FFMPEG-0.11.1分析之ffmpeg流转码中的时间戳问题
【该文章，是属于ffmpeg的细枝末节，会写的比较啰嗦】【不同的转码环境，会有代码流程的不同】
首先普及下：
时间戳，DTS(decoding time stamp)，PTS(presention time stamp)，CTS（current time stamp）。
ffmepg中的时间戳，是以微秒为单位，关乎timebase变量，它是作为dts、pts的时间基准粒度，数值会很大。
其中函数av_rescale_q()是很多的，AV_ROUND_NEAR_INF是就近、中间从零，av_rescale_rnd它是计算a*b/c，传入参数为八字节，为避免溢出，里面做了与INT_MAX的比较，分开计算。
先看前端的packets parsing，也就是av_read_frame函数：
const int genpts = s->flags & AVFMT_FLAG_GENPTS;//ffmpeg.c, opt_input_file()
ic->flags |= AVFMT_FLAG_NONBLOCK;while (!got_packet && !s->parse_queue) {...} //got_packet有效则返回在 ff_read_packet() 函数中，
ret= s->iformat->read_packet(s, pkt); if(!pktl && st->request_probe <= 0)compute_pkt_fields(s, st, NULL, pkt);got_packet = 1;来看看transcode中在parser和解码前做了什么，
if (pkt.dts != AV_NOPTS_VALUE && ist->next_dts != AV_NOPTS_VALUE && !copy_ts) {
int64_t pkt_dts = av_rescale_q(pkt.dts, ist->st->time_base, AV_TIME_BASE_Q);
int64_t delta = pkt_dts - ist->next_dts;
if (is->iformat->flags & AVFMT_TS_DISCONT) {
if(delta < -1LL*dts_delta_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_delta_threshold*AV_TIME_BASE &&
ist->st->codec->codec_type != AVMEDIA_TYPE_SUBTITLE) ||
pkt_dts+1pts){
input_files[ist->file_index]->ts_offset -= delta;
pkt.dts-= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base);
if (pkt.pts != AV_NOPTS_VALUE)
pkt.pts-= av_rescale_q(delta, AV_TIME_BASE_Q, ist->st->time_base);
}
} else {
if ( delta < -1LL*dts_error_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_error_threshold*AV_TIME_BASE && ist->st->codec->codec_type != AVMEDIA_TYPE_SUBTITLE) ||
pkt_dts+1pts){
pkt.dts = AV_NOPTS_VALUE;
}
if (pkt.pts != AV_NOPTS_VALUE){
int64_t pkt_pts = av_rescale_q(pkt.pts, ist->st->time_base, AV_TIME_BASE_Q);
delta = pkt_pts - ist->next_dts;
if ( delta < -1LL*dts_error_threshold*AV_TIME_BASE ||
(delta > 1LL*dts_error_threshold*AV_TIME_BASE && ist->st->codec->codec_type != AVMEDIA_TYPE_SUBTITLE) ||
pkt_pts+1pts) {
pkt.pts = AV_NOPTS_VALUE;//fallenink:如果pts小了，这里置为无效。则在output_packet中置为ist->dts
}
}
}
}
再看解码 InputStream：【关注InputStream结构中的dts、next_dts、pts、next_pts】
在output_packet中，用saw_first_ts标记给dts、pts做一次性初始化，等
if (!ist->saw_first_ts) {
ist->dts = ist->st->avg_frame_rate.num ? - ist->st->codec->has_b_frames * AV_TIME_BASE / av_q2d(ist->st->avg_frame_rate) : 0;
ist->pts = 0;
if (pkt != NULL && pkt->pts != AV_NOPTS_VALUE && !ist->decoding_needed) {
ist->dts += av_rescale_q(pkt->pts, ist->st->time_base, AV_TIME_BASE_Q);
ist->pts = ist->dts; //unused but better to set it to a value thats not totally wrong
}
ist->saw_first_ts = 1;
}
if (ist->next_dts == AV_NOPTS_VALUE)
ist->next_dts = ist->dts;
if (ist->next_pts == AV_NOPTS_VALUE)
ist->next_pts = ist->pts; if (pkt->dts != AV_NOPTS_VALUE) {//这里如果pkt的时戳被置为无效了，则不作ist的更新
ist->next_dts = ist->dts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q);
if (ist->st->codec->codec_type != AVMEDIA_TYPE_VIDEO || !ist->decoding_needed)
//fallenink: "not video" or "copy"
ist->next_pts = ist->pts = av_rescale_q(pkt->dts, ist->st->time_base, AV_TIME_BASE_Q);
} if (!ist->decoding_needed) {
rate_emu_sleep(ist);
ist->dts = ist->next_dts;
switch (ist->st->codec->codec_type) {
case AVMEDIA_TYPE_AUDIO:
ist->next_dts += ((int64_t)AV_TIME_BASE * ist->st->codec->frame_size) /
ist->st->codec->sample_rate;
break;
case AVMEDIA_TYPE_VIDEO:
//...
}
ist->pts = ist->dts;
ist->next_pts = ist->next_dts;
}for (i = 0; pkt && i < nb_output_streams; i++) {
OutputStream *ost = output_streams[i];
if (!check_output_constraints(ist, ost) || ost->encoding_needed)
continue;
do_streamcopy(ist, ost, pkt);
} ist->pts = ist->next_pts;
ist->dts = ist->next_dts;在decode_video函数中，
pkt->dts = av_rescale_q(ist->dts, AV_TIME_BASE_Q, ist->st->time_base);//这里将输入流的时戳，更新给pkt在avcodec_decode_video2中，单线程情况中，
ret = avctx->codec->decode(avctx, picture, got_picture_ptr, &tmp);
picture->pkt_dts= avpkt->dts;如果解码有输出，则
if (*got_picture_ptr){
avctx->frame_number++;
picture->best_effort_timestamp = guess_correct_pts(avctx,
picture->pkt_pts,
picture->pkt_dts);
}调用guess_correct_pts，一般就是返回picture->pkt_dts的值，再回到decode_video中，
best_effort_timestamp = av_frame_get_best_effort_timestamp(decoded_frame);
if(best_effort_timestamp != AV_NOPTS_VALUE)
ist->next_pts = ist->pts = av_rescale_q(decoded_frame->pts = best_effort_timestamp, ist->st->time_base, AV_TIME_BASE_Q);函数av_frame_get_best_effort_timestamp()定义在哪里呢？是这样的：
/* ./libavcodec/utils.c */
#define MAKE_ACCESSORS(str, name, type, field) \
type av_##name##_get_##field(const str *s) { return s->field; } \
void av_##name##_set_##field(str *s, type v) { s->field = v; }
pre_process_video_frame(ist, (AVPicture *)decoded_frame, &buffer_to_free);if (ist->dr1 && decoded_frame->type==FF_BUFFER_TYPE_USER && !changed) {//fallenink: "type" come from "codec_get_buffer"
FrameBuffer *buf = decoded_frame->opaque;
AVFilterBufferRef *fb = avfilter_get_video_buffer_ref_from_arrays(
decoded_frame->data, decoded_frame->linesize,
AV_PERM_READ | AV_PERM_PRESERVE,
ist->st->codec->width, ist->st->codec->height,
ist->st->codec->pix_fmt);
avfilter_copy_frame_props(fb, decoded_frame);
fb->buf->priv = buf;
fb->buf->free = filter_release_buffer;
av_assert0(buf->refcount>0);
buf->refcount++;
av_buffersrc_add_ref(ist->filters[i]->filter, fb,
AV_BUFFERSRC_FLAG_NO_CHECK_FORMAT |
AV_BUFFERSRC_FLAG_NO_COPY);
} else
if(av_buffersrc_add_frame(ist->filters[i]->filter, decoded_frame, 0)<0) {//fallenink: codec buffer copy to filter
av_log(NULL, AV_LOG_FATAL, "Failed to inject frame into filter network\n");
exit_program(1);
}这里dr1和decoded_frame->type的type的初始化在init_input_stream中，可以看到，
ist->dr1 = (codec->capabilities & CODEC_CAP_DR1) && !do_deinterlace;
if (codec->type == AVMEDIA_TYPE_VIDEO && ist->dr1) {
ist->st->codec->get_buffer = codec_get_buffer;
ist->st->codec->release_buffer = codec_release_buffer;
ist->st->codec->opaque = ist;
}AVCodec ff_h264_decoder = {
.name = "h264",
//...省略
.capabilities = /*CODEC_CAP_DRAW_HORIZ_BAND |*/ CODEC_CAP_DR1 |
CODEC_CAP_DELAY | CODEC_CAP_SLICE_THREADS |
CODEC_CAP_FRAME_THREADS,
//...省略
};接着将解码后的数据及参数扔进filter，后头再编码前av_buffersink_read就可以了，
avfilter_copy_frame_props(fb, decoded_frame);
fb->buf->priv = buf;
fb->buf->free = filter_release_buffer;
av_assert0(buf->refcount>0);
buf->refcount++;
av_buffersrc_add_ref(ist->filters[i]->filter, fb,
AV_BUFFERSRC_FLAG_NO_CHECK_FORMAT |
AV_BUFFERSRC_FLAG_NO_COPY);这样，时戳等信息也就在编码那边获取到了。decode_video函数返回之后，
if (avpkt.duration) {
duration = av_rescale_q(avpkt.duration, ist->st->time_base, AV_TIME_BASE_Q);
} else if(ist->st->codec->time_base.num != 0 && ist->st->codec->time_base.den != 0) {
int ticks= ist->st->parser ? ist->st->parser->repeat_pict+1 : ist->st->codec->ticks_per_frame;
duration = ((int64_t)AV_TIME_BASE *
ist->st->codec->time_base.num * ticks) /
ist->st->codec->time_base.den;
} else
duration = 0;
if(ist->dts != AV_NOPTS_VALUE && duration) {
ist->next_dts += duration;
}else
ist->next_dts = AV_NOPTS_VALUE;
if (got_output)
ist->next_pts += duration; //FIXME the duration is not correct in some cases现在看看编码这一端poll_filters：从graph中取出一帧后，
frame_pts = AV_NOPTS_VALUE;
if (picref->pts != AV_NOPTS_VALUE) {
filtered_frame->pts = frame_pts = av_rescale_q(picref->pts, ost->filter->filter->inputs[0]->time_base,
ost->st->codec->time_base) - av_rescale_q(of->start_time,
AV_TIME_BASE_Q,
ost->st->codec->time_base);
if (of->start_time && filtered_frame->pts < 0) {
avfilter_unref_buffer(picref);
continue;
}
}
//...
avfilter_fill_frame_from_video_buffer_ref(filtered_frame, picref);
filtered_frame->pts = frame_pts;if(ist && ist->st->start_time != AV_NOPTS_VALUE && ist->st->first_dts != AV_NOPTS_VALUE && ost->frame_rate.num)
duration = 1/(av_q2d(ost->frame_rate) * av_q2d(enc->time_base));
sync_ipts = in_picture->pts;
delta = sync_ipts - ost->sync_opts + duration;
switch (format_video_sync) {
/*ost->sync_opts = lrint(sync_ipts);*/}
in_picture->pts = ost->sync_opts;
if (pkt.pts == AV_NOPTS_VALUE && !(enc->codec->capabilities & CODEC_CAP_DELAY))
pkt.pts = ost->sync_opts;
if (pkt.pts != AV_NOPTS_VALUE)
pkt.pts = av_rescale_q(pkt.pts, enc->time_base, ost->st->time_base);
if (pkt.dts != AV_NOPTS_VALUE)
pkt.dts = av_rescale_q(pkt.dts, enc->time_base, ost->st->time_base);接下来就不多说了，直接就送到mux，然后写到远端去了。
_______________________________________________无聊的分割线_________________________________________________
下面谈谈我遇到的问题吧，上面说了一些流程，没什么技术含量，只是作为一个梳理，不梳理很难发现并处理好细节问题。
现象一：流媒体转码中（前端为多线程解码），如果去掉ff_interleave_packet_per_dts()函数中的输出限制，改成有任意流都送去muxer，发现此时出去的流，视频是晚于（时戳值偏小）音频的。原因：正因为前端是多线程解码，如果不把线程数目控制好，cpu过载，会有packet缓冲在线程中，没有得到及时的处理，导致该现象。
现象二：基于现象一，改为单线程处理，如果多数时候，发出去的流，视频又是提前于音频的，甚至数秒。原因：（说明一下，这里的原因只是在下遇到的情况，不具普遍性。）服务器端一开始发了好一些视频的，时戳为0的包，小于了ist->next_dts则被替换，而ist->next_dts是按序，按duration_frame递增的，所以出现该情况，这里我在解码后将这样的情况，置为got output none。这儿是不能释放frame的，因为出来的几片内存实在codec中分配的，然后拷贝去了滤波器模块中。在我这里，导致了不同步问题，重点在这里，时戳问题是表面的，我们大家关注的还是音视频同步问题。
另外，在现象一的基础上，我这里是往fms推流，视频时戳总是晚于音频（或者早于音频很多），出现了一段时间后，rtmp的写端在write，select总是失败，具体原因还不明白。但是在现象二中，却不会出现这个问题。why？？？转码过程中，当然不会有严格处理同步的能力，它是以前端过来的packet时戳为根据的，但转码后端要做好音视频包的交错，也就是ff_interleave_packet_per_dts()这个函数所做的，当然如果mux本身提供interleave_packet则优先使用。
另外有个问题，就是当解码端收到，视频帧被拆分的情况，ffmpeg会连续收到几个包为pts相同的情况，下面这段代码关注下：
if(ist->dts != AV_NOPTS_VALUE && duration) {
ist->next_dts += duration;
}else
ist->next_dts = AV_NOPTS_VALUE;
if (got_output)
ist->next_pts += duration; //FIXME the duration is not correct in some cases按理说，当解码没有输出的时候，是不应该next_pts累加duration的。在我这里，视频需要编解码，音频直接copy，导致了不同步，以及在音视频交错那边视频帧pts增长过快，在那里囤积，导致客户端视频卡住。