MediaCodec.dequeueOutputBuffer demora muito tempo ao codificar h264 no Android

Estou tentando codificar o vídeo h264 no Android para streaming de vídeo em tempo real usando o MediaCodec, mas o dequeueOutputBuffer continua demorando muito tempo (na verdade, é muito rápido às vezes, mas muito lento em outros momentos, veja a saída do log abaixo). Eu já vi até 200ms para o buffer de saída estar pronto. Existe algo que estou fazendo de errado com meu código ou você acha que esse é um problema com o OMX.Nvidia.h264.encoder?

Talvez eu precise diminuir o tamanho da imagem de 1280x720 para algo menor? Ou talvez eu precise desenfileirar e enfileirar mais buffers de entrada enquanto aguardo o buffer de saída? (Existem 6 buffers de entrada e 6 de saída disponíveis). Estou usando a API 19 do Android, portanto não posso usar o método de processamento assíncrono do MediaCodec. Na verdade, estou transmitindo uma imagem de um tablet do Google Project Tango, então minha outra suspeita é que talvez as operações em segundo plano do Tango estejam demorando muito e fazendo com que o codificador fique lento. Alguma idéia sobre o que pode estar atrasando tanto isso?

01-20 23:36:30.728 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 0.400666ms.
01-20 23:36:30.855 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 94.290667ms.
01-20 23:36:30.880 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 0.57ms.
01-20 23:36:30.929 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 4.878417ms.
01-20 23:36:31.042 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 77.495417ms.
01-20 23:36:31.064 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 0.3225ms.
01-20 23:36:31.182 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 74.777583ms.
01-20 23:36:31.195 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 0.23ms.
01-20 23:36:31.246 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 17.243583ms.
01-20 23:36:31.350 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 80.14725ms.
01-20 23:36:31.373 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 2.493834ms.
01-20 23:36:31.421 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 13.273ms.
01-20 23:36:31.546 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 93.543667ms.
01-20 23:36:31.576 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 5.309334ms.
01-20 23:36:31.619 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 13.402583ms.
01-20 23:36:31.686 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 22.5485ms.
01-20 23:36:31.809 2920-3014/com.... D/StreamingThread: dequeueOutputBuffer took 91.392083ms.

Meu código relevante é o seguinte:

public class StreamingThread extends Thread {
    ...

    // encoding
    private MediaCodec mVideoEncoder = null;
    private ByteBuffer[] mEncoderInputBuffers = null;
    private ByteBuffer[] mEncoderOutputBuffers = null;
    private NV21Convertor mNV21Converter = null;

    public static native VideoFrame getNewFrame();

    public StreamingThread()
    {
        this.setPriority(MAX_PRIORITY);
    }

    @Override
    public void run()
    {
        Looper.prepare();
        init();
        Looper.loop();
    }

    private void init()
    {
        mHandler = new Handler() {
            public void handleMessage(Message msg) {
                // process incoming messages here
                switch(msg.what)
                {
                    case HAVE_NEW_FRAME: // new frame has arrived (signaled from main thread)
                        processBufferedFrames();
                        break;

                    case CLOSE_THREAD:
                        close();
                        break;

                    default:
                        Log.e(LOGTAG, "received unknown message!");
                }
            }
        };

        try {
            ...
            // set up video encoding
            final String mime = "video/avc"; // H.264/AVC
            listAvailableEncoders(mime); // (this creates some debug output only)
            String codec = "OMX.Nvidia.h264.encoder"; // instead, hard-code the codec we want to use for now

            mVideoEncoder = MediaCodec.createByCodecName(codec);
            if(mVideoEncoder == null)
                Log.e(LOGTAG, "Media codec " + codec + " is not available!");

            // TODO: change, based on what we're streaming...
            int FRAME_WIDTH = 1280;
            int FRAME_HEIGHT = 720;

            // https://github.com/fyhertz/libstreaming/blob/ac44416d88ed3112869ef0f7eab151a184bbb78d/src/net/majorkernelpanic/streaming/hw/EncoderDebugger.java
            mNV21Converter = new NV21Convertor();
            mNV21Converter.setSize(FRAME_WIDTH, FRAME_HEIGHT);
            mNV21Converter.setEncoderColorFormat(MediaCodecInfo.CodecCapabilities.COLOR_FormatYUV420Planar);
            mNV21Converter.setColorPanesReversed(true);
            mNV21Converter.setYPadding(0);

            MediaFormat format = MediaFormat.createVideoFormat(mime, FRAME_WIDTH, FRAME_HEIGHT);
            format.setInteger(MediaFormat.KEY_FRAME_RATE, 25);
            format.setInteger(MediaFormat.KEY_I_FRAME_INTERVAL, 10);
            format.setInteger(MediaFormat.KEY_COLOR_FORMAT, MediaCodecInfo.CodecCapabilities.COLOR_FormatYUV420Planar);
            // TODO: optimize bit rate
            format.setInteger(MediaFormat.KEY_BIT_RATE, 250000); // 4 Million bits/second = 0.48 Megabytes/s

            mVideoEncoder.configure(format, null, null, MediaCodec.CONFIGURE_FLAG_ENCODE);
            mVideoEncoder.start();
            mEncoderInputBuffers  = mVideoEncoder.getInputBuffers();
            mEncoderOutputBuffers = mVideoEncoder.getOutputBuffers();

            Log.d(LOGTAG, "Number of input buffers " + mEncoderInputBuffers.length);
            Log.d(LOGTAG, "Number of output buffers " + mEncoderOutputBuffers.length);

            initialized = true;

        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    private void close()
    {
        Looper.myLooper().quit();
        mVideoEncoder.stop();
        mVideoEncoder.release();
        mVideoEncoder = null;
    }

    private void processBufferedFrames()
    {
        if (!initialized)
            return;
        VideoFrame frame = getNewFrame();

        try {
            sendTCPFrame(frame);

        } catch (Exception e) {
            e.printStackTrace();
        }
    }
    private void sendTCPFrame(VideoFrame frame)
    {
        long start = System.nanoTime();

        long start2 = System.nanoTime();
        int inputBufferIndex = -1;
        while((inputBufferIndex = mVideoEncoder.dequeueInputBuffer(-1)) < 0 ) { // -1: wait indefinitely for the buffer
            switch(inputBufferIndex) {
                default:
                    Log.e(LOGTAG, "dequeueInputBuffer returned unknown value: " + inputBufferIndex);
            }
        }
        // fill in input (raw) data:
        mEncoderInputBuffers[inputBufferIndex].clear();

        long stop2 = System.nanoTime();
        Log.d(LOGTAG, "dequeueInputBuffer took " + (stop2 - start2) / 1e6 + "ms.");

        start2 = System.nanoTime();
        byte[] pixels = mNV21Converter.convert(frame.pixels);
        stop2 = System.nanoTime();
        Log.d(LOGTAG, "mNV21Converter.convert took " + (stop2-start2)/1e6 + "ms.");

        start2 = System.nanoTime();
        mEncoderInputBuffers[inputBufferIndex].put(pixels);
        stop2 = System.nanoTime();
        Log.d(LOGTAG, "mEncoderInputBuffers[inputBufferIndex].put(pixels) took " + (stop2 - start2) / 1e6 + "ms.");

        start2 = System.nanoTime();
        //mVideoEncoder.queueInputBuffer(inputBufferIndex, 0, pixels.length, 0, 0);
        //mVideoEncoder.queueInputBuffer(inputBufferIndex, 0, pixels.length, System.nanoTime() / 1000, 0);
        mVideoEncoder.queueInputBuffer(inputBufferIndex, 0, pixels.length, System.nanoTime(), 0);
        stop2 = System.nanoTime();
        Log.d(LOGTAG, "queueInputBuffer took " + (stop2 - start2) / 1e6 + "ms.");

        start2 = System.nanoTime();
        // wait for encoded data to become available:
        int outputBufferIndex = -1;
        MediaCodec.BufferInfo bufInfo = new MediaCodec.BufferInfo();
        long timeoutUs = -1;//10000; // microseconds
        while((outputBufferIndex = mVideoEncoder.dequeueOutputBuffer(bufInfo, timeoutUs)) < 0 ) { // -1: wait indefinitely for the buffer
            Log.i(LOGTAG, "dequeueOutputBuffer returned value: " + outputBufferIndex);
            switch(outputBufferIndex) {
                case MediaCodec.INFO_OUTPUT_BUFFERS_CHANGED:
                    // output buffers have changed, move reference
                    mEncoderOutputBuffers = mVideoEncoder.getOutputBuffers();
                    break;
                case MediaCodec.INFO_OUTPUT_FORMAT_CHANGED:
                    // Subsequent data will conform to new format.
                    //MediaFormat format = codec.getOutputFormat();
                    Log.e(LOGTAG, "dequeueOutputBuffer returned INFO_OUTPUT_FORMAT_CHANGED ?!");
                    break;
                case MediaCodec.INFO_TRY_AGAIN_LATER:
                    Log.w(LOGTAG, "dequeueOutputBuffer return INFO_TRY_AGAIN_LATER");
                    break;
                default:
                    Log.e(LOGTAG, "dequeueOutputBuffer returned unknown value: " + outputBufferIndex);
            }
        }
        stop2 = System.nanoTime();
        Log.d(LOGTAG, "dequeueOutputBuffer took " + (stop2 - start2) / 1e6 + "ms.");

        // output (encoded) data available!
        Log.d(LOGTAG, "encoded buffer info: size = " + bufInfo.size + ", offset = " + bufInfo.offset + ", presentationTimeUs = " + bufInfo.presentationTimeUs + ", flags = " + bufInfo.flags);
        ByteBuffer encodedData = mEncoderOutputBuffers[outputBufferIndex];
        final int sizeOfImageData = bufInfo.size;

        long stop = System.nanoTime();
        Log.d(LOGTAG, "Encoding image took " + (stop-start)/1e6 + "ms.");

        start = System.nanoTime();
        // assemble header:
    ... 

        encodedData.rewind();
        // copy (!) raw image data to "direct" (array-backed) buffer:
        ByteBuffer imageBuffer = ByteBuffer.allocateDirect(encodedData.remaining());
        imageBuffer.put(encodedData); // TODO: can this copy be avoided?

        stop = System.nanoTime();
        Log.d(LOGTAG, "Preparing content for streaming took " + (stop - start) / 1e6 + "ms.");
        // do streaming via TCP
        ...
        mVideoEncoder.releaseOutputBuffer(outputBufferIndex, false);
    }

    // see http://developer.android.com/reference/android/media/MediaCodecInfo.html
    private void listAvailableEncoders(String mimeType)
    {
        Log.d(LOGTAG, "Available encoders for mime type " + mimeType + ":");
        for (int i = 0; i < MediaCodecList.getCodecCount(); i++) {
            MediaCodecInfo codec = MediaCodecList.getCodecInfoAt(i);

            if (!codec.isEncoder())
                continue;

            String[] types = codec.getSupportedTypes();
            for (int j = 0; j < types.length; j++) {
                //if (types[j].equalsIgnoreCase(mimeType)) {
                String msg = "- name: " + codec.getName() + ", supported color formats for " + mimeType + ":";
                MediaCodecInfo.CodecCapabilities cap = codec.getCapabilitiesForType(mimeType);
                for(int k = 0; k < cap.colorFormats.length; ++k) msg = msg + " " + cap.colorFormats[k];
                Log.d(LOGTAG, msg);
                //  break;
                //}
            }
        }
    }

questionAnswers(1)

yourAnswerToTheQuestion