git@vger.kernel.org mailing list mirror (one of many)
 help / Atom feed
From: Christian Couder <christian.couder@gmail.com>
To: Jonathan Tan <jonathantanmy@google.com>
Cc: git <git@vger.kernel.org>, Junio C Hamano <gitster@pobox.com>,
	Jeff Hostetler <git@jeffhostetler.com>,
	Ben Peart <peartben@gmail.com>
Subject: Re: [PATCH 07/18] sha1_file: support lazily fetching missing objects
Date: Thu, 12 Oct 2017 16:42:10 +0200
Message-ID: <CAP8UFD2THRj7+RXmismUtUOpXQv4wM7aZsejpd_FHEOycP+ZJA@mail.gmail.com> (raw)
In-Reply-To: <5a9242024013345d7a3b0f63580360cdc8cc1c43.1506714999.git.jonathantanmy@google.com>

On Fri, Sep 29, 2017 at 10:11 PM, Jonathan Tan <jonathantanmy@google.com> wrote:

> 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

  reply index

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-29 20:11 [PATCH 00/18] Partial clone (from clone to lazy fetch in 18 patches) Jonathan Tan
2017-09-29 20:11 ` [PATCH 01/18] fsck: introduce partialclone extension Jonathan Tan
2017-09-29 20:11 ` [PATCH 02/18] fsck: support refs pointing to promisor objects Jonathan Tan
2017-09-29 20:11 ` [PATCH 03/18] fsck: support referenced " Jonathan Tan
2017-09-29 20:11 ` [PATCH 04/18] fsck: support promisor objects as CLI argument Jonathan Tan
2017-09-29 20:11 ` [PATCH 05/18] index-pack: refactor writing of .keep files Jonathan Tan
2017-09-29 20:11 ` [PATCH 06/18] introduce fetch-object: fetch one promisor object Jonathan Tan
2017-09-29 20:11 ` [PATCH 07/18] sha1_file: support lazily fetching missing objects Jonathan Tan
2017-10-12 14:42   ` Christian Couder [this message]
2017-10-12 15:45     ` Christian Couder
2017-09-29 20:11 ` [PATCH 08/18] rev-list: support termination at promisor objects Jonathan Tan
2017-09-29 20:11 ` [PATCH 09/18] gc: do not repack promisor packfiles Jonathan Tan
2017-09-29 20:11 ` [PATCH 10/18] pack-objects: rename want_.* to ignore_.* Jonathan Tan
2017-09-29 20:11 ` [PATCH 11/18] pack-objects: support --blob-max-bytes Jonathan Tan
2017-09-29 20:11 ` [PATCH 12/18] fetch-pack: support excluding large blobs Jonathan Tan
2017-09-29 20:11 ` [PATCH 13/18] fetch: refactor calculation of remote list Jonathan Tan
2017-09-29 20:11 ` [PATCH 14/18] fetch: support excluding large blobs Jonathan Tan
2017-09-29 20:11 ` [PATCH 15/18] clone: " Jonathan Tan
2017-09-29 20:11 ` [PATCH 16/18] clone: configure blobmaxbytes in created repos Jonathan Tan
2017-09-29 20:11 ` [PATCH 17/18] unpack-trees: batch fetching of missing blobs Jonathan Tan
2017-09-29 20:11 ` [PATCH 18/18] fetch-pack: restore save_commit_buffer after use Jonathan Tan
2017-09-29 21:08 ` [PATCH 00/18] Partial clone (from clone to lazy fetch in 18 patches) Johannes Schindelin
2017-10-02  4:23 ` Junio C Hamano
2017-10-03  6:15 ` Christian Couder
2017-10-03  8:50   ` Junio C Hamano
2017-10-03 14:39     ` Jeff Hostetler
2017-10-03 23:42       ` Jonathan Tan
2017-10-04 13:30         ` Jeff Hostetler

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAP8UFD2THRj7+RXmismUtUOpXQv4wM7aZsejpd_FHEOycP+ZJA@mail.gmail.com \
    --to=christian.couder@gmail.com \
    --cc=git@jeffhostetler.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jonathantanmy@google.com \
    --cc=peartben@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org mailing list mirror (one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/
       or Tor2web: https://www.tor2web.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox