[PATCH 3/3] packfile: use oidset for bad objects

From

René Scharfe <l.s.r@web.de>

Date

Sep 11, 2021, 08:01 UTC

Message-ID

<14d48124-d8bb-aa34-aad0-4203d699e17e@web.de>

In-Reply-To

<4a702bfe-afd0-669a-c893-0262289c24b8@web.de>

Signed-off-by: René Scharfe <l.s.r@web.de>
---
 midx.c         | 13 ++++---------
 object-store.h |  4 ++--
 packfile.c     | 27 +++++----------------------
 3 files changed, 11 insertions(+), 33 deletions(-)

diff --git a/midx.c b/midx.c
index 321c6fdd2f..01623fb339 100644
--- a/midx.c
+++ b/midx.c
@@ -283,6 +283,7 @@ static int nth_midxed_pack_entry(struct repository *r,
 {
 	uint32_t pack_int_id;
 	struct packed_git *p;
+	struct object_id oid;

 	if (pos >= m->num_objects)
 		return 0;
@@ -303,15 +304,9 @@ static int nth_midxed_pack_entry(struct repository *r,
 	if (!is_pack_valid(p))
 		return 0;

-	if (p->num_bad_objects) {
-		uint32_t i;
-		struct object_id oid;
-		nth_midxed_object_oid(&oid, m, pos);
-		for (i = 0; i < p->num_bad_objects; i++)
-			if (hasheq(oid.hash,
-				   p->bad_object_sha1 + the_hash_algo->rawsz * i))
-				return 0;
-	}
+	nth_midxed_object_oid(&oid, m, pos);
+	if (oidset_contains(&p->bad_objects, &oid))
+		return 0;

 	e->offset = nth_midxed_offset(m, pos);
 	e->p = p;
diff --git a/object-store.h b/object-store.h
index b4dc6668aa..c7bead66f6 100644
--- a/object-store.h
+++ b/object-store.h
@@ -10,6 +10,7 @@
 #include "khash.h"
 #include "dir.h"
 #include "oidtree.h"
+#include "oidset.h"

 struct object_directory {
 	struct object_directory *next;
@@ -75,9 +76,8 @@ struct packed_git {
 	const void *index_data;
 	size_t index_size;
 	uint32_t num_objects;
-	uint32_t num_bad_objects;
 	uint32_t crc_offset;
-	unsigned char *bad_object_sha1;
+	struct oidset bad_objects;
 	int index_version;
 	time_t mtime;
 	int pack_fd;
diff --git a/packfile.c b/packfile.c
index 04080a558b..8f6d1d6328 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1163,29 +1163,17 @@ int unpack_object_header(struct packed_git *p,

 void mark_bad_packed_object(struct packed_git *p, const struct object_id *oid)
 {
-	unsigned i;
-	const unsigned hashsz = the_hash_algo->rawsz;
-	for (i = 0; i < p->num_bad_objects; i++)
-		if (hasheq(oid->hash, p->bad_object_sha1 + hashsz * i))
-			return;
-	p->bad_object_sha1 = xrealloc(p->bad_object_sha1,
-				      st_mult(GIT_MAX_RAWSZ,
-					      st_add(p->num_bad_objects, 1)));
-	hashcpy(p->bad_object_sha1 + hashsz * p->num_bad_objects, oid->hash);
-	p->num_bad_objects++;
+	oidset_insert(&p->bad_objects, oid);
 }

 const struct packed_git *has_packed_and_bad(struct repository *r,
 					    const struct object_id *oid)
 {
 	struct packed_git *p;
-	unsigned i;

 	for (p = r->objects->packed_git; p; p = p->next)
-		for (i = 0; i < p->num_bad_objects; i++)
-			if (hasheq(oid->hash,
-				   p->bad_object_sha1 + the_hash_algo->rawsz * i))
-				return p;
+		if (oidset_contains(&p->bad_objects, oid))
+			return p;
 	return NULL;
 }

@@ -2016,13 +2004,8 @@ static int fill_pack_entry(const struct object_id *oid,
 {
 	off_t offset;

-	if (p->num_bad_objects) {
-		unsigned i;
-		for (i = 0; i < p->num_bad_objects; i++)
-			if (hasheq(oid->hash,
-				   p->bad_object_sha1 + the_hash_algo->rawsz * i))
-				return 0;
-	}
+	if (oidset_contains(&p->bad_objects, oid))
+		return 0;

 	offset = find_pack_entry_one(oid->hash, p);
 	if (!offset)
--
2.33.0