Optimize zlib reader and consolidate sync.pools

Expands on the optimisations from https://github.com/fluxcd/go-git/pull/5
and ensures that zlib reader does not need to recreate a deflate
dictionary at every use.

The use of sync pools was consolidated into a new sync utils package.

name       old time/op    new time/op    delta
Parser-16    7.51ms ± 3%    7.71ms ± 6%     ~     (p=0.222 n=5+5)

name       old alloc/op   new alloc/op   delta
Parser-16    4.65MB ± 3%    1.90MB ± 3%  -59.06%  (p=0.008 n=5+5)

name       old allocs/op  new allocs/op  delta
Parser-16     3.48k ± 0%     3.32k ± 0%   -4.57%  (p=0.016 n=5+4)

Signed-off-by: Paulo Gomes <pjbgf@linux.com>

8 files changed, 80 insertions, 117 deletions

diff --git a/plumbing/format/objfile/reader.go b/plumbing/format/objfile/reader.go
index b6b2ca0..d7932f4 100644
--- a/plumbing/format/objfile/reader.go
+++ b/plumbing/format/objfile/reader.go
@@ -1,13 +1,13 @@
 package objfile
 
 import (
-	"compress/zlib"
 	"errors"
 	"io"
 	"strconv"
 
 	"github.com/go-git/go-git/v5/plumbing"
 	"github.com/go-git/go-git/v5/plumbing/format/packfile"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 var (
@@ -20,20 +20,22 @@ var (
 // Reader implements io.ReadCloser. Close should be called when finished with
 // the Reader. Close will not close the underlying io.Reader.
 type Reader struct {
-	multi  io.Reader
-	zlib   io.ReadCloser
-	hasher plumbing.Hasher
+	multi   io.Reader
+	zlib    io.Reader
+	zlibref sync.ZLibReader
+	hasher  plumbing.Hasher
 }
 
 // NewReader returns a new Reader reading from r.
 func NewReader(r io.Reader) (*Reader, error) {
-	zlib, err := zlib.NewReader(r)
+	zlib, err := sync.GetZlibReader(r)
 	if err != nil {
 		return nil, packfile.ErrZLib.AddDetails(err.Error())
 	}
 
 	return &Reader{
-		zlib: zlib,
+		zlib:    zlib.Reader,
+		zlibref: zlib,
 	}, nil
 }
 
@@ -110,5 +112,6 @@ func (r *Reader) Hash() plumbing.Hash {
 // Close releases any resources consumed by the Reader. Calling Close does not
 // close the wrapped io.Reader originally passed to NewReader.
 func (r *Reader) Close() error {
-	return r.zlib.Close()
+	sync.PutZlibReader(r.zlibref)
+	return nil
 }
diff --git a/plumbing/format/objfile/writer.go b/plumbing/format/objfile/writer.go
index 248f81b..0d0f154 100644
--- a/plumbing/format/objfile/writer.go
+++ b/plumbing/format/objfile/writer.go
@@ -5,9 +5,9 @@ import (
 	"errors"
 	"io"
 	"strconv"
-	"sync"
 
 	"github.com/go-git/go-git/v5/plumbing"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 var (
@@ -21,7 +21,7 @@ type Writer struct {
 	raw    io.Writer
 	hasher plumbing.Hasher
 	multi  io.Writer
-	zlib   io.WriteCloser
+	zlib   *zlib.Writer
 
 	closed  bool
 	pending int64 // number of unwritten bytes
@@ -32,21 +32,13 @@ type Writer struct {
 // The returned Writer implements io.WriteCloser. Close should be called when
 // finished with the Writer. Close will not close the underlying io.Writer.
 func NewWriter(w io.Writer) *Writer {
-	zlib := zlibPool.Get().(*zlib.Writer)
-	zlib.Reset(w)
-
+	zlib := sync.GetZlibWriter(w)
 	return &Writer{
 		raw:  w,
 		zlib: zlib,
 	}
 }
 
-var zlibPool = sync.Pool{
-	New: func() interface{} {
-		return zlib.NewWriter(nil)
-	},
-}
-
 // WriteHeader writes the type and the size and prepares to accept the object's
 // contents. If an invalid t is provided, plumbing.ErrInvalidType is returned. If a
 // negative size is provided, ErrNegativeSize is returned.
@@ -110,7 +102,7 @@ func (w *Writer) Hash() plumbing.Hash {
 // Calling Close does not close the wrapped io.Writer originally passed to
 // NewWriter.
 func (w *Writer) Close() error {
-	defer zlibPool.Put(w.zlib)
+	defer sync.PutZlibWriter(w.zlib)
 	if err := w.zlib.Close(); err != nil {
 		return err
 	}
diff --git a/plumbing/format/packfile/common.go b/plumbing/format/packfile/common.go
index df423ad..36c5ef5 100644
--- a/plumbing/format/packfile/common.go
+++ b/plumbing/format/packfile/common.go
@@ -1,10 +1,7 @@
 package packfile
 
 import (
-	"bytes"
-	"compress/zlib"
 	"io"
-	"sync"
 
 	"github.com/go-git/go-git/v5/plumbing/storer"
 	"github.com/go-git/go-git/v5/utils/ioutil"
@@ -61,18 +58,3 @@ func WritePackfileToObjectStorage(
 
 	return err
 }
-
-var bufPool = sync.Pool{
-	New: func() interface{} {
-		return bytes.NewBuffer(nil)
-	},
-}
-
-var zlibInitBytes = []byte{0x78, 0x9c, 0x01, 0x00, 0x00, 0xff, 0xff, 0x00, 0x00, 0x00, 0x01}
-
-var zlibReaderPool = sync.Pool{
-	New: func() interface{} {
-		r, _ := zlib.NewReader(bytes.NewReader(zlibInitBytes))
-		return r
-	},
-}
diff --git a/plumbing/format/packfile/diff_delta.go b/plumbing/format/packfile/diff_delta.go
index 1951b34..2c7a335 100644
--- a/plumbing/format/packfile/diff_delta.go
+++ b/plumbing/format/packfile/diff_delta.go
@@ -5,6 +5,7 @@ import (
 
 	"github.com/go-git/go-git/v5/plumbing"
 	"github.com/go-git/go-git/v5/utils/ioutil"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 // See https://github.com/jelmer/dulwich/blob/master/dulwich/pack.py and
@@ -43,18 +44,16 @@ func getDelta(index *deltaIndex, base, target plumbing.EncodedObject) (o plumbin
 
 	defer ioutil.CheckClose(tr, &err)
 
-	bb := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(bb)
-	bb.Reset()
+	bb := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(bb)
 
 	_, err = bb.ReadFrom(br)
 	if err != nil {
 		return nil, err
 	}
 
-	tb := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(tb)
-	tb.Reset()
+	tb := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(tb)
 
 	_, err = tb.ReadFrom(tr)
 	if err != nil {
@@ -80,9 +79,8 @@ func DiffDelta(src, tgt []byte) []byte {
 }
 
 func diffDelta(index *deltaIndex, src []byte, tgt []byte) []byte {
-	buf := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(buf)
-	buf.Reset()
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
 	buf.Write(deltaEncodeSize(len(src)))
 	buf.Write(deltaEncodeSize(len(tgt)))
 
@@ -90,9 +88,8 @@ func diffDelta(index *deltaIndex, src []byte, tgt []byte) []byte {
 		index.init(src)
 	}
 
-	ibuf := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(ibuf)
-	ibuf.Reset()
+	ibuf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(ibuf)
 	for i := 0; i < len(tgt); i++ {
 		offset, l := index.findMatch(src, tgt, i)
 
diff --git a/plumbing/format/packfile/packfile.go b/plumbing/format/packfile/packfile.go
index 8dd6041..6852702 100644
--- a/plumbing/format/packfile/packfile.go
+++ b/plumbing/format/packfile/packfile.go
@@ -2,7 +2,6 @@ package packfile
 
 import (
 	"bytes"
-	"compress/zlib"
 	"fmt"
 	"io"
 	"os"
@@ -13,6 +12,7 @@ import (
 	"github.com/go-git/go-git/v5/plumbing/format/idxfile"
 	"github.com/go-git/go-git/v5/plumbing/storer"
 	"github.com/go-git/go-git/v5/utils/ioutil"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 var (
@@ -138,9 +138,8 @@ func (p *Packfile) getObjectSize(h *ObjectHeader) (int64, error) {
 	case plumbing.CommitObject, plumbing.TreeObject, plumbing.BlobObject, plumbing.TagObject:
 		return h.Length, nil
 	case plumbing.REFDeltaObject, plumbing.OFSDeltaObject:
-		buf := bufPool.Get().(*bytes.Buffer)
-		defer bufPool.Put(buf)
-		buf.Reset()
+		buf := sync.GetBytesBuffer()
+		defer sync.PutBytesBuffer(buf)
 
 		if _, _, err := p.s.NextObject(buf); err != nil {
 			return 0, err
@@ -227,9 +226,9 @@ func (p *Packfile) getNextObject(h *ObjectHeader, hash plumbing.Hash) (plumbing.
 		// For delta objects we read the delta data and apply the small object
 		// optimization only if the expanded version of the object still meets
 		// the small object threshold condition.
-		buf := bufPool.Get().(*bytes.Buffer)
-		defer bufPool.Put(buf)
-		buf.Reset()
+		buf := sync.GetBytesBuffer()
+		defer sync.PutBytesBuffer(buf)
+
 		if _, _, err := p.s.NextObject(buf); err != nil {
 			return nil, err
 		}
@@ -290,14 +289,13 @@ func (p *Packfile) getObjectContent(offset int64) (io.ReadCloser, error) {
 
 func asyncReader(p *Packfile) (io.ReadCloser, error) {
 	reader := ioutil.NewReaderUsingReaderAt(p.file, p.s.r.offset)
-	zr := zlibReaderPool.Get().(io.ReadCloser)
-
-	if err := zr.(zlib.Resetter).Reset(reader, nil); err != nil {
+	zr, err := sync.GetZlibReader(reader)
+	if err != nil {
 		return nil, fmt.Errorf("zlib reset error: %s", err)
 	}
 
-	return ioutil.NewReadCloserWithCloser(zr, func() error {
-		zlibReaderPool.Put(zr)
+	return ioutil.NewReadCloserWithCloser(zr.Reader, func() error {
+		sync.PutZlibReader(zr)
 		return nil
 	}), nil
 
@@ -373,9 +371,9 @@ func (p *Packfile) fillRegularObjectContent(obj plumbing.EncodedObject) (err err
 }
 
 func (p *Packfile) fillREFDeltaObjectContent(obj plumbing.EncodedObject, ref plumbing.Hash) error {
-	buf := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(buf)
-	buf.Reset()
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
+
 	_, _, err := p.s.NextObject(buf)
 	if err != nil {
 		return err
@@ -417,9 +415,9 @@ func (p *Packfile) fillREFDeltaObjectContentWithBuffer(obj plumbing.EncodedObjec
 }
 
 func (p *Packfile) fillOFSDeltaObjectContent(obj plumbing.EncodedObject, offset int64) error {
-	buf := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(buf)
-	buf.Reset()
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
+
 	_, _, err := p.s.NextObject(buf)
 	if err != nil {
 		return err
diff --git a/plumbing/format/packfile/parser.go b/plumbing/format/packfile/parser.go
index 9ec838e..522c146 100644
--- a/plumbing/format/packfile/parser.go
+++ b/plumbing/format/packfile/parser.go
@@ -10,6 +10,7 @@ import (
 	"github.com/go-git/go-git/v5/plumbing/cache"
 	"github.com/go-git/go-git/v5/plumbing/storer"
 	"github.com/go-git/go-git/v5/utils/ioutil"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 var (
@@ -175,7 +176,8 @@ func (p *Parser) init() error {
 }
 
 func (p *Parser) indexObjects() error {
-	buf := new(bytes.Buffer)
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
 
 	for i := uint32(0); i < p.count; i++ {
 		buf.Reset()
@@ -219,6 +221,7 @@ func (p *Parser) indexObjects() error {
 			ota = newBaseObject(oh.Offset, oh.Length, t)
 		}
 
+		buf.Grow(int(oh.Length))
 		_, crc, err := p.scanner.NextObject(buf)
 		if err != nil {
 			return err
@@ -264,7 +267,9 @@ func (p *Parser) indexObjects() error {
 }
 
 func (p *Parser) resolveDeltas() error {
-	buf := &bytes.Buffer{}
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
+
 	for _, obj := range p.oi {
 		buf.Reset()
 		err := p.get(obj, buf)
@@ -346,9 +351,8 @@ func (p *Parser) get(o *objectInfo, buf *bytes.Buffer) (err error) {
 	}
 
 	if o.DiskType.IsDelta() {
-		b := bufPool.Get().(*bytes.Buffer)
-		defer bufPool.Put(b)
-		b.Reset()
+		b := sync.GetBytesBuffer()
+		defer sync.PutBytesBuffer(b)
 		err := p.get(o.Parent, b)
 		if err != nil {
 			return err
@@ -382,9 +386,8 @@ func (p *Parser) resolveObject(
 	if !o.DiskType.IsDelta() {
 		return nil
 	}
-	buf := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(buf)
-	buf.Reset()
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
 	err := p.readData(buf, o)
 	if err != nil {
 		return err
diff --git a/plumbing/format/packfile/patch_delta.go b/plumbing/format/packfile/patch_delta.go
index 053466d..f00562d 100644
--- a/plumbing/format/packfile/patch_delta.go
+++ b/plumbing/format/packfile/patch_delta.go
@@ -9,6 +9,7 @@ import (
 
 	"github.com/go-git/go-git/v5/plumbing"
 	"github.com/go-git/go-git/v5/utils/ioutil"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 // See https://github.com/git/git/blob/49fa3dc76179e04b0833542fa52d0f287a4955ac/delta.h
@@ -34,18 +35,16 @@ func ApplyDelta(target, base plumbing.EncodedObject, delta []byte) (err error) {
 
 	defer ioutil.CheckClose(w, &err)
 
-	buf := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(buf)
-	buf.Reset()
+	buf := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(buf)
 	_, err = buf.ReadFrom(r)
 	if err != nil {
 		return err
 	}
 	src := buf.Bytes()
 
-	dst := bufPool.Get().(*bytes.Buffer)
-	defer bufPool.Put(dst)
-	dst.Reset()
+	dst := sync.GetBytesBuffer()
+	defer sync.PutBytesBuffer(dst)
 	err = patchDelta(dst, src, delta)
 	if err != nil {
 		return err
@@ -53,10 +52,9 @@ func ApplyDelta(target, base plumbing.EncodedObject, delta []byte) (err error) {
 
 	target.SetSize(int64(dst.Len()))
 
-	bufp := byteSlicePool.Get().(*[]byte)
-	b := *bufp
-	_, err = io.CopyBuffer(w, dst, b)
-	byteSlicePool.Put(bufp)
+	b := sync.GetByteSlice()
+	_, err = io.CopyBuffer(w, dst, *b)
+	sync.PutByteSlice(b)
 	return err
 }
 
diff --git a/plumbing/format/packfile/scanner.go b/plumbing/format/packfile/scanner.go
index b655594..9ebb84a 100644
--- a/plumbing/format/packfile/scanner.go
+++ b/plumbing/format/packfile/scanner.go
@@ -3,17 +3,16 @@ package packfile
 import (
 	"bufio"
 	"bytes"
-	"compress/zlib"
 	"fmt"
 	"hash"
 	"hash/crc32"
 	"io"
 	stdioutil "io/ioutil"
-	"sync"
 
 	"github.com/go-git/go-git/v5/plumbing"
 	"github.com/go-git/go-git/v5/utils/binary"
 	"github.com/go-git/go-git/v5/utils/ioutil"
+	"github.com/go-git/go-git/v5/utils/sync"
 )
 
 var (
@@ -323,14 +322,14 @@ func (s *Scanner) NextObject(w io.Writer) (written int64, crc32 uint32, err erro
 // ReadObject returns a reader for the object content and an error
 func (s *Scanner) ReadObject() (io.ReadCloser, error) {
 	s.pendingObject = nil
-	zr := zlibReaderPool.Get().(io.ReadCloser)
+	zr, err := sync.GetZlibReader(s.r)
 
-	if err := zr.(zlib.Resetter).Reset(s.r, nil); err != nil {
+	if err != nil {
 		return nil, fmt.Errorf("zlib reset error: %s", err)
 	}
 
-	return ioutil.NewReadCloserWithCloser(zr, func() error {
-		zlibReaderPool.Put(zr)
+	return ioutil.NewReadCloserWithCloser(zr.Reader, func() error {
+		sync.PutZlibReader(zr)
 		return nil
 	}), nil
 }
@@ -338,28 +337,20 @@ func (s *Scanner) ReadObject() (io.ReadCloser, error) {
 // ReadRegularObject reads and write a non-deltified object
 // from it zlib stream in an object entry in the packfile.
 func (s *Scanner) copyObject(w io.Writer) (n int64, err error) {
-	zr := zlibReaderPool.Get().(io.ReadCloser)
-	defer zlibReaderPool.Put(zr)
+	zr, err := sync.GetZlibReader(s.r)
+	defer sync.PutZlibReader(zr)
 
-	if err = zr.(zlib.Resetter).Reset(s.r, nil); err != nil {
+	if err != nil {
 		return 0, fmt.Errorf("zlib reset error: %s", err)
 	}
 
-	defer ioutil.CheckClose(zr, &err)
-	bufp := byteSlicePool.Get().(*[]byte)
-	buf := *bufp
-	n, err = io.CopyBuffer(w, zr, buf)
-	byteSlicePool.Put(bufp)
+	defer ioutil.CheckClose(zr.Reader, &err)
+	buf := sync.GetByteSlice()
+	n, err = io.CopyBuffer(w, zr.Reader, *buf)
+	sync.PutByteSlice(buf)
 	return
 }
 
-var byteSlicePool = sync.Pool{
-	New: func() interface{} {
-		b := make([]byte, 32*1024)
-		return &b
-	},
-}
-
 // SeekFromStart sets a new offset from start, returns the old position before
 // the change.
 func (s *Scanner) SeekFromStart(offset int64) (previous int64, err error) {
@@ -389,10 +380,9 @@ func (s *Scanner) Checksum() (plumbing.Hash, error) {
 
 // Close reads the reader until io.EOF
 func (s *Scanner) Close() error {
-	bufp := byteSlicePool.Get().(*[]byte)
-	buf := *bufp
-	_, err := io.CopyBuffer(stdioutil.Discard, s.r, buf)
-	byteSlicePool.Put(bufp)
+	buf := sync.GetByteSlice()
+	_, err := io.CopyBuffer(stdioutil.Discard, s.r, *buf)
+	sync.PutByteSlice(buf)
 
 	return err
 }
@@ -403,13 +393,13 @@ func (s *Scanner) Flush() error {
 }
 
 // scannerReader has the following characteristics:
-// - Provides an io.SeekReader impl for bufio.Reader, when the underlying
-//   reader supports it.
-// - Keeps track of the current read position, for when the underlying reader
-//   isn't an io.SeekReader, but we still want to know the current offset.
-// - Writes to the hash writer what it reads, with the aid of a smaller buffer.
-//   The buffer helps avoid a performance penalty for performing small writes
-//   to the crc32 hash writer.
+//   - Provides an io.SeekReader impl for bufio.Reader, when the underlying
+//     reader supports it.
+//   - Keeps track of the current read position, for when the underlying reader
+//     isn't an io.SeekReader, but we still want to know the current offset.
+//   - Writes to the hash writer what it reads, with the aid of a smaller buffer.
+//     The buffer helps avoid a performance penalty for performing small writes
+//     to the crc32 hash writer.
 type scannerReader struct {
 	reader io.Reader
 	crc    io.Writer