Re: [PATCH 21/23] midx: prevent duplicate packfile loads

From: Duy Nguyen <pclouds@gmail.com>
Date: Jun 9, 2018, 18:05 UTC
Message-ID: <CACsJy8DbF3AXuHK9yaEtYPwkhP_BC47b50iTT0tHqODGVp7FCA@mail.gmail.com>
In-Reply-To: <20180607140338.32440-22-dstolee@microsoft.com>

On Thu, Jun 7, 2018 at 4:07 PM Derrick Stolee <stolee@gmail.com> wrote:

>
> If the multi-pack-index contains a packfile, then we do not need to add
> that packfile to the packed_git linked list or the MRU list.

Because...?

I think I see the reason, but I'd like it spelled out to avoid any misunderstanding.

Show 82 quoted lines

>
> Signed-off-by: Derrick Stolee <dstolee@microsoft.com>
> ---
>  midx.c     | 23 +++++++++++++++++++++++
>  midx.h     |  1 +
>  packfile.c |  7 +++++++
>  3 files changed, 31 insertions(+)
>
> diff --git a/midx.c b/midx.c
> index 388d79b7d9..3242646fe0 100644
> --- a/midx.c
> +++ b/midx.c
> @@ -278,6 +278,29 @@ int fill_midx_entry(const struct object_id *oid, struct pack_entry *e, struct mi
>         return nth_midxed_pack_entry(m, e, pos);
>  }
>
> +int midx_contains_pack(struct midxed_git *m, const char *idx_name)
> +{
> +       uint32_t first = 0, last = m->num_packs;
> +
> +       while (first < last) {
> +               uint32_t mid = first + (last - first) / 2;
> +               const char *current;
> +               int cmp;
> +
> +               current = m->pack_names[mid];
> +               cmp = strcmp(idx_name, current);
> +               if (!cmp)
> +                       return 1;
> +               if (cmp > 0) {
> +                       first = mid + 1;
> +                       continue;
> +               }
> +               last = mid;
> +       }
> +
> +       return 0;
> +}
> +
>  int prepare_midxed_git_one(struct repository *r, const char *object_dir)
>  {
>         struct midxed_git *m = r->objects->midxed_git;
> diff --git a/midx.h b/midx.h
> index 497bdcc77c..c1db58d8c4 100644
> --- a/midx.h
> +++ b/midx.h
> @@ -13,6 +13,7 @@ struct object_id *nth_midxed_object_oid(struct object_id *oid,
>                                         struct midxed_git *m,
>                                         uint32_t n);
>  int fill_midx_entry(const struct object_id *oid, struct pack_entry *e, struct midxed_git *m);
> +int midx_contains_pack(struct midxed_git *m, const char *idx_name);
>  int prepare_midxed_git_one(struct repository *r, const char *object_dir);
>
>  int write_midx_file(const char *object_dir);
> diff --git a/packfile.c b/packfile.c
> index 059b2aa097..479cb69b9f 100644
> --- a/packfile.c
> +++ b/packfile.c
> @@ -746,6 +746,11 @@ static void prepare_packed_git_one(struct repository *r, char *objdir, int local
>         DIR *dir;
>         struct dirent *de;
>         struct string_list garbage = STRING_LIST_INIT_DUP;
> +       struct midxed_git *m = r->objects->midxed_git;
> +
> +       /* look for the multi-pack-index for this object directory */
> +       while (m && strcmp(m->object_dir, objdir))
> +               m = m->next;
>
>         strbuf_addstr(&path, objdir);
>         strbuf_addstr(&path, "/pack");
> @@ -772,6 +777,8 @@ static void prepare_packed_git_one(struct repository *r, char *objdir, int local
>                 base_len = path.len;
>                 if (strip_suffix_mem(path.buf, &base_len, ".idx")) {
>                         /* Don't reopen a pack we already have. */
> +                       if (m && midx_contains_pack(m, de->d_name))
> +                               continue;
>                         for (p = r->objects->packed_git; p;
>                              p = p->next) {
>                                 size_t len;
> --
> 2.18.0.rc1
>

-- 
Duy