avformat/demux: add duration_probesize AVOption

Yet another probesize used to get the durations when
estimate_timings_from_pts is required. It is aimed at users interested
in better durations probing for itself, or because using
avformat_find_stream_info indirectly and requiring exact values: for
concatdec for example, especially if streamcopying above it.
The current code is a performance trade-off that can fail to get video
stream durations in a scenario with high bitrates and buffering for
files ending cleanly (as opposed to live captures): the physical gap
between the last video packet and the last audio packet is very high in
such a case.

Default behaviour is unchanged: 250k up to 250k << 6 (step by step).
Setting this new option has two effects:
- override the maximum probesize (currently 250k << 6)
- reduce the number of steps to 1 instead of 6, this is to avoid
detecting the audio "too early" and failing to reach a video packet.
Even if a single audio stream duration is found but not the other
audio/video stream durations, there will be a retry, so at the end the
full user-overriden probesize will be used as expected by the user.

Signed-off-by: Nicolas Gaullier <nicolas.gaullier@cji.paris>

6 files changed, 45 insertions, 9 deletions

diff --git a/doc/APIchanges b/doc/APIchanges
index aa102b4925..e7677658b1 100644
--- a/doc/APIchanges
+++ b/doc/APIchanges
@@ -2,6 +2,9 @@ The last version increases of all libraries were on 2024-03-07
 
 API changes, most recent first:
 
+2024-03-29 - xxxxxxxxxx - lavf 61.3.100 - avformat.h
+  Add AVFormatContext.duration_probesize.
+
 2024-03-27 - xxxxxxxxxx - lavu 59.10.100 - frame.h
   Add AVSideDataDescriptor, enum AVSideDataProps, and
   av_frame_side_data_desc().
diff --git a/doc/formats.texi b/doc/formats.texi
index 69fc1457a4..876a9e92b3 100644
--- a/doc/formats.texi
+++ b/doc/formats.texi
@@ -225,9 +225,26 @@ Specifies the maximum number of streams. This can be used to reject files that
 would require too many resources due to a large number of streams.
 
 @item skip_estimate_duration_from_pts @var{bool} (@emph{input})
-Skip estimation of input duration when calculated using PTS.
+Skip estimation of input duration if it requires an additional probing for PTS at end of file.
 At present, applicable for MPEG-PS and MPEG-TS.
 
+@item duration_probesize @var{integer} (@emph{input})
+Set probing size, in bytes, for input duration estimation when it actually requires
+an additional probing for PTS at end of file (at present: MPEG-PS and MPEG-TS).
+It is aimed at users interested in better durations probing for itself, or indirectly
+because using the concat demuxer, for example.
+The typical use case is an MPEG-TS CBR with a high bitrate, high video buffering and
+ending cleaning with similar PTS for video and audio: in such a scenario, the large
+physical gap between the last video packet and the last audio packet makes it necessary
+to read many bytes in order to get the video stream duration.
+Another use case is where the default probing behaviour only reaches a single video frame which is
+not the last one of the stream due to frame reordering, so the duration is not accurate.
+Setting this option has a performance impact even for small files because the probing
+size is fixed.
+Default behaviour is a general purpose trade-off, largely adaptive, but the probing size
+will not be extended to get streams durations at all costs.
+Must be an integer not lesser than 1, or 0 for default behaviour.
+
 @item strict, f_strict @var{integer} (@emph{input/output})
 Specify how strictly to follow the standards. @code{f_strict} is deprecated and
 should be used only via the @command{ffmpeg} tool.
diff --git a/libavformat/avformat.h b/libavformat/avformat.h
index de40397676..8afdcd9fd0 100644
--- a/libavformat/avformat.h
+++ b/libavformat/avformat.h
@@ -1439,7 +1439,7 @@ typedef struct AVFormatContext {
      *
      * @note this is \e not  used for determining the \ref AVInputFormat
      *       "input format"
-     * @sa format_probesize
+     * @see format_probesize
      */
     int64_t probesize;
 
@@ -1667,6 +1667,8 @@ typedef struct AVFormatContext {
      * Skip duration calcuation in estimate_timings_from_pts.
      * - encoding: unused
      * - decoding: set by user
+     *
+     * @see duration_probesize
      */
     int skip_estimate_duration_from_pts;
 
@@ -1729,7 +1731,7 @@ typedef struct AVFormatContext {
      *
      * Demuxing only, set by the caller before avformat_open_input().
      *
-     * @sa probesize
+     * @see probesize
      */
     int format_probesize;
 
@@ -1870,6 +1872,16 @@ typedef struct AVFormatContext {
      * @return 0 on success, a negative AVERROR code on failure
      */
     int (*io_close2)(struct AVFormatContext *s, AVIOContext *pb);
+
+    /**
+     * Maximum number of bytes read from input in order to determine stream durations
+     * when using estimate_timings_from_pts in avformat_find_stream_info().
+     * Demuxing only, set by the caller before avformat_find_stream_info().
+     * Can be set to 0 to let avformat choose using a heuristic.
+     *
+     * @see skip_estimate_duration_from_pts
+     */
+    int64_t duration_probesize;
 } AVFormatContext;
 
 /**
diff --git a/libavformat/demux.c b/libavformat/demux.c
index 3ead690df0..abfd5fee7d 100644
--- a/libavformat/demux.c
+++ b/libavformat/demux.c
@@ -1804,8 +1804,9 @@ static void estimate_timings_from_bit_rate(AVFormatContext *ic)
                "Estimating duration from bitrate, this may be inaccurate\n");
 }
 
-#define DURATION_MAX_READ_SIZE 250000LL
-#define DURATION_MAX_RETRY 6
+#define DURATION_DEFAULT_MAX_READ_SIZE 250000LL
+#define DURATION_DEFAULT_MAX_RETRY 6
+#define DURATION_MAX_RETRY 1
 
 /* only usable for MPEG-PS streams */
 static void estimate_timings_from_pts(AVFormatContext *ic, int64_t old_offset)
@@ -1813,6 +1814,8 @@ static void estimate_timings_from_pts(AVFormatContext *ic, int64_t old_offset)
     FFFormatContext *const si = ffformatcontext(ic);
     AVPacket *const pkt = si->pkt;
     int num, den, read_size, ret;
+    int64_t duration_max_read_size = ic->duration_probesize ? ic->duration_probesize >> DURATION_MAX_RETRY : DURATION_DEFAULT_MAX_READ_SIZE;
+    int duration_max_retry = ic->duration_probesize ? DURATION_MAX_RETRY : DURATION_DEFAULT_MAX_RETRY;
     int found_duration = 0;
     int is_end;
     int64_t filesize, offset, duration;
@@ -1848,7 +1851,7 @@ static void estimate_timings_from_pts(AVFormatContext *ic, int64_t old_offset)
     filesize = ic->pb ? avio_size(ic->pb) : 0;
     do {
         is_end = found_duration;
-        offset = filesize - (DURATION_MAX_READ_SIZE << retry);
+        offset = filesize - (duration_max_read_size << retry);
         if (offset < 0)
             offset = 0;
 
@@ -1857,7 +1860,7 @@ static void estimate_timings_from_pts(AVFormatContext *ic, int64_t old_offset)
         for (;;) {
             AVStream *st;
             FFStream *sti;
-            if (read_size >= DURATION_MAX_READ_SIZE << (FFMAX(retry - 1, 0)))
+            if (read_size >= duration_max_read_size << (FFMAX(retry - 1, 0)))
                 break;
 
             do {
@@ -1911,7 +1914,7 @@ static void estimate_timings_from_pts(AVFormatContext *ic, int64_t old_offset)
         }
     } while (!is_end &&
              offset &&
-             ++retry <= DURATION_MAX_RETRY);
+             ++retry <= duration_max_retry);
 
     av_opt_set_int(ic, "skip_changes", 0, AV_OPT_SEARCH_CHILDREN);
 
diff --git a/libavformat/options_table.h b/libavformat/options_table.h
index b9dca147f9..311880d24d 100644
--- a/libavformat/options_table.h
+++ b/libavformat/options_table.h
@@ -108,6 +108,7 @@ static const AVOption avformat_options[] = {
 {"max_streams", "maximum number of streams", OFFSET(max_streams), AV_OPT_TYPE_INT, { .i64 = 1000 }, 0, INT_MAX, D },
 {"skip_estimate_duration_from_pts", "skip duration calculation in estimate_timings_from_pts", OFFSET(skip_estimate_duration_from_pts), AV_OPT_TYPE_BOOL, {.i64 = 0}, 0, 1, D},
 {"max_probe_packets", "Maximum number of packets to probe a codec", OFFSET(max_probe_packets), AV_OPT_TYPE_INT, { .i64 = 2500 }, 0, INT_MAX, D },
+{"duration_probesize", "Maximum number of bytes to probe the durations of the streams in estimate_timings_from_pts", OFFSET(duration_probesize), AV_OPT_TYPE_INT64, {.i64 = 0 }, 0, INT64_MAX, D},
 {NULL},
 };
 
diff --git a/libavformat/version.h b/libavformat/version.h
index 904e7f06aa..7ff1483912 100644
--- a/libavformat/version.h
+++ b/libavformat/version.h
@@ -31,7 +31,7 @@
 
 #include "version_major.h"
 
-#define LIBAVFORMAT_VERSION_MINOR   2
+#define LIBAVFORMAT_VERSION_MINOR   3
 #define LIBAVFORMAT_VERSION_MICRO 100
 
 #define LIBAVFORMAT_VERSION_INT AV_VERSION_INT(LIBAVFORMAT_VERSION_MAJOR, \