avformat/mov: add interleaved_read option

For badly interleaved files, interleave packets from multiple tracks
at the demuxer level can trigger seeking back and forth, which can be
dramatically slow depending on the protocol. Demuxer level interleave
can be useless sometimes, e.g., reading mp4 via http and then
transcoding/remux to DASH. Disable this option when you don't need the
demuxer level interleave, and want to avoid the IO penalizes.

Co-authored-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>

doc/demuxers.texi

@@ -779,6 +779,13 @@ cast to int32 are used to adjust onward dts.
 
 Unit is the track time scale. Range is 0 to UINT_MAX. Default is @code{UINT_MAX - 48000*10} which allows upto
 a 10 second dts correction for 48 kHz audio streams while accommodating 99.9% of @code{uint32} range.
+
+@item interleaved_read
+Interleave packets from multiple tracks at demuxer level. For badly interleaved files, this prevents playback issues
+caused by large gaps between packets in different tracks, as MOV/MP4 do not have packet placement requirements.
+However, this can cause excessive seeking on very badly interleaved files, due to seeking between tracks, so disabling
+it may prevent I/O issues, at the expense of playback.
+
 @end table
 
 @subsection Audible AAX

libavformat/isom.h

@@ -327,6 +327,7 @@ typedef struct MOVContext {
         int64_t extent_offset;
     } *avif_info;
     int avif_info_size;
+    int interleaved_read;
 } MOVContext;
 
 int ff_mp4_read_descr_len(AVIOContext *pb);

libavformat/mov.c

@@ -8780,6 +8780,8 @@ static AVIndexEntry *mov_find_next_sample(AVFormatContext *s, AVStream **st)
     AVIndexEntry *sample = NULL;
     int64_t best_dts = INT64_MAX;
     int i;
+    MOVContext *mov = s->priv_data;
+    int no_interleave = !mov->interleaved_read || !(s->pb->seekable & AVIO_SEEKABLE_NORMAL);
     for (i = 0; i < s->nb_streams; i++) {
         AVStream *avst = s->streams[i];
         FFStream *const avsti = ffstream(avst);
@@ -8788,7 +8790,7 @@ static AVIndexEntry *mov_find_next_sample(AVFormatContext *s, AVStream **st)
             AVIndexEntry *current_sample = &avsti->index_entries[msc->current_sample];
             int64_t dts = av_rescale(current_sample->timestamp, AV_TIME_BASE, msc->time_scale);
             av_log(s, AV_LOG_TRACE, "stream %d, sample %d, dts %"PRId64"\n", i, msc->current_sample, dts);
-            if (!sample || (!(s->pb->seekable & AVIO_SEEKABLE_NORMAL) && current_sample->pos < sample->pos) ||
+            if (!sample || (no_interleave && current_sample->pos < sample->pos) ||
                 ((s->pb->seekable & AVIO_SEEKABLE_NORMAL) &&
                  ((msc->pb != s->pb && dts < best_dts) || (msc->pb == s->pb && dts != AV_NOPTS_VALUE &&
                  ((FFABS(best_dts - dts) <= AV_TIME_BASE && current_sample->pos < sample->pos) ||
@@ -9282,6 +9284,7 @@ static const AVOption mov_options[] = {
     { "enable_drefs", "Enable external track support.", OFFSET(enable_drefs), AV_OPT_TYPE_BOOL,
         {.i64 = 0}, 0, 1, FLAGS },
     { "max_stts_delta", "treat offsets above this value as invalid", OFFSET(max_stts_delta), AV_OPT_TYPE_INT, {.i64 = UINT_MAX-48000*10 }, 0, UINT_MAX, .flags = AV_OPT_FLAG_DECODING_PARAM },
+    { "interleaved_read", "Interleave packets from multiple tracks at demuxer level", OFFSET(interleaved_read), AV_OPT_TYPE_BOOL, {.i64 = 1 }, 0, 1, .flags = AV_OPT_FLAG_DECODING_PARAM },
 
     { NULL },
 };

libavformat/version.h

@@ -32,7 +32,7 @@
 #include "version_major.h"
 
 #define LIBAVFORMAT_VERSION_MINOR  12
-#define LIBAVFORMAT_VERSION_MICRO 100
+#define LIBAVFORMAT_VERSION_MICRO 101
 
 #define LIBAVFORMAT_VERSION_INT AV_VERSION_INT(LIBAVFORMAT_VERSION_MAJOR, \
                                                LIBAVFORMAT_VERSION_MINOR, \