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.
93 lines
2.2 KiB
Go
93 lines
2.2 KiB
Go
package chunk_cache
|
|
|
|
import (
|
|
"fmt"
|
|
"path"
|
|
"slices"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
)
|
|
|
|
type OnDiskCacheLayer struct {
|
|
diskCaches []*ChunkCacheVolume
|
|
}
|
|
|
|
func NewOnDiskCacheLayer(dir, namePrefix string, diskSize int64, segmentCount int) *OnDiskCacheLayer {
|
|
|
|
volumeCount, volumeSize := int(diskSize/(30000*1024*1024)), int64(30000*1024*1024)
|
|
if volumeCount < segmentCount {
|
|
volumeCount, volumeSize = segmentCount, diskSize/int64(segmentCount)
|
|
}
|
|
|
|
c := &OnDiskCacheLayer{}
|
|
for i := 0; i < volumeCount; i++ {
|
|
fileName := path.Join(dir, fmt.Sprintf("%s_%d", namePrefix, i))
|
|
diskCache, err := LoadOrCreateChunkCacheVolume(fileName, volumeSize)
|
|
if err != nil {
|
|
glog.Errorf("failed to add cache %s : %v", fileName, err)
|
|
} else {
|
|
c.diskCaches = append(c.diskCaches, diskCache)
|
|
}
|
|
}
|
|
|
|
// keep newest cache to the front
|
|
slices.SortFunc(c.diskCaches, func(a, b *ChunkCacheVolume) int {
|
|
return b.lastModTime.Compare(a.lastModTime)
|
|
})
|
|
return c
|
|
}
|
|
|
|
func (c *OnDiskCacheLayer) setChunk(needleId types.NeedleId, data []byte) {
|
|
|
|
if len(c.diskCaches) == 0 {
|
|
return
|
|
}
|
|
|
|
if c.diskCaches[0].fileSize+int64(len(data)) > c.diskCaches[0].sizeLimit {
|
|
t, resetErr := c.diskCaches[len(c.diskCaches)-1].Reset()
|
|
if resetErr != nil {
|
|
glog.Errorf("failed to reset cache file %s", c.diskCaches[len(c.diskCaches)-1].fileName)
|
|
return
|
|
}
|
|
for i := len(c.diskCaches) - 1; i > 0; i-- {
|
|
c.diskCaches[i] = c.diskCaches[i-1]
|
|
}
|
|
c.diskCaches[0] = t
|
|
}
|
|
|
|
if err := c.diskCaches[0].WriteNeedle(needleId, data); err != nil {
|
|
glog.V(0).Infof("cache write %v size %d: %v", needleId, len(data), err)
|
|
}
|
|
|
|
}
|
|
|
|
func (c *OnDiskCacheLayer) readChunkAt(buffer []byte, needleId types.NeedleId, offset uint64) (n int, err error) {
|
|
|
|
for _, diskCache := range c.diskCaches {
|
|
n, err = diskCache.readNeedleSliceAt(buffer, needleId, offset)
|
|
if err == storage.ErrorNotFound {
|
|
continue
|
|
}
|
|
if err != nil {
|
|
glog.Warningf("failed to read cache file %s id %d: %v", diskCache.fileName, needleId, err)
|
|
continue
|
|
}
|
|
if n > 0 {
|
|
return
|
|
}
|
|
}
|
|
|
|
return
|
|
|
|
}
|
|
|
|
func (c *OnDiskCacheLayer) shutdown() {
|
|
|
|
for _, diskCache := range c.diskCaches {
|
|
diskCache.Shutdown()
|
|
}
|
|
|
|
}
|