Integrate zstd compression into chain exchange #842
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,86 @@ | ||
| package encoding | ||
|
|
||
| import ( | ||
| "bytes" | ||
| "fmt" | ||
|
|
||
| "github.com/klauspost/compress/zstd" | ||
| cbg "github.com/whyrusleeping/cbor-gen" | ||
| ) | ||
|
|
||
| // maxDecompressedSize is the default maximum amount of memory allocated by the | ||
| // zstd decoder. The limit of 1MiB is chosen based on the default maximum message | ||
| // size in GossipSub. | ||
| const maxDecompressedSize = 1 << 20 | ||
|
|
||
| type CBORMarshalUnmarshaler interface { | ||
| cbg.CBORMarshaler | ||
| cbg.CBORUnmarshaler | ||
| } | ||
|
|
||
| type EncodeDecoder[T CBORMarshalUnmarshaler] interface { | ||
| Encode(v T) ([]byte, error) | ||
| Decode([]byte, T) error | ||
| } | ||
|
|
||
| type CBOR[T CBORMarshalUnmarshaler] struct{} | ||
|
|
||
| func NewCBOR[T CBORMarshalUnmarshaler]() *CBOR[T] { | ||
| return &CBOR[T]{} | ||
| } | ||
|
|
||
| func (c *CBOR[T]) Encode(m T) ([]byte, error) { | ||
| var buf bytes.Buffer | ||
| if err := m.MarshalCBOR(&buf); err != nil { | ||
| return nil, err | ||
| } | ||
| return buf.Bytes(), nil | ||
| } | ||
|
|
||
| func (c *CBOR[T]) Decode(v []byte, t T) error { | ||
| r := bytes.NewReader(v) | ||
| return t.UnmarshalCBOR(r) | ||
| } | ||
|
|
||
| type ZSTD[T CBORMarshalUnmarshaler] struct { | ||
| cborEncoding *CBOR[T] | ||
| compressor *zstd.Encoder | ||
| decompressor *zstd.Decoder | ||
| } | ||
|
|
||
| func NewZSTD[T CBORMarshalUnmarshaler]() (*ZSTD[T], error) { | ||
| writer, err := zstd.NewWriter(nil) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| reader, err := zstd.NewReader(nil, zstd.WithDecoderMaxMemory(maxDecompressedSize)) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| return &ZSTD[T]{ | ||
| cborEncoding: &CBOR[T]{}, | ||
| compressor: writer, | ||
| decompressor: reader, | ||
| }, nil | ||
| } | ||
|
|
||
| func (c *ZSTD[T]) Encode(m T) ([]byte, error) { | ||
| cborEncoded, err := c.cborEncoding.Encode(m) | ||
| if len(cborEncoded) > maxDecompressedSize { | ||
| // Error out early if the encoded value is too large to be decompressed. | ||
| return nil, fmt.Errorf("encoded value cannot exceed maximum size: %d > %d", len(cborEncoded), maxDecompressedSize) | ||
| } | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
| compressed := c.compressor.EncodeAll(cborEncoded, make([]byte, 0, len(cborEncoded))) | ||
| return compressed, nil | ||
| } | ||
|
|
||
| func (c *ZSTD[T]) Decode(v []byte, t T) error { | ||
| cborEncoded, err := c.decompressor.DecodeAll(v, make([]byte, 0, len(v))) | ||
|
There was a problem hiding this comment. Future change: we should use a buffer pool for these short-lived buffers (https://pkg.go.dev/sync#Pool). If we do that, we can also allocate these buffers with 1MiB capacities and use |
||
| if err != nil { | ||
| return err | ||
| } | ||
| return c.cborEncoding.Decode(cborEncoded, t) | ||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Are we going with ZSTD by default?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
For chain exchange yes. For GPBFT it's configurable via manifest.
Happy to make it configurable for chain exchange too if you think it's worth doing.