frostfs-node/pkg/local_object_storage/blobstor/compression/compress.go

119 lines
2.9 KiB
Go
Raw Permalink Normal View History

package compression
import (
"bytes"
"strings"
objectSDK "git.frostfs.info/TrueCloudLab/frostfs-sdk-go/object"
"github.com/klauspost/compress"
"github.com/klauspost/compress/zstd"
)
// Config represents common compression-related configuration.
type Config struct {
Enabled bool
UncompressableContentTypes []string
UseCompressEstimation bool
CompressEstimationThreshold float64
encoder *zstd.Encoder
decoder *zstd.Decoder
}
// zstdFrameMagic contains first 4 bytes of any compressed object
// https://github.com/klauspost/compress/blob/master/zstd/framedec.go#L58 .
var zstdFrameMagic = []byte{0x28, 0xb5, 0x2f, 0xfd}
// Init initializes compression routines.
func (c *Config) Init() error {
var err error
if c.Enabled {
c.encoder, err = zstd.NewWriter(nil)
if err != nil {
return err
}
}
c.decoder, err = zstd.NewReader(nil)
return err
}
// NeedsCompression returns true if the object should be compressed.
// For an object to be compressed 2 conditions must hold:
// 1. Compression is enabled in settings.
// 2. Object MIME Content-Type is allowed for compression.
func (c *Config) NeedsCompression(obj *objectSDK.Object) bool {
if !c.Enabled || len(c.UncompressableContentTypes) == 0 {
return c.Enabled
}
for _, attr := range obj.Attributes() {
if attr.Key() == objectSDK.AttributeContentType {
for _, value := range c.UncompressableContentTypes {
match := false
switch {
case len(value) > 0 && value[len(value)-1] == '*':
match = strings.HasPrefix(attr.Value(), value[:len(value)-1])
case len(value) > 0 && value[0] == '*':
match = strings.HasSuffix(attr.Value(), value[1:])
default:
match = attr.Value() == value
}
if match {
return false
}
}
}
}
return c.Enabled
}
// Decompress decompresses data if it starts with the magic
// and returns data untouched otherwise.
func (c *Config) Decompress(data []byte) ([]byte, error) {
if len(data) < 4 || !bytes.Equal(data[:4], zstdFrameMagic) {
return data, nil
}
return c.decoder.DecodeAll(data, nil)
}
// Compress compresses data if compression is enabled
// and returns data untouched otherwise.
func (c *Config) Compress(data []byte) []byte {
if c == nil || !c.Enabled {
return data
}
if c.UseCompressEstimation {
estimated := compress.Estimate(data)
if estimated >= c.CompressEstimationThreshold {
return c.compress(data)
}
return data
}
return c.compress(data)
}
func (c *Config) compress(data []byte) []byte {
[#2184] compression: Properly calculate upper bound If the data is not compressible allocating `len(data)` will lead to a slice reallocation. For a compressible data the results for small size are flaky and we allocate a bit more. However, it feels right to use a provided function if we need to pick any size at all. ``` name old time/op new time/op delta Compression/size=128/zeroed_slice-8 2.23µs ±12% 2.06µs ± 6% -7.35% (p=0.009 n=10+10) Compression/size=128/not_so_random_slice_(block_=_123)-8 19.0µs ±10% 15.8µs ±16% -17.09% (p=0.000 n=9+10) Compression/size=128/random_slice-8 17.6µs ±15% 16.1µs ±16% ~ (p=0.075 n=10+10) Compression/size=1024/zeroed_slice-8 3.05µs ±11% 2.84µs ±10% ~ (p=0.089 n=10+10) Compression/size=1024/not_so_random_slice_(block_=_123)-8 18.1µs ± 6% 18.2µs ±12% ~ (p=0.971 n=10+10) Compression/size=1024/random_slice-8 48.6µs ± 6% 45.6µs ± 5% -6.07% (p=0.006 n=10+9) Compression/size=32768/zeroed_slice-8 26.8µs ± 3% 28.7µs ± 8% +7.23% (p=0.001 n=10+10) Compression/size=32768/not_so_random_slice_(block_=_123)-8 44.3µs ± 8% 43.7µs ±13% ~ (p=0.762 n=8+10) Compression/size=32768/random_slice-8 97.3µs ±32% 68.9µs ±15% -29.13% (p=0.000 n=10+10) Compression/size=33554432/zeroed_slice-8 29.8ms ± 9% 30.3ms ±17% ~ (p=1.000 n=9+9) Compression/size=33554432/not_so_random_slice_(block_=_123)-8 33.1ms ±14% 30.3ms ±11% -8.61% (p=0.043 n=10+10) Compression/size=33554432/random_slice-8 41.7ms ± 3% 30.1ms ± 8% -27.72% (p=0.000 n=9+10) name old alloc/op new alloc/op delta Compression/size=128/zeroed_slice-8 128B ± 0% 144B ± 0% +12.50% (p=0.000 n=10+10) Compression/size=128/not_so_random_slice_(block_=_123)-8 384B ± 0% 144B ± 0% -62.50% (p=0.000 n=10+10) Compression/size=128/random_slice-8 384B ± 0% 144B ± 0% -62.50% (p=0.000 n=10+10) Compression/size=1024/zeroed_slice-8 1.02kB ± 0% 1.15kB ± 0% +12.50% (p=0.000 n=10+10) Compression/size=1024/not_so_random_slice_(block_=_123)-8 1.02kB ± 0% 1.15kB ± 0% +12.50% (p=0.000 n=10+10) Compression/size=1024/random_slice-8 2.56kB ± 0% 1.15kB ± 0% -55.00% (p=0.000 n=10+10) Compression/size=32768/zeroed_slice-8 32.8kB ± 0% 41.0kB ± 0% +25.00% (p=0.000 n=10+10) Compression/size=32768/not_so_random_slice_(block_=_123)-8 32.8kB ± 0% 41.0kB ± 0% +25.00% (p=0.000 n=10+10) Compression/size=32768/random_slice-8 81.9kB ± 0% 41.0kB ± 0% -50.00% (p=0.000 n=10+10) Compression/size=33554432/zeroed_slice-8 33.6MB ± 0% 33.6MB ± 0% +0.02% (p=0.000 n=9+9) Compression/size=33554432/not_so_random_slice_(block_=_123)-8 33.6MB ± 0% 33.6MB ± 0% +0.02% (p=0.000 n=8+10) Compression/size=33554432/random_slice-8 75.5MB ± 0% 33.6MB ± 0% -55.55% (p=0.000 n=10+10) name old allocs/op new allocs/op delta Compression/size=128/zeroed_slice-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=128/not_so_random_slice_(block_=_123)-8 2.00 ± 0% 1.00 ± 0% -50.00% (p=0.000 n=10+10) Compression/size=128/random_slice-8 2.00 ± 0% 1.00 ± 0% -50.00% (p=0.000 n=10+10) Compression/size=1024/zeroed_slice-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=1024/not_so_random_slice_(block_=_123)-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=1024/random_slice-8 2.00 ± 0% 1.00 ± 0% -50.00% (p=0.000 n=10+10) Compression/size=32768/zeroed_slice-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=32768/not_so_random_slice_(block_=_123)-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=32768/random_slice-8 2.00 ± 0% 1.00 ± 0% -50.00% (p=0.000 n=10+10) Compression/size=33554432/zeroed_slice-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=33554432/not_so_random_slice_(block_=_123)-8 1.00 ± 0% 1.00 ± 0% ~ (all equal) Compression/size=33554432/random_slice-8 2.00 ± 0% 1.00 ± 0% -50.00% (p=0.000 n=10+10) ``` Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-28 12:47:58 +00:00
maxSize := c.encoder.MaxEncodedSize(len(data))
compressed := c.encoder.EncodeAll(data, make([]byte, 0, maxSize))
if len(data) < len(compressed) {
return data
}
return compressed
}
// Close closes encoder and decoder, returns any error occurred.
func (c *Config) Close() error {
var err error
if c.encoder != nil {
err = c.encoder.Close()
}
if c.decoder != nil {
c.decoder.Close()
}
return err
}