[FFmpeg-devel] [PATCH] lavc/qsv: improve the default GPU memory usage

[Linjie Fu]

A large initial_pool_size leads to redundant GPU memory allocations
compared with MSDK.

For some special cases which needs larger GPU memory like look_ahead,
add -extra_hw_frames to allocate more.

CMD:
ffmpeg -hwaccel qsv -extra_hw_frames 50 -c:v hevc_qsv -i hevc.h265 -c:v h264_qsv
-look_ahead 1 -look_ahead_depth 50 -y output.h264

Fix #7943.

Reported-by: Eero T
Signed-off-by: Linjie Fu <linjie.fu at intel.com>
---
 fftools/ffmpeg_qsv.c     | 2 +-
 libavcodec/qsvdec.c      | 5 ++++-
 libavcodec/qsvenc_h264.c | 4 ++--
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/fftools/ffmpeg_qsv.c b/fftools/ffmpeg_qsv.c
index 9c4285b..5039a5a 100644
--- a/fftools/ffmpeg_qsv.c
+++ b/fftools/ffmpeg_qsv.c
@@ -93,7 +93,7 @@ int qsv_init(AVCodecContext *s)
     frames_ctx->height            = FFALIGN(s->coded_height, 32);
     frames_ctx->format            = AV_PIX_FMT_QSV;
     frames_ctx->sw_format         = s->sw_pix_fmt;
-    frames_ctx->initial_pool_size = 64 + s->extra_hw_frames;
+    frames_ctx->initial_pool_size = 24 + s->extra_hw_frames;
     frames_hwctx->frame_type      = MFX_MEMTYPE_VIDEO_MEMORY_DECODER_TARGET;
 
     ret = av_hwframe_ctx_init(ist->hw_frames_ctx);
diff --git a/libavcodec/qsvdec.c b/libavcodec/qsvdec.c
index 0d34021..407e6de 100644
--- a/libavcodec/qsvdec.c
+++ b/libavcodec/qsvdec.c
@@ -300,8 +300,11 @@ static int alloc_frame(AVCodecContext *avctx, QSVContext *q, QSVFrame *frame)
     else
         ret = ff_get_buffer(avctx, frame->frame, AV_GET_BUFFER_FLAG_REF);
 
-    if (ret < 0)
+    if (ret < 0) {
+        av_log(avctx, AV_LOG_ERROR, "More memory in need, "
+            "try -extra_hw_frames to allocate more.\n");
         return ret;
+    }
 
     if (frame->frame->format == AV_PIX_FMT_QSV) {
         frame->surface = *(mfxFrameSurface1*)frame->frame->data[3];
diff --git a/libavcodec/qsvenc_h264.c b/libavcodec/qsvenc_h264.c
index 27f36b9..4e8035b 100644
--- a/libavcodec/qsvenc_h264.c
+++ b/libavcodec/qsvenc_h264.c
@@ -112,8 +112,8 @@ static const AVOption options[] = {
     { "max_dec_frame_buffering", "Maximum number of frames buffered in the DPB", OFFSET(qsv.max_dec_frame_buffering), AV_OPT_TYPE_INT, { .i64 = 0 },   0, UINT16_MAX, VE },
 
 #if QSV_HAVE_LA
-    { "look_ahead",       "Use VBR algorithm with look ahead",    OFFSET(qsv.look_ahead),       AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, VE },
-    { "look_ahead_depth", "Depth of look ahead in number frames", OFFSET(qsv.look_ahead_depth), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 100, VE },
+    { "look_ahead",       "Use VBR algorithm with look ahead, extra_hw_frames is needed",    OFFSET(qsv.look_ahead),       AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 1, VE },
+    { "look_ahead_depth", "Depth of look ahead in number frames, extra_hw_frames is needed", OFFSET(qsv.look_ahead_depth), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 100, VE },
 #endif
 #if QSV_HAVE_LA_DS
     { "look_ahead_downsampling", "Downscaling factor for the frames saved for the lookahead analysis", OFFSET(qsv.look_ahead_downsampling),
-- 
2.7.4