avformat/av1: Avoid allocation + copying when filtering OBUs

Certain types of OBUs are stripped away before muxing into Matroska and
ISOBMFF; there are two functions to do this: One that outputs by
directly writing in an AVIOContext and one that returns a freshly
allocated buffer with the units not stripped away copied into it.

The latter option is bad for performance, especially when the input
does already not contain any of the units intended to be stripped away
(this covers typical remuxing scenarios). Therefore this commit changes
this by avoiding allocating and copying when possible; it is possible if
the OBUs to be retained are consecutively in the input buffer (without
an OBU to be discarded between them). In this case, the caller receives
the offset as well as the length of the part of the buffer that contains
the units to be kept. This also avoids copying when e.g. the only unit
to be discarded is a temporal delimiter at the front.

For a 22.7mb/s file with average framesize 113 kB this improved the time
for the calls to ff_av1_filter_obus_buf() when writing Matroska from
313319 decicycles to 2368 decicycles; for another file with 1.5mb/s
(average framesize 7.3 kB) it improved from 34539 decicycles to 1922
decicyles. For these files the only units that needed to be stripped
away were temporal unit delimiters at the front.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>

1 files changed, 41 insertions, 9 deletions

diff --git a/libavformat/av1.c b/libavformat/av1.c
index 709484b361..1e7a67d2f2 100644
--- a/libavformat/av1.c
+++ b/libavformat/av1.c
@@ -29,13 +29,20 @@
 #include "avio.h"
 #include "avio_internal.h"
 
-int ff_av1_filter_obus(AVIOContext *pb, const uint8_t *buf, int size)
+static int av1_filter_obus(AVIOContext *pb, const uint8_t *buf,
+                           int size, int *offset)
 {
-    const uint8_t *end = buf + size;
+    const uint8_t *start = buf, *end = buf + size;
     int64_t obu_size;
-    int start_pos, type, temporal_id, spatial_id;
-
-    size = 0;
+    int off, start_pos, type, temporal_id, spatial_id;
+    enum {
+        START_NOT_FOUND,
+        START_FOUND,
+        END_FOUND,
+        OFFSET_IMPOSSIBLE,
+    } state = START_NOT_FOUND;
+
+    off = size = 0;
     while (buf < end) {
         int len = parse_obu_header(buf, end - buf, &obu_size, &start_pos,
                                    &type, &temporal_id, &spatial_id);
@@ -47,8 +54,16 @@ int ff_av1_filter_obus(AVIOContext *pb, const uint8_t *buf, int size)
         case AV1_OBU_REDUNDANT_FRAME_HEADER:
         case AV1_OBU_TILE_LIST:
         case AV1_OBU_PADDING:
+            if (state == START_FOUND)
+                state = END_FOUND;
             break;
         default:
+            if (state == START_NOT_FOUND) {
+                off   = buf - start;
+                state = START_FOUND;
+            } else if (state == END_FOUND) {
+                state = OFFSET_IMPOSSIBLE;
+            }
             if (pb)
                 avio_write(pb, buf, len);
             size += len;
@@ -57,19 +72,35 @@ int ff_av1_filter_obus(AVIOContext *pb, const uint8_t *buf, int size)
         buf += len;
     }
 
+    if (offset)
+        *offset = state != OFFSET_IMPOSSIBLE ? off : -1;
+
     return size;
 }
 
-int ff_av1_filter_obus_buf(const uint8_t *in, uint8_t **out, int *size)
+int ff_av1_filter_obus(AVIOContext *pb, const uint8_t *buf, int size)
+{
+    return av1_filter_obus(pb, buf, size, NULL);
+}
+
+int ff_av1_filter_obus_buf(const uint8_t *in, uint8_t **out,
+                           int *size, int *offset)
 {
     AVIOContext pb;
     uint8_t *buf;
-    int len, ret;
+    int len, off, ret;
 
-    len = ret = ff_av1_filter_obus(NULL, in, *size);
+    len = ret = av1_filter_obus(NULL, in, *size, &off);
     if (ret < 0) {
         return ret;
     }
+    if (off >= 0) {
+        *out    = (uint8_t *)in;
+        *size   = len;
+        *offset = off;
+
+        return 0;
+    }
 
     buf = av_malloc(len + AV_INPUT_BUFFER_PADDING_SIZE);
     if (!buf)
@@ -77,13 +108,14 @@ int ff_av1_filter_obus_buf(const uint8_t *in, uint8_t **out, int *size)
 
     ffio_init_context(&pb, buf, len, 1, NULL, NULL, NULL, NULL);
 
-    ret = ff_av1_filter_obus(&pb, in, *size);
+    ret = av1_filter_obus(&pb, in, *size, NULL);
     av_assert1(ret == len);
 
     memset(buf + len, 0, AV_INPUT_BUFFER_PADDING_SIZE);
 
     *out  = buf;
     *size = len;
+    *offset = 0;
 
     return 0;
 }