packfile: use oidset for bad objects

Store the object ID of broken pack entries in an oidset instead of
keeping only their hashes in an unsorted array.  The resulting code is
shorter and easier to read.  It also handles the (hopefully) very rare
case of having a high number of bad objects better.

Helped-by: Jeff King <peff@peff.net>
Signed-off-by: René Scharfe <l.s.r@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/midx.c b/midx.c
index 8cb063023cc9764c6e4d3a566a435618d694a706..76322b713c2908399257940a21803022b1896e9b 100644 (file)
--- a/midx.c
+++ b/midx.c
@@ -307,13 +307,9 @@ int fill_midx_entry(struct repository * r,
        if (!is_pack_valid(p))
                return 0;
 
-       if (p->num_bad_objects) {
-               uint32_t 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_size(&p->bad_objects) &&
+           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 b4dc6668aa281d64774998a70c02ee02da8b6696..c7bead66f62de95b5d5b30f19e15c50cb83efa16 100644 (file)
--- 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 04080a558bfe7265495a22dbab046e05f17f0696..caba29c6249500cae52504ac5a7b62c031cf3f01 100644 (file)
--- 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 +2004,9 @@ 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_size(&p->bad_objects) &&
+           oidset_contains(&p->bad_objects, oid))
+               return 0;
 
        offset = find_pack_entry_one(oid->hash, p);
        if (!offset)