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.
99 lines
3.2 KiB
Go
99 lines
3.2 KiB
Go
package erasure_coding
|
|
|
|
import (
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
)
|
|
|
|
type Interval struct {
|
|
BlockIndex int // the index of the block in either the large blocks or the small blocks
|
|
InnerBlockOffset int64
|
|
Size types.Size
|
|
IsLargeBlock bool // whether the block is a large block or a small block
|
|
LargeBlockRowsCount int
|
|
}
|
|
|
|
// LocateData finds the intervals of data within erasure coding blocks for a given offset and size.
|
|
func LocateData(largeBlockLength, smallBlockLength int64, shardDatSize int64, offset int64, size types.Size) (intervals []Interval) {
|
|
blockIndex, isLargeBlock, nLargeBlockRows, innerBlockOffset := locateOffset(largeBlockLength, smallBlockLength, shardDatSize, offset)
|
|
|
|
for size > 0 {
|
|
blockRemaining := largeBlockLength - innerBlockOffset
|
|
if !isLargeBlock {
|
|
blockRemaining = smallBlockLength - innerBlockOffset
|
|
}
|
|
|
|
if blockRemaining <= 0 {
|
|
// move to next block
|
|
blockIndex, isLargeBlock = moveToNextBlock(blockIndex, isLargeBlock, nLargeBlockRows)
|
|
innerBlockOffset = 0
|
|
continue
|
|
}
|
|
|
|
interval := Interval{
|
|
BlockIndex: blockIndex,
|
|
InnerBlockOffset: innerBlockOffset,
|
|
IsLargeBlock: isLargeBlock,
|
|
LargeBlockRowsCount: int(nLargeBlockRows),
|
|
}
|
|
|
|
if int64(size) <= blockRemaining {
|
|
interval.Size = size
|
|
intervals = append(intervals, interval)
|
|
return
|
|
}
|
|
interval.Size = types.Size(blockRemaining)
|
|
intervals = append(intervals, interval)
|
|
|
|
size -= interval.Size
|
|
blockIndex, isLargeBlock = moveToNextBlock(blockIndex, isLargeBlock, nLargeBlockRows)
|
|
innerBlockOffset = 0
|
|
|
|
}
|
|
return
|
|
}
|
|
|
|
func moveToNextBlock(blockIndex int, isLargeBlock bool, nLargeBlockRows int64) (int, bool) {
|
|
nextBlockIndex := blockIndex + 1
|
|
nextIsLargeBlock := isLargeBlock
|
|
if isLargeBlock && int64(nextBlockIndex) == nLargeBlockRows*DataShardsCount {
|
|
nextIsLargeBlock = false
|
|
nextBlockIndex = 0
|
|
}
|
|
return nextBlockIndex, nextIsLargeBlock
|
|
}
|
|
|
|
func locateOffset(largeBlockLength, smallBlockLength int64, shardDatSize int64, offset int64) (blockIndex int, isLargeBlock bool, nLargeBlockRows int64, innerBlockOffset int64) {
|
|
largeRowSize := largeBlockLength * DataShardsCount
|
|
nLargeBlockRows = shardDatSize / largeBlockLength
|
|
|
|
// if offset is within the large block area
|
|
if offset < nLargeBlockRows*largeRowSize {
|
|
isLargeBlock = true
|
|
blockIndex, innerBlockOffset = locateOffsetWithinBlocks(largeBlockLength, offset)
|
|
return
|
|
}
|
|
|
|
isLargeBlock = false
|
|
offset -= nLargeBlockRows * largeRowSize
|
|
blockIndex, innerBlockOffset = locateOffsetWithinBlocks(smallBlockLength, offset)
|
|
return
|
|
}
|
|
|
|
func locateOffsetWithinBlocks(blockLength int64, offset int64) (blockIndex int, innerBlockOffset int64) {
|
|
blockIndex = int(offset / blockLength)
|
|
innerBlockOffset = offset % blockLength
|
|
return
|
|
}
|
|
|
|
func (interval Interval) ToShardIdAndOffset(largeBlockSize, smallBlockSize int64) (ShardId, int64) {
|
|
ecFileOffset := interval.InnerBlockOffset
|
|
rowIndex := interval.BlockIndex / DataShardsCount
|
|
if interval.IsLargeBlock {
|
|
ecFileOffset += int64(rowIndex) * largeBlockSize
|
|
} else {
|
|
ecFileOffset += int64(interval.LargeBlockRowsCount)*largeBlockSize + int64(rowIndex)*smallBlockSize
|
|
}
|
|
ecFileIndex := interval.BlockIndex % DataShardsCount
|
|
return ShardId(ecFileIndex), ecFileOffset
|
|
}
|