repack: add --keep-unreachable option

The usual way to do a full repack (and what is done by
git-gc) is to run "repack -Ad --unpack-unreachable=<when>",
which will loosen any unreachable objects newer than
"<when>", and drop any older ones.

This is a safer alternative to "repack -ad", because
"<when>" becomes a grace period during which we will not
drop any new objects that are about to be referenced.
However, it isn't perfectly safe. It's always possible that
a process is about to reference an old object. Even if that
process were to take care to update the timestamp on the
object, there is no atomicity with a simultaneously running
"repack" process.

So while unlikely, there is a small race wherein we may drop
an object that is in the process of being referenced. If you
do automated repacking on a large number of active
repositories, you may hit it eventually, and the result is a
corrupted repository.

It would be nice to fix that race in the long run, but it's
complicated.  In the meantime, there is a much simpler
strategy for automated repository maintenance: do not drop
objects at all. We already have a "--keep-unreachable"
option in pack-objects; we just need to plumb it through
from git-repack.

Note that this _isn't_ plumbed through from git-gc, so at
this point it's strictly a tool for people doing their own
advanced repository maintenance strategy.

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

diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
index cde7b4441d5dcc7d926731cd46fe37f5bfbc430e..68702eab192b126fc2397cda87e39f4ac28c38fc 100644 (file)
--- a/Documentation/git-repack.txt
+++ b/Documentation/git-repack.txt
@@ -134,6 +134,12 @@ other objects in that pack they already have locally.
        the write of any objects that would be immediately pruned by
        a follow-up `git prune`.
 
+-k::
+--keep-unreachable::
+       When used with `-ad`, any unreachable objects from existing
+       packs will be appended to the end of the packfile instead of
+       being removed.
+
 Configuration
 -------------
 

diff --git a/builtin/repack.c b/builtin/repack.c
index 858db38f52e878a41cefdd47bbafd1250c7483b0..573e66c1b45f46fe1e1fdd27b0e5755d935f1d23 100644 (file)
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -146,6 +146,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
        int pack_everything = 0;
        int delete_redundant = 0;
        const char *unpack_unreachable = NULL;
+       int keep_unreachable = 0;
        const char *window = NULL, *window_memory = NULL;
        const char *depth = NULL;
        const char *max_pack_size = NULL;
@@ -175,6 +176,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
                                N_("write bitmap index")),
                OPT_STRING(0, "unpack-unreachable", &unpack_unreachable, N_("approxidate"),
                                N_("with -A, do not loosen objects older than this")),
+               OPT_BOOL('k', "keep-unreachable", &keep_unreachable,
+                               N_("with -a, repack unreachable objects")),
                OPT_STRING(0, "window", &window, N_("n"),
                                N_("size of the window used for delta compression")),
                OPT_STRING(0, "window-memory", &window_memory, N_("bytes"),
@@ -196,6 +199,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
        if (delete_redundant && repository_format_precious_objects)
                die(_("cannot delete packs in a precious-objects repo"));
 
+       if (keep_unreachable &&
+           (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)))
+               die(_("--keep-unreachable and -A are incompatible"));
+
        if (pack_kept_objects < 0)
                pack_kept_objects = write_bitmaps;
 
@@ -239,6 +246,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
                        } else if (pack_everything & LOOSEN_UNREACHABLE) {
                                argv_array_push(&cmd.args,
                                                "--unpack-unreachable");
+                       } else if (keep_unreachable) {
+                               argv_array_push(&cmd.args, "--keep-unreachable");
                        } else {
                                argv_array_push(&cmd.env_array, "GIT_REF_PARANOIA=1");
                        }

diff --git a/t/t7701-repack-unpack-unreachable.sh b/t/t7701-repack-unpack-unreachable.sh
index b66e3838665ea47d748a7e1a64facd755ee32fb8..f13df432992dc6da82fcca9317447b2d8381279b 100755 (executable)
--- a/t/t7701-repack-unpack-unreachable.sh
+++ b/t/t7701-repack-unpack-unreachable.sh
@@ -122,4 +122,19 @@ test_expect_success 'keep packed objects found only in index' '
        git cat-file blob :file
 '
 
+test_expect_success 'repack -k keeps unreachable packed objects' '
+       # create packed-but-unreachable object
+       sha1=$(echo unreachable-packed | git hash-object -w --stdin) &&
+       pack=$(echo $sha1 | git pack-objects .git/objects/pack/pack) &&
+       git prune-packed &&
+
+       # -k should keep it
+       git repack -adk &&
+       git cat-file -p $sha1 &&
+
+       # and double check that without -k it would have been removed
+       git repack -ad &&
+       test_must_fail git cat-file -p $sha1
+'
+
 test_done