个人认为，这这部分教程的新增代码量虽然不是最多的，难度却是最大的，重复看了多次才明白，因为有两个问题的困扰，搞得还不清楚：
1.音频和视频既然都有各自的时间戳，各自按各自的时间戳来播放不就行了，为什么还需要同步呢？
2.如果要把视频同步到音频，怎么同步？或者说以什么标准来同步？
第一个问题的答案可能是，一是音频和视频的开始播放的时间是不一样，二是播放每帧音频或视频时可能必须把解码数据，视频格式转换消耗的时间考虑进来，解码数据，视频格式转换等步骤又和不同的机器配置相关，设想一下这种极端的情况，有一帧图片应该在此时刻播放了（根据时间戳），而解码器还没来及解码完（程序代码或者机器配置太烂），解码完后，可能需要丢弃该帧，不然视频赶不上音频。
第二个问题的答案也不是很清楚，但根据这个教程的代码来分析，特别是video_refresh_timer函数中关于时间戳部分的代码告诉了这个问题答案，首先大结构体VideoState保存了两个用于同步的两个重要变量audio_clock和video_clock，分别保存了音频和视频的播放了多长时间，也就是教程中说的音频和视频的内部时钟。把视频同步到音频的方法就是比较video_clock（当前视频播放到的时刻）和audio_clock（当前音频播放到的时刻）差的绝对值如果大于同步阈值sync_threshold，就重新计算延迟delay，这时视频如果播放得太快就直接让延迟delay = 2*delay，反之则立即播放。而video_clock和audio_clock之差在可接受范围内，delay的值直接取上一帧和当前帧的延迟，delay将被用于下一帧的播放延迟。
时钟的同步，教程中分为三个部分。
第一部分讲如何保存视频帧的时间戳和video_clock，代码主要在video_thread函数中，该函数中的这行代码len1 = avcodec_decode_video(is->video_st->codec, pFrame, &frameFinished,packet->data, packet->size);解码packet中的数据到pFrame时，会调用我们自己些的帧内存分配函数our_get_buffer，把第一个包的时间戳保存到帧pFrame中（一个帧可能由多个数据包组成），帧的时间戳优先取最后一个包的dts，没有才取第一个包的pts，都没有就取video_clock。
video_thread函数在解码完一帧后，立马调用synchronize_video函数，synchronize_video函数的作用就是维护video_clock的值，让video_clock变量始终保存视频播放了多长时间的信息，其中还考虑到了帧重复的问题。得到当前视频帧的时间戳相对音频来说简单些。
第二部分讲，假设我们能得到当前音频的时间戳，如何让视频同步到音频，也就是上面第二个问题的答案。
第三部分讲如何获得当前音频帧的时间戳，代码主要在get_audio_clock函数中，这个并不是简单地返回is->audio_clock了事，如果那样做就忽略了把数据包转移到输出缓冲的时间花费，我们声音时钟中记录的时间比实际的要早太多。所以我们必须要检查一下我们还有多少没有写入。audio_clock的维护工作交给了audio_decode_frame函数来处理，首先在函数末尾初始化is->audio_clock = av_q2d(is->audio_st->time_base)*pkt->pts;然后解码完一帧音频后又有更新。
// tutorial05.c // A pedagogical video player that really works! // // Code based on FFplay, Copyright (c) 2003 Fabrice Bellard, // and a tutorial by Martin Bohme ([email protected]) // Tested on Gentoo, CVS version 5/01/07 compiled with GCC 4.1.1 // Use // // gcc -o tutorial05 tutorial05.c -lavformat -lavcodec -lz -lm `sdl-config --cflags --libs` // to build (assuming libavformat and libavcodec are correctly installed, // and assuming you have sdl-config. Please refer to SDL docs for your installation.) // // Run using // tutorial05 myvideofile.mpg // // to play the video. #include "libavformat/avformat.h" #include "libswscale/swscale.h" #include #include #ifdef main #undef main /* Prevents SDL from overriding main() */ #endif #include #include #define SDL_AUDIO_BUFFER_SIZE 1024 #define MAX_AUDIOQ_SIZE (5 * 16 * 1024) #define MAX_VIDEOQ_SIZE (5 * 256 * 1024) #define AV_SYNC_THRESHOLD 0.01 #define AV_NOSYNC_THRESHOLD 10.0 #define FF_ALLOC_EVENT (SDL_USEREVENT) #define FF_REFRESH_EVENT (SDL_USEREVENT + 1) #define FF_QUIT_EVENT (SDL_USEREVENT + 2) #define VIDEO_PICTURE_QUEUE_SIZE 1 typedef struct PacketQueue { AVPacketList *first_pkt, *last_pkt; int nb_packets; int size; SDL_mutex *mutex; SDL_cond *cond; } PacketQueue; typedef struct VideoPicture { SDL_Overlay *bmp; int width, height; /* source height & width */ int allocated; double pts; } VideoPicture; typedef struct VideoState { AVFormatContext *pFormatCtx; int videoStream, audioStream; double audio_clock; AVStream *audio_st; PacketQueue audioq; uint8_t audio_buf[(AVCODEC_MAX_AUDIO_FRAME_SIZE * 3) / 2]; unsigned int audio_buf_size; unsigned int audio_buf_index; AVPacket audio_pkt; uint8_t *audio_pkt_data; int audio_pkt_size; int audio_hw_buf_size; double frame_timer; double frame_last_pts; double frame_last_delay; double video_clock; ///mutex = SDL_CreateMutex(); q->cond = SDL_CreateCond(); } int packet_queue_put(PacketQueue *q, AVPacket *pkt) { AVPacketList *pkt1; if(av_dup_packet(pkt) < 0) { return -1; } pkt1 = (AVPacketList *)av_malloc(sizeof(AVPacketList)); if (!pkt1) return -1; pkt1->pkt = *pkt; pkt1->next = NULL; SDL_LockMutex(q->mutex); if (!q->last_pkt) q->first_pkt = pkt1; else q->last_pkt->next = pkt1; q->last_pkt = pkt1; q->nb_packets++; q->size += pkt1->pkt.size; SDL_CondSignal(q->cond); SDL_UnlockMutex(q->mutex); return 0; } static int packet_queue_get(PacketQueue *q, AVPacket *pkt, int block) { AVPacketList *pkt1; int ret; SDL_LockMutex(q->mutex); for(;;) { if(global_video_state->quit) { ret = -1; break; } pkt1 = q->first_pkt; if (pkt1) { q->first_pkt = pkt1->next; if (!q->first_pkt) q->last_pkt = NULL; q->nb_packets--; q->size -= pkt1->pkt.size; *pkt = pkt1->pkt; av_free(pkt1); ret = 1; break; } else if (!block) { ret = 0; break; } else { SDL_CondWait(q->cond, q->mutex); } } SDL_UnlockMutex(q->mutex); return ret; } double get_audio_clock(VideoState *is) { double pts; int hw_buf_size, bytes_per_sec, n; pts = is->audio_clock; /* maintained in the audio thread */ hw_buf_size = is->audio_buf_size - is->audio_buf_index; bytes_per_sec = 0; n = is->audio_st->codec->channels * 2; if(is->audio_st) { bytes_per_sec = is->audio_st->codec->sample_rate * n; } if(bytes_per_sec) { pts -= (double)hw_buf_size / bytes_per_sec; } return pts; } int audio_decode_frame(VideoState *is, uint8_t *audio_buf, int buf_size, double *pts_ptr) { int len1, data_size, n; AVPacket *pkt = &is->audio_pkt; double pts; for(;;) { while(is->audio_pkt_size > 0) { data_size = buf_size; len1 = avcodec_decode_audio2(is->audio_st->codec, (int16_t *)audio_buf, &data_size, is->audio_pkt_data, is->audio_pkt_size); if(len1 < 0) { /* if error, skip frame */ is->audio_pkt_size = 0; break; } is->audio_pkt_data += len1; is->audio_pkt_size -= len1; if(data_size <= 0) { /* No data yet, get more frames */ continue; } pts = is->audio_clock; *pts_ptr = pts; n = 2 * is->audio_st->codec->channels; is->audio_clock += (double)data_size / (double)(n * is->audio_st->codec->sample_rate); /* We have data, return it and come back for more later */ return data_size; } if(pkt->data) av_free_packet(pkt); if(is->quit) { return -1; } /* next packet */ if(packet_queue_get(&is->audioq, pkt, 1) < 0) { return -1; } is->audio_pkt_data = pkt->data; is->audio_pkt_size = pkt->size; /* if update, update the audio clock w/pts */ if(pkt->pts != AV_NOPTS_VALUE) { is->audio_clock = av_q2d(is->audio_st->time_base)*pkt->pts; } } } void audio_callback(void *userdata, Uint8 *stream, int len) { VideoState *is = (VideoState *)userdata; int len1, audio_size; double pts; while(len > 0) { if(is->audio_buf_index >= is->audio_buf_size) { /* We have already sent all our data; get more */ audio_size = audio_decode_frame(is, is->audio_buf, sizeof(is->audio_buf), &pts); if(audio_size < 0) { /* If error, output silence */ is->audio_buf_size = 1024; memset(is->audio_buf, 0, is->audio_buf_size); } else { is->audio_buf_size = audio_size; } is->audio_buf_index = 0; } len1 = is->audio_buf_size - is->audio_buf_index; if(len1 > len) len1 = len; memcpy(stream, (uint8_t *)is->audio_buf + is->audio_buf_index, len1); len -= len1; stream += len1; is->audio_buf_index += len1; } } static Uint32 sdl_refresh_timer_cb(Uint32 interval, void *opaque) { SDL_Event event; event.type = FF_REFRESH_EVENT; event.user.data1 = opaque; SDL_PushEvent(&event); return 0; /* 0 means stop timer */ } /* schedule a video refresh in 'delay' ms */ static void schedule_refresh(VideoState *is, int delay) { SDL_AddTimer(delay, sdl_refresh_timer_cb, is); } void video_display(VideoState *is) { SDL_Rect rect; VideoPicture *vp; AVPicture pict; float aspect_ratio; int w, h, x, y; int i; vp = &is->pictq[is->pictq_rindex]; if(vp->bmp) { if(is->video_st->codec->sample_aspect_ratio.num == 0) { aspect_ratio = 0; } else { aspect_ratio = av_q2d(is->video_st->codec->sample_aspect_ratio) * is->video_st->codec->width / is->video_st->codec->height; } if(aspect_ratio <= 0.0) { aspect_ratio = (float)is->video_st->codec->width / (float)is->video_st->codec->height; } h = screen->h; w = ((int)(h * aspect_ratio)) & -3; if(w > screen->w) { w = screen->w; h = ((int)(w / aspect_ratio)) & -3; } x = (screen->w - w) / 2; y = (screen->h - h) / 2; rect.x = x; rect.y = y; rect.w = w; rect.h = h; SDL_DisplayYUVOverlay(vp->bmp, &rect); } } void video_refresh_timer(void *userdata) { VideoState *is = (VideoState *)userdata; VideoPicture *vp; double actual_delay, delay, sync_threshold, ref_clock, diff; if(is->video_st) { if(is->pictq_size == 0) { schedule_refresh(is, 1); } else { vp = &is->pictq[is->pictq_rindex]; delay = vp->pts - is->frame_last_pts; /* the pts from last time */ if(delay <= 0 || delay >= 1.0) { /* if incorrect delay, use previous one */ delay = is->frame_last_delay; } /* save for next time */ is->frame_last_delay = delay; is->frame_last_pts = vp->pts; /* update delay to sync to audio */ ref_clock = get_audio_clock(is); diff = vp->pts - ref_clock; /* Skip or repeat the frame. Take delay into account FFPlay still doesn't "know if this is the best guess." */ sync_threshold = (delay > AV_SYNC_THRESHOLD) ? delay : AV_SYNC_THRESHOLD; if(fabs(diff) < AV_NOSYNC_THRESHOLD) { if(diff <= -sync_threshold) { delay = 0; } else if(diff >= sync_threshold) { delay = 2 * delay; } } is->frame_timer += delay; /* computer the REAL delay */ actual_delay = is->frame_timer - (av_gettime() / 1000000.0); if(actual_delay < 0.010) { /* Really it should skip the picture instead */ actual_delay = 0.010; } schedule_refresh(is, (int)(actual_delay * 1000 + 0.5)); /* show the picture! */ video_display(is); /* update queue for next picture! */ if(++is->pictq_rindex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_rindex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size--; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } } else { schedule_refresh(is, 100); } } void alloc_picture(void *userdata) { VideoState *is = (VideoState *)userdata; VideoPicture *vp; vp = &is->pictq[is->pictq_windex]; if(vp->bmp) { // we already have one make another, bigger/smaller SDL_FreeYUVOverlay(vp->bmp); } // Allocate a place to put our YUV image on that screen vp->bmp = SDL_CreateYUVOverlay(is->video_st->codec->width, is->video_st->codec->height, SDL_YV12_OVERLAY, screen); vp->width = is->video_st->codec->width; vp->height = is->video_st->codec->height; SDL_LockMutex(is->pictq_mutex); vp->allocated = 1; SDL_CondSignal(is->pictq_cond); SDL_UnlockMutex(is->pictq_mutex); } int queue_picture(VideoState *is, AVFrame *pFrame, double pts) { VideoPicture *vp; //int dst_pix_fmt; AVPicture pict; /* wait until we have space for a new pic */ SDL_LockMutex(is->pictq_mutex); while(is->pictq_size >= VIDEO_PICTURE_QUEUE_SIZE && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if(is->quit) return -1; // windex is set to 0 initially vp = &is->pictq[is->pictq_windex]; /* allocate or resize the buffer! */ if(!vp->bmp || vp->width != is->video_st->codec->width || vp->height != is->video_st->codec->height) { SDL_Event event; vp->allocated = 0; /* we have to do it in the main thread */ event.type = FF_ALLOC_EVENT; event.user.data1 = is; SDL_PushEvent(&event); /* wait until we have a picture allocated */ SDL_LockMutex(is->pictq_mutex); while(!vp->allocated && !is->quit) { SDL_CondWait(is->pictq_cond, is->pictq_mutex); } SDL_UnlockMutex(is->pictq_mutex); if(is->quit) { return -1; } } /* We have a place to put our picture on the queue */ /* If we are skipping a frame, do we set this to null but still return vp->allocated = 1? */ static struct SwsContext *img_convert_ctx; if (img_convert_ctx == NULL) { img_convert_ctx = sws_getContext(is->video_st->codec->width, is->video_st->codec->height, is->video_st->codec->pix_fmt, is->video_st->codec->width, is->video_st->codec->height, PIX_FMT_YUV420P, SWS_BICUBIC, NULL, NULL, NULL); if (img_convert_ctx == NULL) { fprintf(stderr, "Cannot initialize the conversion context/n"); exit(1); } } if(vp->bmp) { SDL_LockYUVOverlay(vp->bmp); //dst_pix_fmt = PIX_FMT_YUV420P; /* point pict at the queue */ pict.data[0] = vp->bmp->pixels[0]; pict.data[1] = vp->bmp->pixels[2]; pict.data[2] = vp->bmp->pixels[1]; pict.linesize[0] = vp->bmp->pitches[0]; pict.linesize[1] = vp->bmp->pitches[2]; pict.linesize[2] = vp->bmp->pitches[1]; // Convert the image into YUV format that SDL uses /*img_convert(&pict, dst_pix_fmt, (AVPicture *)pFrame, is->video_st->codec->pix_fmt, is->video_st->codec->width, is->video_st->codec->height);*/ sws_scale(img_convert_ctx, pFrame->data, pFrame->linesize, 0, is->video_st->codec->height, pict.data, pict.linesize); SDL_UnlockYUVOverlay(vp->bmp); vp->pts = pts; /* now we inform our display thread that we have a pic ready */ if(++is->pictq_windex == VIDEO_PICTURE_QUEUE_SIZE) { is->pictq_windex = 0; } SDL_LockMutex(is->pictq_mutex); is->pictq_size++; SDL_UnlockMutex(is->pictq_mutex); } return 0; } double synchronize_video(VideoState *is, AVFrame *src_frame, double pts) { double frame_delay; if(pts != 0) { /* if we have pts, set video clock to it */ is->video_clock = pts; } else { /* if we aren't given a pts, set it to the clock */ pts = is->video_clock; } /* update the video clock */ frame_delay = av_q2d(is->video_st->codec->time_base); /* if we are repeating a frame, adjust clock accordingly */ frame_delay += src_frame->repeat_pict * (frame_delay * 0.5); is->video_clock += frame_delay; return pts; } uint64_t global_video_pkt_pts = AV_NOPTS_VALUE; /* These are called whenever we allocate a frame * buffer. We use this to store the global_pts in * a frame at the time it is allocated. */ int our_get_buffer(struct AVCodecContext *c, AVFrame *pic) { int ret = avcodec_default_get_buffer(c, pic); uint64_t *pts = (uint64_t *)av_malloc(sizeof(uint64_t)); *pts = global_video_pkt_pts; pic->opaque = pts; return ret; } void our_release_buffer(struct AVCodecContext *c, AVFrame *pic) { if(pic) av_freep(&pic->opaque); avcodec_default_release_buffer(c, pic); } int video_thread(void *arg) { VideoState *is = (VideoState *)arg; AVPacket pkt1, *packet = &pkt1; int len1, frameFinished; AVFrame *pFrame; double pts; pFrame = avcodec_alloc_frame(); for(;;) { if(packet_queue_get(&is->videoq, packet, 1) < 0) { // means we quit getting packets break; } pts = 0; // Save global pts to be stored in pFrame in first call global_video_pkt_pts = packet->pts; // Decode video frame len1 = avcodec_decode_video(is->video_st->codec, pFrame, &frameFinished, packet->data, packet->size); if(packet->dts == AV_NOPTS_VALUE && pFrame->opaque && *(uint64_t*)pFrame->opaque != AV_NOPTS_VALUE) { pts = *(uint64_t *)pFrame->opaque; } else if(packet->dts != AV_NOPTS_VALUE) { pts = packet->dts; } else { pts = 0; } pts *= av_q2d(is->video_st->time_base); // Did we get a video frame? if(frameFinished) { pts = synchronize_video(is, pFrame, pts); if(queue_picture(is, pFrame, pts) < 0) { break; } } av_free_packet(packet); } av_free(pFrame); return 0; } int stream_component_open(VideoState *is, int stream_index) { AVFormatContext *pFormatCtx = is->pFormatCtx; AVCodecContext *codecCtx; AVCodec *codec; SDL_AudioSpec wanted_spec, spec; if(stream_index < 0 || stream_index >= pFormatCtx->nb_streams) { return -1; } // Get a pointer to the codec context for the video stream codecCtx = pFormatCtx->streams[stream_index]->codec; if(codecCtx->codec_type == CODEC_TYPE_AUDIO) { // Set audio settings from codec info wanted_spec.freq = codecCtx->sample_rate; wanted_spec.format = AUDIO_S16SYS; wanted_spec.channels = codecCtx->channels; wanted_spec.silence = 0; wanted_spec.samples = SDL_AUDIO_BUFFER_SIZE; wanted_spec.callback = audio_callback; wanted_spec.userdata = is; if(SDL_OpenAudio(&wanted_spec, &spec) < 0) { fprintf(stderr, "SDL_OpenAudio: %s/n", SDL_GetError()); return -1; } is->audio_hw_buf_size = spec.size; } codec = avcodec_find_decoder(codecCtx->codec_id); if(!codec || (avcodec_open(codecCtx, codec) < 0)) { fprintf(stderr, "Unsupported codec!/n"); return -1; } switch(codecCtx->codec_type) { case CODEC_TYPE_AUDIO: is->audioStream = stream_index; is->audio_st = pFormatCtx->streams[stream_index]; is->audio_buf_size = 0; is->audio_buf_index = 0; memset(&is->audio_pkt, 0, sizeof(is->audio_pkt)); packet_queue_init(&is->audioq); SDL_PauseAudio(0); break; case CODEC_TYPE_VIDEO: is->videoStream = stream_index; is->video_st = pFormatCtx->streams[stream_index]; is->frame_timer = (double)av_gettime() / 1000000.0; is->frame_last_delay = 40e-3; packet_queue_init(&is->videoq); is->video_tid = SDL_CreateThread(video_thread, is); codecCtx->get_buffer = our_get_buffer; codecCtx->release_buffer = our_release_buffer; break; default: break; } return 0; } int decode_interrupt_cb(void) { return (global_video_state && global_video_state->quit); } int decode_thread(void *arg) { VideoState *is = (VideoState *)arg; AVFormatContext *pFormatCtx; AVPacket pkt1, *packet = &pkt1; int video_index = -1; int audio_index = -1; int i; is->videoStream=-1; is->audioStream=-1; global_video_state = is; // will interrupt blocking functions if we quit! url_set_interrupt_cb(decode_interrupt_cb); // Open video file if(av_open_input_file(&pFormatCtx, is->filename, NULL, 0, NULL)!=0) return -1; // Couldn't open file is->pFormatCtx = pFormatCtx; // Retrieve stream information if(av_find_stream_info(pFormatCtx)<0) return -1; // Couldn't find stream information // Dump information about file onto standard error dump_format(pFormatCtx, 0, is->filename, 0); // Find the first video stream for(i=0; inb_streams; i++) { if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_VIDEO && video_index < 0) { video_index=i; } if(pFormatCtx->streams[i]->codec->codec_type==CODEC_TYPE_AUDIO && audio_index < 0) { audio_index=i; } } if(audio_index >= 0) { stream_component_open(is, audio_index); } if(video_index >= 0) { stream_component_open(is, video_index); } if(is->videoStream < 0 || is->audioStream < 0) { fprintf(stderr, "%s: could not open codecs/n", is->filename); goto fail; } // main decode loop for(;;) { if(is->quit) { break; } // seek stuff goes here if(is->audioq.size > MAX_AUDIOQ_SIZE || is->videoq.size > MAX_VIDEOQ_SIZE) { SDL_Delay(10); continue; } if(av_read_frame(is->pFormatCtx, packet) < 0) { if(url_ferror(pFormatCtx->pb) == 0) { SDL_Delay(100); /* no error; wait for user input */ continue; } else { break; } } // Is this a packet from the video stream? if(packet->stream_index == is->videoStream) { packet_queue_put(&is->videoq, packet); } else if(packet->stream_index == is->audioStream) { packet_queue_put(&is->audioq, packet); } else { av_free_packet(packet); } } /* all done - wait for it */ while(!is->quit) { SDL_Delay(100); } fail: { SDL_Event event; event.type = FF_QUIT_EVENT; event.user.data1 = is; SDL_PushEvent(&event); } return 0; } int main(int argc, char *argv[]) { SDL_Event event; VideoState *is; is = (VideoState *)av_mallocz(sizeof(VideoState)); if(argc < 2) { fprintf(stderr, "Usage: test /n"); exit(1); } // Register all formats and codecs av_register_all(); if(SDL_Init(SDL_INIT_VIDEO | SDL_INIT_AUDIO | SDL_INIT_TIMER)) { fprintf(stderr, "Could not initialize SDL - %s/n", SDL_GetError()); exit(1); } // Make a screen to put our video #ifndef __DARWIN__ screen = SDL_SetVideoMode(640, 480, 0, 0); #else screen = SDL_SetVideoMode(640, 480, 24, 0); #endif if(!screen) { fprintf(stderr, "SDL: could not set video mode - exiting/n"); exit(1); } //pstrcpy(is->filename, sizeof(is->filename), argv[1]); strcpy(is->filename,argv[1]); is->pictq_mutex = SDL_CreateMutex(); is->pictq_cond = SDL_CreateCond(); schedule_refresh(is, 40); is->parse_tid = SDL_CreateThread(decode_thread, is); if(!is->parse_tid) { av_free(is); return -1; } for(;;) { SDL_WaitEvent(&event); switch(event.type) { case FF_QUIT_EVENT: case SDL_QUIT: is->quit = 1; SDL_Quit(); exit(0); break; case FF_ALLOC_EVENT: alloc_picture(event.user.data1); break; case FF_REFRESH_EVENT: video_refresh_timer(event.user.data1); break; default: break; } } return 0; }
