[FFmpeg-devel] [PATCH V2 2/3] libavcodec/vaapi_encode: Change the way to call async to increase performance

[Andreas Rheinhardt]

Chen, Wenbin:
>> Wenbin Chen:
>>> Fix: #7706. After commit 5fdcf85bbffe7451c2, vaapi encoder's performance
>>> decrease. The reason is that vaRenderPicture() and vaSyncBuffer() are
>>> called at the same time (vaRenderPicture() always followed by a
>>> vaSyncBuffer()). When we encode stream with B frames, we need buffer to
>>> reorder frames, so we can send serveral frames to HW at once to increase
>>> performance. Now I changed them to be called in a asynchronous way,
>> which
>>> will make better use of hardware. 1080p transcoding increases about 17%
>>> fps on my environment.
>>>
>>> This change fits vaSyncBuffer(), so if driver does not support
>>> vaSyncBuffer, it will keep previous operation.
>>>
>>> Signed-off-by: Wenbin Chen <wenbin.chen at intel.com>
>>> ---
>>>  libavcodec/vaapi_encode.c | 64 ++++++++++++++++++++++++++++++++-----
>> --
>>>  libavcodec/vaapi_encode.h |  5 +++
>>>  2 files changed, 58 insertions(+), 11 deletions(-)
>>>
>>> diff --git a/libavcodec/vaapi_encode.c b/libavcodec/vaapi_encode.c
>>> index b87b58a42b..9a3b3ba4ad 100644
>>> --- a/libavcodec/vaapi_encode.c
>>> +++ b/libavcodec/vaapi_encode.c
>>> @@ -984,8 +984,10 @@ static int
>> vaapi_encode_pick_next(AVCodecContext *avctx,
>>>      if (!pic && ctx->end_of_stream) {
>>>          --b_counter;
>>>          pic = ctx->pic_end;
>>> -        if (pic->encode_issued)
>>> +        if (pic->encode_complete)
>>>              return AVERROR_EOF;
>>> +        else if (pic->encode_issued)
>>> +            return AVERROR(EAGAIN);
>>>      }
>>>
>>>      if (!pic) {
>>> @@ -1210,18 +1212,45 @@ int
>> ff_vaapi_encode_receive_packet(AVCodecContext *avctx, AVPacket *pkt)
>>>              return AVERROR(EAGAIN);
>>>      }
>>>
>>> -    pic = NULL;
>>> -    err = vaapi_encode_pick_next(avctx, &pic);
>>> -    if (err < 0)
>>> -        return err;
>>> -    av_assert0(pic);
>>> +#if VA_CHECK_VERSION(1, 9, 0)
>>> +    if (ctx->has_sync_buffer_func) {
>>> +        while (av_fifo_size(ctx->encode_fifo) <=
>>> +               MAX_PICTURE_REFERENCES * sizeof(VAAPIEncodePicture *)) {
>>> +            pic = NULL;
>>> +            err = vaapi_encode_pick_next(avctx, &pic);
>>> +            if (err < 0)
>>> +                break;
>>> +
>>> +            av_assert0(pic);
>>> +            pic->encode_order = ctx->encode_order +
>>> +                (av_fifo_size(ctx->encode_fifo) / sizeof(VAAPIEncodePicture *));
>>> +            err = vaapi_encode_issue(avctx, pic);
>>> +            if (err < 0) {
>>> +                av_log(avctx, AV_LOG_ERROR, "Encode failed: %d.\n", err);
>>> +                return err;
>>> +            }
>>> +            av_fifo_generic_write(ctx->encode_fifo, &pic, sizeof(pic), NULL);
>>> +        }
>>> +        if (!av_fifo_size(ctx->encode_fifo))
>>> +            return err;
>>> +        av_fifo_generic_read(ctx->encode_fifo, &pic, sizeof(pic), NULL);
>>> +        ctx->encode_order = pic->encode_order + 1;
>>> +    } else
>>> +#endif
>>> +    {
>>> +        pic = NULL;
>>> +        err = vaapi_encode_pick_next(avctx, &pic);
>>> +        if (err < 0)
>>> +            return err;
>>> +        av_assert0(pic);
>>>
>>> -    pic->encode_order = ctx->encode_order++;
>>> +        pic->encode_order = ctx->encode_order++;
>>>
>>> -    err = vaapi_encode_issue(avctx, pic);
>>> -    if (err < 0) {
>>> -        av_log(avctx, AV_LOG_ERROR, "Encode failed: %d.\n", err);
>>> -        return err;
>>> +        err = vaapi_encode_issue(avctx, pic);
>>> +        if (err < 0) {
>>> +            av_log(avctx, AV_LOG_ERROR, "Encode failed: %d.\n", err);
>>> +            return err;
>>> +        }
>>>      }
>>>
>>>      err = vaapi_encode_output(avctx, pic, pkt);
>>> @@ -2555,6 +2584,18 @@ av_cold int
>> ff_vaapi_encode_init(AVCodecContext *avctx)
>>>          }
>>>      }
>>>
>>> +#if VA_CHECK_VERSION(1, 9, 0)
>>> +    //check vaSyncBuffer function
>>> +    vas = vaSyncBuffer(ctx->hwctx->display, 0, 0);
>>> +    if (vas != VA_STATUS_ERROR_UNIMPLEMENTED) {
>>> +        ctx->has_sync_buffer_func = 1;
>>> +        ctx->encode_fifo = av_fifo_alloc((MAX_PICTURE_REFERENCES + 1) *
>>> +                                        sizeof(VAAPIEncodePicture *));
>>> +        if (!ctx->encode_fifo)
>>> +            return AVERROR(ENOMEM);
>>> +    }
>>> +#endif
>>> +
>>>      return 0;
>>>
>>>  fail:
>>> @@ -2592,6 +2633,7 @@ av_cold int
>> ff_vaapi_encode_close(AVCodecContext *avctx)
>>>
>>>      av_freep(&ctx->codec_sequence_params);
>>>      av_freep(&ctx->codec_picture_params);
>>> +    av_fifo_freep(&ctx->encode_fifo);
>>
>> Is it guaranteed that the fifo is empty at this point? I don't think so.
> 
> I don't check the fifo size, because in ff_vaapi_encode_close() all pics
> are already freed and encode_fifo only buffer pic.
> ```
>     for (pic = ctx->pic_start; pic; pic = next) {
>         next = pic->next;
>         vaapi_encode_free(avctx, pic);
>     }
> ```
> 

Ok, seems like the FIFO does not have ownership of the pics. Alright then.

>>
>>>
>>>      av_buffer_unref(&ctx->recon_frames_ref);
>>>      av_buffer_unref(&ctx->input_frames_ref);
>>> diff --git a/libavcodec/vaapi_encode.h b/libavcodec/vaapi_encode.h
>>> index b41604a883..560a1c42a9 100644
>>> --- a/libavcodec/vaapi_encode.h
>>> +++ b/libavcodec/vaapi_encode.h
>>> @@ -29,6 +29,7 @@
>>>
>>>  #include "libavutil/hwcontext.h"
>>>  #include "libavutil/hwcontext_vaapi.h"
>>> +#include "libavutil/fifo.h"
>>>
>>>  #include "avcodec.h"
>>>  #include "hwconfig.h"
>>> @@ -345,6 +346,10 @@ typedef struct VAAPIEncodeContext {
>>>      int             roi_warned;
>>>
>>>      AVFrame         *frame;
>>> +    //Store buffered pic
>>> +    AVFifoBuffer *encode_fifo;
>>> +    //Whether the driver support vaSyncBuffer
>>> +    int has_sync_buffer_func;
>>>  } VAAPIEncodeContext;
>>>
>>>  enum {
>>>
>>