#include "pack-bitmap.h"
#include "refs.h"
+#define ALL_INTO_ONE 1
+#define LOOSEN_UNREACHABLE 2
+#define PACK_CRUFT 4
+
+static int pack_everything;
static int delta_base_offset = 1;
static int pack_kept_objects = -1;
static int write_bitmaps = -1;
static int use_delta_islands;
static int run_update_server_info = 1;
static char *packdir, *packtmp_name, *packtmp;
+static char *cruft_expiration;
static const char *const git_repack_usage[] = {
N_("git repack [<options>]"),
die(_("could not finish pack-objects to repack promisor objects"));
}
-#define ALL_INTO_ONE 1
-#define LOOSEN_UNREACHABLE 2
-
struct pack_geometry {
struct packed_git **pack;
uint32_t pack_nr, pack_alloc;
for (p = get_all_packs(the_repository); p; p = p->next) {
if (!pack_kept_objects && p->pack_keep)
continue;
+ if (p->is_cruft)
+ continue;
ALLOC_GROW(geometry->pack,
geometry->pack_nr + 1,
return finish_command(&cmd);
}
+static int write_cruft_pack(const struct pack_objects_args *args,
+ const char *pack_prefix,
+ struct string_list *names,
+ struct string_list *existing_packs,
+ struct string_list *existing_kept_packs)
+{
+ struct child_process cmd = CHILD_PROCESS_INIT;
+ struct strbuf line = STRBUF_INIT;
+ struct string_list_item *item;
+ FILE *in, *out;
+ int ret;
+
+ prepare_pack_objects(&cmd, args);
+
+ strvec_push(&cmd.args, "--cruft");
+ if (cruft_expiration)
+ strvec_pushf(&cmd.args, "--cruft-expiration=%s",
+ cruft_expiration);
+
+ strvec_push(&cmd.args, "--honor-pack-keep");
+ strvec_push(&cmd.args, "--non-empty");
+ strvec_push(&cmd.args, "--max-pack-size=0");
+
+ cmd.in = -1;
+
+ ret = start_command(&cmd);
+ if (ret)
+ return ret;
+
+ /*
+ * names has a confusing double use: it both provides the list
+ * of just-written new packs, and accepts the name of the cruft
+ * pack we are writing.
+ *
+ * By the time it is read here, it contains only the pack(s)
+ * that were just written, which is exactly the set of packs we
+ * want to consider kept.
+ */
+ 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);
+ for_each_string_list_item(item, existing_kept_packs)
+ fprintf(in, "%s.pack\n", item->string);
+ fclose(in);
+
+ out = xfdopen(cmd.out, "r");
+ while (strbuf_getline_lf(&line, out) != EOF) {
+ if (line.len != the_hash_algo->hexsz)
+ die(_("repack: Expecting full hex object ID lines only "
+ "from pack-objects."));
+ string_list_append(names, line.buf);
+ }
+ fclose(out);
+
+ strbuf_release(&line);
+
+ return finish_command(&cmd);
+}
+
int cmd_repack(int argc, const char **argv, const char *prefix)
{
struct child_process cmd = CHILD_PROCESS_INIT;
int show_progress;
/* variables to be filled by option parsing */
- int pack_everything = 0;
int delete_redundant = 0;
const char *unpack_unreachable = NULL;
int keep_unreachable = 0;
OPT_BIT('A', NULL, &pack_everything,
N_("same as -a, and turn unreachable objects loose"),
LOOSEN_UNREACHABLE | ALL_INTO_ONE),
+ OPT_BIT(0, "cruft", &pack_everything,
+ N_("same as -a, pack unreachable cruft objects separately"),
+ PACK_CRUFT),
+ OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"),
+ N_("with -C, expire objects older than this")),
OPT_BOOL('d', NULL, &delete_redundant,
N_("remove redundant packs, and run git-prune-packed")),
OPT_BOOL('f', NULL, &po_args.no_reuse_delta,
(unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)))
die(_("options '%s' and '%s' cannot be used together"), "--keep-unreachable", "-A");
+ if (pack_everything & PACK_CRUFT) {
+ pack_everything |= ALL_INTO_ONE;
+
+ if (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE))
+ die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-A");
+ if (keep_unreachable)
+ die(_("options '%s' and '%s' cannot be used together"), "--cruft", "-k");
+ }
+
if (write_bitmaps < 0) {
if (!write_midx &&
(!(pack_everything & ALL_INTO_ONE) || !is_bare_repository()))
if (pack_everything & ALL_INTO_ONE) {
repack_promisor_objects(&po_args, &names);
- if (existing_nonkept_packs.nr && delete_redundant) {
+ if (existing_nonkept_packs.nr && delete_redundant &&
+ !(pack_everything & PACK_CRUFT)) {
for_each_string_list_item(item, &names) {
strvec_pushf(&cmd.args, "--keep-pack=%s-%s.pack",
packtmp_name, item->string);
if (!names.nr && !po_args.quiet)
printf_ln(_("Nothing new to pack."));
+ if (pack_everything & PACK_CRUFT) {
+ const char *pack_prefix;
+ if (!skip_prefix(packtmp, packdir, &pack_prefix))
+ die(_("pack prefix %s does not begin with objdir %s"),
+ packtmp, packdir);
+ if (*pack_prefix == '/')
+ pack_prefix++;
+
+ ret = write_cruft_pack(&po_args, pack_prefix, &names,
+ &existing_nonkept_packs,
+ &existing_kept_packs);
+ if (ret)
+ return ret;
+ }
+
for_each_string_list_item(item, &names) {
item->util = (void *)(uintptr_t)populate_pack_exts(item->string);
}
)
'
+test_expect_success 'repack --cruft generates a cruft pack' '
+ git init repo &&
+ test_when_finished "rm -fr repo" &&
+ (
+ cd repo &&
+
+ test_commit reachable &&
+ git branch -M main &&
+ git checkout --orphan other &&
+ test_commit unreachable &&
+
+ git checkout main &&
+ git branch -D other &&
+ git tag -d unreachable &&
+ # objects are not cruft if they are contained in the reflogs
+ git reflog expire --all --expire=all &&
+
+ git rev-list --objects --all --no-object-names >reachable.raw &&
+ git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
+ sort <reachable.raw >reachable &&
+ comm -13 reachable objects >unreachable &&
+
+ git repack --cruft -d &&
+
+ cruft=$(basename $(ls $packdir/pack-*.mtimes) .mtimes) &&
+ pack=$(basename $(ls $packdir/pack-*.pack | grep -v $cruft) .pack) &&
+
+ git show-index <$packdir/$pack.idx >actual.raw &&
+ cut -f2 -d" " actual.raw | sort >actual &&
+ test_cmp reachable actual &&
+
+ git show-index <$packdir/$cruft.idx >actual.raw &&
+ cut -f2 -d" " actual.raw | sort >actual &&
+ test_cmp unreachable actual
+ )
+'
+
+test_expect_success 'loose objects mtimes upsert others' '
+ git init repo &&
+ test_when_finished "rm -fr repo" &&
+ (
+ cd repo &&
+
+ test_commit reachable &&
+ git repack -Ad &&
+ git branch -M main &&
+
+ git checkout --orphan other &&
+ test_commit cruft &&
+ # incremental repack, leaving existing objects loose (so
+ # they can be "freshened")
+ git repack &&
+
+ tip="$(git rev-parse cruft)" &&
+ path="$objdir/$(test_oid_to_path "$tip")" &&
+ test-tool chmtime --get +1000 "$path" >expect &&
+
+ git checkout main &&
+ git branch -D other &&
+ git tag -d cruft &&
+ git reflog expire --all --expire=all &&
+
+ git repack --cruft -d &&
+
+ mtimes="$(basename $(ls $packdir/pack-*.mtimes))" &&
+ test-tool pack-mtimes "$mtimes" >actual.raw &&
+ grep "$tip" actual.raw | cut -d" " -f2 >actual &&
+ test_cmp expect actual
+ )
+'
+
+test_expect_success 'cruft packs are not included in geometric repack' '
+ git init repo &&
+ test_when_finished "rm -fr repo" &&
+ (
+ cd repo &&
+
+ test_commit reachable &&
+ git repack -Ad &&
+ git branch -M main &&
+
+ git checkout --orphan other &&
+ test_commit cruft &&
+ git repack -d &&
+
+ git checkout main &&
+ git branch -D other &&
+ git tag -d cruft &&
+ git reflog expire --all --expire=all &&
+
+ git repack --cruft &&
+
+ find $packdir -type f | sort >before &&
+ git repack --geometric=2 -d &&
+ find $packdir -type f | sort >after &&
+
+ test_cmp before after
+ )
+'
+
+test_expect_success 'repack --geometric collects once-cruft objects' '
+ git init repo &&
+ test_when_finished "rm -fr repo" &&
+ (
+ cd repo &&
+
+ test_commit reachable &&
+ git repack -Ad &&
+ git branch -M main &&
+
+ git checkout --orphan other &&
+ git rm -rf . &&
+ test_commit --no-tag cruft &&
+ cruft="$(git rev-parse HEAD)" &&
+
+ git checkout main &&
+ git branch -D other &&
+ git reflog expire --all --expire=all &&
+
+ # Pack the objects created in the previous step into a cruft
+ # pack. Intentionally leave loose copies of those objects
+ # around so we can pick them up in a subsequent --geometric
+ # reapack.
+ git repack --cruft &&
+
+ # Now make those objects reachable, and ensure that they are
+ # packed into the new pack created via a --geometric repack.
+ git update-ref refs/heads/other $cruft &&
+
+ # Without this object, the set of unpacked objects is exactly
+ # the set of objects already in the cruft pack. Tweak that set
+ # to ensure we do not overwrite the cruft pack entirely.
+ test_commit reachable2 &&
+
+ find $packdir -name "pack-*.idx" | sort >before &&
+ git repack --geometric=2 -d &&
+ find $packdir -name "pack-*.idx" | sort >after &&
+
+ {
+ git rev-list --objects --no-object-names $cruft &&
+ git rev-list --objects --no-object-names reachable..reachable2
+ } >want.raw &&
+ sort want.raw >want &&
+
+ pack=$(comm -13 before after) &&
+ git show-index <$pack >objects.raw &&
+
+ cut -d" " -f2 objects.raw | sort >got &&
+
+ test_cmp want got
+ )
+'
+
+test_expect_success 'cruft repack with no reachable objects' '
+ git init repo &&
+ test_when_finished "rm -fr repo" &&
+ (
+ cd repo &&
+
+ test_commit base &&
+ git repack -ad &&
+
+ base="$(git rev-parse base)" &&
+
+ git for-each-ref --format="delete %(refname)" >in &&
+ git update-ref --stdin <in &&
+ git reflog expire --all --expire=all &&
+ rm -fr .git/index &&
+
+ git repack --cruft -d &&
+
+ git cat-file -t $base
+ )
+'
+
+test_expect_success 'cruft repack ignores --max-pack-size' '
+ git init max-pack-size &&
+ (
+ cd max-pack-size &&
+ test_commit base &&
+ # two cruft objects which exceed the maximum pack size
+ test-tool genrandom foo 1048576 | git hash-object --stdin -w &&
+ test-tool genrandom bar 1048576 | git hash-object --stdin -w &&
+ git repack --cruft --max-pack-size=1M &&
+ find $packdir -name "*.mtimes" >cruft &&
+ test_line_count = 1 cruft &&
+ test-tool pack-mtimes "$(basename "$(cat cruft)")" >objects &&
+ test_line_count = 2 objects
+ )
+'
+
+test_expect_success 'cruft repack ignores pack.packSizeLimit' '
+ (
+ cd max-pack-size &&
+ # repack everything back together to remove the existing cruft
+ # pack (but to keep its objects)
+ git repack -adk &&
+ git -c pack.packSizeLimit=1M repack --cruft &&
+ # ensure the same post condition is met when --max-pack-size
+ # would otherwise be inferred from the configuration
+ find $packdir -name "*.mtimes" >cruft &&
+ test_line_count = 1 cruft &&
+ test-tool pack-mtimes "$(basename "$(cat cruft)")" >objects &&
+ test_line_count = 2 objects
+ )
+'
+
test_done
projects / thirdparty / git.git / commitdiff
