Merge branch 'hx/unpack-streaming' into seen

source: <[email protected]>

* hx/unpack-streaming:
  unpack-objects: use stream_loose_object() to unpack large objects
  core doc: modernize core.bigFileThreshold documentation
  object-file.c: add "stream_loose_object()" to handle large object
  object-file.c: factor out deflate part of write_loose_object()
  object-file.c: refactor write_loose_object() to several steps
  object-file.c: do fsync() and close() before post-write die()
  unpack-objects: low memory footprint for get_data() in dry_run mode

Author: gitster

Documentation/config/core.txt

@@ -444,17 +444,32 @@ You probably do not need to adjust this value.
 Common unit suffixes of 'k', 'm', or 'g' are supported.
 
 core.bigFileThreshold::
-	Files larger than this size are stored deflated, without
-	attempting delta compression.  Storing large files without
-	delta compression avoids excessive memory usage, at the
-	slight expense of increased disk usage. Additionally files
-	larger than this size are always treated as binary.
+	The size of files considered "big", which as discussed below
+	changes the behavior of numerous git commands, as well as how
+	such files are stored within the repository. The default is
+	512 MiB. Common unit suffixes of 'k', 'm', or 'g' are
+	supported.
 +
-Default is 512 MiB on all platforms.  This should be reasonable
-for most projects as source code and other text files can still
-be delta compressed, but larger binary media files won't be.
+Files above the configured limit will be:
 +
-Common unit suffixes of 'k', 'm', or 'g' are supported.
+* Stored deflated, without attempting delta compression.
++
+The default limit is primarily set with this use-case in mind. With it
+most projects will have their source code and other text files delta
+compressed, but not larger binary media files.
++
+Storing large files without delta compression avoids excessive memory
+usage, at the slight expense of increased disk usage.
++
+* Will be treated as if though they were labeled "binary" (see
+  linkgit:gitattributes[5]). This means that e.g. linkgit:git-log[1]
+  and linkgit:git-diff[1] will not diffs for files above this limit.
++
+* Will be generally be streamed when written, which avoids excessive
+memory usage, at the cost of some fixed overhead. Commands that make
+use of this include linkgit:git-archive[1],
+linkgit:git-fast-import[1], linkgit:git-index-pack[1],
+linkgit:git-unpack-objects[1] and linkgit:git-fsck[1].
 
 core.excludesFile::
 	Specifies the pathname to the file that contains patterns to

builtin/unpack-objects.c

@@ -97,15 +97,26 @@ static void use(int bytes)
 	display_throughput(progress, consumed_bytes);
 }
 
+/*
+ * Decompress zstream from stdin and return specific size of data.
+ * The caller is responsible to free the returned buffer.
+ *
+ * But for dry_run mode, "get_data()" is only used to check the
+ * integrity of data, and the returned buffer is not used at all.
+ * Therefore, in dry_run mode, "get_data()" will release the small
+ * allocated buffer which is reused to hold temporary zstream output
+ * and return NULL instead of returning garbage data.
+ */
 static void *get_data(unsigned long size)
 {
 	git_zstream stream;
-	void *buf = xmallocz(size);
+	unsigned long bufsize = dry_run && size > 8192 ? 8192 : size;
+	void *buf = xmallocz(bufsize);
 
 	memset(&stream, 0, sizeof(stream));
 
 	stream.next_out = buf;
-	stream.avail_out = size;
+	stream.avail_out = bufsize;
 	stream.next_in = fill(1);
 	stream.avail_in = len;
 	git_inflate_init(&stream);
@@ -125,8 +136,15 @@ static void *get_data(unsigned long size)
 		}
 		stream.next_in = fill(1);
 		stream.avail_in = len;
+		if (dry_run) {
+			/* reuse the buffer in dry_run mode */
+			stream.next_out = buf;
+			stream.avail_out = bufsize;
+		}
 	}
 	git_inflate_end(&stream);
+	if (dry_run)
+		FREE_AND_NULL(buf);
 	return buf;
 }
 
@@ -326,10 +344,70 @@ static void unpack_non_delta_entry(enum object_type type, unsigned long size,
 {
 	void *buf = get_data(size);
 
-	if (!dry_run && buf)
+	if (buf)
 		write_object(nr, type, buf, size);
-	else
-		free(buf);
+}
+
+struct input_zstream_data {
+	git_zstream *zstream;
+	unsigned char buf[8192];
+	int status;
+};
+
+static const void *feed_input_zstream(struct input_stream *in_stream,
+				      unsigned long *readlen)
+{
+	struct input_zstream_data *data = in_stream->data;
+	git_zstream *zstream = data->zstream;
+	void *in = fill(1);
+
+	if (in_stream->is_finished) {
+		*readlen = 0;
+		return NULL;
+	}
+
+	zstream->next_out = data->buf;
+	zstream->avail_out = sizeof(data->buf);
+	zstream->next_in = in;
+	zstream->avail_in = len;
+
+	data->status = git_inflate(zstream, 0);
+
+	in_stream->is_finished = data->status != Z_OK;
+	use(len - zstream->avail_in);
+	*readlen = sizeof(data->buf) - zstream->avail_out;
+
+	return data->buf;
+}
+
+static void stream_blob(unsigned long size, unsigned nr)
+{
+	git_zstream zstream = { 0 };
+	struct input_zstream_data data = { 0 };
+	struct input_stream in_stream = {
+		.read = feed_input_zstream,
+		.data = &data,
+	};
+	struct obj_info *info = &obj_list[nr];
+
+	data.zstream = &zstream;
+	git_inflate_init(&zstream);
+
+	if (stream_loose_object(&in_stream, size, &info->oid))
+		die(_("failed to write object in stream"));
+
+	if (data.status != Z_STREAM_END)
+		die(_("inflate returned (%d)"), data.status);
+	git_inflate_end(&zstream);
+
+	if (strict) {
+		struct blob *blob = lookup_blob(the_repository, &info->oid);
+
+		if (!blob)
+			die(_("invalid blob object from stream"));
+		blob->object.flags |= FLAG_WRITTEN;
+	}
+	info->obj = NULL;
 }
 
 static int resolve_against_held(unsigned nr, const struct object_id *base,
@@ -359,10 +437,8 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
 		oidread(&base_oid, fill(the_hash_algo->rawsz));
 		use(the_hash_algo->rawsz);
 		delta_data = get_data(delta_size);
-		if (dry_run || !delta_data) {
-			free(delta_data);
+		if (!delta_data)
 			return;
-		}
 		if (has_object_file(&base_oid))
 			; /* Ok we have this one */
 		else if (resolve_against_held(nr, &base_oid,
@@ -398,10 +474,8 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
 			die("offset value out of bound for delta base object");
 
 		delta_data = get_data(delta_size);
-		if (dry_run || !delta_data) {
-			free(delta_data);
+		if (!delta_data)
 			return;
-		}
 		lo = 0;
 		hi = nr;
 		while (lo < hi) {
@@ -468,9 +542,14 @@ static void unpack_one(unsigned nr)
 	}
 
 	switch (type) {
+	case OBJ_BLOB:
+		if (!dry_run && size > big_file_threshold) {
+			stream_blob(size, nr);
+			return;
+		}
+		/* fallthrough */
 	case OBJ_COMMIT:
 	case OBJ_TREE:
-	case OBJ_BLOB:
 	case OBJ_TAG:
 		unpack_non_delta_entry(type, size, nr);
 		return;