From 16108ced954d1c517f5beb37f7158b16f7c0ec93 Mon Sep 17 00:00:00 2001
From: Lei Xue <vfs@live.com>
Date: Sat, 14 Mar 2026 19:03:30 +0800
Subject: [PATCH] optimize performance: reduce allocations, buffered I/O, and
 zero-copy reads

- Read path: eliminate redundant allocation in bsPerformCommand - remove
  the pre-allocation before bs.Read() and the append loop for zero-fill,
  use direct copy and in-place zero-fill instead
- parseHeader: use command pool (getCommand) instead of direct allocation,
  reducing GC pressure on the hot path
- Unmap: use a shared 1MB zero buffer instead of allocating per-descriptor,
  dramatically reducing allocations for large unmap operations
- Network I/O: add 256KB bufio.Writer to iSCSI connections, batching
  small PDU writes into fewer syscalls. Flush after txHandler completes

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 pkg/port/iscsit/cmd.go          |  3 +--
 pkg/port/iscsit/conn.go         | 10 +++++++++-
 pkg/port/iscsit/iscsid.go       |  7 +++++++
 pkg/scsi/backingstore.go        | 10 ++++++----
 pkg/scsi/backingstore/common.go | 21 ++++++++++++++++++---
 5 files changed, 41 insertions(+), 10 deletions(-)

diff --git a/pkg/port/iscsit/cmd.go b/pkg/port/iscsit/cmd.go
index 51f90bc..55be0de 100644
--- a/pkg/port/iscsit/cmd.go
+++ b/pkg/port/iscsit/cmd.go
@@ -312,8 +312,7 @@ func parseHeader(data []byte) (*ISCSICommand, error) {
 	if len(data) != BHS_SIZE {
 		return nil, fmt.Errorf("garbled header")
 	}
-	// TODO: sync.Pool
-	m := &ISCSICommand{}
+	m := getCommand()
 	m.Immediate = 0x40&data[0] == 0x40
 	m.OpCode = OpCode(data[0] & ISCSI_OPCODE_MASK)
 	m.Final = 0x80&data[1] == 0x80
diff --git a/pkg/port/iscsit/conn.go b/pkg/port/iscsit/conn.go
index 5535214..19fb165 100644
--- a/pkg/port/iscsit/conn.go
+++ b/pkg/port/iscsit/conn.go
@@ -17,6 +17,7 @@ limitations under the License.
 package iscsit
 
 import (
+	"bufio"
 	"io"
 	"net"
 	"sort"
@@ -61,6 +62,7 @@ type iscsiConnection struct {
 	txIOState int
 	refcount  int
 	conn      net.Conn
+	writer    *bufio.Writer
 
 	rxBuffer []byte
 	txBuffer []byte
@@ -117,6 +119,7 @@ func (c *iscsiConnection) init() {
 	c.state = CONN_STATE_FREE
 	c.refcount = 1
 	c.readLock = new(sync.RWMutex)
+	c.writer = bufio.NewWriterSize(c.conn, 256*1024)
 	c.loginParam.sessionParam = []ISCSISessionParam{}
 	c.loginParam.tgtCSG = LoginOperationalNegotiation
 	c.loginParam.tgtNSG = LoginOperationalNegotiation
@@ -136,10 +139,15 @@ func (c *iscsiConnection) readData(buf []byte) (int, error) {
 }
 
 func (c *iscsiConnection) write(resp []byte) (int, error) {
-	return c.conn.Write(resp)
+	return c.writer.Write(resp)
+}
+
+func (c *iscsiConnection) flush() error {
+	return c.writer.Flush()
 }
 
 func (c *iscsiConnection) close() {
+	c.writer.Flush()
 	c.conn.Close()
 }
 
diff --git a/pkg/port/iscsit/iscsid.go b/pkg/port/iscsit/iscsid.go
index 84d35c9..fb35a89 100644
--- a/pkg/port/iscsit/iscsid.go
+++ b/pkg/port/iscsit/iscsid.go
@@ -830,6 +830,13 @@ SendRemainingData:
 		}
 	}
 
+	// Flush buffered writes to the network
+	if err := conn.flush(); err != nil {
+		log.Errorf("failed to flush data to client: %v", err)
+		conn.state = CONN_STATE_CLOSE
+		return
+	}
+
 	log.Debugf("connection state: %v", conn.State())
 	switch conn.state {
 	case CONN_STATE_CLOSE, CONN_STATE_EXIT:
diff --git a/pkg/scsi/backingstore.go b/pkg/scsi/backingstore.go
index 01f781c..38956f2 100644
--- a/pkg/scsi/backingstore.go
+++ b/pkg/scsi/backingstore.go
@@ -109,7 +109,6 @@ func bsPerformCommand(bs api.BackingStore, cmd *api.SCSICommand) (err error, key
 		// TODO
 		break
 	case api.READ_6, api.READ_10, api.READ_12, api.READ_16:
-		rbuf = make([]byte, int(tl))
 		rbuf, err = bs.Read(int64(offset), tl)
 		if err != nil && err != io.EOF {
 			key = MEDIUM_ERROR
@@ -117,9 +116,6 @@ func bsPerformCommand(bs api.BackingStore, cmd *api.SCSICommand) (err error, key
 			break
 		}
 		length = len(rbuf)
-		for i := 0; i < int(tl)-length; i++ {
-			rbuf = append(rbuf, 0)
-		}
 
 		if (opcode != api.READ_6) && (scb[1]&0x10 != 0) {
 			bs.DataAdvise(int64(offset), int64(length), util.POSIX_FADV_NOREUSE)
@@ -131,6 +127,12 @@ func bsPerformCommand(bs api.BackingStore, cmd *api.SCSICommand) (err error, key
 			goto sense
 		}
 		copy(cmd.InSDBBuffer.Buffer, rbuf)
+		// Zero-fill any remaining bytes if read was short
+		if length < int(tl) {
+			for i := length; i < int(tl) && i < len(cmd.InSDBBuffer.Buffer); i++ {
+				cmd.InSDBBuffer.Buffer[i] = 0
+			}
+		}
 	case api.PRE_FETCH_10, api.PRE_FETCH_16:
 		err = bs.DataAdvise(int64(offset), tl, util.POSIX_FADV_WILLNEED)
 		if err != nil {
diff --git a/pkg/scsi/backingstore/common.go b/pkg/scsi/backingstore/common.go
index f8abfe3..0232bac 100644
--- a/pkg/scsi/backingstore/common.go
+++ b/pkg/scsi/backingstore/common.go
@@ -159,11 +159,26 @@ func (bs *FileBackingStore) DataAdvise(offset, length int64, advise uint32) erro
 	return util.Fadvise(bs.file, offset, length, advise)
 }
 
+// unmapZeroBufSize is the size of the reusable zero buffer for unmap operations.
+const unmapZeroBufSize = 1 << 20 // 1MB
+
+// unmapZeroBuf is a pre-allocated zero buffer shared across unmap calls.
+var unmapZeroBuf = make([]byte, unmapZeroBufSize)
+
 func (bs *FileBackingStore) Unmap(descriptors []api.UnmapBlockDescriptor) error {
 	for _, desc := range descriptors {
-		zeros := make([]byte, desc.TL)
-		if _, err := bs.file.WriteAt(zeros, int64(desc.Offset)); err != nil {
-			return err
+		remaining := desc.TL
+		off := int64(desc.Offset)
+		for remaining > 0 {
+			writeLen := remaining
+			if writeLen > unmapZeroBufSize {
+				writeLen = unmapZeroBufSize
+			}
+			if _, err := bs.file.WriteAt(unmapZeroBuf[:writeLen], off); err != nil {
+				return err
+			}
+			off += int64(writeLen)
+			remaining -= writeLen
 		}
 	}
 	return nil