git/list[1] front-page[2] threads[3] people[4] search[5] about
 

Re: [PATCH 07/18] sha1_file: support lazily fetching missing objects

From
Christian Couder <christian.couder@gmail.com>
Date
Oct 12, 2017, 14:42 UTC
Message-ID
<CAP8UFD2THRj7+RXmismUtUOpXQv4wM7aZsejpd_FHEOycP+ZJA@mail.gmail.com>
In-Reply-To
<5a9242024013345d7a3b0f63580360cdc8cc1c43.1506714999.git.jonathantanmy@google.com>
On Fri, Sep 29, 2017 at 10:11 PM, Jonathan Tan <jonathantanmy@google.com> wrote:
Show 79 quoted lines
> diff --git a/sha1_file.c b/sha1_file.c
> index b4a67bb83..77aa0ffdf 100644
> --- a/sha1_file.c
> +++ b/sha1_file.c
> @@ -29,6 +29,7 @@
>  #include "mergesort.h"
>  #include "quote.h"
>  #include "packfile.h"
> +#include "fetch-object.h"
>
>  const unsigned char null_sha1[GIT_MAX_RAWSZ];
>  const struct object_id null_oid;
> @@ -1149,6 +1150,8 @@ static int sha1_loose_object_info(const unsigned char *sha1,
>         return (status < 0) ? status : 0;
>  }
>
> +int fetch_if_missing = 1;
> +
>  int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi, unsigned flags)
>  {
>         static struct object_info blank_oi = OBJECT_INFO_INIT;
> @@ -1157,6 +1160,7 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
>         const unsigned char *real = (flags & OBJECT_INFO_LOOKUP_REPLACE) ?
>                                     lookup_replace_object(sha1) :
>                                     sha1;
> +       int already_retried = 0;
>
>         if (!oi)
>                 oi = &blank_oi;
> @@ -1181,28 +1185,36 @@ int sha1_object_info_extended(const unsigned char *sha1, struct object_info *oi,
>                 }
>         }
>
> -       if (!find_pack_entry(real, &e)) {
> -               /* Most likely it's a loose object. */
> -               if (!sha1_loose_object_info(real, oi, flags))
> -                       return 0;
> +retry:
> +       if (find_pack_entry(real, &e))
> +               goto found_packed;
>
> -               /* Not a loose object; someone else may have just packed it. */
> -               if (flags & OBJECT_INFO_QUICK) {
> -                       return -1;
> -               } else {
> -                       reprepare_packed_git();
> -                       if (!find_pack_entry(real, &e))
> -                               return -1;
> -               }
> +       /* Most likely it's a loose object. */
> +       if (!sha1_loose_object_info(real, oi, flags))
> +               return 0;
> +
> +       /* Not a loose object; someone else may have just packed it. */
> +       reprepare_packed_git();
> +       if (find_pack_entry(real, &e))
> +               goto found_packed;
> +
> +       /* Check if it is a missing object */
> +       if (fetch_if_missing && repository_format_partial_clone &&
> +           !already_retried) {
> +               fetch_object(repository_format_partial_clone, real);
> +               already_retried = 1;
> +               goto retry;
>         }
>
> +       return -1;
> +
> +found_packed:
>         if (oi == &blank_oi)
>                 /*
>                  * We know that the caller doesn't actually need the
>                  * information below, so return early.
>                  */
>                 return 0;
> -
>         rtype = packed_object_info(e.p, e.offset, oi);
>         if (rtype < 0) {
>                 mark_bad_packed_object(e.p, real);

Instead of adding labels and gotos, I would suggest adding a new function like the following does on top of your changes:

diff --git a/sha1_file.c b/sha1_file.c
index cc1aa0bd7f..02a6ed1e9b 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1171,18 +1171,40 @@ static int sha1_loose_object_info(const
unsigned char *sha1,
        return (status < 0) ? status : 0;
 }

+int try_find_packed_entry_or_loose_object(const unsigned char *real,
struct object_info *oi,
+                                         unsigned flags, struct
pack_entry *e, int retry)
+{
+       if (find_pack_entry(real, e))
+               return 1;
+
+       /* Most likely it's a loose object. */
+       if (!sha1_loose_object_info(real, oi, flags))
+               return 0;
+
+       /* Not a loose object; someone else may have just packed it. */
+       reprepare_packed_git();
+       if (find_pack_entry(real, e))
+               return 1;
+
+       /* Check if it is a missing object */
+       if (fetch_if_missing && repository_format_partial_clone && retry) {
+               fetch_object(repository_format_partial_clone, real);
+               return try_find_packed_entry_or_loose_object(real, oi,
flags, e, 0);
+       }
+
+       return -1;
+}
+
 int fetch_if_missing = 1;

 int sha1_object_info_extended(const unsigned char *sha1, struct
object_info *oi, unsigned flags)
 {
        static struct object_info blank_oi = OBJECT_INFO_INIT;
        struct pack_entry e;
-       int rtype;
+       int rtype, res;
        const unsigned char *real = (flags & OBJECT_INFO_LOOKUP_REPLACE) ?
                                    lookup_replace_object(sha1) :
                                    sha1;
-       int already_retried = 0;
-
        if (!oi)
                oi = &blank_oi;

@@ -1206,30 +1228,10 @@ int sha1_object_info_extended(const unsigned
char *sha1, struct object_info *oi,
                }
        }

-retry:
-       if (find_pack_entry(real, &e))
-               goto found_packed;
-
-       /* Most likely it's a loose object. */
-       if (!sha1_loose_object_info(real, oi, flags))
-               return 0;
-
-       /* Not a loose object; someone else may have just packed it. */
-       reprepare_packed_git();
-       if (find_pack_entry(real, &e))
-               goto found_packed;
-
-       /* Check if it is a missing object */
-       if (fetch_if_missing && repository_format_partial_clone &&
-           !already_retried) {
-               fetch_object(repository_format_partial_clone, real);
-               already_retried = 1;
-               goto retry;
-       }
-
-       return -1;
+       res = try_find_packed_entry_or_loose_object(real, oi, flags, &e, 1);
+       if (res < 1)
+               return res;

-found_packed:
        if (oi == &blank_oi)
                /*
                 * We know that the caller doesn't actually need the
Previous: Jonathan TanNext: Christian Couder
Message 6 of 28 in “Partial clone (from clone to lazy fetch in 18 patches)”
  1. 00/18 Partial clone (from clone to lazy fetch in 18 patches)Jonathan Tan, Sep 29, 2017
  2. 01/18 fsck: introduce partialclone extensionJonathan Tan, Sep 29, 2017
  3. 04/18 fsck: support promisor objects as CLI argumentJonathan Tan, Sep 29, 2017
  4. 06/18 introduce fetch-object: fetch one promisor objectJonathan Tan, Sep 29, 2017
  5. 07/18 sha1_file: support lazily fetching missing objectsJonathan Tan, Sep 29, 2017
  6. Christian CouderOct 12, 2017
  7. Christian CouderOct 12, 2017
  8. 08/18 rev-list: support termination at promisor objectsJonathan Tan, Sep 29, 2017
  9. 02/18 fsck: support refs pointing to promisor objectsJonathan Tan, Sep 29, 2017
  10. 13/18 fetch: refactor calculation of remote listJonathan Tan, Sep 29, 2017
  11. 17/18 unpack-trees: batch fetching of missing blobsJonathan Tan, Sep 29, 2017
  12. 15/18 clone: support excluding large blobsJonathan Tan, Sep 29, 2017
  13. 14/18 fetch: support excluding large blobsJonathan Tan, Sep 29, 2017
  14. 16/18 clone: configure blobmaxbytes in created reposJonathan Tan, Sep 29, 2017
  15. 18/18 fetch-pack: restore save_commit_buffer after useJonathan Tan, Sep 29, 2017
  16. 03/18 fsck: support referenced promisor objectsJonathan Tan, Sep 29, 2017
  17. 12/18 fetch-pack: support excluding large blobsJonathan Tan, Sep 29, 2017
  18. 05/18 index-pack: refactor writing of .keep filesJonathan Tan, Sep 29, 2017
  19. 09/18 gc: do not repack promisor packfilesJonathan Tan, Sep 29, 2017
  20. 10/18 pack-objects: rename want_.* to ignore_.*Jonathan Tan, Sep 29, 2017
  21. 11/18 pack-objects: support --blob-max-bytesJonathan Tan, Sep 29, 2017
  22. Johannes SchindelinSep 29, 2017
  23. Junio C HamanoOct 2, 2017
  24. Christian CouderOct 3, 2017
  25. Junio C HamanoOct 3, 2017
  26. Jeff HostetlerOct 3, 2017
  27. Jonathan TanOct 3, 2017
  28. Jeff HostetlerOct 4, 2017

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.