@matheusbsbs / matheus-bagliano / commits / be18153b97

builtin/pack-objects.c: avoid iterating all refs

In git-pack-objects, we iterate over all the tags if the --include-tag option is passed on the command line. For some reason this uses for_each_ref which is expensive if the repo has many refs. We should use for_each_tag_ref instead. Because the add_ref_tag callback will now only visit tags we simplified it a bit. The motivation for this change is that we observed performance issues with a repository on gitlab.com that has 500,000 refs but only 2,000 tags. The fetch traffic on that repo is dominated by CI, and when we changed CI to fetch with 'git fetch --no-tags' we saw a dramatic change in the CPU profile of git-pack-objects. This lead us to this particular ref walk. More details in: https://gitlab.com/gitlab-com/gl-infra/scalability/-/issues/746#note_483546598 Signed-off-by: Jacob Vosmaer <jacob@gitlab.com> Reviewed-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Jacob Vosmaer committed Jan 20, 2021 at 13:45 UTC be18153b975844f8792b03e337f1a4c86fe87531

1 file changed +3 -5

builtin/pack-objects.c

+3 -5

@@ -2803,13 +2803,11 @@ static void add_tag_chain(const struct object_id *oid)

2803 }

2804 }

2805

2806 -static int add_ref_tag(const char *path, const struct object_id *oid, int flag, void *cb_data)

2806 +static int add_ref_tag(const char *tag, const struct object_id *oid, int flag, void *cb_data)

2807 {

2808 struct object_id peeled;

2809

2810 - if (starts_with(path, "refs/tags/") && /* is a tag? */

2811 - !peel_ref(path, &peeled) && /* peelable? */

2812 - obj_is_packed(&peeled)) /* object packed? */

2810 + if (!peel_ref(tag, &peeled) && obj_is_packed(&peeled))

2811 add_tag_chain(oid);

2812 return 0;

2813 }

@@ -3740,7 +3738,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)

3738 }

3739 cleanup_preferred_base();

3740 if (include_tag && nr_result)

3743 - for_each_ref(add_ref_tag, NULL);

3741 + for_each_tag_ref(add_ref_tag, NULL);

3742 stop_progress(&progress_state);

3743 trace2_region_leave("pack-objects", "enumerate-objects",

3744 the_repository);