@@ -143,6 +143,18 @@ depth is 4095.
a larger and slower repository; see the discussion in
`pack.packSizeLimit`.
+--filter=<filter-spec>::
+ Remove objects matching the filter specification from the
+ resulting packfile and put them into a separate packfile. Note
+ that objects used in the working directory are not filtered
+ out. So for the split to fully work, it's best to perform it
+ in a bare repo and to use the `-a` and `-d` options along with
+ this option. Also `--no-write-bitmap-index` (or the
+ `repack.writebitmaps` config option set to `false`) should be
+ used otherwise writing bitmap index will fail, as it supposes
+ a single packfile containing all the objects. See
+ linkgit:git-rev-list[1] for valid `<filter-spec>` forms.
+
-b::
--write-bitmap-index::
Write a reachability bitmap index as part of the repack. This
@@ -21,6 +21,7 @@
#include "pack.h"
#include "pack-bitmap.h"
#include "refs.h"
+#include "list-objects-filter-options.h"
#define ALL_INTO_ONE 1
#define LOOSEN_UNREACHABLE 2
@@ -57,6 +58,7 @@ struct pack_objects_args {
int no_reuse_object;
int quiet;
int local;
+ struct list_objects_filter_options filter_options;
};
static int repack_config(const char *var, const char *value,
@@ -726,6 +728,57 @@ static int finish_pack_objects_cmd(struct child_process *cmd,
return finish_command(cmd);
}
+static int write_filtered_pack(const struct pack_objects_args *args,
+ const char *destination,
+ const char *pack_prefix,
+ struct string_list *keep_pack_list,
+ struct string_list *names,
+ struct string_list *existing_packs,
+ struct string_list *existing_kept_packs)
+{
+ struct child_process cmd = CHILD_PROCESS_INIT;
+ struct string_list_item *item;
+ FILE *in;
+ int ret, i;
+ const char *caret;
+ const char *scratch;
+ int local = skip_prefix(destination, packdir, &scratch);
+
+ prepare_pack_objects(&cmd, args, destination);
+
+ strvec_push(&cmd.args, "--stdin-packs");
+
+ if (!pack_kept_objects)
+ strvec_push(&cmd.args, "--honor-pack-keep");
+ for (i = 0; i < keep_pack_list->nr; i++)
+ strvec_pushf(&cmd.args, "--keep-pack=%s",
+ keep_pack_list->items[i].string);
+
+ cmd.in = -1;
+
+ ret = start_command(&cmd);
+ if (ret)
+ return ret;
+
+ /*
+ * Here 'names' contains only the pack(s) that were just
+ * written, which is exactly the packs we want to keep. Also
+ * 'existing_kept_packs' already contains the packs in
+ * 'keep_pack_list'.
+ */
+ in = xfdopen(cmd.in, "w");
+ for_each_string_list_item(item, names)
+ fprintf(in, "^%s-%s.pack\n", pack_prefix, item->string);
+ for_each_string_list_item(item, existing_packs)
+ fprintf(in, "%s.pack\n", item->string);
+ caret = pack_kept_objects ? "" : "^";
+ for_each_string_list_item(item, existing_kept_packs)
+ fprintf(in, "%s%s.pack\n", caret, item->string);
+ fclose(in);
+
+ return finish_pack_objects_cmd(&cmd, names, local);
+}
+
static int write_cruft_pack(const struct pack_objects_args *args,
const char *destination,
const char *pack_prefix,
@@ -858,6 +911,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
N_("limits the maximum number of threads")),
OPT_STRING(0, "max-pack-size", &po_args.max_pack_size, N_("bytes"),
N_("maximum size of each packfile")),
+ OPT_PARSE_LIST_OBJECTS_FILTER(&po_args.filter_options),
OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects,
N_("repack objects in packs marked with .keep")),
OPT_STRING_LIST(0, "keep-pack", &keep_pack_list, N_("name"),
@@ -871,6 +925,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
OPT_END()
};
+ list_objects_filter_init(&po_args.filter_options);
+ list_objects_filter_init(&cruft_po_args.filter_options);
+
git_config(repack_config, &cruft_po_args);
argc = parse_options(argc, argv, prefix, builtin_repack_options,
@@ -1011,6 +1068,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
strvec_push(&cmd.args, "--incremental");
}
+ if (po_args.filter_options.choice)
+ strvec_pushf(&cmd.args, "--filter=%s",
+ expand_list_objects_filter_spec(&po_args.filter_options));
+
if (geometry)
cmd.in = -1;
else
@@ -1097,6 +1158,18 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
}
}
+ if (po_args.filter_options.choice) {
+ ret = write_filtered_pack(&po_args,
+ packtmp,
+ find_pack_prefix(packdir, packtmp),
+ &keep_pack_list,
+ &names,
+ &existing_nonkept_packs,
+ &existing_kept_packs);
+ if (ret)
+ goto cleanup;
+ }
+
string_list_sort(&names);
close_object_store(the_repository->objects);
@@ -1231,6 +1304,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
string_list_clear(&existing_nonkept_packs, 0);
string_list_clear(&existing_kept_packs, 0);
clear_pack_geometry(geometry);
+ list_objects_filter_release(&po_args.filter_options);
+ list_objects_filter_release(&cruft_po_args.filter_options);
return ret;
}
@@ -327,6 +327,140 @@ test_expect_success 'auto-bitmaps do not complain if unavailable' '
test_must_be_empty actual
'
+test_expect_success 'repacking with a filter works' '
+ git -C bare.git repack -a -d &&
+ test_stdout_line_count = 1 ls bare.git/objects/pack/*.pack &&
+ git -C bare.git -c repack.writebitmaps=false repack -a -d --filter=blob:none &&
+ test_stdout_line_count = 2 ls bare.git/objects/pack/*.pack &&
+ commit_pack=$(test-tool -C bare.git find-pack -c 1 HEAD) &&
+ blob_pack=$(test-tool -C bare.git find-pack -c 1 HEAD:file1) &&
+ test "$commit_pack" != "$blob_pack" &&
+ tree_pack=$(test-tool -C bare.git find-pack -c 1 HEAD^{tree}) &&
+ test "$tree_pack" = "$commit_pack" &&
+ blob_pack2=$(test-tool -C bare.git find-pack -c 1 HEAD:file2) &&
+ test "$blob_pack2" = "$blob_pack"
+'
+
+test_expect_success '--filter fails with --write-bitmap-index' '
+ GIT_TEST_MULTI_PACK_INDEX_WRITE_BITMAP=0 test_must_fail git -C bare.git repack \
+ -a -d --write-bitmap-index --filter=blob:none
+'
+
+test_expect_success 'repacking with two filters works' '
+ git init two-filters &&
+ (
+ cd two-filters &&
+ mkdir subdir &&
+ test_commit foo &&
+ test_commit subdir_bar subdir/bar &&
+ test_commit subdir_baz subdir/baz
+ ) &&
+ git clone --no-local --bare two-filters two-filters.git &&
+ (
+ cd two-filters.git &&
+ test_stdout_line_count = 1 ls objects/pack/*.pack &&
+ git -c repack.writebitmaps=false repack -a -d \
+ --filter=blob:none --filter=tree:1 &&
+ test_stdout_line_count = 2 ls objects/pack/*.pack &&
+ commit_pack=$(test-tool find-pack -c 1 HEAD) &&
+ blob_pack=$(test-tool find-pack -c 1 HEAD:foo.t) &&
+ root_tree_pack=$(test-tool find-pack -c 1 HEAD^{tree}) &&
+ subdir_tree_hash=$(git ls-tree --object-only HEAD -- subdir) &&
+ subdir_tree_pack=$(test-tool find-pack -c 1 "$subdir_tree_hash") &&
+
+ # Root tree and subdir tree are not in the same packfiles
+ test "$commit_pack" != "$blob_pack" &&
+ test "$commit_pack" = "$root_tree_pack" &&
+ test "$blob_pack" = "$subdir_tree_pack"
+ )
+'
+
+prepare_for_keep_packs () {
+ git init keep-packs &&
+ (
+ cd keep-packs &&
+ test_commit foo &&
+ test_commit bar
+ ) &&
+ git clone --no-local --bare keep-packs keep-packs.git &&
+ (
+ cd keep-packs.git &&
+
+ # Create two packs
+ # The first pack will contain all of the objects except one blob
+ git rev-list --objects --all >objs &&
+ grep -v "bar.t" objs | git pack-objects pack &&
+ # The second pack will contain the excluded object and be kept
+ packid=$(grep "bar.t" objs | git pack-objects pack) &&
+ >pack-$packid.keep &&
+
+ # Replace the existing pack with the 2 new ones
+ rm -f objects/pack/pack* &&
+ mv pack-* objects/pack/
+ )
+}
+
+test_expect_success '--filter works with .keep packs' '
+ prepare_for_keep_packs &&
+ (
+ cd keep-packs.git &&
+
+ foo_pack=$(test-tool find-pack -c 1 HEAD:foo.t) &&
+ bar_pack=$(test-tool find-pack -c 1 HEAD:bar.t) &&
+ head_pack=$(test-tool find-pack -c 1 HEAD) &&
+
+ test "$foo_pack" != "$bar_pack" &&
+ test "$foo_pack" = "$head_pack" &&
+
+ git -c repack.writebitmaps=false repack -a -d --filter=blob:none &&
+
+ foo_pack_1=$(test-tool find-pack -c 1 HEAD:foo.t) &&
+ bar_pack_1=$(test-tool find-pack -c 1 HEAD:bar.t) &&
+ head_pack_1=$(test-tool find-pack -c 1 HEAD) &&
+
+ # Object bar is still only in the old .keep pack
+ test "$foo_pack_1" != "$foo_pack" &&
+ test "$bar_pack_1" = "$bar_pack" &&
+ test "$head_pack_1" != "$head_pack" &&
+
+ test "$foo_pack_1" != "$bar_pack_1" &&
+ test "$foo_pack_1" != "$head_pack_1" &&
+ test "$bar_pack_1" != "$head_pack_1"
+ )
+'
+
+test_expect_success '--filter works with --pack-kept-objects and .keep packs' '
+ rm -rf keep-packs keep-packs.git &&
+ prepare_for_keep_packs &&
+ (
+ cd keep-packs.git &&
+
+ foo_pack=$(test-tool find-pack -c 1 HEAD:foo.t) &&
+ bar_pack=$(test-tool find-pack -c 1 HEAD:bar.t) &&
+ head_pack=$(test-tool find-pack -c 1 HEAD) &&
+
+ test "$foo_pack" != "$bar_pack" &&
+ test "$foo_pack" = "$head_pack" &&
+
+ git -c repack.writebitmaps=false repack -a -d --filter=blob:none \
+ --pack-kept-objects &&
+
+ foo_pack_1=$(test-tool find-pack -c 1 HEAD:foo.t) &&
+ test-tool find-pack -c 2 HEAD:bar.t >bar_pack_1 &&
+ head_pack_1=$(test-tool find-pack -c 1 HEAD) &&
+
+ test "$foo_pack_1" != "$foo_pack" &&
+ test "$foo_pack_1" != "$bar_pack" &&
+ test "$head_pack_1" != "$head_pack" &&
+
+ # Object bar is in both the old .keep pack and the new
+ # pack that contained the filtered out objects
+ grep "$bar_pack" bar_pack_1 &&
+ grep "$foo_pack_1" bar_pack_1 &&
+ test "$foo_pack_1" != "$head_pack_1"
+ )
+'
+
objdir=.git/objects
midx=$objdir/pack/multi-pack-index
This new option puts the objects specified by `<filter-spec>` into a separate packfile. This could be useful if, for example, some blobs take up a lot of precious space on fast storage while they are rarely accessed. It could make sense to move them into a separate cheaper, though slower, storage. It's possible to find which new packfile contains the filtered out objects using one of the following: - `git verify-pack -v ...`, - `test-tool find-pack ...`, which a previous commit added, - `--filter-to=<dir>`, which a following commit will add to specify where the pack containing the filtered out objects will be. This feature is implemented by running `git pack-objects` twice in a row. The first command is run with `--filter=<filter-spec>`, using the specified filter. It packs objects while omitting the objects specified by the filter. Then another `git pack-objects` command is launched using `--stdin-packs`. We pass it all the previously existing packs into its stdin, so that it will pack all the objects in the previously existing packs. But we also pass into its stdin, the pack created by the previous `git pack-objects --filter=<filter-spec>` command as well as the kept packs, all prefixed with '^', so that the objects in these packs will be omitted from the resulting pack. The result is that only the objects filtered out by the first `git pack-objects` command are in the pack resulting from the second `git pack-objects` command. As the interactions with kept packs are a bit tricky, a few related tests are added. Signed-off-by: John Cai <johncai86@gmail.com> Signed-off-by: Christian Couder <chriscool@tuxfamily.org> --- Documentation/git-repack.txt | 12 ++++ builtin/repack.c | 75 ++++++++++++++++++++ t/t7700-repack.sh | 134 +++++++++++++++++++++++++++++++++++ 3 files changed, 221 insertions(+)