[06/11] multi-pack-index: implement 'expire' subcommand

Commit Message

Jean-Noël Avila via GitGitGadget June 10, 2019, 11:35 p.m. UTC

From: Derrick Stolee <[e-mail]>

The 'git multi-pack-index expire' subcommand looks at the existing
mult-pack-index, counts the number of objects referenced in each
pack-file, deletes the pack-fils with no referenced objects, and
rewrites the multi-pack-index to no longer reference those packs.

Refactor the write_midx_file() method to call write_midx_internal()
which now takes an existing 'struct multi_pack_index' and a list
of pack-files to drop (as specified by the names of their pack-
indexes). As we write the new multi-pack-index, we drop those
file names from the list of known pack-files.

The expire_midx_packs() method removes the unreferenced pack-files
after carefully closing the packs to avoid open handles.

Test that a new pack-file that covers the contents of two other
pack-files leads to those pack-files being deleted during the
expire subcommand. Be sure to read the multi-pack-index to ensure
it no longer references those packs.

Signed-off-by: Derrick Stolee <[e-mail]>
---
 midx.c                      | 119 +++++++++++++++++++++++++++++++++---
 t/t5319-multi-pack-index.sh |  20 ++++++
 2 files changed, 129 insertions(+), 10 deletions(-)

Comments

Junio C Hamano June 11, 2019, 6:51 p.m. UTC | #1

"Derrick Stolee via GitGitGadget" <[e-mail]> writes:

> From: Derrick Stolee <[e-mail]>
>
> The 'git multi-pack-index expire' subcommand looks at the existing
> mult-pack-index, counts the number of objects referenced in each

s/mult/&i/

> pack-file, deletes the pack-fils with no referenced objects, and

s/fils/files/

> rewrites the multi-pack-index to no longer reference those packs.

As we do *not* want to expire a packfile that was created after the
last run of "git multi-pack-index write", "... in each pack-file" in
the above paragraph is a bit tricky.  It cannot literally be "in
each packfile", but a subset of all existing packfiles that are
known to the midx we are looking at.

An obvious alternative is to actually update midx file (so it no
longer "looks at the existing multi-pack-index", but "makes sure we
have up-to-date view of the multi-pack-index that covers all packs).

And I actually suspect that you implemented that alternative here.
IOW, "looks at the existing multi-pack-index" in the first paragraph
is misleading.

I wondered if the error behaviour of add_pack_to_midx() that ignores
a pack that cannot be added to midx for whatever reason can cause
issues, but such a pack would not become part of m->packs[] so it
may not have anything count[]ed from it, but it will not be eligible
for expiration, either.  So we'd be safe there, I think.

> Test that a new pack-file that covers the contents of two other
> pack-files leads to those pack-files being deleted during the
> expire subcommand. Be sure to read the multi-pack-index to ensure
> it no longer references those packs.

I am curious to learn how we guarantee that the midx logic chooses
to record the copy of an object in the new single packfile over the
other copy of the same object in one of the two older and presumably
smaller packfiles for all objects in the latter two packfiles,
because they cannot be expired if even one object were used from
there.

Patch

diff --git a/midx.c b/midx.c
index 6d4b84e243..9b0b4c1520 100644
--- a/midx.c
+++ b/midx.c
@@ -34,6 +34,8 @@ 
 #define MIDX_CHUNK_LARGE_OFFSET_WIDTH (sizeof(uint64_t))
 #define MIDX_LARGE_OFFSET_NEEDED 0x80000000
 
+#define PACK_EXPIRED UINT_MAX
+
 static char *get_midx_filename(const char *object_dir)
 {
 	return xstrfmt("%s/pack/multi-pack-index", object_dir);
@@ -431,6 +433,7 @@  struct pack_info {
 	uint32_t orig_pack_int_id;
 	char *pack_name;
 	struct packed_git *p;
+	unsigned expired : 1;
 };
 
 static int pack_info_compare(const void *_a, const void *_b)
@@ -478,6 +481,7 @@  static void add_pack_to_midx(const char *full_path, size_t full_path_len,
 
 		packs->info[packs->nr].pack_name = xstrdup(file_name);
 		packs->info[packs->nr].orig_pack_int_id = packs->nr;
+		packs->info[packs->nr].expired = 0;
 		packs->nr++;
 	}
 }
@@ -637,13 +641,17 @@  static size_t write_midx_pack_names(struct hashfile *f,
 	size_t written = 0;
 
 	for (i = 0; i < num_packs; i++) {
-		size_t writelen = strlen(info[i].pack_name) + 1;
+		size_t writelen;
+
+		if (info[i].expired)
+			continue;
 
 		if (i && strcmp(info[i].pack_name, info[i - 1].pack_name) <= 0)
 			BUG("incorrect pack-file order: %s before %s",
 			    info[i - 1].pack_name,
 			    info[i].pack_name);
 
+		writelen = strlen(info[i].pack_name) + 1;
 		hashwrite(f, info[i].pack_name, writelen);
 		written += writelen;
 	}
@@ -725,6 +733,11 @@  static size_t write_midx_object_offsets(struct hashfile *f, int large_offset_nee
 	for (i = 0; i < nr_objects; i++) {
 		struct pack_midx_entry *obj = list++;
 
+		if (perm[obj->pack_int_id] == PACK_EXPIRED)
+			BUG("object %s is in an expired pack with int-id %d",
+			    oid_to_hex(&obj->oid),
+			    obj->pack_int_id);
+
 		hashwrite_be32(f, perm[obj->pack_int_id]);
 
 		if (large_offset_needed && obj->offset >> 31)
@@ -771,7 +784,8 @@  static size_t write_midx_large_offsets(struct hashfile *f, uint32_t nr_large_off
 	return written;
 }
 
-int write_midx_file(const char *object_dir)
+static int write_midx_internal(const char *object_dir, struct multi_pack_index *m,
+			       struct string_list *packs_to_drop)
 {
 	unsigned char cur_chunk, num_chunks = 0;
 	char *midx_name;
@@ -787,6 +801,8 @@  int write_midx_file(const char *object_dir)
 	struct pack_midx_entry *entries = NULL;
 	int large_offsets_needed = 0;
 	int pack_name_concat_len = 0;
+	int dropped_packs = 0;
+	int result = 0;
 
 	midx_name = get_midx_filename(object_dir);
 	if (safe_create_leading_directories(midx_name)) {
@@ -795,7 +811,10 @@  int write_midx_file(const char *object_dir)
 			  midx_name);
 	}
 
-	packs.m = load_multi_pack_index(object_dir, 1);
+	if (m)
+		packs.m = m;
+	else
+		packs.m = load_multi_pack_index(object_dir, 1);
 
 	packs.nr = 0;
 	packs.alloc = packs.m ? packs.m->num_packs : 16;
@@ -809,13 +828,14 @@  int write_midx_file(const char *object_dir)
 			packs.info[packs.nr].orig_pack_int_id = i;
 			packs.info[packs.nr].pack_name = xstrdup(packs.m->pack_names[i]);
 			packs.info[packs.nr].p = NULL;
+			packs.info[packs.nr].expired = 0;
 			packs.nr++;
 		}
 	}
 
 	for_each_file_in_pack_dir(object_dir, add_pack_to_midx, &packs);
 
-	if (packs.m && packs.nr == packs.m->num_packs)
+	if (packs.m && packs.nr == packs.m->num_packs && !packs_to_drop)
 		goto cleanup;
 
 	entries = get_sorted_entries(packs.m, packs.info, packs.nr, &nr_entries);
@@ -829,6 +849,34 @@  int write_midx_file(const char *object_dir)
 
 	QSORT(packs.info, packs.nr, pack_info_compare);
 
+	if (packs_to_drop && packs_to_drop->nr) {
+		int drop_index = 0;
+		int missing_drops = 0;
+
+		for (i = 0; i < packs.nr && drop_index < packs_to_drop->nr; i++) {
+			int cmp = strcmp(packs.info[i].pack_name,
+					 packs_to_drop->items[drop_index].string);
+
+			if (!cmp) {
+				drop_index++;
+				packs.info[i].expired = 1;
+			} else if (cmp > 0) {
+				error(_("did not see pack-file %s to drop"),
+				      packs_to_drop->items[drop_index].string);
+				drop_index++;
+				missing_drops++;
+				i--;
+			} else {
+				packs.info[i].expired = 0;
+			}
+		}
+
+		if (missing_drops) {
+			result = 1;
+			goto cleanup;
+		}
+	}
+
 	/*
 	 * pack_perm stores a permutation between pack-int-ids from the
 	 * previous multi-pack-index to the new one we are writing:
@@ -837,11 +885,18 @@  int write_midx_file(const char *object_dir)
 	 */
 	ALLOC_ARRAY(pack_perm, packs.nr);
 	for (i = 0; i < packs.nr; i++) {
-		pack_perm[packs.info[i].orig_pack_int_id] = i;
+		if (packs.info[i].expired) {
+			dropped_packs++;
+			pack_perm[packs.info[i].orig_pack_int_id] = PACK_EXPIRED;
+		} else {
+			pack_perm[packs.info[i].orig_pack_int_id] = i - dropped_packs;
+		}
 	}
 
-	for (i = 0; i < packs.nr; i++)
-		pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
+	for (i = 0; i < packs.nr; i++) {
+		if (!packs.info[i].expired)
+			pack_name_concat_len += strlen(packs.info[i].pack_name) + 1;
+	}
 
 	if (pack_name_concat_len % MIDX_CHUNK_ALIGNMENT)
 		pack_name_concat_len += MIDX_CHUNK_ALIGNMENT -
@@ -857,7 +912,7 @@  int write_midx_file(const char *object_dir)
 	cur_chunk = 0;
 	num_chunks = large_offsets_needed ? 5 : 4;
 
-	written = write_midx_header(f, num_chunks, packs.nr);
+	written = write_midx_header(f, num_chunks, packs.nr - dropped_packs);
 
 	chunk_ids[cur_chunk] = MIDX_CHUNKID_PACKNAMES;
 	chunk_offsets[cur_chunk] = written + (num_chunks + 1) * MIDX_CHUNKLOOKUP_WIDTH;
@@ -958,7 +1013,12 @@  int write_midx_file(const char *object_dir)
 	free(entries);
 	free(pack_perm);
 	free(midx_name);
-	return 0;
+	return result;
+}
+
+int write_midx_file(const char *object_dir)
+{
+	return write_midx_internal(object_dir, NULL, NULL);
 }
 
 void clear_midx_file(struct repository *r)
@@ -1125,5 +1185,44 @@  int verify_midx_file(struct repository *r, const char *object_dir)
 
 int expire_midx_packs(struct repository *r, const char *object_dir)
 {
-	return 0;
+	uint32_t i, *count, result = 0;
+	struct string_list packs_to_drop = STRING_LIST_INIT_DUP;
+	struct multi_pack_index *m = load_multi_pack_index(object_dir, 1);
+
+	if (!m)
+		return 0;
+
+	count = xcalloc(m->num_packs, sizeof(uint32_t));
+	for (i = 0; i < m->num_objects; i++) {
+		int pack_int_id = nth_midxed_pack_int_id(m, i);
+		count[pack_int_id]++;
+	}
+
+	for (i = 0; i < m->num_packs; i++) {
+		char *pack_name;
+
+		if (count[i])
+			continue;
+
+		if (prepare_midx_pack(r, m, i))
+			continue;
+
+		if (m->packs[i]->pack_keep)
+			continue;
+
+		pack_name = xstrdup(m->packs[i]->pack_name);
+		close_pack(m->packs[i]);
+
+		string_list_insert(&packs_to_drop, m->pack_names[i]);
+		unlink_pack_path(pack_name, 0);
+		free(pack_name);
+	}
+
+	free(count);
+
+	if (packs_to_drop.nr)
+		result = write_midx_internal(object_dir, m, &packs_to_drop);
+
+	string_list_clear(&packs_to_drop, 0);
+	return result;
 }
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index 1b2d32f475..12570fe7ac 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -412,4 +412,24 @@  test_expect_success 'expire does not remove any packs' '
 	)
 '
 
+test_expect_success 'expire removes unreferenced packs' '
+	(
+		cd dup &&
+		git pack-objects --revs .git/objects/pack/pack-combined <<-EOF &&
+		refs/heads/A
+		^refs/heads/C
+		EOF
+		git multi-pack-index write &&
+		ls .git/objects/pack | grep -v -e pack-[AB] >expect &&
+		git multi-pack-index expire &&
+		ls .git/objects/pack >actual &&
+		test_cmp expect actual &&
+		ls .git/objects/pack/ | grep idx >expect-idx &&
+		test-tool read-midx .git/objects | grep idx >actual-midx &&
+		test_cmp expect-idx actual-midx &&
+		git multi-pack-index verify &&
+		git fsck
+	)
+'
+
 test_done