cocos2dx Sprite使用同一张纹理会只调用一次渲染

cocos2dx3.x中，Sprite调用draw函数时会添加一个TrianglesCommand类型的渲染指令。

CCSprite.cpp

_trianglesCommand.init(_globalZOrder, 
            _texture, 
            getGLProgramState(), 
            _blendFunc, 
            _polyInfo.triangles, 
            transform, 
            flags);

        renderer->addCommand(&_trianglesCommand);

在render执行这个指令时，TrianglesCommand并不会立即执行opengl的渲染，而是把它添加到一个std::vector

CCRender.cpp

if( RenderCommand::Type::TRIANGLES_COMMAND == commandType)
    {
        // flush other queues
        flush3D();

        auto cmd = static_cast<TrianglesCommand*>(command);

        // flush own queue when buffer is full
        if(_filledVertex + cmd->getVertexCount() > VBO_SIZE || _filledIndex + cmd->getIndexCount() > INDEX_VBO_SIZE)
        {
            CCASSERT(cmd->getVertexCount()>= 0 && cmd->getVertexCount() < VBO_SIZE, "VBO for vertex is not big enough, please break the data down or use customized render command");
            CCASSERT(cmd->getIndexCount()>= 0 && cmd->getIndexCount() < INDEX_VBO_SIZE, "VBO for index is not big enough, please break the data down or use customized render command");
            drawBatchedTriangles();
        }

        // queue it
        _queuedTriangleCommands.push_back(cmd);
        _filledIndex += cmd->getIndexCount();
        _filledVertex += cmd->getVertexCount();
    }

这里做了一个限制，如果当前顶点缓冲区满了，就会立即执行opengl的渲染，所以当Sprite足够多时，虽然他们使用的是同一张纹理，也会调用多次渲染。

CCRender.cpp

void Renderer::drawBatchedTriangles()
{
    if(_queuedTriangleCommands.empty())
        return;

    CCGL_DEBUG_INSERT_EVENT_MARKER("RENDERER_BATCH_TRIANGLES");

    _filledVertex = 0;
    _filledIndex = 0;

    /************** 1: Setup up vertices/indices *************/

    _triBatchesToDraw[0].offset = 0;
    _triBatchesToDraw[0].indicesToDraw = 0;
    _triBatchesToDraw[0].cmd = nullptr;

    int batchesTotal = 0;
    int prevMaterialID = -1;
    bool firstCommand = true;

    for(auto it = std::begin(_queuedTriangleCommands); it != std::end(_queuedTriangleCommands); ++it)
    {
        const auto& cmd = *it;
        auto currentMaterialID = cmd->getMaterialID();
        const bool batchable = !cmd->isSkipBatching();

        fillVerticesAndIndices(cmd);

        // in the same batch ?
        if (batchable && (prevMaterialID == currentMaterialID || firstCommand))
        {
            CC_ASSERT(firstCommand || _triBatchesToDraw[batchesTotal].cmd->getMaterialID() == cmd->getMaterialID() && "argh... error in logic");
            _triBatchesToDraw[batchesTotal].indicesToDraw += cmd->getIndexCount();
            _triBatchesToDraw[batchesTotal].cmd = cmd;
        }
        else
        {
            // is this the first one?
            if (!firstCommand) {
                batchesTotal++;
                _triBatchesToDraw[batchesTotal].offset = _triBatchesToDraw[batchesTotal-1].offset + _triBatchesToDraw[batchesTotal-1].indicesToDraw;
            }

            _triBatchesToDraw[batchesTotal].cmd = cmd;
            _triBatchesToDraw[batchesTotal].indicesToDraw = (int) cmd->getIndexCount();

            // is this a single batch ? Prevent creating a batch group then
            if (!batchable)
                currentMaterialID = -1;
        }

        // capacity full ?
        if (batchesTotal + 1 >= _triBatchesToDrawCapacity) {
            _triBatchesToDrawCapacity *= 1.4;
            _triBatchesToDraw = (TriBatchToDraw*) realloc(_triBatchesToDraw, sizeof(_triBatchesToDraw[0]) * _triBatchesToDrawCapacity);
        }

        prevMaterialID = currentMaterialID;
        firstCommand = false;
    }
    batchesTotal++;

    /************** 2: Copy vertices/indices to GL objects *************/
    auto conf = Configuration::getInstance();
    if (conf->supportsShareableVAO() && conf->supportsMapBuffer())
    {
        //Bind VAO
        GL::bindVAO(_buffersVAO);
        //Set VBO data
        glBindBuffer(GL_ARRAY_BUFFER, _buffersVBO[0]);

        // option 1: subdata
// glBufferSubData(GL_ARRAY_BUFFER, sizeof(_quads[0])*start, sizeof(_quads[0]) * n , &_quads[start] );

        // option 2: data
// glBufferData(GL_ARRAY_BUFFER, sizeof(_verts[0]) * _filledVertex, _verts, GL_STATIC_DRAW);

        // option 3: orphaning + glMapBuffer
        // FIXME: in order to work as fast as possible, it must "and the exact same size and usage hints it had before."
        // source: https://www.opengl.org/wiki/Buffer_Object_Streaming#Explicit_multiple_buffering
        // so most probably we won't have any benefit of using it
        glBufferData(GL_ARRAY_BUFFER, sizeof(_verts[0]) * _filledVertex, nullptr, GL_STATIC_DRAW);
        void *buf = glMapBuffer(GL_ARRAY_BUFFER, GL_WRITE_ONLY);
        memcpy(buf, _verts, sizeof(_verts[0]) * _filledVertex);
        glUnmapBuffer(GL_ARRAY_BUFFER);

        glBindBuffer(GL_ARRAY_BUFFER, 0);

        glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, _buffersVBO[1]);
        glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(_indices[0]) * _filledIndex, _indices, GL_STATIC_DRAW);
    }
    else
    {
        // Client Side Arrays
#define kQuadSize sizeof(_verts[0])
        glBindBuffer(GL_ARRAY_BUFFER, _buffersVBO[0]);

        glBufferData(GL_ARRAY_BUFFER, sizeof(_verts[0]) * _filledVertex , _verts, GL_DYNAMIC_DRAW);

        GL::enableVertexAttribs(GL::VERTEX_ATTRIB_FLAG_POS_COLOR_TEX);

        // vertices
        glVertexAttribPointer(GLProgram::VERTEX_ATTRIB_POSITION, 3, GL_FLOAT, GL_FALSE, kQuadSize, (GLvoid*) offsetof(V3F_C4B_T2F, vertices));

        // colors
        glVertexAttribPointer(GLProgram::VERTEX_ATTRIB_COLOR, 4, GL_UNSIGNED_BYTE, GL_TRUE, kQuadSize, (GLvoid*) offsetof(V3F_C4B_T2F, colors));

        // tex coords
        glVertexAttribPointer(GLProgram::VERTEX_ATTRIB_TEX_COORD, 2, GL_FLOAT, GL_FALSE, kQuadSize, (GLvoid*) offsetof(V3F_C4B_T2F, texCoords));

        glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, _buffersVBO[1]);
        glBufferData(GL_ELEMENT_ARRAY_BUFFER, sizeof(_indices[0]) * _filledIndex, _indices, GL_STATIC_DRAW);
    }

    /************** 3: Draw *************/
    for (int i=0; i<batchesTotal; ++i)
    {
        CC_ASSERT(_triBatchesToDraw[i].cmd && "Invalid batch");
        _triBatchesToDraw[i].cmd->useMaterial();
        glDrawElements(GL_TRIANGLES, (GLsizei) _triBatchesToDraw[i].indicesToDraw, GL_UNSIGNED_SHORT, (GLvoid*) (_triBatchesToDraw[i].offset*sizeof(_indices[0])) );
        _drawnBatches++;
        _drawnVertices += _triBatchesToDraw[i].indicesToDraw;
    }

    /************** 4: Cleanup *************/
    if (Configuration::getInstance()->supportsShareableVAO())
    {
        //Unbind VAO
        GL::bindVAO(0);
    }
    else
    {
        glBindBuffer(GL_ARRAY_BUFFER, 0);
        glBindBuffer(GL_ELEMENT_ARRAY_BUFFER, 0);
    }

    _queuedTriangleCommands.clear();
    _filledVertex = 0;
    _filledIndex = 0;
}

这个函数就是用来绘制TriangleCommand指令的，这里出现了一个新的类型TriBatchToDraw

struct TriBatchToDraw {
        TrianglesCommand* cmd;  // needed for the Material
        GLushort indicesToDraw;
        GLushort offset;
    };

TriBatchToDraw 有三个成员变量，渲染指令cmd，需要渲染的顶点数量indicesToDraw，顶点数据在顶点缓冲区初始的偏移位置offset 如果一个渲染指令的MaterialID和上一个指令的MaterialID相等，就会把两条渲染指令整合到一起，如果两条指令使用了相同的MaterialID但是两条指令不连续，就不会整合到一个渲染指令里。 所以cocos2dx的Sprite使用同一张纹理时，必须是连续添加到父节点，中间不会有使用其他纹理的Sprite添加到父节点，才会达到SpriteBatchNode的效果