Sort算子落盘性能太慢，希望产品层面进行优化

这个最大的耗时应该在从磁盘拿数据的时候是一次IO是一行中的一个column获取数据导致的性能瓶颈，如果一次获取是一个chunk，效率上应该会好很多。

// GetRowAndAppendToChunk gets a Row from the ListInDisk by RowPtr. Return the Row and the Ref Chunk.
func (l *ListInDisk) GetRowAndAppendToChunk(ptr RowPtr, chk *Chunk) (row Row, _ *Chunk, err error) {
	off, err := l.getOffset(ptr.ChkIdx, ptr.RowIdx)
	if err != nil {
		return
	}
	r := l.dataFile.getSectionReader(off)
	format := rowInDisk{numCol: len(l.fieldTypes)}
	_, err = format.ReadFrom(r)
	if err != nil {
		return row, nil, err
	}
	row, chk = format.toRow(l.fieldTypes, chk)
	return row, chk, err
}

// ReadFrom reads data of r, deserializes it from the format of diskFormatRow
// into Row.
func (row *rowInDisk) ReadFrom(r io.Reader) (n int64, err error) {
	b := make([]byte, 8*row.numCol)
	var n1 int
	n1, err = io.ReadFull(r, b)
	n += int64(n1)
	if err != nil {
		return
	}
	row.sizesOfColumns = bytesToI64Slice(b)
	row.cells = make([][]byte, 0, row.numCol)
	for _, size := range row.sizesOfColumns {
		if size == -1 {
			continue
		}
		cell := make([]byte, size)
		row.cells = append(row.cells, cell)
		n1, err = io.ReadFull(r, cell)
		n += int64(n1)
		if err != nil {
			return
		}
	}
	return
}