From: Han Xin <hanxin.hx@xxxxxxxxxxxxxxx>
We used to call "get_data()" in "unpack_non_delta_entry()" to read the
entire contents of a blob object, no matter how big it is. This
implementation may consume all the memory and cause OOM.
This can be improved by feeding data to "write_stream_object_file()"
in a stream. The input stream is implemented as an interface.
The difference with "write_loose_object()" is that we have no chance
to run "write_object_file_prepare()" to calculate the oid in advance.
In "write_loose_object()", we know the oid and we can write the
temporary file in the same directory as the final object, but for an
object with an undetermined oid, we don't know the exact directory for
the object, so we have to save the temporary file in ".git/objects/"
directory instead.
"freshen_packed_object()" or "freshen_loose_object()" will be called
inside "write_stream_object_file()" after obtaining the "oid".
Helped-by: René Scharfe <l.s.r@xxxxxx>
Helped-by: Ævar Arnfjörð Bjarmason <avarab@xxxxxxxxx>
Helped-by: Jiang Xin <zhiyou.jx@xxxxxxxxxxxxxxx>
Signed-off-by: Han Xin <hanxin.hx@xxxxxxxxxxxxxxx>
---
object-file.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++
object-store.h | 9 ++++++
2 files changed, 94 insertions(+)
diff --git a/object-file.c b/object-file.c
index e048f3d39e..d0573e2a61 100644
--- a/object-file.c
+++ b/object-file.c
@@ -1989,6 +1989,91 @@ static int freshen_packed_object(const struct object_id *oid)
return 1;
}
+int write_stream_object_file(struct input_stream *in_stream, size_t len,
+ enum object_type type, time_t mtime,
+ unsigned flags, struct object_id *oid)
+{
+ int fd, ret, flush = 0;
+ unsigned char compressed[4096];
+ git_zstream stream;
+ git_hash_ctx c;
+ struct object_id parano_oid;
+ static struct strbuf tmp_file = STRBUF_INIT;
+ static struct strbuf filename = STRBUF_INIT;
+ int dirlen;
+ char hdr[MAX_HEADER_LEN];
+ int hdrlen = sizeof(hdr);
+
+ /* Since "filename" is defined as static, it will be reused. So reset it
+ * first before using it. */
+ strbuf_reset(&filename);
+ /* When oid is not determined, save tmp file to odb path. */
+ strbuf_addf(&filename, "%s/", get_object_directory());
+
+ fd = create_tmpfile(&tmp_file, filename.buf, flags);
+ if (fd < 0)
+ return -1;
+
+ hdrlen = format_object_header(hdr, hdrlen, type, len);
+
+ /* Set it up and write header */
+ setup_stream_and_header(&stream, compressed, sizeof(compressed),
+ &c, hdr, hdrlen);
+
+ /* Then the data itself.. */
+ do {
+ unsigned char *in0 = stream.next_in;
+ if (!stream.avail_in) {
+ const void *in = in_stream->read(in_stream, &stream.avail_in);
+ stream.next_in = (void *)in;
+ in0 = (unsigned char *)in;
+ /* All data has been read. */
+ if (len + hdrlen == stream.total_in + stream.avail_in)
+ flush = Z_FINISH;
+ }
+ ret = git_deflate(&stream, flush);
+ the_hash_algo->update_fn(&c, in0, stream.next_in - in0);
+ if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
+ die(_("unable to write loose object file"));
+ stream.next_out = compressed;
+ stream.avail_out = sizeof(compressed);
+ } while (ret == Z_OK || ret == Z_BUF_ERROR);
+
+ if (ret != Z_STREAM_END)
+ die(_("unable to deflate new object streamingly (%d)"), ret);
+ ret = git_deflate_end_gently(&stream);
+ if (ret != Z_OK)
+ die(_("deflateEnd on object streamingly failed (%d)"), ret);
+ the_hash_algo->final_oid_fn(¶no_oid, &c);
+
+ close_loose_object(fd);
+
+ oidcpy(oid, ¶no_oid);
+
+ if (freshen_packed_object(oid) || freshen_loose_object(oid)) {
+ unlink_or_warn(tmp_file.buf);
+ return 0;
+ }
+
+ loose_object_path(the_repository, &filename, oid);
+
+ /* We finally know the object path, and create the missing dir. */
+ dirlen = directory_size(filename.buf);
+ if (dirlen) {
+ struct strbuf dir = STRBUF_INIT;
+ strbuf_add(&dir, filename.buf, dirlen - 1);
+
+ if (mkdir_in_gitdir(dir.buf) && errno != EEXIST) {
+ ret = error_errno(_("unable to create directory %s"), dir.buf);
+ strbuf_release(&dir);
+ return ret;
+ }
+ strbuf_release(&dir);
+ }
+
+ return finalize_object_file_with_mtime(tmp_file.buf, filename.buf, mtime, flags);
+}
+
int write_object_file_flags(const void *buf, unsigned long len,
const char *type, struct object_id *oid,
unsigned flags)
diff --git a/object-store.h b/object-store.h
index 952efb6a4b..061b0cb2ba 100644
--- a/object-store.h
+++ b/object-store.h
@@ -34,6 +34,11 @@ struct object_directory {
char *path;
};
+struct input_stream {
+ const void *(*read)(struct input_stream *, unsigned long *len);
+ void *data;
+};
+
KHASH_INIT(odb_path_map, const char * /* key: odb_path */,
struct object_directory *, 1, fspathhash, fspatheq)
@@ -232,6 +237,10 @@ static inline int write_object_file(const void *buf, unsigned long len,
return write_object_file_flags(buf, len, type, oid, 0);
}
+int write_stream_object_file(struct input_stream *in_stream, size_t len,
+ enum object_type type, time_t mtime,
+ unsigned flags, struct object_id *oid);
+
int hash_object_file_literally(const void *buf, unsigned long len,
const char *type, struct object_id *oid,
unsigned flags);
--
2.34.1.52.g80008efde6.agit.6.5.6
