
)
|
|
|
|
/**
|
|
* Read data
|
|
*
|
|
* Read should send exactly the number of bytes requested except
|
|
* on EOF or error, otherwise the rest of the data will be
|
|
* substituted with zeroes. An exception to this is when the file
|
|
* has been opened in 'direct_io' mode, in which case the return
|
|
* value of the read system call will reflect the return value of
|
|
* this operation.
|
|
*
|
|
* fi->fh will contain the value set by the open method, or will
|
|
* be undefined if the open method didn't set any value.
|
|
*
|
|
* Valid replies:
|
|
* fuse_reply_buf
|
|
* fuse_reply_iov
|
|
* fuse_reply_data
|
|
* fuse_reply_err
|
|
*
|
|
* @param req request handle
|
|
* @param ino the inode number
|
|
* @param size number of bytes to read
|
|
* @param off offset to read from
|
|
* @param fi file information
|
|
*/
|
|
func (wfs *WFS) Read(cancel <-chan struct{}, in *fuse.ReadIn, buff []byte) (fuse.ReadResult, fuse.Status) {
|
|
fh := wfs.GetHandle(FileHandleId(in.Fh))
|
|
if fh == nil {
|
|
return nil, fuse.ENOENT
|
|
}
|
|
|
|
fhActiveLock := fh.wfs.fhLockTable.AcquireLock("Read", fh.fh, util.SharedLock)
|
|
defer fh.wfs.fhLockTable.ReleaseLock(fh.fh, fhActiveLock)
|
|
|
|
// Create a context that will be cancelled when the cancel channel receives a signal
|
|
ctx, cancelFunc := context.WithCancel(context.Background())
|
|
defer cancelFunc() // Ensure cleanup
|
|
|
|
go func() {
|
|
select {
|
|
case <-cancel:
|
|
cancelFunc()
|
|
case <-ctx.Done():
|
|
}
|
|
}()
|
|
|
|
offset := int64(in.Offset)
|
|
totalRead, err := readDataByFileHandleWithContext(ctx, buff, fh, offset)
|
|
if err != nil {
|
|
glog.Warningf("file handle read %s %d: %v", fh.FullPath(), totalRead, err)
|
|
return nil, fuse.EIO
|
|
}
|
|
|
|
if IsDebugFileReadWrite {
|
|
// print(".")
|
|
mirrorData := make([]byte, totalRead)
|
|
fh.mirrorFile.ReadAt(mirrorData, offset)
|
|
if bytes.Compare(mirrorData, buff[:totalRead]) != 0 {
|
|
|
|
againBuff := make([]byte, len(buff))
|
|
againRead, _ := readDataByFileHandleWithContext(ctx, againBuff, fh, offset)
|
|
againCorrect := bytes.Compare(mirrorData, againBuff[:againRead]) == 0
|
|
againSame := bytes.Compare(buff[:totalRead], againBuff[:againRead]) == 0
|
|
|
|
fmt.Printf("\ncompare %v [%d,%d) size:%d againSame:%v againCorrect:%v\n", fh.mirrorFile.Name(), offset, offset+totalRead, totalRead, againSame, againCorrect)
|
|
//fmt.Printf("read mirrow data: %v\n", mirrorData)
|
|
//fmt.Printf("read actual data: %v\n", againBuff[:totalRead])
|
|
}
|
|
}
|
|
|
|
return fuse.ReadResultData(buff[:totalRead]), fuse.OK
|
|
}
|
|
|
|
func readDataByFileHandle(buff []byte, fhIn *FileHandle, offset int64) (int64, error) {
|
|
// read data from source file
|
|
size := len(buff)
|
|
fhIn.lockForRead(offset, size)
|
|
defer fhIn.unlockForRead(offset, size)
|
|
|
|
n, tsNs, err := fhIn.readFromChunks(buff, offset)
|
|
if err == nil || err == io.EOF {
|
|
maxStop := fhIn.readFromDirtyPages(buff, offset, tsNs)
|
|
n = max(maxStop-offset, n)
|
|
}
|
|
if err == io.EOF {
|
|
err = nil
|
|
}
|
|
return n, err
|
|
}
|
|
|
|
func readDataByFileHandleWithContext(ctx context.Context, buff []byte, fhIn *FileHandle, offset int64) (int64, error) {
|
|
// read data from source file
|
|
size := len(buff)
|
|
fhIn.lockForRead(offset, size)
|
|
defer fhIn.unlockForRead(offset, size)
|
|
|
|
n, tsNs, err := fhIn.readFromChunksWithContext(ctx, buff, offset)
|
|
if err == nil || err == io.EOF {
|
|
maxStop := fhIn.readFromDirtyPages(buff, offset, tsNs)
|
|
n = max(maxStop-offset, n)
|
|
}
|
|
if err == io.EOF {
|
|
err = nil
|
|
}
|
|
return n, err
|
|
}
|