Merge branch 'jk/dumb-http-finalize'

The dumb-http code regressed when the result of re-indexing a pack
yielded an *.idx file that differs in content from the *.idx file it
downloaded from the remote. This has been corrected by no longer
relying on the *.idx file we got from the remote.

* jk/dumb-http-finalize:
  packfile: use oidread() instead of hashcpy() to fill object_id
  packfile: use object_id in find_pack_entry_one()
  packfile: convert find_sha1_pack() to use object_id
  http-walker: use object_id instead of bare hash
  packfile: warn people away from parse_packed_git()
  packfile: drop sha1_pack_index_name()
  packfile: drop sha1_pack_name()
  packfile: drop has_pack_index()
  dumb-http: store downloaded pack idx as tempfile
  t5550: count fetches in "previously-fetched .idx" test
  midx: avoid duplicate packed_git entries
This commit is contained in:
Taylor Blau
2024-11-01 12:53:31 -04:00
16 changed files with 153 additions and 101 deletions

View File

@ -966,8 +966,7 @@ static int store_object(
if (e->idx.offset) { if (e->idx.offset) {
duplicate_count_by_type[type]++; duplicate_count_by_type[type]++;
return 1; return 1;
} else if (find_sha1_pack(oid.hash, } else if (find_oid_pack(&oid, get_all_packs(the_repository))) {
get_all_packs(the_repository))) {
e->type = type; e->type = type;
e->pack_id = MAX_PACK_ID; e->pack_id = MAX_PACK_ID;
e->idx.offset = 1; /* just not zero! */ e->idx.offset = 1; /* just not zero! */
@ -1167,8 +1166,7 @@ static void stream_blob(uintmax_t len, struct object_id *oidout, uintmax_t mark)
duplicate_count_by_type[OBJ_BLOB]++; duplicate_count_by_type[OBJ_BLOB]++;
truncate_pack(&checkpoint); truncate_pack(&checkpoint);
} else if (find_sha1_pack(oid.hash, } else if (find_oid_pack(&oid, get_all_packs(the_repository))) {
get_all_packs(the_repository))) {
e->type = OBJ_BLOB; e->type = OBJ_BLOB;
e->pack_id = MAX_PACK_ID; e->pack_id = MAX_PACK_ID;
e->idx.offset = 1; /* just not zero! */ e->idx.offset = 1; /* just not zero! */

View File

@ -1556,7 +1556,7 @@ static int want_object_in_pack_one(struct packed_git *p,
if (p == *found_pack) if (p == *found_pack)
offset = *found_offset; offset = *found_offset;
else else
offset = find_pack_entry_one(oid->hash, p); offset = find_pack_entry_one(oid, p);
if (offset) { if (offset) {
if (!*found_pack) { if (!*found_pack) {
@ -3984,7 +3984,7 @@ static int has_sha1_pack_kept_or_nonlocal(const struct object_id *oid)
while (p) { while (p) {
if ((!p->pack_local || p->pack_keep || if ((!p->pack_local || p->pack_keep ||
p->pack_keep_in_core) && p->pack_keep_in_core) &&
find_pack_entry_one(oid->hash, p)) { find_pack_entry_one(oid, p)) {
last_found = p; last_found = p;
return 1; return 1;
} }

View File

@ -13,6 +13,7 @@
#include "packfile.h" #include "packfile.h"
#include "object-store-ll.h" #include "object-store-ll.h"
#include "strbuf.h"
#define BLKSIZE 512 #define BLKSIZE 512
@ -591,6 +592,7 @@ static void load_all(void)
int cmd_pack_redundant(int argc, const char **argv, const char *prefix UNUSED, struct repository *repo UNUSED) { int cmd_pack_redundant(int argc, const char **argv, const char *prefix UNUSED, struct repository *repo UNUSED) {
int i; int i_still_use_this = 0; struct pack_list *min = NULL, *red, *pl; int i; int i_still_use_this = 0; struct pack_list *min = NULL, *red, *pl;
struct llist *ignore; struct llist *ignore;
struct strbuf idx_name = STRBUF_INIT;
char buf[GIT_MAX_HEXSZ + 2]; /* hex hash + \n + \0 */ char buf[GIT_MAX_HEXSZ + 2]; /* hex hash + \n + \0 */
if (argc == 2 && !strcmp(argv[1], "-h")) if (argc == 2 && !strcmp(argv[1], "-h"))
@ -688,7 +690,7 @@ int cmd_pack_redundant(int argc, const char **argv, const char *prefix UNUSED, s
pl = red = pack_list_difference(local_packs, min); pl = red = pack_list_difference(local_packs, min);
while (pl) { while (pl) {
printf("%s\n%s\n", printf("%s\n%s\n",
sha1_pack_index_name(pl->pack->hash), odb_pack_name(&idx_name, pl->pack->hash, "idx"),
pl->pack->pack_name); pl->pack->pack_name);
pl = pl->next; pl = pl->next;
} }
@ -699,5 +701,6 @@ int cmd_pack_redundant(int argc, const char **argv, const char *prefix UNUSED, s
pack_list_free(red); pack_list_free(red);
pack_list_free(min); pack_list_free(min);
llist_free(ignore); llist_free(ignore);
strbuf_release(&idx_name);
return 0; return 0;
} }

View File

@ -78,7 +78,7 @@ int check_connected(oid_iterate_fn fn, void *cb_data,
for (p = get_all_packs(the_repository); p; p = p->next) { for (p = get_all_packs(the_repository); p; p = p->next) {
if (!p->pack_promisor) if (!p->pack_promisor)
continue; continue;
if (find_pack_entry_one(oid->hash, p)) if (find_pack_entry_one(oid, p))
goto promisor_pack_found; goto promisor_pack_found;
} }
/* /*
@ -144,7 +144,7 @@ no_promisor_pack_found:
* are sure the ref is good and not sending it to * are sure the ref is good and not sending it to
* rev-list for verification. * rev-list for verification.
*/ */
if (new_pack && find_pack_entry_one(oid->hash, new_pack)) if (new_pack && find_pack_entry_one(oid, new_pack))
continue; continue;
if (fprintf(rev_list_in, "%s\n", oid_to_hex(oid)) < 0) if (fprintf(rev_list_in, "%s\n", oid_to_hex(oid)) < 0)

View File

@ -309,7 +309,7 @@ static void start_fetch_packed(struct transfer_request *request)
struct transfer_request *check_request = request_queue_head; struct transfer_request *check_request = request_queue_head;
struct http_pack_request *preq; struct http_pack_request *preq;
target = find_sha1_pack(request->obj->oid.hash, repo->packs); target = find_oid_pack(&request->obj->oid, repo->packs);
if (!target) { if (!target) {
fprintf(stderr, "Unable to fetch %s, will not be able to update server info refs\n", oid_to_hex(&request->obj->oid)); fprintf(stderr, "Unable to fetch %s, will not be able to update server info refs\n", oid_to_hex(&request->obj->oid));
repo->can_update_info_refs = 0; repo->can_update_info_refs = 0;
@ -681,7 +681,7 @@ static int add_send_request(struct object *obj, struct remote_lock *lock)
get_remote_object_list(obj->oid.hash[0]); get_remote_object_list(obj->oid.hash[0]);
if (obj->flags & (REMOTE | PUSHING)) if (obj->flags & (REMOTE | PUSHING))
return 0; return 0;
target = find_sha1_pack(obj->oid.hash, repo->packs); target = find_oid_pack(&obj->oid, repo->packs);
if (target) { if (target) {
obj->flags |= REMOTE; obj->flags |= REMOTE;
return 0; return 0;

View File

@ -147,14 +147,14 @@ static int fill_active_slot(void *data UNUSED)
return 0; return 0;
} }
static void prefetch(struct walker *walker, unsigned char *sha1) static void prefetch(struct walker *walker, const struct object_id *oid)
{ {
struct object_request *newreq; struct object_request *newreq;
struct walker_data *data = walker->data; struct walker_data *data = walker->data;
newreq = xmalloc(sizeof(*newreq)); newreq = xmalloc(sizeof(*newreq));
newreq->walker = walker; newreq->walker = walker;
oidread(&newreq->oid, sha1, the_repository->hash_algo); oidcpy(&newreq->oid, oid);
newreq->repo = data->alt; newreq->repo = data->alt;
newreq->state = WAITING; newreq->state = WAITING;
newreq->req = NULL; newreq->req = NULL;
@ -422,7 +422,8 @@ static int fetch_indices(struct walker *walker, struct alt_base *repo)
return ret; return ret;
} }
static int http_fetch_pack(struct walker *walker, struct alt_base *repo, unsigned char *sha1) static int http_fetch_pack(struct walker *walker, struct alt_base *repo,
const struct object_id *oid)
{ {
struct packed_git *target; struct packed_git *target;
int ret; int ret;
@ -431,7 +432,7 @@ static int http_fetch_pack(struct walker *walker, struct alt_base *repo, unsigne
if (fetch_indices(walker, repo)) if (fetch_indices(walker, repo))
return -1; return -1;
target = find_sha1_pack(sha1, repo->packs); target = find_oid_pack(oid, repo->packs);
if (!target) if (!target)
return -1; return -1;
close_pack_index(target); close_pack_index(target);
@ -440,7 +441,7 @@ static int http_fetch_pack(struct walker *walker, struct alt_base *repo, unsigne
fprintf(stderr, "Getting pack %s\n", fprintf(stderr, "Getting pack %s\n",
hash_to_hex(target->hash)); hash_to_hex(target->hash));
fprintf(stderr, " which contains %s\n", fprintf(stderr, " which contains %s\n",
hash_to_hex(sha1)); oid_to_hex(oid));
} }
preq = new_http_pack_request(target->hash, repo->base); preq = new_http_pack_request(target->hash, repo->base);
@ -477,9 +478,9 @@ static void abort_object_request(struct object_request *obj_req)
release_object_request(obj_req); release_object_request(obj_req);
} }
static int fetch_object(struct walker *walker, unsigned char *hash) static int fetch_object(struct walker *walker, const struct object_id *oid)
{ {
char *hex = hash_to_hex(hash); char *hex = oid_to_hex(oid);
int ret = 0; int ret = 0;
struct object_request *obj_req = NULL; struct object_request *obj_req = NULL;
struct http_object_request *req; struct http_object_request *req;
@ -487,7 +488,7 @@ static int fetch_object(struct walker *walker, unsigned char *hash)
list_for_each(pos, head) { list_for_each(pos, head) {
obj_req = list_entry(pos, struct object_request, node); obj_req = list_entry(pos, struct object_request, node);
if (hasheq(obj_req->oid.hash, hash, the_repository->hash_algo)) if (oideq(&obj_req->oid, oid))
break; break;
} }
if (!obj_req) if (!obj_req)
@ -548,20 +549,20 @@ static int fetch_object(struct walker *walker, unsigned char *hash)
return ret; return ret;
} }
static int fetch(struct walker *walker, unsigned char *hash) static int fetch(struct walker *walker, const struct object_id *oid)
{ {
struct walker_data *data = walker->data; struct walker_data *data = walker->data;
struct alt_base *altbase = data->alt; struct alt_base *altbase = data->alt;
if (!fetch_object(walker, hash)) if (!fetch_object(walker, oid))
return 0; return 0;
while (altbase) { while (altbase) {
if (!http_fetch_pack(walker, altbase, hash)) if (!http_fetch_pack(walker, altbase, oid))
return 0; return 0;
fetch_alternates(walker, data->alt->base); fetch_alternates(walker, data->alt->base);
altbase = altbase->next; altbase = altbase->next;
} }
return error("Unable to find %s under %s", hash_to_hex(hash), return error("Unable to find %s under %s", oid_to_hex(oid),
data->alt->base); data->alt->base);
} }

43
http.c
View File

@ -19,6 +19,7 @@
#include "string-list.h" #include "string-list.h"
#include "object-file.h" #include "object-file.h"
#include "object-store-ll.h" #include "object-store-ll.h"
#include "tempfile.h"
static struct trace_key trace_curl = TRACE_KEY_INIT(CURL); static struct trace_key trace_curl = TRACE_KEY_INIT(CURL);
static int trace_curl_data = 1; static int trace_curl_data = 1;
@ -2390,8 +2391,24 @@ static char *fetch_pack_index(unsigned char *hash, const char *base_url)
strbuf_addf(&buf, "objects/pack/pack-%s.idx", hash_to_hex(hash)); strbuf_addf(&buf, "objects/pack/pack-%s.idx", hash_to_hex(hash));
url = strbuf_detach(&buf, NULL); url = strbuf_detach(&buf, NULL);
strbuf_addf(&buf, "%s.temp", sha1_pack_index_name(hash)); /*
tmp = strbuf_detach(&buf, NULL); * Don't put this into packs/, since it's just temporary and we don't
* want to confuse it with our local .idx files. We'll generate our
* own index if we choose to download the matching packfile.
*
* It's tempting to use xmks_tempfile() here, but it's important that
* the file not exist, otherwise http_get_file() complains. So we
* create a filename that should be unique, and then just register it
* as a tempfile so that it will get cleaned up on exit.
*
* In theory we could hold on to the tempfile and delete these as soon
* as we download the matching pack, but it would take a bit of
* refactoring. Leaving them until the process ends is probably OK.
*/
tmp = xstrfmt("%s/tmp_pack_%s.idx",
repo_get_object_directory(the_repository),
hash_to_hex(hash));
register_tempfile(tmp);
if (http_get_file(url, tmp, NULL) != HTTP_OK) { if (http_get_file(url, tmp, NULL) != HTTP_OK) {
error("Unable to get pack index %s", url); error("Unable to get pack index %s", url);
@ -2405,15 +2422,17 @@ static char *fetch_pack_index(unsigned char *hash, const char *base_url)
static int fetch_and_setup_pack_index(struct packed_git **packs_head, static int fetch_and_setup_pack_index(struct packed_git **packs_head,
unsigned char *sha1, const char *base_url) unsigned char *sha1, const char *base_url)
{ {
struct packed_git *new_pack; struct packed_git *new_pack, *p;
char *tmp_idx = NULL; char *tmp_idx = NULL;
int ret; int ret;
if (has_pack_index(sha1)) { /*
new_pack = parse_pack_index(sha1, sha1_pack_index_name(sha1)); * If we already have the pack locally, no need to fetch its index or
if (!new_pack) * even add it to list; we already have all of its objects.
return -1; /* parse_pack_index() already issued error message */ */
goto add_pack; for (p = get_all_packs(the_repository); p; p = p->next) {
if (hasheq(p->hash, sha1, the_repository->hash_algo))
return 0;
} }
tmp_idx = fetch_pack_index(sha1, base_url); tmp_idx = fetch_pack_index(sha1, base_url);
@ -2429,15 +2448,12 @@ static int fetch_and_setup_pack_index(struct packed_git **packs_head,
} }
ret = verify_pack_index(new_pack); ret = verify_pack_index(new_pack);
if (!ret) { if (!ret)
close_pack_index(new_pack); close_pack_index(new_pack);
ret = finalize_object_file(tmp_idx, sha1_pack_index_name(sha1));
}
free(tmp_idx); free(tmp_idx);
if (ret) if (ret)
return -1; return -1;
add_pack:
new_pack->next = *packs_head; new_pack->next = *packs_head;
*packs_head = new_pack; *packs_head = new_pack;
return 0; return 0;
@ -2565,7 +2581,8 @@ struct http_pack_request *new_direct_http_pack_request(
preq->url = url; preq->url = url;
strbuf_addf(&preq->tmpfile, "%s.temp", sha1_pack_name(packed_git_hash)); odb_pack_name(&preq->tmpfile, packed_git_hash, "pack");
strbuf_addstr(&preq->tmpfile, ".temp");
preq->packfile = fopen(preq->tmpfile.buf, "a"); preq->packfile = fopen(preq->tmpfile.buf, "a");
if (!preq->packfile) { if (!preq->packfile) {
error("Unable to open local file %s for pack", error("Unable to open local file %s for pack",

22
midx.c
View File

@ -445,6 +445,7 @@ int prepare_midx_pack(struct repository *r, struct multi_pack_index *m,
uint32_t pack_int_id) uint32_t pack_int_id)
{ {
struct strbuf pack_name = STRBUF_INIT; struct strbuf pack_name = STRBUF_INIT;
struct strbuf key = STRBUF_INIT;
struct packed_git *p; struct packed_git *p;
pack_int_id = midx_for_pack(&m, pack_int_id); pack_int_id = midx_for_pack(&m, pack_int_id);
@ -455,16 +456,29 @@ int prepare_midx_pack(struct repository *r, struct multi_pack_index *m,
strbuf_addf(&pack_name, "%s/pack/%s", m->object_dir, strbuf_addf(&pack_name, "%s/pack/%s", m->object_dir,
m->pack_names[pack_int_id]); m->pack_names[pack_int_id]);
p = add_packed_git(pack_name.buf, pack_name.len, m->local); /* pack_map holds the ".pack" name, but we have the .idx */
strbuf_addbuf(&key, &pack_name);
strbuf_strip_suffix(&key, ".idx");
strbuf_addstr(&key, ".pack");
p = hashmap_get_entry_from_hash(&r->objects->pack_map,
strhash(key.buf), key.buf,
struct packed_git, packmap_ent);
if (!p) {
p = add_packed_git(pack_name.buf, pack_name.len, m->local);
if (p) {
install_packed_git(r, p);
list_add_tail(&p->mru, &r->objects->packed_git_mru);
}
}
strbuf_release(&pack_name); strbuf_release(&pack_name);
strbuf_release(&key);
if (!p) if (!p)
return 1; return 1;
p->multi_pack_index = 1; p->multi_pack_index = 1;
m->packs[pack_int_id] = p; m->packs[pack_int_id] = p;
install_packed_git(r, p);
list_add_tail(&p->mru, &r->objects->packed_git_mru);
return 0; return 0;
} }
@ -973,7 +987,7 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag
} }
m_offset = e.offset; m_offset = e.offset;
p_offset = find_pack_entry_one(oid.hash, e.p); p_offset = find_pack_entry_one(&oid, e.p);
if (m_offset != p_offset) if (m_offset != p_offset)
midx_report(_("incorrect object offset for oid[%d] = %s: %"PRIx64" != %"PRIx64), midx_report(_("incorrect object offset for oid[%d] = %s: %"PRIx64" != %"PRIx64),

View File

@ -935,7 +935,7 @@ static inline int bitmap_position_packfile(struct bitmap_index *bitmap_git,
const struct object_id *oid) const struct object_id *oid)
{ {
uint32_t pos; uint32_t pos;
off_t offset = find_pack_entry_one(oid->hash, bitmap_git->pack); off_t offset = find_pack_entry_one(oid, bitmap_git->pack);
if (!offset) if (!offset)
return -1; return -1;
@ -1609,7 +1609,7 @@ static int in_bitmapped_pack(struct bitmap_index *bitmap_git,
if (bsearch_midx(&object->oid, bitmap_git->midx, NULL)) if (bsearch_midx(&object->oid, bitmap_git->midx, NULL))
return 1; return 1;
} else { } else {
if (find_pack_entry_one(object->oid.hash, bitmap_git->pack) > 0) if (find_pack_entry_one(&object->oid, bitmap_git->pack) > 0)
return 1; return 1;
} }
} }

View File

@ -35,18 +35,6 @@ char *odb_pack_name(struct strbuf *buf,
return buf->buf; return buf->buf;
} }
char *sha1_pack_name(const unsigned char *sha1)
{
static struct strbuf buf = STRBUF_INIT;
return odb_pack_name(&buf, sha1, "pack");
}
char *sha1_pack_index_name(const unsigned char *sha1)
{
static struct strbuf buf = STRBUF_INIT;
return odb_pack_name(&buf, sha1, "idx");
}
static unsigned int pack_used_ctr; static unsigned int pack_used_ctr;
static unsigned int pack_mmap_calls; static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows; static unsigned int peak_pack_open_windows;
@ -237,13 +225,22 @@ static struct packed_git *alloc_packed_git(int extra)
return p; return p;
} }
static char *pack_path_from_idx(const char *idx_path)
{
size_t len;
if (!strip_suffix(idx_path, ".idx", &len))
BUG("idx path does not end in .idx: %s", idx_path);
return xstrfmt("%.*s.pack", (int)len, idx_path);
}
struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path) struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
{ {
const char *path = sha1_pack_name(sha1); char *path = pack_path_from_idx(idx_path);
size_t alloc = st_add(strlen(path), 1); size_t alloc = st_add(strlen(path), 1);
struct packed_git *p = alloc_packed_git(alloc); struct packed_git *p = alloc_packed_git(alloc);
memcpy(p->pack_name, path, alloc); /* includes NUL */ memcpy(p->pack_name, path, alloc); /* includes NUL */
free(path);
hashcpy(p->hash, sha1, the_repository->hash_algo); hashcpy(p->hash, sha1, the_repository->hash_algo);
if (check_packed_git_idx(idx_path, p)) { if (check_packed_git_idx(idx_path, p)) {
free(p); free(p);
@ -1242,7 +1239,9 @@ off_t get_delta_base(struct packed_git *p,
*curpos += used; *curpos += used;
} else if (type == OBJ_REF_DELTA) { } else if (type == OBJ_REF_DELTA) {
/* The base entry _must_ be in the same pack */ /* The base entry _must_ be in the same pack */
base_offset = find_pack_entry_one(base_info, p); struct object_id oid;
oidread(&oid, base_info, the_repository->hash_algo);
base_offset = find_pack_entry_one(&oid, p);
*curpos += the_hash_algo->rawsz; *curpos += the_hash_algo->rawsz;
} else } else
die("I am totally screwed"); die("I am totally screwed");
@ -1974,11 +1973,10 @@ off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
} }
} }
off_t find_pack_entry_one(const unsigned char *sha1, off_t find_pack_entry_one(const struct object_id *oid,
struct packed_git *p) struct packed_git *p)
{ {
const unsigned char *index = p->index_data; const unsigned char *index = p->index_data;
struct object_id oid;
uint32_t result; uint32_t result;
if (!index) { if (!index) {
@ -1986,8 +1984,7 @@ off_t find_pack_entry_one(const unsigned char *sha1,
return 0; return 0;
} }
hashcpy(oid.hash, sha1, the_repository->hash_algo); if (bsearch_pack(oid, p, &result))
if (bsearch_pack(&oid, p, &result))
return nth_packed_object_offset(p, result); return nth_packed_object_offset(p, result);
return 0; return 0;
} }
@ -2013,13 +2010,13 @@ int is_pack_valid(struct packed_git *p)
return !open_packed_git(p); return !open_packed_git(p);
} }
struct packed_git *find_sha1_pack(const unsigned char *sha1, struct packed_git *find_oid_pack(const struct object_id *oid,
struct packed_git *packs) struct packed_git *packs)
{ {
struct packed_git *p; struct packed_git *p;
for (p = packs; p; p = p->next) { for (p = packs; p; p = p->next) {
if (find_pack_entry_one(sha1, p)) if (find_pack_entry_one(oid, p))
return p; return p;
} }
return NULL; return NULL;
@ -2036,7 +2033,7 @@ static int fill_pack_entry(const struct object_id *oid,
oidset_contains(&p->bad_objects, oid)) oidset_contains(&p->bad_objects, oid))
return 0; return 0;
offset = find_pack_entry_one(oid->hash, p); offset = find_pack_entry_one(oid, p);
if (!offset) if (!offset)
return 0; return 0;
@ -2151,14 +2148,6 @@ int has_object_kept_pack(const struct object_id *oid, unsigned flags)
return find_kept_pack_entry(the_repository, oid, flags, &e); return find_kept_pack_entry(the_repository, oid, flags, &e);
} }
int has_pack_index(const unsigned char *sha1)
{
struct stat st;
if (stat(sha1_pack_index_name(sha1), &st))
return 0;
return 1;
}
int for_each_object_in_pack(struct packed_git *p, int for_each_object_in_pack(struct packed_git *p,
each_packed_object_fn cb, void *data, each_packed_object_fn cb, void *data,
enum for_each_object_flags flags) enum for_each_object_flags flags)

View File

@ -31,26 +31,21 @@ struct pack_entry {
*/ */
char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext); char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext);
/*
* Return the name of the (local) packfile with the specified sha1 in
* its name. The return value is a pointer to memory that is
* overwritten each time this function is called.
*/
char *sha1_pack_name(const unsigned char *sha1);
/*
* Return the name of the (local) pack index file with the specified
* sha1 in its name. The return value is a pointer to memory that is
* overwritten each time this function is called.
*/
char *sha1_pack_index_name(const unsigned char *sha1);
/* /*
* Return the basename of the packfile, omitting any containing directory * Return the basename of the packfile, omitting any containing directory
* (e.g., "pack-1234abcd[...].pack"). * (e.g., "pack-1234abcd[...].pack").
*/ */
const char *pack_basename(struct packed_git *p); const char *pack_basename(struct packed_git *p);
/*
* Parse the pack idx file found at idx_path and create a packed_git struct
* which can be used with find_pack_entry_one().
*
* You probably don't want to use this function! It skips most of the normal
* sanity checks (including whether we even have the matching .pack file),
* and does not add the resulting packed_git struct to the internal list of
* packs. You probably want add_packed_git() instead.
*/
struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path); struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path);
typedef void each_file_in_pack_dir_fn(const char *full_path, size_t full_path_len, typedef void each_file_in_pack_dir_fn(const char *full_path, size_t full_path_len,
@ -84,8 +79,13 @@ struct packed_git *get_all_packs(struct repository *r);
*/ */
unsigned long repo_approximate_object_count(struct repository *r); unsigned long repo_approximate_object_count(struct repository *r);
struct packed_git *find_sha1_pack(const unsigned char *sha1, /*
struct packed_git *packs); * Find the pack within the "packs" list whose index contains the object "oid".
* For general object lookups, you probably don't want this; use
* find_pack_entry() instead.
*/
struct packed_git *find_oid_pack(const struct object_id *oid,
struct packed_git *packs);
void pack_report(void); void pack_report(void);
@ -154,10 +154,10 @@ int nth_packed_object_id(struct object_id *, struct packed_git *, uint32_t n);
off_t nth_packed_object_offset(const struct packed_git *, uint32_t n); off_t nth_packed_object_offset(const struct packed_git *, uint32_t n);
/* /*
* If the object named sha1 is present in the specified packfile, * If the object named by oid is present in the specified packfile,
* return its offset within the packfile; otherwise, return 0. * return its offset within the packfile; otherwise, return 0.
*/ */
off_t find_pack_entry_one(const unsigned char *sha1, struct packed_git *); off_t find_pack_entry_one(const struct object_id *oid, struct packed_git *);
int is_pack_valid(struct packed_git *); int is_pack_valid(struct packed_git *);
void *unpack_entry(struct repository *r, struct packed_git *, off_t, enum object_type *, unsigned long *); void *unpack_entry(struct repository *r, struct packed_git *, off_t, enum object_type *, unsigned long *);
@ -193,8 +193,6 @@ int find_kept_pack_entry(struct repository *r, const struct object_id *oid, unsi
int has_object_pack(const struct object_id *oid); int has_object_pack(const struct object_id *oid);
int has_object_kept_pack(const struct object_id *oid, unsigned flags); int has_object_kept_pack(const struct object_id *oid, unsigned flags);
int has_pack_index(const unsigned char *sha1);
/* /*
* Return 1 if an object in a promisor packfile is or refers to the given * Return 1 if an object in a promisor packfile is or refers to the given
* object, 0 otherwise. * object, 0 otherwise.
@ -209,7 +207,7 @@ int is_promisor_object(const struct object_id *oid);
* *
* This function should not be used directly. It is exposed here only so that we * This function should not be used directly. It is exposed here only so that we
* have a convenient entry-point for fuzz testing. For real uses, you should * have a convenient entry-point for fuzz testing. For real uses, you should
* probably use open_pack_index() or parse_pack_index() instead. * probably use open_pack_index() instead.
*/ */
int load_idx(const char *path, const unsigned int hashsz, void *idx_map, int load_idx(const char *path, const unsigned int hashsz, void *idx_map,
size_t idx_size, struct packed_git *p); size_t idx_size, struct packed_git *p);

View File

@ -40,7 +40,7 @@ int cmd__find_pack(int argc, const char **argv)
die("cannot parse %s as an object name", argv[0]); die("cannot parse %s as an object name", argv[0]);
for (p = get_all_packs(the_repository); p; p = p->next) for (p = get_all_packs(the_repository); p; p = p->next)
if (find_pack_entry_one(oid.hash, p)) { if (find_pack_entry_one(&oid, p)) {
printf("%s\n", p->pack_name); printf("%s\n", p->pack_name);
actual_count++; actual_count++;
} }

View File

@ -39,4 +39,12 @@ test_expect_success 'info/refs updates when changes are made' '
! test_cmp a b ! test_cmp a b
' '
test_expect_success 'midx does not create duplicate pack entries' '
git repack -d --write-midx &&
git repack -d &&
grep ^P .git/objects/info/packs >packs &&
uniq -d <packs >dups &&
test_must_be_empty dups
'
test_done test_done

View File

@ -307,6 +307,14 @@ test_expect_success 'fetch notices corrupt idx' '
) )
' '
# usage: count_fetches <nr> <extension> <trace_file>
count_fetches () {
# ignore grep exit code; it may return non-zero if we are expecting no
# matches
grep "GET .*objects/pack/pack-[a-z0-9]*.$2" "$3" >trace.count
test_line_count = "$1" trace.count
}
test_expect_success 'fetch can handle previously-fetched .idx files' ' test_expect_success 'fetch can handle previously-fetched .idx files' '
git checkout --orphan branch1 && git checkout --orphan branch1 &&
echo base >file && echo base >file &&
@ -321,8 +329,14 @@ test_expect_success 'fetch can handle previously-fetched .idx files' '
git push "$HTTPD_DOCUMENT_ROOT_PATH"/repo_packed_branches.git branch2 && git push "$HTTPD_DOCUMENT_ROOT_PATH"/repo_packed_branches.git branch2 &&
git --git-dir="$HTTPD_DOCUMENT_ROOT_PATH"/repo_packed_branches.git repack -d && git --git-dir="$HTTPD_DOCUMENT_ROOT_PATH"/repo_packed_branches.git repack -d &&
git --bare init clone_packed_branches.git && git --bare init clone_packed_branches.git &&
git --git-dir=clone_packed_branches.git fetch "$HTTPD_URL"/dumb/repo_packed_branches.git branch1:branch1 && GIT_TRACE_CURL=$PWD/one.trace git --git-dir=clone_packed_branches.git \
git --git-dir=clone_packed_branches.git fetch "$HTTPD_URL"/dumb/repo_packed_branches.git branch2:branch2 fetch "$HTTPD_URL"/dumb/repo_packed_branches.git branch1:branch1 &&
count_fetches 2 idx one.trace &&
count_fetches 1 pack one.trace &&
GIT_TRACE_CURL=$PWD/two.trace git --git-dir=clone_packed_branches.git \
fetch "$HTTPD_URL"/dumb/repo_packed_branches.git branch2:branch2 &&
count_fetches 1 idx two.trace &&
count_fetches 1 pack two.trace
' '
test_expect_success 'did not use upload-pack service' ' test_expect_success 'did not use upload-pack service' '
@ -507,4 +521,14 @@ test_expect_success 'fetching via http alternates works' '
git -c http.followredirects=true clone "$HTTPD_URL/dumb/alt-child.git" git -c http.followredirects=true clone "$HTTPD_URL/dumb/alt-child.git"
' '
test_expect_success 'dumb http can fetch index v1' '
server=$HTTPD_DOCUMENT_ROOT_PATH/idx-v1.git &&
git init --bare "$server" &&
git -C "$server" --work-tree=. commit --allow-empty -m foo &&
git -C "$server" -c pack.indexVersion=1 gc &&
git clone "$HTTPD_URL/dumb/idx-v1.git" &&
git -C idx-v1 fsck
'
test_done test_done

View File

@ -157,7 +157,7 @@ static int process(struct walker *walker, struct object *obj)
else { else {
if (obj->flags & COMPLETE) if (obj->flags & COMPLETE)
return 0; return 0;
walker->prefetch(walker, obj->oid.hash); walker->prefetch(walker, &obj->oid);
} }
object_list_insert(obj, process_queue_end); object_list_insert(obj, process_queue_end);
@ -186,7 +186,7 @@ static int loop(struct walker *walker)
* the queue because we needed to fetch it first. * the queue because we needed to fetch it first.
*/ */
if (! (obj->flags & TO_SCAN)) { if (! (obj->flags & TO_SCAN)) {
if (walker->fetch(walker, obj->oid.hash)) { if (walker->fetch(walker, &obj->oid)) {
stop_progress(&progress); stop_progress(&progress);
report_missing(obj); report_missing(obj);
return -1; return -1;

View File

@ -6,8 +6,8 @@
struct walker { struct walker {
void *data; void *data;
int (*fetch_ref)(struct walker *, struct ref *ref); int (*fetch_ref)(struct walker *, struct ref *ref);
void (*prefetch)(struct walker *, unsigned char *sha1); void (*prefetch)(struct walker *, const struct object_id *oid);
int (*fetch)(struct walker *, unsigned char *sha1); int (*fetch)(struct walker *, const struct object_id *oid);
void (*cleanup)(struct walker *); void (*cleanup)(struct walker *);
int get_verbosely; int get_verbosely;
int get_progress; int get_progress;