| Message ID | 20200404144747.24347-1-cus@passwd.hu |
|---|---|
| State | New |
| Headers | show |
| Series | [FFmpeg-devel] avformat/mpegts: use buffer pools for allocating packets | expand |
| Context | Check | Description |
|---|---|---|
| andriy/ffmpeg-patchwork | success | Make fate finished |
On 4/4/2020 11:47 AM, Marton Balint wrote: > This brings a performance improvement when demuxing files, most of the > improvement comes from buffer pooling unbound packets. Yes, as i mentioned in my last reply this was my experience as well. > > time ffprobe -i samples/ffmpeg-bugs/trac/ticket6132/Samsung_HDR_-_Chasing_the_Light.ts -show_packets >/dev/null 2>&1 > > Before: > real 0m1.967s > user 0m1.471s > sys 0m0.493s > > After: > real 0m1.497s > user 0m1.364s > sys 0m0.129s > > Based on a patch of James Almer. > > Signed-off-by: Marton Balint <cus@passwd.hu> > --- > libavformat/mpegts.c | 23 +++++++++++++++++++---- > 1 file changed, 19 insertions(+), 4 deletions(-) > > diff --git a/libavformat/mpegts.c b/libavformat/mpegts.c > index 7f56bacb2c..fbafc1d257 100644 > --- a/libavformat/mpegts.c > +++ b/libavformat/mpegts.c > @@ -170,6 +170,7 @@ struct MpegTSContext { > int current_pid; > > AVStream *epg_stream; > + AVBufferPool* pools[32]; Isn't 32 way more than required? > }; > > #define MPEGTS_OPTIONS \ > @@ -1103,6 +1104,18 @@ static int read_sl_header(PESContext *pes, SLConfigDescr *sl, > return (get_bits_count(&gb) + 7) >> 3; > } > > +static AVBufferRef *buffer_pool_get(MpegTSContext *ts, int size) > +{ > + int index = av_log2(size + AV_INPUT_BUFFER_PADDING_SIZE); > + if (!ts->pools[index]) { > + int pool_size = FFMIN(MAX_PES_PAYLOAD + AV_INPUT_BUFFER_PADDING_SIZE, 2 << index); > + ts->pools[index] = av_buffer_pool_init(pool_size, NULL); > + if (!ts->pools[index]) > + return NULL; > + } > + return av_buffer_pool_get(ts->pools[index]); > +} > + > /* return non zero if a packet could be constructed */ > static int mpegts_push_data(MpegTSFilter *filter, > const uint8_t *buf, int buf_size, int is_start, > @@ -1177,8 +1190,8 @@ static int mpegts_push_data(MpegTSFilter *filter, > pes->total_size = MAX_PES_PAYLOAD; > > /* allocate pes buffer */ > - pes->buffer = av_buffer_alloc(pes->total_size + > - AV_INPUT_BUFFER_PADDING_SIZE); > + pes->buffer = buffer_pool_get(ts, pes->total_size); > + > if (!pes->buffer) > return AVERROR(ENOMEM); > > @@ -1351,8 +1364,7 @@ skip: > if (ret < 0) > return ret; > pes->total_size = MAX_PES_PAYLOAD; > - pes->buffer = av_buffer_alloc(pes->total_size + > - AV_INPUT_BUFFER_PADDING_SIZE); > + pes->buffer = buffer_pool_get(ts, pes->total_size); > if (!pes->buffer) > return AVERROR(ENOMEM); > ts->stop_parse = 1; > @@ -3200,6 +3212,9 @@ static void mpegts_free(MpegTSContext *ts) > > clear_programs(ts); > > + for (i = 0; i < FF_ARRAY_ELEMS(ts->pools); i++) > + av_buffer_pool_uninit(&ts->pools[i]); > + > for (i = 0; i < NB_PID_MAX; i++) > if (ts->pids[i]) > mpegts_close_filter(ts, ts->pids[i]); LGTM. I assume the pools for the smaller sizes will not end up being slower than just allocating new buffers each time.
On Sat, 4 Apr 2020, James Almer wrote: > On 4/4/2020 11:47 AM, Marton Balint wrote: >> This brings a performance improvement when demuxing files, most of the >> improvement comes from buffer pooling unbound packets. > > Yes, as i mentioned in my last reply this was my experience as well. > >> >> time ffprobe -i samples/ffmpeg-bugs/trac/ticket6132/Samsung_HDR_-_Chasing_the_Light.ts -show_packets >/dev/null 2>&1 >> >> Before: >> real 0m1.967s >> user 0m1.471s >> sys 0m0.493s >> >> After: >> real 0m1.497s >> user 0m1.364s >> sys 0m0.129s >> >> Based on a patch of James Almer. >> >> Signed-off-by: Marton Balint <cus@passwd.hu> >> --- >> libavformat/mpegts.c | 23 +++++++++++++++++++---- >> 1 file changed, 19 insertions(+), 4 deletions(-) >> >> diff --git a/libavformat/mpegts.c b/libavformat/mpegts.c >> index 7f56bacb2c..fbafc1d257 100644 >> --- a/libavformat/mpegts.c >> +++ b/libavformat/mpegts.c >> @@ -170,6 +170,7 @@ struct MpegTSContext { >> int current_pid; >> >> AVStream *epg_stream; >> + AVBufferPool* pools[32]; > > Isn't 32 way more than required? The number of required pools is log2(MAX_PES_PAYLOAD+AV_INPUT_BUFFER_PADDING_SIZE)+1, so currently 18, but since as far as I know there is no compile time log2 I did not want to limit it here so MAX_PES_PAYLOAD can still be changeable without adjusting this. > >> }; >> >> #define MPEGTS_OPTIONS \ >> @@ -1103,6 +1104,18 @@ static int read_sl_header(PESContext *pes, SLConfigDescr *sl, >> return (get_bits_count(&gb) + 7) >> 3; >> } >> >> +static AVBufferRef *buffer_pool_get(MpegTSContext *ts, int size) >> +{ >> + int index = av_log2(size + AV_INPUT_BUFFER_PADDING_SIZE); >> + if (!ts->pools[index]) { >> + int pool_size = FFMIN(MAX_PES_PAYLOAD + AV_INPUT_BUFFER_PADDING_SIZE, 2 << index); >> + ts->pools[index] = av_buffer_pool_init(pool_size, NULL); >> + if (!ts->pools[index]) >> + return NULL; >> + } >> + return av_buffer_pool_get(ts->pools[index]); >> +} >> + >> /* return non zero if a packet could be constructed */ >> static int mpegts_push_data(MpegTSFilter *filter, >> const uint8_t *buf, int buf_size, int is_start, >> @@ -1177,8 +1190,8 @@ static int mpegts_push_data(MpegTSFilter *filter, >> pes->total_size = MAX_PES_PAYLOAD; >> >> /* allocate pes buffer */ >> - pes->buffer = av_buffer_alloc(pes->total_size + >> - AV_INPUT_BUFFER_PADDING_SIZE); >> + pes->buffer = buffer_pool_get(ts, pes->total_size); >> + >> if (!pes->buffer) >> return AVERROR(ENOMEM); >> >> @@ -1351,8 +1364,7 @@ skip: >> if (ret < 0) >> return ret; >> pes->total_size = MAX_PES_PAYLOAD; >> - pes->buffer = av_buffer_alloc(pes->total_size + >> - AV_INPUT_BUFFER_PADDING_SIZE); >> + pes->buffer = buffer_pool_get(ts, pes->total_size); >> if (!pes->buffer) >> return AVERROR(ENOMEM); >> ts->stop_parse = 1; >> @@ -3200,6 +3212,9 @@ static void mpegts_free(MpegTSContext *ts) >> >> clear_programs(ts); >> >> + for (i = 0; i < FF_ARRAY_ELEMS(ts->pools); i++) >> + av_buffer_pool_uninit(&ts->pools[i]); >> + >> for (i = 0; i < NB_PID_MAX; i++) >> if (ts->pids[i]) >> mpegts_close_filter(ts, ts->pids[i]); > > LGTM. I assume the pools for the smaller sizes will not end up being > slower than just allocating new buffers each time. I tried to measure this but there was no significant difference. Will apply. Thanks, Marton
diff --git a/libavformat/mpegts.c b/libavformat/mpegts.c index 7f56bacb2c..fbafc1d257 100644 --- a/libavformat/mpegts.c +++ b/libavformat/mpegts.c @@ -170,6 +170,7 @@ struct MpegTSContext { int current_pid; AVStream *epg_stream; + AVBufferPool* pools[32]; }; #define MPEGTS_OPTIONS \ @@ -1103,6 +1104,18 @@ static int read_sl_header(PESContext *pes, SLConfigDescr *sl, return (get_bits_count(&gb) + 7) >> 3; } +static AVBufferRef *buffer_pool_get(MpegTSContext *ts, int size) +{ + int index = av_log2(size + AV_INPUT_BUFFER_PADDING_SIZE); + if (!ts->pools[index]) { + int pool_size = FFMIN(MAX_PES_PAYLOAD + AV_INPUT_BUFFER_PADDING_SIZE, 2 << index); + ts->pools[index] = av_buffer_pool_init(pool_size, NULL); + if (!ts->pools[index]) + return NULL; + } + return av_buffer_pool_get(ts->pools[index]); +} + /* return non zero if a packet could be constructed */ static int mpegts_push_data(MpegTSFilter *filter, const uint8_t *buf, int buf_size, int is_start, @@ -1177,8 +1190,8 @@ static int mpegts_push_data(MpegTSFilter *filter, pes->total_size = MAX_PES_PAYLOAD; /* allocate pes buffer */ - pes->buffer = av_buffer_alloc(pes->total_size + - AV_INPUT_BUFFER_PADDING_SIZE); + pes->buffer = buffer_pool_get(ts, pes->total_size); + if (!pes->buffer) return AVERROR(ENOMEM); @@ -1351,8 +1364,7 @@ skip: if (ret < 0) return ret; pes->total_size = MAX_PES_PAYLOAD; - pes->buffer = av_buffer_alloc(pes->total_size + - AV_INPUT_BUFFER_PADDING_SIZE); + pes->buffer = buffer_pool_get(ts, pes->total_size); if (!pes->buffer) return AVERROR(ENOMEM); ts->stop_parse = 1; @@ -3200,6 +3212,9 @@ static void mpegts_free(MpegTSContext *ts) clear_programs(ts); + for (i = 0; i < FF_ARRAY_ELEMS(ts->pools); i++) + av_buffer_pool_uninit(&ts->pools[i]); + for (i = 0; i < NB_PID_MAX; i++) if (ts->pids[i]) mpegts_close_filter(ts, ts->pids[i]);
This brings a performance improvement when demuxing files, most of the improvement comes from buffer pooling unbound packets. time ffprobe -i samples/ffmpeg-bugs/trac/ticket6132/Samsung_HDR_-_Chasing_the_Light.ts -show_packets >/dev/null 2>&1 Before: real 0m1.967s user 0m1.471s sys 0m0.493s After: real 0m1.497s user 0m1.364s sys 0m0.129s Based on a patch of James Almer. Signed-off-by: Marton Balint <cus@passwd.hu> --- libavformat/mpegts.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-)