repack: add `repack.packKeptObjects` config var

The git-repack command always passes `--honor-pack-keep`
to pack-objects. This has traditionally been a good thing,
as we do not want to duplicate those objects in a new pack,
and we are not going to delete the old pack.

However, when bitmaps are in use, it is important for a full
repack to include all reachable objects, even if they may be
duplicated in a .keep pack. Otherwise, we cannot generate
the bitmaps, as the on-disk format requires the set of
objects in the pack to be fully closed.

Even if the repository does not generally have .keep files,
a simultaneous push could cause a race condition in which a
.keep file exists at the moment of a repack. The repack may
try to include those objects in one of two situations:

1. The pushed .keep pack contains objects that were
already in the repository (e.g., blobs due to a revert of
an old commit).

2. Receive-pack updates the refs, making the objects
reachable, but before it removes the .keep file, the
repack runs.

In either case, we may prefer to duplicate some objects in
the new, full pack, and let the next repack (after the .keep
file is cleaned up) take care of removing them.

This patch introduces both a command-line and config option
to disable the `--honor-pack-keep` option.  By default, it
is triggered when pack.writeBitmaps (or `--write-bitmap-index`
is turned on), but specifying it explicitly can override the
behavior (e.g., in cases where you prefer .keep files to
bitmaps, but only when they are present).

Note that this option just disables the pack-objects
behavior. We still leave packs with a .keep in place, as we
do not necessarily know that we have duplicated all of their
objects.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 499a3c43608ecca1525756df78c31df1a1519a23..c0a6e0d05607698e71dd62537eb88fb0f5911475 100644 (file)
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -2128,6 +2128,13 @@ repack.usedeltabaseoffset::
        "false" and repack. Access from old Git versions over the
        native protocol are unaffected by this option.
 
        "false" and repack. Access from old Git versions over the
        native protocol are unaffected by this option.
 

+repack.packKeptObjects::
+       If set to true, makes `git repack` act as if
+       `--pack-kept-objects` was passed. See linkgit:git-repack[1] for
+       details. Defaults to `false` normally, but `true` if a bitmap
+       index is being written (either via `--write-bitmap-index` or
+       `pack.writeBitmaps`).
+

 rerere.autoupdate::
        When set to true, `git-rerere` updates the index with the
        resulting contents after it cleanly resolves conflicts using
 rerere.autoupdate::
        When set to true, `git-rerere` updates the index with the
        resulting contents after it cleanly resolves conflicts using

diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
index dad186c694cb6b03ec64f3767abc84f83cacc350..1eedf880ebadae3c95388d930c67296fc9a57088 100644 (file)
--- a/Documentation/git-repack.txt
+++ b/Documentation/git-repack.txt
@@ -117,6 +117,14 @@ other objects in that pack they already have locally.
        must be able to refer to all reachable objects. This option
        overrides the setting of `pack.writebitmaps`.
 
        must be able to refer to all reachable objects. This option
        overrides the setting of `pack.writebitmaps`.
 

+--pack-kept-objects::
+       Include objects in `.keep` files when repacking.  Note that we
+       still do not delete `.keep` packs after `pack-objects` finishes.
+       This means that we may duplicate objects, but this makes the
+       option safe to use when there are concurrent pushes or fetches.
+       This option is generally only useful if you are writing bitmaps
+       with `-b` or `pack.writebitmaps`, as it ensures that the
+       bitmapped packfile has the necessary objects.

 
 Configuration
 -------------
 
 Configuration
 -------------

diff --git a/builtin/repack.c b/builtin/repack.c
index 239f278fac9c2be6655458992022b23117ea5020..50cc2815279e17b255ddc74d23f619e1259b8a7c 100644 (file)
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -9,6 +9,7 @@
 #include "argv-array.h"
 
 static int delta_base_offset = 1;
 #include "argv-array.h"
 
 static int delta_base_offset = 1;

+static int pack_kept_objects = -1;

 static char *packdir, *packtmp;
 
 static const char *const git_repack_usage[] = {
 static char *packdir, *packtmp;
 
 static const char *const git_repack_usage[] = {


@@ -22,6 +23,10 @@ static int repack_config(const char *var, const char *value, void *cb)
                delta_base_offset = git_config_bool(var, value);
                return 0;
        }
                delta_base_offset = git_config_bool(var, value);
                return 0;
        }

+       if (!strcmp(var, "repack.packkeptobjects")) {
+               pack_kept_objects = git_config_bool(var, value);
+               return 0;
+       }

        return git_default_config(var, value, cb);
 }
 
        return git_default_config(var, value, cb);
 }
 


@@ -175,6 +180,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
                                N_("limits the maximum delta depth")),
                OPT_INTEGER(0, "max-pack-size", &max_pack_size,
                                N_("maximum size of each packfile")),
                                N_("limits the maximum delta depth")),
                OPT_INTEGER(0, "max-pack-size", &max_pack_size,
                                N_("maximum size of each packfile")),

+               OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects,
+                               N_("repack objects in packs marked with .keep")),

                OPT_END()
        };
 
                OPT_END()
        };
 


@@ -183,6 +190,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
        argc = parse_options(argc, argv, prefix, builtin_repack_options,
                                git_repack_usage, 0);
 
        argc = parse_options(argc, argv, prefix, builtin_repack_options,
                                git_repack_usage, 0);
 

+       if (pack_kept_objects < 0)
+               pack_kept_objects = write_bitmap;
+

        packdir = mkpathdup("%s/pack", get_object_directory());
        packtmp = mkpathdup("%s/.tmp-%d-pack", packdir, (int)getpid());
 
        packdir = mkpathdup("%s/pack", get_object_directory());
        packtmp = mkpathdup("%s/.tmp-%d-pack", packdir, (int)getpid());
 


@@ -190,7 +200,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 
        argv_array_push(&cmd_args, "pack-objects");
        argv_array_push(&cmd_args, "--keep-true-parents");
 
        argv_array_push(&cmd_args, "pack-objects");
        argv_array_push(&cmd_args, "--keep-true-parents");

-       argv_array_push(&cmd_args, "--honor-pack-keep");
+       if (!pack_kept_objects)
+               argv_array_push(&cmd_args, "--honor-pack-keep");

        argv_array_push(&cmd_args, "--non-empty");
        argv_array_push(&cmd_args, "--all");
        argv_array_push(&cmd_args, "--reflog");
        argv_array_push(&cmd_args, "--non-empty");
        argv_array_push(&cmd_args, "--all");
        argv_array_push(&cmd_args, "--reflog");

diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh
index d954b846a17d6374dd8c7dae7f901170ff3c8c24..44f949742152c8bf063c2493fb1de67df433de8c 100755 (executable)
--- a/t/t7700-repack.sh
+++ b/t/t7700-repack.sh
@@ -21,7 +21,7 @@ test_expect_success 'objects in packs marked .keep are not repacked' '
        objsha1=$(git verify-pack -v pack-$packsha1.idx | head -n 1 |
                sed -e "s/^\([0-9a-f]\{40\}\).*/\1/") &&
        mv pack-* .git/objects/pack/ &&
        objsha1=$(git verify-pack -v pack-$packsha1.idx | head -n 1 |
                sed -e "s/^\([0-9a-f]\{40\}\).*/\1/") &&
        mv pack-* .git/objects/pack/ &&

-       git repack -A -d -l &&
+       git repack --no-pack-kept-objects -A -d -l &&

        git prune-packed &&
        for p in .git/objects/pack/*.idx; do
                idx=$(basename $p)
        git prune-packed &&
        for p in .git/objects/pack/*.idx; do
                idx=$(basename $p)


@@ -35,6 +35,22 @@ test_expect_success 'objects in packs marked .keep are not repacked' '
        test -z "$found_duplicate_object"
 '
 
        test -z "$found_duplicate_object"
 '
 

+test_expect_success 'writing bitmaps can duplicate .keep objects' '
+       # build on $objsha1, $packsha1, and .keep state from previous
+       git repack -Adl &&
+       test_when_finished "found_duplicate_object=" &&
+       for p in .git/objects/pack/*.idx; do
+               idx=$(basename $p)
+               test "pack-$packsha1.idx" = "$idx" && continue
+               if git verify-pack -v $p | egrep "^$objsha1"; then
+                       found_duplicate_object=1
+                       echo "DUPLICATE OBJECT FOUND"
+                       break
+               fi
+       done &&
+       test "$found_duplicate_object" = 1
+'
+

 test_expect_success 'loose objects in alternate ODB are not repacked' '
        mkdir alt_objects &&
        echo `pwd`/alt_objects > .git/objects/info/alternates &&
 test_expect_success 'loose objects in alternate ODB are not repacked' '
        mkdir alt_objects &&
        echo `pwd`/alt_objects > .git/objects/info/alternates &&