This series makes "unpack-objects" capable of streaming large objects to disk. As 7/7 shows streaming e.g. a 100MB blob now uses ~5MB of memory instead of ~105MB. This streaming method is slower if you've got memory to handle the blobs in-core, but if you don't it allows you to unpack objects at all, as you might otherwise OOM. This series by Han Xin was originally waiting on some in-flight patches that landed in 430883a70c7 (Merge branch 'ab/object-file-api-updates', 2022-03-16), and until yesterday with 83937e95928 (Merge branch 'ns/batch-fsync', 2022-06-03) had a textual and semantic conflict with "master". Changes since v12: * Since v12 Han Xin submitted 1/1 here as https://lore.kernel.org/git/cover.1653015534.git.chiyutianyi@xxxxxxxxx/; I think this is better off reviewed as a whole, and hopefully will be picked up as such. * Dropped the previous 7/8, which was a refactoring to make 8/8 slightly smaller. Per dicsussion with René it's better to leave it out. * The rest (especially 2/8) is due to rebasing on ns/batch-fsync. Han Xin (4): unpack-objects: low memory footprint for get_data() in dry_run mode object-file.c: refactor write_loose_object() to several steps object-file.c: add "stream_loose_object()" to handle large object unpack-objects: use stream_loose_object() to unpack large objects Ævar Arnfjörð Bjarmason (3): object-file.c: do fsync() and close() before post-write die() object-file.c: factor out deflate part of write_loose_object() core doc: modernize core.bigFileThreshold documentation Documentation/config/core.txt | 33 +++-- builtin/unpack-objects.c | 103 ++++++++++++-- object-file.c | 237 +++++++++++++++++++++++++++----- object-store.h | 8 ++ t/t5351-unpack-large-objects.sh | 61 ++++++++ 5 files changed, 387 insertions(+), 55 deletions(-) create mode 100755 t/t5351-unpack-large-objects.sh Range-diff against v12: 1: e95f6a1cfb6 = 1: 12873fc9915 unpack-objects: low memory footprint for get_data() in dry_run mode 2: 54060eb8c6b ! 2: b3568f0c5c0 object-file.c: do fsync() and close() before post-write die() @@ Commit message Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@xxxxxxxxx> ## object-file.c ## -@@ object-file.c: void hash_object_file(const struct git_hash_algo *algo, const void *buf, - hash_object_file_literally(algo, buf, len, type_name(type), oid); - } - --/* Finalize a file on disk, and close it. */ -+/* -+ * We already did a write_buffer() to the "fd", let's fsync() -+ * and close(). -+ * -+ * Finalize a file on disk, and close it. We might still die() on a -+ * subsequent sanity check, but let's not add to that confusion by not -+ * flushing any outstanding writes to disk first. -+ */ - static void close_loose_object(int fd) - { - if (the_repository->objects->odb->will_destroy) @@ object-file.c: static int write_loose_object(const struct object_id *oid, char *hdr, die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid), ret); the_hash_algo->final_oid_fn(¶no_oid, &c); -+ close_loose_object(fd); ++ close_loose_object(fd, tmp_file.buf); + if (!oideq(oid, ¶no_oid)) die(_("confused by unstable object source data for %s"), oid_to_hex(oid)); -- close_loose_object(fd); +- close_loose_object(fd, tmp_file.buf); - if (mtime) { struct utimbuf utb; 3: 3dcaa5d6589 ! 3: 9dc0f56878a object-file.c: refactor write_loose_object() to several steps @@ object-file.c: static int write_loose_object(const struct object_id *oid, char * - ret); - the_hash_algo->final_oid_fn(¶no_oid, &c); + die(_("deflateEnd on object %s failed (%d)"), oid_to_hex(oid), ret); - close_loose_object(fd); + close_loose_object(fd, tmp_file.buf); if (!oideq(oid, ¶no_oid)) 4: 03f4e91ac89 = 4: a0434835fe7 object-file.c: factor out deflate part of write_loose_object() 5: 3d64cf1cf33 ! 5: 0b07b29836b object-file.c: add "stream_loose_object()" to handle large object @@ object-file.c: static int freshen_packed_object(const struct object_id *oid) + ret = end_loose_object_common(&c, &stream, oid); + if (ret != Z_OK) + die(_("deflateEnd on stream object failed (%d)"), ret); -+ close_loose_object(fd); ++ close_loose_object(fd, tmp_file.buf); + + if (freshen_packed_object(oid) || freshen_loose_object(oid)) { + unlink_or_warn(tmp_file.buf); 6: 33ffcbbc1f0 = 6: 5ed79c58b18 core doc: modernize core.bigFileThreshold documentation 7: 11f7aa026b4 < -: ----------- unpack-objects: refactor away unpack_non_delta_entry() 8: 34ee6a28a54 ! 7: 5bc8fa9bc8d unpack-objects: use stream_loose_object() to unpack large objects @@ Documentation/config/core.txt: usage, at the slight expense of increased disk us Specifies the pathname to the file that contains patterns to ## builtin/unpack-objects.c ## -@@ builtin/unpack-objects.c: static void added_object(unsigned nr, enum object_type type, - } +@@ builtin/unpack-objects.c: static void unpack_non_delta_entry(enum object_type type, unsigned long size, + write_object(nr, type, buf, size); } +struct input_zstream_data { @@ builtin/unpack-objects.c: static void added_object(unsigned nr, enum object_type void *delta_data, unsigned long delta_size) { @@ builtin/unpack-objects.c: static void unpack_one(unsigned nr) + } switch (type) { - case OBJ_BLOB: ++ case OBJ_BLOB: + if (!dry_run && size > big_file_threshold) { + stream_blob(size, nr); + return; @@ builtin/unpack-objects.c: static void unpack_one(unsigned nr) + /* fallthrough */ case OBJ_COMMIT: case OBJ_TREE: +- case OBJ_BLOB: case OBJ_TAG: + unpack_non_delta_entry(type, size, nr); + return; ## t/t5351-unpack-large-objects.sh ## @@ t/t5351-unpack-large-objects.sh: test_description='git unpack-objects with large objects' -- 2.36.1.1124.g52838f02905
