From 2cf3fe63f6eedd6d132c530b897595345a05088b Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:43:55 +0100 Subject: [PATCH 01/18] packfile: add repository to struct `packed_git` The struct `packed_git` holds information regarding a packed object file. Let's add the repository variable to this object, to represent the repository that this packfile belongs to. This helps remove dependency on the global `the_repository` object in `packfile.c` by simply using repository information now readily available in the struct. We do need to consider that a packfile could be part of the alternates of a repository, but considering that we only have one repository struct and also that we currently anyways use 'the_repository', we should be OK with this change. We also modify `alloc_packed_git` to ensure that the repository is added to newly created `packed_git` structs. This requires modifying the function and all its callee to pass the repository object down the levels. Helped-by: Taylor Blau Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/fast-import.c | 3 ++- builtin/index-pack.c | 6 ++++-- commit-graph.c | 2 +- connected.c | 3 ++- http.c | 2 +- midx-write.c | 2 +- midx.c | 2 +- object-store-ll.h | 5 +++++ packfile.c | 15 +++++++++------ packfile.h | 6 ++++-- 10 files changed, 30 insertions(+), 16 deletions(-) diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 76d5c20f14..da7e2d613b 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -765,6 +765,7 @@ static void start_packfile(void) p->pack_fd = pack_fd; p->do_not_close = 1; + p->repo = the_repository; pack_file = hashfd(pack_fd, p->pack_name); pack_data = p; @@ -888,7 +889,7 @@ static void end_packfile(void) idx_name = keep_pack(create_index()); /* Register the packfile with core git's machinery. */ - new_p = add_packed_git(idx_name, strlen(idx_name), 1); + new_p = add_packed_git(pack_data->repo, idx_name, strlen(idx_name), 1); if (!new_p) die("core git rejected index %s", idx_name); all_packs[pack_id] = new_p; diff --git a/builtin/index-pack.c b/builtin/index-pack.c index 9d23b41b3a..be2f99625e 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1552,7 +1552,8 @@ static void final(const char *final_pack_name, const char *curr_pack_name, if (do_fsck_object) { struct packed_git *p; - p = add_packed_git(final_index_name, strlen(final_index_name), 0); + p = add_packed_git(the_repository, final_index_name, + strlen(final_index_name), 0); if (p) install_packed_git(the_repository, p); } @@ -1650,7 +1651,8 @@ static void read_v2_anomalous_offsets(struct packed_git *p, static void read_idx_option(struct pack_idx_option *opts, const char *pack_name) { - struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1); + struct packed_git *p = add_packed_git(the_repository, pack_name, + strlen(pack_name), 1); if (!p) die(_("Cannot open existing pack file '%s'"), pack_name); diff --git a/commit-graph.c b/commit-graph.c index 5bd89c0acd..83dd69bfeb 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -1914,7 +1914,7 @@ static int fill_oids_from_packs(struct write_commit_graph_context *ctx, struct packed_git *p; strbuf_setlen(&packname, dirlen); strbuf_addstr(&packname, pack_indexes->items[i].string); - p = add_packed_git(packname.buf, packname.len, 1); + p = add_packed_git(ctx->r, packname.buf, packname.len, 1); if (!p) { ret = error(_("error adding pack %s"), packname.buf); goto cleanup; diff --git a/connected.c b/connected.c index a9e2e13995..3099da84f3 100644 --- a/connected.c +++ b/connected.c @@ -54,7 +54,8 @@ int check_connected(oid_iterate_fn fn, void *cb_data, strbuf_add(&idx_file, transport->pack_lockfiles.items[0].string, base_len); strbuf_addstr(&idx_file, ".idx"); - new_pack = add_packed_git(idx_file.buf, idx_file.len, 1); + new_pack = add_packed_git(the_repository, idx_file.buf, + idx_file.len, 1); strbuf_release(&idx_file); } diff --git a/http.c b/http.c index 58242b9d2d..6744e18409 100644 --- a/http.c +++ b/http.c @@ -2439,7 +2439,7 @@ static int fetch_and_setup_pack_index(struct packed_git **packs_head, if (!tmp_idx) return -1; - new_pack = parse_pack_index(sha1, tmp_idx); + new_pack = parse_pack_index(the_repository, sha1, tmp_idx); if (!new_pack) { unlink(tmp_idx); free(tmp_idx); diff --git a/midx-write.c b/midx-write.c index b3a5f6c516..c57726ef94 100644 --- a/midx-write.c +++ b/midx-write.c @@ -154,7 +154,7 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len, return; ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); - p = add_packed_git(full_path, full_path_len, 0); + p = add_packed_git(the_repository, full_path, full_path_len, 0); if (!p) { warning(_("failed to add packfile '%s'"), full_path); diff --git a/midx.c b/midx.c index e82d4f2e65..8edb75f51d 100644 --- a/midx.c +++ b/midx.c @@ -464,7 +464,7 @@ int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, strhash(key.buf), key.buf, struct packed_git, packmap_ent); if (!p) { - p = add_packed_git(pack_name.buf, pack_name.len, m->local); + p = add_packed_git(r, 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); diff --git a/object-store-ll.h b/object-store-ll.h index 53b8e693b1..d46cd0e654 100644 --- a/object-store-ll.h +++ b/object-store-ll.h @@ -10,6 +10,7 @@ struct oidmap; struct oidtree; struct strbuf; +struct repository; struct object_directory { struct object_directory *next; @@ -135,6 +136,10 @@ struct packed_git { */ const uint32_t *mtimes_map; size_t mtimes_size; + + /* repo denotes the repository this packfile belongs to */ + struct repository *repo; + /* something like ".git/objects/pack/xxxxx.pack" */ char pack_name[FLEX_ARRAY]; /* more */ }; diff --git a/packfile.c b/packfile.c index 9560f0a33c..6058eddf35 100644 --- a/packfile.c +++ b/packfile.c @@ -217,11 +217,12 @@ uint32_t get_pack_fanout(struct packed_git *p, uint32_t value) return ntohl(level1_ofs[value]); } -static struct packed_git *alloc_packed_git(int extra) +static struct packed_git *alloc_packed_git(struct repository *r, int extra) { struct packed_git *p = xmalloc(st_add(sizeof(*p), extra)); memset(p, 0, sizeof(*p)); p->pack_fd = -1; + p->repo = r; return p; } @@ -233,11 +234,12 @@ static char *pack_path_from_idx(const char *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(struct repository *r, unsigned char *sha1, + const char *idx_path) { char *path = pack_path_from_idx(idx_path); size_t alloc = st_add(strlen(path), 1); - struct packed_git *p = alloc_packed_git(alloc); + struct packed_git *p = alloc_packed_git(r, alloc); memcpy(p->pack_name, path, alloc); /* includes NUL */ free(path); @@ -703,7 +705,8 @@ void unuse_pack(struct pack_window **w_cursor) } } -struct packed_git *add_packed_git(const char *path, size_t path_len, int local) +struct packed_git *add_packed_git(struct repository *r, const char *path, + size_t path_len, int local) { struct stat st; size_t alloc; @@ -721,7 +724,7 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local) * the use xsnprintf double-checks that) */ alloc = st_add3(path_len, strlen(".promisor"), 1); - p = alloc_packed_git(alloc); + p = alloc_packed_git(r, alloc); memcpy(p->pack_name, path, path_len); xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep"); @@ -877,7 +880,7 @@ static void prepare_pack(const char *full_name, size_t full_name_len, /* Don't reopen a pack we already have. */ if (!hashmap_get(&data->r->objects->pack_map, &hent, pack_name)) { - p = add_packed_git(full_name, full_name_len, data->local); + p = add_packed_git(data->r, full_name, full_name_len, data->local); if (p) install_packed_git(data->r, p); } diff --git a/packfile.h b/packfile.h index 08f88a7ff5..aee69d1a0b 100644 --- a/packfile.h +++ b/packfile.h @@ -46,7 +46,8 @@ const char *pack_basename(struct packed_git *p); * 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(struct repository *r, unsigned char *sha1, + const char *idx_path); typedef void each_file_in_pack_dir_fn(const char *full_path, size_t full_path_len, const char *file_name, void *data); @@ -113,7 +114,8 @@ void close_pack(struct packed_git *); void close_object_store(struct raw_object_store *o); void unuse_pack(struct pack_window **); void clear_delta_base_cache(void); -struct packed_git *add_packed_git(const char *path, size_t path_len, int local); +struct packed_git *add_packed_git(struct repository *r, const char *path, + size_t path_len, int local); /* * Unlink the .pack and associated extension files. From 9c5ce06d74251601ca0dcb3ebe2284639f96f9a2 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:43:56 +0100 Subject: [PATCH 02/18] packfile: use `repository` from `packed_git` directly In the previous commit, we introduced the `repository` structure inside `packed_git`. This provides an alternative route instead of using the global `the_repository` variable. Let's modify `packfile.c` now to use this field wherever possible instead of relying on the global state. There are still a few instances of `the_repository` usage in the file, where there is no struct `packed_git` locally available, which will be fixed in the following commits. Helped-by: Taylor Blau Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- packfile.c | 50 +++++++++++++++++++++++++++----------------------- 1 file changed, 27 insertions(+), 23 deletions(-) diff --git a/packfile.c b/packfile.c index 6058eddf35..5bfa1e17c2 100644 --- a/packfile.c +++ b/packfile.c @@ -79,7 +79,7 @@ static int check_packed_git_idx(const char *path, struct packed_git *p) size_t idx_size; int fd = git_open(path), ret; struct stat st; - const unsigned int hashsz = the_hash_algo->rawsz; + const unsigned int hashsz = p->repo->hash_algo->rawsz; if (fd < 0) return -1; @@ -243,7 +243,7 @@ struct packed_git *parse_pack_index(struct repository *r, unsigned char *sha1, memcpy(p->pack_name, path, alloc); /* includes NUL */ free(path); - hashcpy(p->hash, sha1, the_repository->hash_algo); + hashcpy(p->hash, sha1, p->repo->hash_algo); if (check_packed_git_idx(idx_path, p)) { free(p); return NULL; @@ -278,7 +278,7 @@ static int unuse_one_window(struct packed_git *current) if (current) scan_windows(current, &lru_p, &lru_w, &lru_l); - for (p = the_repository->objects->packed_git; p; p = p->next) + for (p = current->repo->objects->packed_git; p; p = p->next) scan_windows(p, &lru_p, &lru_w, &lru_l); if (lru_p) { munmap(lru_w->base, lru_w->len); @@ -540,7 +540,7 @@ static int open_packed_git_1(struct packed_git *p) unsigned char hash[GIT_MAX_RAWSZ]; unsigned char *idx_hash; ssize_t read_result; - const unsigned hashsz = the_hash_algo->rawsz; + const unsigned hashsz = p->repo->hash_algo->rawsz; if (open_pack_index(p)) return error("packfile %s index unavailable", p->pack_name); @@ -597,7 +597,7 @@ static int open_packed_git_1(struct packed_git *p) if (read_result != hashsz) return error("packfile %s signature is unavailable", p->pack_name); idx_hash = ((unsigned char *)p->index_data) + p->index_size - hashsz * 2; - if (!hasheq(hash, idx_hash, the_repository->hash_algo)) + if (!hasheq(hash, idx_hash, p->repo->hash_algo)) return error("packfile %s does not match index", p->pack_name); return 0; } @@ -637,7 +637,7 @@ unsigned char *use_pack(struct packed_git *p, */ if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p)) die("packfile %s cannot be accessed", p->pack_name); - if (offset > (p->pack_size - the_hash_algo->rawsz)) + if (offset > (p->pack_size - p->repo->hash_algo->rawsz)) die("offset beyond end of packfile (truncated pack?)"); if (offset < 0) die(_("offset before end of packfile (broken .idx?)")); @@ -711,6 +711,7 @@ struct packed_git *add_packed_git(struct repository *r, const char *path, struct stat st; size_t alloc; struct packed_git *p; + struct object_id oid; /* * Make sure a corresponding .pack file exists and that @@ -751,9 +752,13 @@ struct packed_git *add_packed_git(struct repository *r, const char *path, p->pack_size = st.st_size; p->pack_local = local; p->mtime = st.st_mtime; - if (path_len < the_hash_algo->hexsz || - get_hash_hex(path + path_len - the_hash_algo->hexsz, p->hash)) - hashclr(p->hash, the_repository->hash_algo); + if (path_len < r->hash_algo->hexsz || + get_oid_hex_algop(path + path_len - r->hash_algo->hexsz, &oid, + r->hash_algo)) + hashclr(p->hash, r->hash_algo); + else + hashcpy(p->hash, oid.hash, r->hash_algo); + return p; } @@ -1243,9 +1248,9 @@ off_t get_delta_base(struct packed_git *p, } else if (type == OBJ_REF_DELTA) { /* The base entry _must_ be in the same pack */ struct object_id oid; - oidread(&oid, base_info, the_repository->hash_algo); + oidread(&oid, base_info, p->repo->hash_algo); base_offset = find_pack_entry_one(&oid, p); - *curpos += the_hash_algo->rawsz; + *curpos += p->repo->hash_algo->rawsz; } else die("I am totally screwed"); return base_offset; @@ -1266,7 +1271,7 @@ static int get_delta_base_oid(struct packed_git *p, { if (type == OBJ_REF_DELTA) { unsigned char *base = use_pack(p, w_curs, curpos, NULL); - oidread(oid, base, the_repository->hash_algo); + oidread(oid, base, p->repo->hash_algo); return 0; } else if (type == OBJ_OFS_DELTA) { uint32_t base_pos; @@ -1608,7 +1613,7 @@ int packed_object_info(struct repository *r, struct packed_git *p, goto out; } } else - oidclr(oi->delta_base_oid, the_repository->hash_algo); + oidclr(oi->delta_base_oid, p->repo->hash_algo); } oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED : @@ -1897,7 +1902,7 @@ int bsearch_pack(const struct object_id *oid, const struct packed_git *p, uint32 { const unsigned char *index_fanout = p->index_data; const unsigned char *index_lookup; - const unsigned int hashsz = the_hash_algo->rawsz; + const unsigned int hashsz = p->repo->hash_algo->rawsz; int index_lookup_width; if (!index_fanout) @@ -1922,7 +1927,7 @@ int nth_packed_object_id(struct object_id *oid, uint32_t n) { const unsigned char *index = p->index_data; - const unsigned int hashsz = the_hash_algo->rawsz; + const unsigned int hashsz = p->repo->hash_algo->rawsz; if (!index) { if (open_pack_index(p)) return -1; @@ -1933,11 +1938,10 @@ int nth_packed_object_id(struct object_id *oid, index += 4 * 256; if (p->index_version == 1) { oidread(oid, index + st_add(st_mult(hashsz + 4, n), 4), - the_repository->hash_algo); + p->repo->hash_algo); } else { index += 8; - oidread(oid, index + st_mult(hashsz, n), - the_repository->hash_algo); + oidread(oid, index + st_mult(hashsz, n), p->repo->hash_algo); } return 0; } @@ -1959,7 +1963,7 @@ void check_pack_index_ptr(const struct packed_git *p, const void *vptr) off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n) { const unsigned char *index = p->index_data; - const unsigned int hashsz = the_hash_algo->rawsz; + const unsigned int hashsz = p->repo->hash_algo->rawsz; index += 4 * 256; if (p->index_version == 1) { return ntohl(*((uint32_t *)(index + st_mult(hashsz + 4, n)))); @@ -2159,7 +2163,7 @@ int for_each_object_in_pack(struct packed_git *p, int r = 0; if (flags & FOR_EACH_OBJECT_PACK_ORDER) { - if (load_pack_revindex(the_repository, p)) + if (load_pack_revindex(p->repo, p)) return -1; } @@ -2227,7 +2231,7 @@ int for_each_packed_object(each_packed_object_fn cb, void *data, } static int add_promisor_object(const struct object_id *oid, - struct packed_git *pack UNUSED, + struct packed_git *pack, uint32_t pos UNUSED, void *set_) { @@ -2235,12 +2239,12 @@ static int add_promisor_object(const struct object_id *oid, struct object *obj; int we_parsed_object; - obj = lookup_object(the_repository, oid); + obj = lookup_object(pack->repo, oid); if (obj && obj->parsed) { we_parsed_object = 0; } else { we_parsed_object = 1; - obj = parse_object(the_repository, oid); + obj = parse_object(pack->repo, oid); } if (!obj) From 4f9e6bd4923728053669c300d3ee8483d95f599b Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:43:57 +0100 Subject: [PATCH 03/18] packfile: pass `repository` to static function in the file Some of the static functions in the `packfile.c` access global variables, which can simply be avoided by passing the `repository` struct down to them. Let's do that. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- packfile.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packfile.c b/packfile.c index 5bfa1e17c2..c96ebc4c69 100644 --- a/packfile.c +++ b/packfile.c @@ -460,13 +460,13 @@ static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struc *accept_windows_inuse = has_windows_inuse; } -static int close_one_pack(void) +static int close_one_pack(struct repository *r) { struct packed_git *p, *lru_p = NULL; struct pack_window *mru_w = NULL; int accept_windows_inuse = 1; - for (p = the_repository->objects->packed_git; p; p = p->next) { + for (p = r->objects->packed_git; p; p = p->next) { if (p->pack_fd == -1) continue; find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse); @@ -555,7 +555,7 @@ static int open_packed_git_1(struct packed_git *p) pack_max_fds = 1; } - while (pack_max_fds <= pack_open_fds && close_one_pack()) + while (pack_max_fds <= pack_open_fds && close_one_pack(p->repo)) ; /* nothing */ p->pack_fd = git_open(p->pack_name); @@ -610,7 +610,8 @@ static int open_packed_git(struct packed_git *p) return -1; } -static int in_window(struct pack_window *win, off_t offset) +static int in_window(struct repository *r, struct pack_window *win, + off_t offset) { /* We must promise at least one full hash after the * offset is available from this window, otherwise the offset @@ -620,7 +621,7 @@ static int in_window(struct pack_window *win, off_t offset) */ off_t win_off = win->offset; return win_off <= offset - && (offset + the_hash_algo->rawsz) <= (win_off + win->len); + && (offset + r->hash_algo->rawsz) <= (win_off + win->len); } unsigned char *use_pack(struct packed_git *p, @@ -642,11 +643,11 @@ unsigned char *use_pack(struct packed_git *p, if (offset < 0) die(_("offset before end of packfile (broken .idx?)")); - if (!win || !in_window(win, offset)) { + if (!win || !in_window(p->repo, win, offset)) { if (win) win->inuse_cnt--; for (win = p->windows; win; win = win->next) { - if (in_window(win, offset)) + if (in_window(p->repo, win, offset)) break; } if (!win) { From 873b00597bbf20c1bcda089a687641167b148fa2 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:43:58 +0100 Subject: [PATCH 04/18] packfile: pass down repository to `odb_pack_name` The function `odb_pack_name` currently relies on the global variable `the_repository`. To eliminate global variable usage in `packfile.c`, we should progressively shift the dependency on the_repository to higher layers. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/fast-import.c | 8 ++++---- builtin/index-pack.c | 4 ++-- builtin/pack-redundant.c | 2 +- http.c | 2 +- packfile.c | 9 ++++----- packfile.h | 3 ++- 6 files changed, 14 insertions(+), 14 deletions(-) diff --git a/builtin/fast-import.c b/builtin/fast-import.c index da7e2d613b..3ccc4c5722 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -806,7 +806,7 @@ static char *keep_pack(const char *curr_index_name) struct strbuf name = STRBUF_INIT; int keep_fd; - odb_pack_name(&name, pack_data->hash, "keep"); + odb_pack_name(pack_data->repo, &name, pack_data->hash, "keep"); keep_fd = odb_pack_keep(name.buf); if (keep_fd < 0) die_errno("cannot create keep file"); @@ -814,11 +814,11 @@ static char *keep_pack(const char *curr_index_name) if (close(keep_fd)) die_errno("failed to write keep file"); - odb_pack_name(&name, pack_data->hash, "pack"); + odb_pack_name(pack_data->repo, &name, pack_data->hash, "pack"); if (finalize_object_file(pack_data->pack_name, name.buf)) die("cannot store pack file"); - odb_pack_name(&name, pack_data->hash, "idx"); + odb_pack_name(pack_data->repo, &name, pack_data->hash, "idx"); if (finalize_object_file(curr_index_name, name.buf)) die("cannot store index file"); free((void *)curr_index_name); @@ -832,7 +832,7 @@ static void unkeep_all_packs(void) for (k = 0; k < pack_id; k++) { struct packed_git *p = all_packs[k]; - odb_pack_name(&name, p->hash, "keep"); + odb_pack_name(p->repo, &name, p->hash, "keep"); unlink_or_warn(name.buf); } strbuf_release(&name); diff --git a/builtin/index-pack.c b/builtin/index-pack.c index be2f99625e..eaefb41761 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1479,7 +1479,7 @@ static void write_special_file(const char *suffix, const char *msg, if (pack_name) filename = derive_filename(pack_name, "pack", suffix, &name_buf); else - filename = odb_pack_name(&name_buf, hash, suffix); + filename = odb_pack_name(the_repository, &name_buf, hash, suffix); fd = odb_pack_keep(filename); if (fd < 0) { @@ -1507,7 +1507,7 @@ static void rename_tmp_packfile(const char **final_name, { if (!*final_name || strcmp(*final_name, curr_name)) { if (!*final_name) - *final_name = odb_pack_name(name, hash, ext); + *final_name = odb_pack_name(the_repository, name, hash, ext); if (finalize_object_file(curr_name, *final_name)) die(_("unable to rename temporary '*.%s' file to '%s'"), ext, *final_name); diff --git a/builtin/pack-redundant.c b/builtin/pack-redundant.c index d2c1c4e5ec..bc61990a93 100644 --- a/builtin/pack-redundant.c +++ b/builtin/pack-redundant.c @@ -690,7 +690,7 @@ int cmd_pack_redundant(int argc, const char **argv, const char *prefix UNUSED, s pl = red = pack_list_difference(local_packs, min); while (pl) { printf("%s\n%s\n", - odb_pack_name(&idx_name, pl->pack->hash, "idx"), + odb_pack_name(pl->pack->repo, &idx_name, pl->pack->hash, "idx"), pl->pack->pack_name); pl = pl->next; } diff --git a/http.c b/http.c index 6744e18409..420f1566f0 100644 --- a/http.c +++ b/http.c @@ -2581,7 +2581,7 @@ struct http_pack_request *new_direct_http_pack_request( preq->url = url; - odb_pack_name(&preq->tmpfile, packed_git_hash, "pack"); + odb_pack_name(the_repository, &preq->tmpfile, packed_git_hash, "pack"); strbuf_addstr(&preq->tmpfile, ".temp"); preq->packfile = fopen(preq->tmpfile.buf, "a"); if (!preq->packfile) { diff --git a/packfile.c b/packfile.c index c96ebc4c69..1015dac6db 100644 --- a/packfile.c +++ b/packfile.c @@ -25,13 +25,12 @@ #include "pack-revindex.h" #include "promisor-remote.h" -char *odb_pack_name(struct strbuf *buf, - const unsigned char *hash, - const char *ext) +char *odb_pack_name(struct repository *r, struct strbuf *buf, + const unsigned char *hash, const char *ext) { strbuf_reset(buf); - strbuf_addf(buf, "%s/pack/pack-%s.%s", repo_get_object_directory(the_repository), - hash_to_hex(hash), ext); + strbuf_addf(buf, "%s/pack/pack-%s.%s", repo_get_object_directory(r), + hash_to_hex_algop(hash, r->hash_algo), ext); return buf->buf; } diff --git a/packfile.h b/packfile.h index aee69d1a0b..51187f2393 100644 --- a/packfile.h +++ b/packfile.h @@ -29,7 +29,8 @@ struct pack_entry { * * Example: odb_pack_name(out, sha1, "idx") => ".git/objects/pack/pack-1234..idx" */ -char *odb_pack_name(struct strbuf *buf, const unsigned char *sha1, const char *ext); +char *odb_pack_name(struct repository *r, struct strbuf *buf, + const unsigned char *hash, const char *ext); /* * Return the basename of the packfile, omitting any containing directory From cc656f4eb2b7b10bc530c96844909c869bdd1fdf Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:43:59 +0100 Subject: [PATCH 05/18] packfile: pass down repository to `has_object[_kept]_pack` The functions `has_object[_kept]_pack` currently rely on the global variable `the_repository`. To eliminate global variable usage in `packfile.c`, we should progressively shift the dependency on the_repository to higher layers. Let's remove its usage from these functions and any related ones. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/count-objects.c | 2 +- builtin/fsck.c | 2 +- builtin/pack-objects.c | 4 ++-- diff.c | 3 ++- list-objects.c | 3 ++- pack-bitmap.c | 2 +- packfile.c | 9 +++++---- packfile.h | 5 +++-- prune-packed.c | 2 +- reachable.c | 2 +- revision.c | 4 ++-- 11 files changed, 21 insertions(+), 17 deletions(-) diff --git a/builtin/count-objects.c b/builtin/count-objects.c index 04d80887e0..1e89148ed7 100644 --- a/builtin/count-objects.c +++ b/builtin/count-objects.c @@ -67,7 +67,7 @@ static int count_loose(const struct object_id *oid, const char *path, else { loose_size += on_disk_bytes(st); loose++; - if (verbose && has_object_pack(oid)) + if (verbose && has_object_pack(the_repository, oid)) packed_loose++; } return 0; diff --git a/builtin/fsck.c b/builtin/fsck.c index 7f4e2f0414..bb56eb98ac 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -272,7 +272,7 @@ static void check_reachable_object(struct object *obj) if (!(obj->flags & HAS_OBJ)) { if (is_promisor_object(&obj->oid)) return; - if (has_object_pack(&obj->oid)) + if (has_object_pack(the_repository, &obj->oid)) return; /* it is in pack - forget about it */ printf_ln(_("missing %s %s"), printable_type(&obj->oid, obj->type), diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 0800714267..0f32e92a3a 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -1529,7 +1529,7 @@ static int want_found_object(const struct object_id *oid, int exclude, return 0; if (ignore_packed_keep_in_core && p->pack_keep_in_core) return 0; - if (has_object_kept_pack(oid, flags)) + if (has_object_kept_pack(p->repo, oid, flags)) return 0; } @@ -3627,7 +3627,7 @@ static void show_cruft_commit(struct commit *commit, void *data) static int cruft_include_check_obj(struct object *obj, void *data UNUSED) { - return !has_object_kept_pack(&obj->oid, IN_CORE_KEEP_PACKS); + return !has_object_kept_pack(to_pack.repo, &obj->oid, IN_CORE_KEEP_PACKS); } static int cruft_include_check(struct commit *commit, void *data) diff --git a/diff.c b/diff.c index dceac20d18..266ddf18e7 100644 --- a/diff.c +++ b/diff.c @@ -4041,7 +4041,8 @@ static int reuse_worktree_file(struct index_state *istate, * objects however would tend to be slower as they need * to be individually opened and inflated. */ - if (!FAST_WORKING_DIRECTORY && !want_file && has_object_pack(oid)) + if (!FAST_WORKING_DIRECTORY && !want_file && + has_object_pack(istate->repo, oid)) return 0; /* diff --git a/list-objects.c b/list-objects.c index 985d008799..31236a8dc9 100644 --- a/list-objects.c +++ b/list-objects.c @@ -41,7 +41,8 @@ static void show_object(struct traversal_context *ctx, { if (!ctx->show_object) return; - if (ctx->revs->unpacked && has_object_pack(&object->oid)) + if (ctx->revs->unpacked && has_object_pack(ctx->revs->repo, + &object->oid)) return; ctx->show_object(object, name, ctx->show_data); diff --git a/pack-bitmap.c b/pack-bitmap.c index 4fa9dfc771..d34ba9909a 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -1889,7 +1889,7 @@ static void filter_packed_objects_from_bitmap(struct bitmap_index *bitmap_git, bitmap_unset(result, i); for (i = 0; i < eindex->count; ++i) { - if (has_object_pack(&eindex->objects[i]->oid)) + if (has_object_pack(the_repository, &eindex->objects[i]->oid)) bitmap_unset(result, objects_nr + i); } } diff --git a/packfile.c b/packfile.c index 1015dac6db..e7dd270217 100644 --- a/packfile.c +++ b/packfile.c @@ -2143,16 +2143,17 @@ int find_kept_pack_entry(struct repository *r, return 0; } -int has_object_pack(const struct object_id *oid) +int has_object_pack(struct repository *r, const struct object_id *oid) { struct pack_entry e; - return find_pack_entry(the_repository, oid, &e); + return find_pack_entry(r, oid, &e); } -int has_object_kept_pack(const struct object_id *oid, unsigned flags) +int has_object_kept_pack(struct repository *r, const struct object_id *oid, + unsigned flags) { struct pack_entry e; - return find_kept_pack_entry(the_repository, oid, flags, &e); + return find_kept_pack_entry(r, oid, flags, &e); } int for_each_object_in_pack(struct packed_git *p, diff --git a/packfile.h b/packfile.h index 51187f2393..b09fb2c530 100644 --- a/packfile.h +++ b/packfile.h @@ -193,8 +193,9 @@ const struct packed_git *has_packed_and_bad(struct repository *, const struct ob int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e); int find_kept_pack_entry(struct repository *r, const struct object_id *oid, unsigned flags, struct pack_entry *e); -int has_object_pack(const struct object_id *oid); -int has_object_kept_pack(const struct object_id *oid, unsigned flags); +int has_object_pack(struct repository *r, const struct object_id *oid); +int has_object_kept_pack(struct repository *r, const struct object_id *oid, + unsigned flags); /* * Return 1 if an object in a promisor packfile is or refers to the given diff --git a/prune-packed.c b/prune-packed.c index 2bb99c29df..d1c65ab10e 100644 --- a/prune-packed.c +++ b/prune-packed.c @@ -24,7 +24,7 @@ static int prune_object(const struct object_id *oid, const char *path, { int *opts = data; - if (!has_object_pack(oid)) + if (!has_object_pack(the_repository, oid)) return 0; if (*opts & PRUNE_PACKED_DRY_RUN) diff --git a/reachable.c b/reachable.c index 3e9b3dd0a4..09d2c50079 100644 --- a/reachable.c +++ b/reachable.c @@ -239,7 +239,7 @@ static int want_recent_object(struct recent_data *data, const struct object_id *oid) { if (data->ignore_in_core_kept_packs && - has_object_kept_pack(oid, IN_CORE_KEEP_PACKS)) + has_object_kept_pack(data->revs->repo, oid, IN_CORE_KEEP_PACKS)) return 0; return 1; } diff --git a/revision.c b/revision.c index f5f5b84f2b..d1d152a67b 100644 --- a/revision.c +++ b/revision.c @@ -4103,10 +4103,10 @@ enum commit_action get_commit_action(struct rev_info *revs, struct commit *commi { if (commit->object.flags & SHOWN) return commit_ignore; - if (revs->unpacked && has_object_pack(&commit->object.oid)) + if (revs->unpacked && has_object_pack(revs->repo, &commit->object.oid)) return commit_ignore; if (revs->no_kept_objects) { - if (has_object_kept_pack(&commit->object.oid, + if (has_object_kept_pack(revs->repo, &commit->object.oid, revs->keep_pack_cache_flags)) return commit_ignore; } From c87910b96b1223d4a1dfe65c04e03863fadef6bc Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:44:00 +0100 Subject: [PATCH 06/18] packfile: pass down repository to `for_each_packed_object` The function `for_each_packed_object` currently relies on the global variable `the_repository`. To eliminate global variable usage in `packfile.c`, we should progressively shift the dependency on the_repository to higher layers. Let's remove its usage from this function and closely related function `is_promisor_object`. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 7 ++++--- builtin/fsck.c | 18 +++++++++++------- builtin/pack-objects.c | 7 +++++-- builtin/repack.c | 2 +- builtin/rev-list.c | 2 +- commit-graph.c | 2 +- fsck.c | 2 +- list-objects.c | 4 ++-- object-store-ll.h | 4 ++-- packfile.c | 14 +++++++------- packfile.h | 2 +- promisor-remote.c | 2 +- reachable.c | 2 +- revision.c | 9 +++++---- tag.c | 2 +- 15 files changed, 44 insertions(+), 35 deletions(-) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index bfdfb51c7c..d67b101c20 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -827,15 +827,16 @@ static int batch_objects(struct batch_options *opt) cb.seen = &seen; for_each_loose_object(batch_unordered_loose, &cb, 0); - for_each_packed_object(batch_unordered_packed, &cb, - FOR_EACH_OBJECT_PACK_ORDER); + for_each_packed_object(the_repository, batch_unordered_packed, + &cb, FOR_EACH_OBJECT_PACK_ORDER); oidset_clear(&seen); } else { struct oid_array sa = OID_ARRAY_INIT; for_each_loose_object(collect_loose_object, &sa, 0); - for_each_packed_object(collect_packed_object, &sa, 0); + for_each_packed_object(the_repository, collect_packed_object, + &sa, 0); oid_array_for_each_unique(&sa, batch_object_cb, &cb); diff --git a/builtin/fsck.c b/builtin/fsck.c index bb56eb98ac..0196c54eb6 100644 --- a/builtin/fsck.c +++ b/builtin/fsck.c @@ -150,7 +150,7 @@ static int mark_object(struct object *obj, enum object_type type, return 0; obj->flags |= REACHABLE; - if (is_promisor_object(&obj->oid)) + if (is_promisor_object(the_repository, &obj->oid)) /* * Further recursion does not need to be performed on this * object since it is a promisor object (so it does not need to @@ -270,7 +270,7 @@ static void check_reachable_object(struct object *obj) * do a full fsck */ if (!(obj->flags & HAS_OBJ)) { - if (is_promisor_object(&obj->oid)) + if (is_promisor_object(the_repository, &obj->oid)) return; if (has_object_pack(the_repository, &obj->oid)) return; /* it is in pack - forget about it */ @@ -391,7 +391,10 @@ static void check_connectivity(void) * traversal. */ for_each_loose_object(mark_loose_unreachable_referents, NULL, 0); - for_each_packed_object(mark_packed_unreachable_referents, NULL, 0); + for_each_packed_object(the_repository, + mark_packed_unreachable_referents, + NULL, + 0); } /* Look up all the requirements, warn about missing objects.. */ @@ -488,7 +491,7 @@ static void fsck_handle_reflog_oid(const char *refname, struct object_id *oid, refname, timestamp); obj->flags |= USED; mark_object_reachable(obj); - } else if (!is_promisor_object(oid)) { + } else if (!is_promisor_object(the_repository, oid)) { error(_("%s: invalid reflog entry %s"), refname, oid_to_hex(oid)); errors_found |= ERROR_REACHABLE; @@ -531,7 +534,7 @@ static int fsck_handle_ref(const char *refname, const char *referent UNUSED, con obj = parse_object(the_repository, oid); if (!obj) { - if (is_promisor_object(oid)) { + if (is_promisor_object(the_repository, oid)) { /* * Increment default_refs anyway, because this is a * valid ref. @@ -966,7 +969,8 @@ int cmd_fsck(int argc, if (connectivity_only) { for_each_loose_object(mark_loose_for_connectivity, NULL, 0); - for_each_packed_object(mark_packed_for_connectivity, NULL, 0); + for_each_packed_object(the_repository, + mark_packed_for_connectivity, NULL, 0); } else { prepare_alt_odb(the_repository); for (odb = the_repository->objects->odb; odb; odb = odb->next) @@ -1011,7 +1015,7 @@ int cmd_fsck(int argc, &oid); if (!obj || !(obj->flags & HAS_OBJ)) { - if (is_promisor_object(&oid)) + if (is_promisor_object(the_repository, &oid)) continue; error(_("%s: object missing"), oid_to_hex(&oid)); errors_found |= ERROR_OBJECT; diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index 0f32e92a3a..db20f0cf51 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -3858,7 +3858,8 @@ static void show_object__ma_allow_promisor(struct object *obj, const char *name, * Quietly ignore EXPECTED missing objects. This avoids problems with * staging them now and getting an odd error later. */ - if (!has_object(the_repository, &obj->oid, 0) && is_promisor_object(&obj->oid)) + if (!has_object(the_repository, &obj->oid, 0) && + is_promisor_object(to_pack.repo, &obj->oid)) return; show_object(obj, name, data); @@ -3927,7 +3928,9 @@ static int add_object_in_unpacked_pack(const struct object_id *oid, static void add_objects_in_unpacked_packs(void) { - if (for_each_packed_object(add_object_in_unpacked_pack, NULL, + if (for_each_packed_object(to_pack.repo, + add_object_in_unpacked_pack, + NULL, FOR_EACH_OBJECT_PACK_ORDER | FOR_EACH_OBJECT_LOCAL_ONLY | FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS | diff --git a/builtin/repack.c b/builtin/repack.c index d6bb37e84a..96a4fa234b 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -404,7 +404,7 @@ static void repack_promisor_objects(const struct pack_objects_args *args, * {type -> existing pack order} ordering when computing deltas instead * of a {type -> size} ordering, which may produce better deltas. */ - for_each_packed_object(write_oid, &cmd, + for_each_packed_object(the_repository, write_oid, &cmd, FOR_EACH_OBJECT_PROMISOR_ONLY); if (cmd.in == -1) { diff --git a/builtin/rev-list.c b/builtin/rev-list.c index f62bcbf2b1..43c42621e3 100644 --- a/builtin/rev-list.c +++ b/builtin/rev-list.c @@ -121,7 +121,7 @@ static inline void finish_object__ma(struct object *obj) return; case MA_ALLOW_PROMISOR: - if (is_promisor_object(&obj->oid)) + if (is_promisor_object(the_repository, &obj->oid)) return; die("unexpected missing %s object '%s'", type_name(obj->type), oid_to_hex(&obj->oid)); diff --git a/commit-graph.c b/commit-graph.c index 83dd69bfeb..e2e2083951 100644 --- a/commit-graph.c +++ b/commit-graph.c @@ -1960,7 +1960,7 @@ static void fill_oids_from_all_packs(struct write_commit_graph_context *ctx) ctx->progress = start_delayed_progress( _("Finding commits for commit graph among packed objects"), ctx->approx_nr_objects); - for_each_packed_object(add_packed_commits, ctx, + for_each_packed_object(ctx->r, add_packed_commits, ctx, FOR_EACH_OBJECT_PACK_ORDER); if (ctx->progress_done < ctx->approx_nr_objects) display_progress(ctx->progress, ctx->approx_nr_objects); diff --git a/fsck.c b/fsck.c index 3756f52459..87ce999a49 100644 --- a/fsck.c +++ b/fsck.c @@ -1295,7 +1295,7 @@ static int fsck_blobs(struct oidset *blobs_found, struct oidset *blobs_done, buf = repo_read_object_file(the_repository, oid, &type, &size); if (!buf) { - if (is_promisor_object(oid)) + if (is_promisor_object(the_repository, oid)) continue; ret |= report(options, oid, OBJ_BLOB, msg_missing, diff --git a/list-objects.c b/list-objects.c index 31236a8dc9..d11a389b3a 100644 --- a/list-objects.c +++ b/list-objects.c @@ -75,7 +75,7 @@ static void process_blob(struct traversal_context *ctx, */ if (ctx->revs->exclude_promisor_objects && !repo_has_object_file(the_repository, &obj->oid) && - is_promisor_object(&obj->oid)) + is_promisor_object(ctx->revs->repo, &obj->oid)) return; pathlen = path->len; @@ -180,7 +180,7 @@ static void process_tree(struct traversal_context *ctx, * an incomplete list of missing objects. */ if (revs->exclude_promisor_objects && - is_promisor_object(&obj->oid)) + is_promisor_object(revs->repo, &obj->oid)) return; if (!revs->do_not_die_on_missing_objects) diff --git a/object-store-ll.h b/object-store-ll.h index d46cd0e654..cd3bd5bd99 100644 --- a/object-store-ll.h +++ b/object-store-ll.h @@ -550,7 +550,7 @@ typedef int each_packed_object_fn(const struct object_id *oid, int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn, void *data, enum for_each_object_flags flags); -int for_each_packed_object(each_packed_object_fn, void *, - enum for_each_object_flags flags); +int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, + void *data, enum for_each_object_flags flags); #endif /* OBJECT_STORE_LL_H */ diff --git a/packfile.c b/packfile.c index e7dd270217..5e8019b1fe 100644 --- a/packfile.c +++ b/packfile.c @@ -2200,15 +2200,15 @@ int for_each_object_in_pack(struct packed_git *p, return r; } -int for_each_packed_object(each_packed_object_fn cb, void *data, - enum for_each_object_flags flags) +int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, + void *data, enum for_each_object_flags flags) { struct packed_git *p; int r = 0; int pack_errors = 0; - prepare_packed_git(the_repository); - for (p = get_all_packs(the_repository); p; p = p->next) { + prepare_packed_git(repo); + for (p = get_all_packs(repo); p; p = p->next) { if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) continue; if ((flags & FOR_EACH_OBJECT_PROMISOR_ONLY) && @@ -2286,14 +2286,14 @@ static int add_promisor_object(const struct object_id *oid, return 0; } -int is_promisor_object(const struct object_id *oid) +int is_promisor_object(struct repository *r, const struct object_id *oid) { static struct oidset promisor_objects; static int promisor_objects_prepared; if (!promisor_objects_prepared) { - if (repo_has_promisor_remote(the_repository)) { - for_each_packed_object(add_promisor_object, + if (repo_has_promisor_remote(r)) { + for_each_packed_object(r, add_promisor_object, &promisor_objects, FOR_EACH_OBJECT_PROMISOR_ONLY | FOR_EACH_OBJECT_PACK_ORDER); diff --git a/packfile.h b/packfile.h index b09fb2c530..addb95b0c4 100644 --- a/packfile.h +++ b/packfile.h @@ -201,7 +201,7 @@ int has_object_kept_pack(struct repository *r, const struct object_id *oid, * Return 1 if an object in a promisor packfile is or refers to the given * object, 0 otherwise. */ -int is_promisor_object(const struct object_id *oid); +int is_promisor_object(struct repository *r, const struct object_id *oid); /* * Expose a function for fuzz testing. diff --git a/promisor-remote.c b/promisor-remote.c index 9345ae3db2..c714f4f007 100644 --- a/promisor-remote.c +++ b/promisor-remote.c @@ -283,7 +283,7 @@ void promisor_remote_get_direct(struct repository *repo, } for (i = 0; i < remaining_nr; i++) { - if (is_promisor_object(&remaining_oids[i])) + if (is_promisor_object(repo, &remaining_oids[i])) die(_("could not fetch %s from promisor remote"), oid_to_hex(&remaining_oids[i])); } diff --git a/reachable.c b/reachable.c index 09d2c50079..ecf7ccf504 100644 --- a/reachable.c +++ b/reachable.c @@ -324,7 +324,7 @@ int add_unseen_recent_objects_to_traversal(struct rev_info *revs, if (ignore_in_core_kept_packs) flags |= FOR_EACH_OBJECT_SKIP_IN_CORE_KEPT_PACKS; - r = for_each_packed_object(add_recent_packed, &data, flags); + r = for_each_packed_object(revs->repo, add_recent_packed, &data, flags); done: oidset_clear(&data.extra_recent_oids); diff --git a/revision.c b/revision.c index d1d152a67b..45dc6d2819 100644 --- a/revision.c +++ b/revision.c @@ -390,7 +390,8 @@ static struct object *get_reference(struct rev_info *revs, const char *name, if (!object) { if (revs->ignore_missing) return NULL; - if (revs->exclude_promisor_objects && is_promisor_object(oid)) + if (revs->exclude_promisor_objects && + is_promisor_object(revs->repo, oid)) return NULL; if (revs->do_not_die_on_missing_objects) { oidset_insert(&revs->missing_commits, oid); @@ -432,7 +433,7 @@ static struct commit *handle_commit(struct rev_info *revs, if (revs->ignore_missing_links || (flags & UNINTERESTING)) return NULL; if (revs->exclude_promisor_objects && - is_promisor_object(&tag->tagged->oid)) + is_promisor_object(revs->repo, &tag->tagged->oid)) return NULL; if (revs->do_not_die_on_missing_objects && oid) { oidset_insert(&revs->missing_commits, oid); @@ -1211,7 +1212,7 @@ static int process_parents(struct rev_info *revs, struct commit *commit, revs->do_not_die_on_missing_objects; if (repo_parse_commit_gently(revs->repo, p, gently) < 0) { if (revs->exclude_promisor_objects && - is_promisor_object(&p->object.oid)) { + is_promisor_object(revs->repo, &p->object.oid)) { if (revs->first_parent_only) break; continue; @@ -3915,7 +3916,7 @@ int prepare_revision_walk(struct rev_info *revs) revs->treesame.name = "treesame"; if (revs->exclude_promisor_objects) { - for_each_packed_object(mark_uninteresting, revs, + for_each_packed_object(revs->repo, mark_uninteresting, revs, FOR_EACH_OBJECT_PROMISOR_ONLY); } diff --git a/tag.c b/tag.c index d24170e340..beef9571b5 100644 --- a/tag.c +++ b/tag.c @@ -84,7 +84,7 @@ struct object *deref_tag(struct repository *r, struct object *o, const char *war o = NULL; } if (!o && warn) { - if (last_oid && is_promisor_object(last_oid)) + if (last_oid && is_promisor_object(r, last_oid)) return NULL; if (!warnlen) warnlen = strlen(warn); From d6b2d21fbf269db7a6be56d28a62cb65a7d7a660 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:44:01 +0100 Subject: [PATCH 07/18] config: make `delta_base_cache_limit` a non-global variable The `delta_base_cache_limit` variable is a global config variable used by multiple subsystems. Let's make this non-global, by adding this variable independently to the subsystems where it is used. First, add the setting to the `repo_settings` struct, this provides access to the config in places where the repository is available. Use this in `packfile.c`. In `index-pack.c` we add it to the `pack_idx_option` struct and its constructor. While the repository struct is available here, it may not be set because `git index-pack` can be used without a repository. In `gc.c` add it to the `gc_config` struct and also the constructor function. The gc functions currently do not have direct access to a repository struct. These changes are made to remove the usage of `delta_base_cache_limit` as a global variable in `packfile.c`. This brings us one step closer to removing the `USE_THE_REPOSITORY_VARIABLE` definition in `packfile.c` which we complete in the next patch. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/gc.c | 12 +++++++++++- builtin/index-pack.c | 10 +++++++--- config.c | 5 ----- environment.c | 1 - environment.h | 1 - pack-objects.h | 3 ++- pack-write.c | 1 + pack.h | 2 ++ packfile.c | 10 ++++++++-- repo-settings.c | 5 +++++ repo-settings.h | 3 +++ 11 files changed, 39 insertions(+), 14 deletions(-) diff --git a/builtin/gc.c b/builtin/gc.c index d52735354c..efb6162fb0 100644 --- a/builtin/gc.c +++ b/builtin/gc.c @@ -138,6 +138,11 @@ struct gc_config { char *repack_filter_to; unsigned long big_pack_threshold; unsigned long max_delta_cache_size; + /* + * Remove this member from gc_config once repo_settings is passed + * through the callchain. + */ + size_t delta_base_cache_limit; }; #define GC_CONFIG_INIT { \ @@ -153,6 +158,7 @@ struct gc_config { .prune_expire = xstrdup("2.weeks.ago"), \ .prune_worktrees_expire = xstrdup("3.months.ago"), \ .max_delta_cache_size = DEFAULT_DELTA_CACHE_SIZE, \ + .delta_base_cache_limit = DEFAULT_DELTA_BASE_CACHE_LIMIT, \ } static void gc_config_release(struct gc_config *cfg) @@ -168,6 +174,7 @@ static void gc_config(struct gc_config *cfg) { const char *value; char *owned = NULL; + unsigned long ulongval; if (!git_config_get_value("gc.packrefs", &value)) { if (value && !strcmp(value, "notbare")) @@ -206,6 +213,9 @@ static void gc_config(struct gc_config *cfg) git_config_get_ulong("gc.bigpackthreshold", &cfg->big_pack_threshold); git_config_get_ulong("pack.deltacachesize", &cfg->max_delta_cache_size); + if (!git_config_get_ulong("core.deltabasecachelimit", &ulongval)) + cfg->delta_base_cache_limit = ulongval; + if (!git_config_get_string("gc.repackfilter", &owned)) { free(cfg->repack_filter); cfg->repack_filter = owned; @@ -416,7 +426,7 @@ static uint64_t estimate_repack_memory(struct gc_config *cfg, * read_sha1_file() (either at delta calculation phase, or * writing phase) also fills up the delta base cache */ - heap += delta_base_cache_limit; + heap += cfg->delta_base_cache_limit; /* and of course pack-objects has its own delta cache */ heap += cfg->max_delta_cache_size; diff --git a/builtin/index-pack.c b/builtin/index-pack.c index eaefb41761..23bfa45403 100644 --- a/builtin/index-pack.c +++ b/builtin/index-pack.c @@ -1238,7 +1238,7 @@ static void parse_pack_objects(unsigned char *hash) * recursively checking if the resulting object is used as a base * for some more deltas. */ -static void resolve_deltas(void) +static void resolve_deltas(struct pack_idx_option *opts) { int i; @@ -1254,7 +1254,7 @@ static void resolve_deltas(void) nr_ref_deltas + nr_ofs_deltas); nr_dispatched = 0; - base_cache_limit = delta_base_cache_limit * nr_threads; + base_cache_limit = opts->delta_base_cache_limit * nr_threads; if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) { init_thread(); work_lock(); @@ -1604,6 +1604,10 @@ static int git_index_pack_config(const char *k, const char *v, else opts->flags &= ~WRITE_REV; } + if (!strcmp(k, "core.deltabasecachelimit")) { + opts->delta_base_cache_limit = git_config_ulong(k, v, ctx->kvi); + return 0; + } return git_default_config(k, v, ctx, cb); } @@ -1930,7 +1934,7 @@ int cmd_index_pack(int argc, parse_pack_objects(pack_hash); if (report_end_of_input) write_in_full(2, "\0", 1); - resolve_deltas(); + resolve_deltas(&opts); conclude_pack(fix_thin_pack, curr_pack, pack_hash); free(ofs_deltas); free(ref_deltas); diff --git a/config.c b/config.c index a11bb85da3..728ef98e42 100644 --- a/config.c +++ b/config.c @@ -1515,11 +1515,6 @@ static int git_default_core_config(const char *var, const char *value, return 0; } - if (!strcmp(var, "core.deltabasecachelimit")) { - delta_base_cache_limit = git_config_ulong(var, value, ctx->kvi); - return 0; - } - if (!strcmp(var, "core.autocrlf")) { if (value && !strcasecmp(value, "input")) { auto_crlf = AUTO_CRLF_INPUT; diff --git a/environment.c b/environment.c index a2ce998081..8e5022c282 100644 --- a/environment.c +++ b/environment.c @@ -51,7 +51,6 @@ enum fsync_method fsync_method = FSYNC_METHOD_DEFAULT; enum fsync_component fsync_components = FSYNC_COMPONENTS_DEFAULT; size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE; size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT; -size_t delta_base_cache_limit = 96 * 1024 * 1024; unsigned long big_file_threshold = 512 * 1024 * 1024; char *editor_program; char *askpass_program; diff --git a/environment.h b/environment.h index 923e12661e..2f43340f0b 100644 --- a/environment.h +++ b/environment.h @@ -165,7 +165,6 @@ extern int zlib_compression_level; extern int pack_compression_level; extern size_t packed_git_window_size; extern size_t packed_git_limit; -extern size_t delta_base_cache_limit; extern unsigned long big_file_threshold; extern unsigned long pack_size_limit_cfg; extern int max_allowed_tree_depth; diff --git a/pack-objects.h b/pack-objects.h index b9898a4e64..3f6f504203 100644 --- a/pack-objects.h +++ b/pack-objects.h @@ -7,7 +7,8 @@ struct repository; -#define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024) +#define DEFAULT_DELTA_CACHE_SIZE (256 * 1024 * 1024) +#define DEFAULT_DELTA_BASE_CACHE_LIMIT (96 * 1024 * 1024) #define OE_DFS_STATE_BITS 2 #define OE_DEPTH_BITS 12 diff --git a/pack-write.c b/pack-write.c index 8c7dfddc5a..98a8c0e785 100644 --- a/pack-write.c +++ b/pack-write.c @@ -21,6 +21,7 @@ void reset_pack_idx_option(struct pack_idx_option *opts) memset(opts, 0, sizeof(*opts)); opts->version = 2; opts->off32_limit = 0x7fffffff; + opts->delta_base_cache_limit = DEFAULT_DELTA_BASE_CACHE_LIMIT; } static int sha1_compare(const void *_a, const void *_b) diff --git a/pack.h b/pack.h index 02bbdfb19c..a8da040629 100644 --- a/pack.h +++ b/pack.h @@ -58,6 +58,8 @@ struct pack_idx_option { */ int anomaly_alloc, anomaly_nr; uint32_t *anomaly; + + size_t delta_base_cache_limit; }; void reset_pack_idx_option(struct pack_idx_option *); diff --git a/packfile.c b/packfile.c index 5e8019b1fe..64248ca664 100644 --- a/packfile.c +++ b/packfile.c @@ -1496,7 +1496,9 @@ void clear_delta_base_cache(void) } static void add_delta_base_cache(struct packed_git *p, off_t base_offset, - void *base, unsigned long base_size, enum object_type type) + void *base, unsigned long base_size, + unsigned long delta_base_cache_limit, + enum object_type type) { struct delta_base_cache_entry *ent; struct list_head *lru, *tmp; @@ -1698,6 +1700,8 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset, int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC; int base_from_cache = 0; + prepare_repo_settings(p->repo); + write_pack_access_log(p, obj_offset); /* PHASE 1: drill down to the innermost base object */ @@ -1878,7 +1882,9 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset, * before we are done using it. */ if (!external_base) - add_delta_base_cache(p, base_obj_offset, base, base_size, type); + add_delta_base_cache(p, base_obj_offset, base, base_size, + p->repo->settings.delta_base_cache_limit, + type); free(delta_data); free(external_base); diff --git a/repo-settings.c b/repo-settings.c index 4699b4b365..acc27eb8fe 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -3,6 +3,7 @@ #include "repo-settings.h" #include "repository.h" #include "midx.h" +#include "pack-objects.h" static void repo_cfg_bool(struct repository *r, const char *key, int *dest, int def) @@ -26,6 +27,7 @@ void prepare_repo_settings(struct repository *r) const char *strval; int manyfiles; int read_changed_paths; + unsigned long ulongval; if (!r->gitdir) BUG("Cannot add settings for uninitialized repository"); @@ -123,6 +125,9 @@ void prepare_repo_settings(struct repository *r) * removed. */ r->settings.command_requires_full_index = 1; + + if (!repo_config_get_ulong(r, "core.deltabasecachelimit", &ulongval)) + r->settings.delta_base_cache_limit = ulongval; } enum log_refs_config repo_settings_get_log_all_ref_updates(struct repository *repo) diff --git a/repo-settings.h b/repo-settings.h index 51d6156a11..10a6f7ed64 100644 --- a/repo-settings.h +++ b/repo-settings.h @@ -57,12 +57,15 @@ struct repo_settings { int core_multi_pack_index; int warn_ambiguous_refs; /* lazily loaded via accessor */ + + size_t delta_base_cache_limit; }; #define REPO_SETTINGS_INIT { \ .index_version = -1, \ .core_untracked_cache = UNTRACKED_CACHE_KEEP, \ .fetch_negotiation_algorithm = FETCH_NEGOTIATION_CONSECUTIVE, \ .warn_ambiguous_refs = -1, \ + .delta_base_cache_limit = DEFAULT_DELTA_BASE_CACHE_LIMIT, \ } void prepare_repo_settings(struct repository *r); From d284713bae71877577cf1a07501c8528f8c44bb2 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:44:02 +0100 Subject: [PATCH 08/18] config: make `packed_git_(limit|window_size)` non-global variables The variables `packed_git_window_size` and `packed_git_limit` are global config variables used in the `packfile.c` file. Since it is only used in this file, let's change it from being a global config variable to a local variable for the subsystem. With this, we rid `packfile.c` from all global variable usage and this means we can also remove the `USE_THE_REPOSITORY_VARIABLE` guard from the file. Helped-by: Taylor Blau Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/fast-import.c | 4 ++-- config.c | 17 ----------------- environment.c | 2 -- packfile.c | 23 +++++++++++++++-------- packfile.h | 2 +- repo-settings.c | 13 +++++++++++++ repo-settings.h | 4 ++++ 7 files changed, 35 insertions(+), 30 deletions(-) diff --git a/builtin/fast-import.c b/builtin/fast-import.c index 3ccc4c5722..0ece070260 100644 --- a/builtin/fast-import.c +++ b/builtin/fast-import.c @@ -3539,7 +3539,7 @@ static void parse_argv(void) int cmd_fast_import(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { unsigned int i; @@ -3660,7 +3660,7 @@ int cmd_fast_import(int argc, fprintf(stderr, " pools: %10lu KiB\n", (unsigned long)((tree_entry_allocd + fi_mem_pool.pool_alloc) /1024)); fprintf(stderr, " objects: %10" PRIuMAX " KiB\n", (alloc_count*sizeof(struct object_entry))/1024); fprintf(stderr, "---------------------------------------------------------------------\n"); - pack_report(); + pack_report(repo); fprintf(stderr, "---------------------------------------------------------------------\n"); fprintf(stderr, "\n"); } diff --git a/config.c b/config.c index 728ef98e42..2c295f7430 100644 --- a/config.c +++ b/config.c @@ -1493,28 +1493,11 @@ static int git_default_core_config(const char *var, const char *value, return 0; } - if (!strcmp(var, "core.packedgitwindowsize")) { - int pgsz_x2 = getpagesize() * 2; - packed_git_window_size = git_config_ulong(var, value, ctx->kvi); - - /* This value must be multiple of (pagesize * 2) */ - packed_git_window_size /= pgsz_x2; - if (packed_git_window_size < 1) - packed_git_window_size = 1; - packed_git_window_size *= pgsz_x2; - return 0; - } - if (!strcmp(var, "core.bigfilethreshold")) { big_file_threshold = git_config_ulong(var, value, ctx->kvi); return 0; } - if (!strcmp(var, "core.packedgitlimit")) { - packed_git_limit = git_config_ulong(var, value, ctx->kvi); - return 0; - } - if (!strcmp(var, "core.autocrlf")) { if (value && !strcasecmp(value, "input")) { auto_crlf = AUTO_CRLF_INPUT; diff --git a/environment.c b/environment.c index 8e5022c282..8389a27270 100644 --- a/environment.c +++ b/environment.c @@ -49,8 +49,6 @@ int fsync_object_files = -1; int use_fsync = -1; enum fsync_method fsync_method = FSYNC_METHOD_DEFAULT; enum fsync_component fsync_components = FSYNC_COMPONENTS_DEFAULT; -size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE; -size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT; unsigned long big_file_threshold = 512 * 1024 * 1024; char *editor_program; char *askpass_program; diff --git a/packfile.c b/packfile.c index 64248ca664..2e0e28c7de 100644 --- a/packfile.c +++ b/packfile.c @@ -1,4 +1,3 @@ -#define USE_THE_REPOSITORY_VARIABLE #include "git-compat-util.h" #include "environment.h" @@ -46,15 +45,15 @@ static size_t pack_mapped; #define SZ_FMT PRIuMAX static inline uintmax_t sz_fmt(size_t s) { return s; } -void pack_report(void) +void pack_report(struct repository *repo) { fprintf(stderr, "pack_report: getpagesize() = %10" SZ_FMT "\n" "pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n" "pack_report: core.packedGitLimit = %10" SZ_FMT "\n", sz_fmt(getpagesize()), - sz_fmt(packed_git_window_size), - sz_fmt(packed_git_limit)); + sz_fmt(repo->settings.packed_git_window_size), + sz_fmt(repo->settings.packed_git_limit)); fprintf(stderr, "pack_report: pack_used_ctr = %10u\n" "pack_report: pack_mmap_calls = %10u\n" @@ -650,8 +649,15 @@ unsigned char *use_pack(struct packed_git *p, break; } if (!win) { - size_t window_align = packed_git_window_size / 2; + size_t window_align; off_t len; + struct repo_settings *settings; + + /* lazy load the settings in case it hasn't been setup */ + prepare_repo_settings(p->repo); + settings = &p->repo->settings; + + window_align = settings->packed_git_window_size / 2; if (p->pack_fd == -1 && open_packed_git(p)) die("packfile %s cannot be accessed", p->pack_name); @@ -659,11 +665,12 @@ unsigned char *use_pack(struct packed_git *p, CALLOC_ARRAY(win, 1); win->offset = (offset / window_align) * window_align; len = p->pack_size - win->offset; - if (len > packed_git_window_size) - len = packed_git_window_size; + if (len > settings->packed_git_window_size) + len = settings->packed_git_window_size; win->len = (size_t)len; pack_mapped += win->len; - while (packed_git_limit < pack_mapped + + while (settings->packed_git_limit < pack_mapped && unuse_one_window(p)) ; /* nothing */ win->base = xmmap_gently(NULL, win->len, diff --git a/packfile.h b/packfile.h index addb95b0c4..58104fa009 100644 --- a/packfile.h +++ b/packfile.h @@ -89,7 +89,7 @@ unsigned long repo_approximate_object_count(struct repository *r); struct packed_git *find_oid_pack(const struct object_id *oid, struct packed_git *packs); -void pack_report(void); +void pack_report(struct repository *repo); /* * mmap the index file for the specified packfile (if it is not diff --git a/repo-settings.c b/repo-settings.c index acc27eb8fe..9d16d5399e 100644 --- a/repo-settings.c +++ b/repo-settings.c @@ -128,6 +128,19 @@ void prepare_repo_settings(struct repository *r) if (!repo_config_get_ulong(r, "core.deltabasecachelimit", &ulongval)) r->settings.delta_base_cache_limit = ulongval; + + if (!repo_config_get_ulong(r, "core.packedgitwindowsize", &ulongval)) { + int pgsz_x2 = getpagesize() * 2; + + /* This value must be multiple of (pagesize * 2) */ + ulongval /= pgsz_x2; + if (ulongval < 1) + ulongval = 1; + r->settings.packed_git_window_size = ulongval * pgsz_x2; + } + + if (!repo_config_get_ulong(r, "core.packedgitlimit", &ulongval)) + r->settings.packed_git_limit = ulongval; } enum log_refs_config repo_settings_get_log_all_ref_updates(struct repository *repo) diff --git a/repo-settings.h b/repo-settings.h index 10a6f7ed64..93ea0c3274 100644 --- a/repo-settings.h +++ b/repo-settings.h @@ -59,6 +59,8 @@ struct repo_settings { int warn_ambiguous_refs; /* lazily loaded via accessor */ size_t delta_base_cache_limit; + size_t packed_git_window_size; + size_t packed_git_limit; }; #define REPO_SETTINGS_INIT { \ .index_version = -1, \ @@ -66,6 +68,8 @@ struct repo_settings { .fetch_negotiation_algorithm = FETCH_NEGOTIATION_CONSECUTIVE, \ .warn_ambiguous_refs = -1, \ .delta_base_cache_limit = DEFAULT_DELTA_BASE_CACHE_LIMIT, \ + .packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE, \ + .packed_git_limit = DEFAULT_PACKED_GIT_LIMIT, \ } void prepare_repo_settings(struct repository *r); From e106040722c746346c3c40d3790789d9e196f60d Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Tue, 3 Dec 2024 15:44:03 +0100 Subject: [PATCH 09/18] midx: add repository to `multi_pack_index` struct The `multi_pack_index` struct represents the MIDX for a repository. Here, we add a pointer to the repository in this struct, allowing direct use of the repository variable without relying on the global `the_repository` struct. With this addition, we can determine the repository associated with a `bitmap_index` struct. A `bitmap_index` points to either a `packed_git` or a `multi_pack_index`, both of which have direct repository references. To support this, we introduce a static helper function, `bitmap_repo`, in `pack-bitmap.c`, which retrieves a repository given a `bitmap_index`. With this, we clear up all usages of `the_repository` within `pack-bitmap.c` and also remove the `USE_THE_REPOSITORY_VARIABLE` definition. Bringing us another step closer to remove all global variable usage. Although this change also opens up the potential to clean up `midx.c`, doing so would require additional refactoring to pass the repository struct to functions where the MIDX struct is created: a task better suited for future patches. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 1 + midx.h | 3 ++ pack-bitmap.c | 90 +++++++++++++++++++++++++++++++-------------------- 3 files changed, 59 insertions(+), 35 deletions(-) diff --git a/midx.c b/midx.c index 8edb75f51d..079c45a1aa 100644 --- a/midx.c +++ b/midx.c @@ -131,6 +131,7 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->data = midx_map; m->data_len = midx_size; m->local = local; + m->repo = the_repository; m->signature = get_be32(m->data); if (m->signature != MIDX_SIGNATURE) diff --git a/midx.h b/midx.h index 42d4f8d149..3b0ac4d878 100644 --- a/midx.h +++ b/midx.h @@ -71,6 +71,9 @@ struct multi_pack_index { const char **pack_names; struct packed_git **packs; + + struct repository *repo; + char object_dir[FLEX_ARRAY]; }; diff --git a/pack-bitmap.c b/pack-bitmap.c index d34ba9909a..0cb1b56c9d 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -1,5 +1,3 @@ -#define USE_THE_REPOSITORY_VARIABLE - #include "git-compat-util.h" #include "commit.h" #include "gettext.h" @@ -177,12 +175,21 @@ static uint32_t bitmap_num_objects(struct bitmap_index *index) return index->pack->num_objects; } +static struct repository *bitmap_repo(struct bitmap_index *bitmap_git) +{ + if (bitmap_is_midx(bitmap_git)) + return bitmap_git->midx->repo; + return bitmap_git->pack->repo; +} + static int load_bitmap_header(struct bitmap_index *index) { struct bitmap_disk_header *header = (void *)index->map; - size_t header_size = sizeof(*header) - GIT_MAX_RAWSZ + the_hash_algo->rawsz; + const struct git_hash_algo *hash_algo = bitmap_repo(index)->hash_algo; - if (index->map_size < header_size + the_hash_algo->rawsz) + size_t header_size = sizeof(*header) - GIT_MAX_RAWSZ + hash_algo->rawsz; + + if (index->map_size < header_size + hash_algo->rawsz) return error(_("corrupted bitmap index (too small)")); if (memcmp(header->magic, BITMAP_IDX_SIGNATURE, sizeof(BITMAP_IDX_SIGNATURE)) != 0) @@ -196,7 +203,7 @@ static int load_bitmap_header(struct bitmap_index *index) { uint32_t flags = ntohs(header->options); size_t cache_size = st_mult(bitmap_num_objects(index), sizeof(uint32_t)); - unsigned char *index_end = index->map + index->map_size - the_hash_algo->rawsz; + unsigned char *index_end = index->map + index->map_size - hash_algo->rawsz; if ((flags & BITMAP_OPT_FULL_DAG) == 0) BUG("unsupported options for bitmap index file " @@ -409,7 +416,7 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, if (bitmap_git->pack || bitmap_git->midx) { struct strbuf buf = STRBUF_INIT; get_midx_filename(&buf, midx->object_dir); - trace2_data_string("bitmap", the_repository, + trace2_data_string("bitmap", bitmap_repo(bitmap_git), "ignoring extra midx bitmap file", buf.buf); close(fd); strbuf_release(&buf); @@ -427,7 +434,7 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, goto cleanup; if (!hasheq(get_midx_checksum(bitmap_git->midx), bitmap_git->checksum, - the_repository->hash_algo)) { + bitmap_repo(bitmap_git)->hash_algo)) { error(_("checksum doesn't match in MIDX and bitmap")); goto cleanup; } @@ -438,7 +445,9 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, } for (i = 0; i < bitmap_git->midx->num_packs; i++) { - if (prepare_midx_pack(the_repository, bitmap_git->midx, i)) { + if (prepare_midx_pack(bitmap_repo(bitmap_git), + bitmap_git->midx, + i)) { warning(_("could not open pack %s"), bitmap_git->midx->pack_names[i]); goto cleanup; @@ -492,8 +501,9 @@ static int open_pack_bitmap_1(struct bitmap_index *bitmap_git, struct packed_git } if (bitmap_git->pack || bitmap_git->midx) { - trace2_data_string("bitmap", the_repository, - "ignoring extra bitmap file", packfile->pack_name); + trace2_data_string("bitmap", bitmap_repo(bitmap_git), + "ignoring extra bitmap file", + packfile->pack_name); close(fd); return -1; } @@ -518,8 +528,8 @@ static int open_pack_bitmap_1(struct bitmap_index *bitmap_git, struct packed_git return -1; } - trace2_data_string("bitmap", the_repository, "opened bitmap file", - packfile->pack_name); + trace2_data_string("bitmap", bitmap_repo(bitmap_git), + "opened bitmap file", packfile->pack_name); return 0; } @@ -649,7 +659,7 @@ struct bitmap_index *prepare_bitmap_git(struct repository *r) struct bitmap_index *prepare_midx_bitmap_git(struct multi_pack_index *midx) { - struct repository *r = the_repository; + struct repository *r = midx->repo; struct bitmap_index *bitmap_git = xcalloc(1, sizeof(*bitmap_git)); if (!open_midx_bitmap_1(bitmap_git, midx) && !load_bitmap(r, bitmap_git)) @@ -1213,6 +1223,7 @@ static struct bitmap *find_boundary_objects(struct bitmap_index *bitmap_git, { struct bitmap_boundary_cb cb; struct object_list *root; + struct repository *repo; unsigned int i; unsigned int tmp_blobs, tmp_trees, tmp_tags; int any_missing = 0; @@ -1222,6 +1233,8 @@ static struct bitmap *find_boundary_objects(struct bitmap_index *bitmap_git, cb.base = bitmap_new(); object_array_init(&cb.boundary); + repo = bitmap_repo(bitmap_git); + revs->ignore_missing_links = 1; if (bitmap_git->pseudo_merges.nr) { @@ -1280,19 +1293,19 @@ static struct bitmap *find_boundary_objects(struct bitmap_index *bitmap_git, * revision walk to (a) OR in any bitmaps that are UNINTERESTING * between the tips and boundary, and (b) record the boundary. */ - trace2_region_enter("pack-bitmap", "boundary-prepare", the_repository); + trace2_region_enter("pack-bitmap", "boundary-prepare", repo); if (prepare_revision_walk(revs)) die("revision walk setup failed"); - trace2_region_leave("pack-bitmap", "boundary-prepare", the_repository); + trace2_region_leave("pack-bitmap", "boundary-prepare", repo); - trace2_region_enter("pack-bitmap", "boundary-traverse", the_repository); + trace2_region_enter("pack-bitmap", "boundary-traverse", repo); revs->boundary = 1; traverse_commit_list_filtered(revs, show_boundary_commit, show_boundary_object, &cb, NULL); revs->boundary = 0; - trace2_region_leave("pack-bitmap", "boundary-traverse", the_repository); + trace2_region_leave("pack-bitmap", "boundary-traverse", repo); revs->blob_objects = tmp_blobs; revs->tree_objects = tmp_trees; @@ -1304,7 +1317,7 @@ static struct bitmap *find_boundary_objects(struct bitmap_index *bitmap_git, /* * Then add the boundary commit(s) as fill-in traversal tips. */ - trace2_region_enter("pack-bitmap", "boundary-fill-in", the_repository); + trace2_region_enter("pack-bitmap", "boundary-fill-in", repo); for (i = 0; i < cb.boundary.nr; i++) { struct object *obj = cb.boundary.objects[i].item; if (bitmap_walk_contains(bitmap_git, cb.base, &obj->oid)) @@ -1314,7 +1327,7 @@ static struct bitmap *find_boundary_objects(struct bitmap_index *bitmap_git, } if (revs->pending.nr) cb.base = fill_in_bitmap(bitmap_git, revs, cb.base, NULL); - trace2_region_leave("pack-bitmap", "boundary-fill-in", the_repository); + trace2_region_leave("pack-bitmap", "boundary-fill-in", repo); cleanup: object_array_clear(&cb.boundary); @@ -1718,7 +1731,8 @@ static unsigned long get_size_by_pos(struct bitmap_index *bitmap_git, ofs = pack_pos_to_offset(pack, pos); } - if (packed_object_info(the_repository, pack, ofs, &oi) < 0) { + if (packed_object_info(bitmap_repo(bitmap_git), pack, ofs, + &oi) < 0) { struct object_id oid; nth_bitmap_object_oid(bitmap_git, &oid, pack_pos_to_index(pack, pos)); @@ -1727,7 +1741,8 @@ static unsigned long get_size_by_pos(struct bitmap_index *bitmap_git, } else { struct eindex *eindex = &bitmap_git->ext_index; struct object *obj = eindex->objects[pos - bitmap_num_objects(bitmap_git)]; - if (oid_object_info_extended(the_repository, &obj->oid, &oi, 0) < 0) + if (oid_object_info_extended(bitmap_repo(bitmap_git), &obj->oid, + &oi, 0) < 0) die(_("unable to get size of %s"), oid_to_hex(&obj->oid)); } @@ -1889,7 +1904,8 @@ static void filter_packed_objects_from_bitmap(struct bitmap_index *bitmap_git, bitmap_unset(result, i); for (i = 0; i < eindex->count; ++i) { - if (has_object_pack(the_repository, &eindex->objects[i]->oid)) + if (has_object_pack(bitmap_repo(bitmap_git), + &eindex->objects[i]->oid)) bitmap_unset(result, objects_nr + i); } } @@ -1907,6 +1923,7 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs, struct bitmap *haves_bitmap = NULL; struct bitmap_index *bitmap_git; + struct repository *repo; /* * We can't do pathspec limiting with bitmaps, because we don't know @@ -1980,18 +1997,20 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs, if (!use_boundary_traversal) object_array_clear(&revs->pending); + repo = bitmap_repo(bitmap_git); + if (haves) { if (use_boundary_traversal) { - trace2_region_enter("pack-bitmap", "haves/boundary", the_repository); + trace2_region_enter("pack-bitmap", "haves/boundary", repo); haves_bitmap = find_boundary_objects(bitmap_git, revs, haves); - trace2_region_leave("pack-bitmap", "haves/boundary", the_repository); + trace2_region_leave("pack-bitmap", "haves/boundary", repo); } else { - trace2_region_enter("pack-bitmap", "haves/classic", the_repository); + trace2_region_enter("pack-bitmap", "haves/classic", repo); revs->ignore_missing_links = 1; haves_bitmap = find_objects(bitmap_git, revs, haves, NULL); reset_revision_walk(); revs->ignore_missing_links = 0; - trace2_region_leave("pack-bitmap", "haves/classic", the_repository); + trace2_region_leave("pack-bitmap", "haves/classic", repo); } if (!haves_bitmap) @@ -2025,17 +2044,17 @@ struct bitmap_index *prepare_bitmap_walk(struct rev_info *revs, object_list_free(&wants); object_list_free(&haves); - trace2_data_intmax("bitmap", the_repository, "pseudo_merges_satisfied", + trace2_data_intmax("bitmap", repo, "pseudo_merges_satisfied", pseudo_merges_satisfied_nr); - trace2_data_intmax("bitmap", the_repository, "pseudo_merges_cascades", + trace2_data_intmax("bitmap", repo, "pseudo_merges_cascades", pseudo_merges_cascades_nr); - trace2_data_intmax("bitmap", the_repository, "bitmap/hits", + trace2_data_intmax("bitmap", repo, "bitmap/hits", existing_bitmaps_hits_nr); - trace2_data_intmax("bitmap", the_repository, "bitmap/misses", + trace2_data_intmax("bitmap", repo, "bitmap/misses", existing_bitmaps_misses_nr); - trace2_data_intmax("bitmap", the_repository, "bitmap/roots_with_bitmap", + trace2_data_intmax("bitmap", repo, "bitmap/roots_with_bitmap", roots_with_bitmaps_nr); - trace2_data_intmax("bitmap", the_repository, "bitmap/roots_without_bitmap", + trace2_data_intmax("bitmap", repo, "bitmap/roots_without_bitmap", roots_without_bitmaps_nr); return bitmap_git; @@ -2256,7 +2275,7 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git, struct bitmap **reuse_out, int multi_pack_reuse) { - struct repository *r = the_repository; + struct repository *r = bitmap_repo(bitmap_git); struct bitmapped_pack *packs = NULL; struct bitmap *result = bitmap_git->result; struct bitmap *reuse; @@ -2792,7 +2811,7 @@ int rebuild_bitmap(const uint32_t *reposition, uint32_t *create_bitmap_mapping(struct bitmap_index *bitmap_git, struct packing_data *mapping) { - struct repository *r = the_repository; + struct repository *r = bitmap_repo(bitmap_git); uint32_t i, num_objects; uint32_t *reposition; @@ -2948,7 +2967,8 @@ static off_t get_disk_usage_for_extended(struct bitmap_index *bitmap_git) st_add(bitmap_num_objects(bitmap_git), i))) continue; - if (oid_object_info_extended(the_repository, &obj->oid, &oi, 0) < 0) + if (oid_object_info_extended(bitmap_repo(bitmap_git), &obj->oid, + &oi, 0) < 0) die(_("unable to get disk usage of '%s'"), oid_to_hex(&obj->oid)); From 281164995159ed641f5e76f40515baf0b5811943 Mon Sep 17 00:00:00 2001 From: Taylor Blau Date: Tue, 3 Dec 2024 15:44:04 +0100 Subject: [PATCH 10/18] packfile.c: remove unnecessary prepare_packed_git() call In 454ea2e4d7 (treewide: use get_all_packs, 2018-08-20) we converted existing calls to both: - get_packed_git(), as well as - the_repository->objects->packed_git , to instead use the new get_all_packs() function. In the instance that this commit addresses, there was a preceding call to prepare_packed_git(), which dates all the way back to 660c889e46 (sha1_file: add for_each iterators for loose and packed objects, 2014-10-15) when its caller (for_each_packed_object()) was first introduced. This call could have been removed in 454ea2e4d7, since get_all_packs() itself calls prepare_packed_git(). But the translation in 454ea2e4d7 was (to the best of my knowledge) a find-and-replace rather than inspecting each individual caller. Having an extra prepare_packed_git() call here is harmless, since it will notice that we have already set the 'packed_git_initialized' field and the call will be a noop. So we're only talking about a few dozen CPU cycles to set up and tear down the stack frame. But having a lone prepare_packed_git() call immediately before a call to get_all_packs() confused me, so let's remove it as redundant to avoid more confusion in the future. Signed-off-by: Taylor Blau Signed-off-by: Junio C Hamano --- packfile.c | 1 - 1 file changed, 1 deletion(-) diff --git a/packfile.c b/packfile.c index 2e0e28c7de..9c4bd81a8c 100644 --- a/packfile.c +++ b/packfile.c @@ -2220,7 +2220,6 @@ int for_each_packed_object(struct repository *repo, each_packed_object_fn cb, int r = 0; int pack_errors = 0; - prepare_packed_git(repo); for (p = get_all_packs(repo); p; p = p->next) { if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local) continue; From 3687a4b3e1c8edac080480677f35a5d267fee6e1 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:26 +0100 Subject: [PATCH 11/18] midx-write: pass down repository to static functions In 'midx-write.c' there are a lot of static functions which use global variables `the_repository` or `the_hash_algo`. In a follow up commit, the repository variable will be added to `write_midx_context`, which some of the functions can use. But for functions which do not have access to this struct, pass down the required information from non-static functions `write_midx_file` and `write_midx_file_only`. This requires that the function `hash_to_hex` is also replaced with `hash_to_hex_algop` since the former internally accesses the `the_hash_algo` global variable. This ensures that the usage of global variables is limited to these non-static functions, which will be cleaned up in a follow up commit. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 57 ++++++++++++++++++++++++++++------------------------ 1 file changed, 31 insertions(+), 26 deletions(-) diff --git a/midx-write.c b/midx-write.c index c57726ef94..22b5233f51 100644 --- a/midx-write.c +++ b/midx-write.c @@ -35,13 +35,13 @@ extern void clear_incremental_midx_files_ext(const char *object_dir, extern int cmp_idx_or_pack_name(const char *idx_or_pack_name, const char *idx_name); -static size_t write_midx_header(struct hashfile *f, - unsigned char num_chunks, +static size_t write_midx_header(const struct git_hash_algo *hash_algo, + struct hashfile *f, unsigned char num_chunks, uint32_t num_packs) { hashwrite_be32(f, MIDX_SIGNATURE); hashwrite_u8(f, MIDX_VERSION); - hashwrite_u8(f, oid_version(the_hash_algo)); + hashwrite_u8(f, oid_version(hash_algo)); hashwrite_u8(f, num_chunks); hashwrite_u8(f, 0); /* unused */ hashwrite_be32(f, num_packs); @@ -702,7 +702,7 @@ static int add_ref_to_pending(const char *refname, const char *referent UNUSED, return 0; } - if (!peel_iterated_oid(the_repository, oid, &peeled)) + if (!peel_iterated_oid(revs->repo, oid, &peeled)) oid = &peeled; object = parse_object_or_die(oid, refname); @@ -827,7 +827,7 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr return cb.commits; } -static int write_midx_bitmap(const char *midx_name, +static int write_midx_bitmap(struct repository *r, const char *midx_name, const unsigned char *midx_hash, struct packing_data *pdata, struct commit **commits, @@ -840,9 +840,9 @@ static int write_midx_bitmap(const char *midx_name, struct bitmap_writer writer; struct pack_idx_entry **index; char *bitmap_name = xstrfmt("%s-%s.bitmap", midx_name, - hash_to_hex(midx_hash)); + hash_to_hex_algop(midx_hash, r->hash_algo)); - trace2_region_enter("midx", "write_midx_bitmap", the_repository); + trace2_region_enter("midx", "write_midx_bitmap", r); if (flags & MIDX_WRITE_BITMAP_HASH_CACHE) options |= BITMAP_OPT_HASH_CACHE; @@ -859,7 +859,7 @@ static int write_midx_bitmap(const char *midx_name, for (i = 0; i < pdata->nr_objects; i++) index[i] = &pdata->objects[i].idx; - bitmap_writer_init(&writer, the_repository, pdata); + bitmap_writer_init(&writer, r, pdata); bitmap_writer_show_progress(&writer, flags & MIDX_PROGRESS); bitmap_writer_build_type_index(&writer, index); @@ -892,7 +892,7 @@ cleanup: free(bitmap_name); bitmap_writer_free(&writer); - trace2_region_leave("midx", "write_midx_bitmap", the_repository); + trace2_region_leave("midx", "write_midx_bitmap", r); return ret; } @@ -1049,7 +1049,7 @@ static void clear_midx_files(const char *object_dir, strbuf_release(&buf); } -static int write_midx_internal(const char *object_dir, +static int write_midx_internal(struct repository *r, const char *object_dir, struct string_list *packs_to_include, struct string_list *packs_to_drop, const char *preferred_pack_name, @@ -1070,7 +1070,8 @@ static int write_midx_internal(const char *object_dir, const char **keep_hashes = NULL; struct chunkfile *cf; - trace2_region_enter("midx", "write_midx_internal", the_repository); + trace2_region_enter("midx", "write_midx_internal", r); + ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL); if (ctx.incremental && (flags & MIDX_WRITE_BITMAP)) @@ -1087,8 +1088,7 @@ static int write_midx_internal(const char *object_dir, midx_name.buf); if (!packs_to_include || ctx.incremental) { - struct multi_pack_index *m = lookup_multi_pack_index(the_repository, - object_dir); + struct multi_pack_index *m = lookup_multi_pack_index(r, object_dir); if (m && !midx_checksum_valid(m)) { warning(_("ignoring existing multi-pack-index; checksum mismatch")); m = NULL; @@ -1351,7 +1351,7 @@ static int write_midx_internal(const char *object_dir, add_chunk(cf, MIDX_CHUNKID_OIDFANOUT, MIDX_CHUNK_FANOUT_SIZE, write_midx_oid_fanout); add_chunk(cf, MIDX_CHUNKID_OIDLOOKUP, - st_mult(ctx.entries_nr, the_hash_algo->rawsz), + st_mult(ctx.entries_nr, r->hash_algo->rawsz), write_midx_oid_lookup); add_chunk(cf, MIDX_CHUNKID_OBJECTOFFSETS, st_mult(ctx.entries_nr, MIDX_CHUNK_OFFSET_WIDTH), @@ -1373,7 +1373,8 @@ static int write_midx_internal(const char *object_dir, write_midx_bitmapped_packs); } - write_midx_header(f, get_num_chunks(cf), ctx.nr - dropped_packs); + write_midx_header(r->hash_algo, f, get_num_chunks(cf), + ctx.nr - dropped_packs); write_chunkfile(cf, &ctx); finalize_hashfile(f, midx_hash, FSYNC_COMPONENT_PACK_METADATA, @@ -1405,7 +1406,7 @@ static int write_midx_internal(const char *object_dir, FREE_AND_NULL(ctx.entries); ctx.entries_nr = 0; - if (write_midx_bitmap(midx_name.buf, midx_hash, &pdata, + if (write_midx_bitmap(r, midx_name.buf, midx_hash, &pdata, commits, commits_nr, ctx.pack_order, flags) < 0) { error(_("could not write multi-pack bitmap")); @@ -1449,12 +1450,13 @@ static int write_midx_internal(const char *object_dir, strbuf_release(&final_midx_name); keep_hashes[ctx.num_multi_pack_indexes_before] = - xstrdup(hash_to_hex(midx_hash)); + xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo)); for (i = 0; i < ctx.num_multi_pack_indexes_before; i++) { uint32_t j = ctx.num_multi_pack_indexes_before - i - 1; - keep_hashes[j] = xstrdup(hash_to_hex(get_midx_checksum(m))); + keep_hashes[j] = xstrdup(hash_to_hex_algop(get_midx_checksum(m), + r->hash_algo)); m = m->base_midx; } @@ -1462,7 +1464,7 @@ static int write_midx_internal(const char *object_dir, fprintf(get_lock_file_fp(&lk), "%s\n", keep_hashes[i]); } else { keep_hashes[ctx.num_multi_pack_indexes_before] = - xstrdup(hash_to_hex(midx_hash)); + xstrdup(hash_to_hex_algop(midx_hash, r->hash_algo)); } if (ctx.m || ctx.base_midx) @@ -1495,7 +1497,7 @@ cleanup: } strbuf_release(&midx_name); - trace2_region_leave("midx", "write_midx_internal", the_repository); + trace2_region_leave("midx", "write_midx_internal", r); return result; } @@ -1505,8 +1507,8 @@ int write_midx_file(const char *object_dir, const char *refs_snapshot, unsigned flags) { - return write_midx_internal(object_dir, NULL, NULL, preferred_pack_name, - refs_snapshot, flags); + return write_midx_internal(the_repository, object_dir, NULL, NULL, + preferred_pack_name, refs_snapshot, flags); } int write_midx_file_only(const char *object_dir, @@ -1515,8 +1517,9 @@ int write_midx_file_only(const char *object_dir, const char *refs_snapshot, unsigned flags) { - return write_midx_internal(object_dir, packs_to_include, NULL, - preferred_pack_name, refs_snapshot, flags); + return write_midx_internal(the_repository, object_dir, packs_to_include, + NULL, preferred_pack_name, refs_snapshot, + flags); } int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags) @@ -1572,7 +1575,8 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla free(count); if (packs_to_drop.nr) - result = write_midx_internal(object_dir, NULL, &packs_to_drop, NULL, NULL, flags); + result = write_midx_internal(r, object_dir, NULL, + &packs_to_drop, NULL, NULL, flags); string_list_clear(&packs_to_drop, 0); @@ -1769,7 +1773,8 @@ int midx_repack(struct repository *r, const char *object_dir, size_t batch_size, goto cleanup; } - result = write_midx_internal(object_dir, NULL, NULL, NULL, NULL, flags); + result = write_midx_internal(r, object_dir, NULL, NULL, NULL, NULL, + flags); cleanup: free(include_pack); From 20df8141f5b7c015abb1090b19e4d24439e500c0 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:27 +0100 Subject: [PATCH 12/18] midx-write: use `revs->repo` inside `read_refs_snapshot` The function `read_refs_snapshot()` uses `parse_oid_hex()`, which relies on the global `the_hash_algo` variable. Let's instead use `parse_oid_hex_algop()` and provide the hash algo via `revs->repo`. Also, while here, fix a missing newline after the function's definition. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/midx-write.c b/midx-write.c index 22b5233f51..564438f616 100644 --- a/midx-write.c +++ b/midx-write.c @@ -760,7 +760,7 @@ static int read_refs_snapshot(const char *refs_snapshot, hex = &buf.buf[1]; } - if (parse_oid_hex(hex, &oid, &end) < 0) + if (parse_oid_hex_algop(hex, &oid, &end, revs->repo->hash_algo) < 0) die(_("could not parse line: %s"), buf.buf); if (*end) die(_("malformed line: %s"), buf.buf); @@ -776,6 +776,7 @@ static int read_refs_snapshot(const char *refs_snapshot, strbuf_release(&buf); return 0; } + static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr_p, const char *refs_snapshot, struct write_midx_context *ctx) From dfa7c68245bc01e7678d85520cbfbac042cb7c5c Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:28 +0100 Subject: [PATCH 13/18] write-midx: add repository field to `write_midx_context` The struct `write_midx_context` is used to pass context for creating MIDX files. Add the repository field here to ensure that most functions within `midx-write.c` have access to the field and can use that instead of the global `the_repository` variable. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/midx-write.c b/midx-write.c index 564438f616..1c355cdf8d 100644 --- a/midx-write.c +++ b/midx-write.c @@ -110,6 +110,8 @@ struct write_midx_context { uint32_t num_multi_pack_indexes_before; struct string_list *to_include; + + struct repository *repo; }; static int should_include_pack(const struct write_midx_context *ctx, @@ -154,7 +156,7 @@ static void add_pack_to_midx(const char *full_path, size_t full_path_len, return; ALLOC_GROW(ctx->info, ctx->nr + 1, ctx->alloc); - p = add_packed_git(the_repository, full_path, full_path_len, 0); + p = add_packed_git(ctx->repo, full_path, full_path_len, 0); if (!p) { warning(_("failed to add packfile '%s'"), full_path); @@ -480,7 +482,7 @@ static int write_midx_oid_lookup(struct hashfile *f, void *data) { struct write_midx_context *ctx = data; - unsigned char hash_len = the_hash_algo->rawsz; + unsigned char hash_len = ctx->repo->hash_algo->rawsz; struct pack_midx_entry *list = ctx->entries; uint32_t i; @@ -605,7 +607,7 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx) uint32_t *pack_order, base_objects = 0; uint32_t i; - trace2_region_enter("midx", "midx_pack_order", the_repository); + trace2_region_enter("midx", "midx_pack_order", ctx->repo); if (ctx->incremental && ctx->base_midx) base_objects = ctx->base_midx->num_objects + @@ -640,7 +642,7 @@ static uint32_t *midx_pack_order(struct write_midx_context *ctx) } free(data); - trace2_region_leave("midx", "midx_pack_order", the_repository); + trace2_region_leave("midx", "midx_pack_order", ctx->repo); return pack_order; } @@ -651,9 +653,10 @@ static void write_midx_reverse_index(char *midx_name, unsigned char *midx_hash, struct strbuf buf = STRBUF_INIT; char *tmp_file; - trace2_region_enter("midx", "write_midx_reverse_index", the_repository); + trace2_region_enter("midx", "write_midx_reverse_index", ctx->repo); - strbuf_addf(&buf, "%s-%s.rev", midx_name, hash_to_hex(midx_hash)); + strbuf_addf(&buf, "%s-%s.rev", midx_name, hash_to_hex_algop(midx_hash, + ctx->repo->hash_algo)); tmp_file = write_rev_file_order(NULL, ctx->pack_order, ctx->entries_nr, midx_hash, WRITE_REV); @@ -664,7 +667,7 @@ static void write_midx_reverse_index(char *midx_name, unsigned char *midx_hash, strbuf_release(&buf); free(tmp_file); - trace2_region_leave("midx", "write_midx_reverse_index", the_repository); + trace2_region_leave("midx", "write_midx_reverse_index", ctx->repo); } static void prepare_midx_packing_data(struct packing_data *pdata, @@ -672,10 +675,10 @@ static void prepare_midx_packing_data(struct packing_data *pdata, { uint32_t i; - trace2_region_enter("midx", "prepare_midx_packing_data", the_repository); + trace2_region_enter("midx", "prepare_midx_packing_data", ctx->repo); memset(pdata, 0, sizeof(struct packing_data)); - prepare_packing_data(the_repository, pdata); + prepare_packing_data(ctx->repo, pdata); for (i = 0; i < ctx->entries_nr; i++) { uint32_t pos = ctx->pack_order[i]; @@ -686,7 +689,7 @@ static void prepare_midx_packing_data(struct packing_data *pdata, ctx->info[ctx->pack_perm[from->pack_int_id]].p); } - trace2_region_leave("midx", "prepare_midx_packing_data", the_repository); + trace2_region_leave("midx", "prepare_midx_packing_data", ctx->repo); } static int add_ref_to_pending(const char *refname, const char *referent UNUSED, @@ -784,17 +787,16 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr struct rev_info revs; struct bitmap_commit_cb cb = {0}; - trace2_region_enter("midx", "find_commits_for_midx_bitmap", - the_repository); + trace2_region_enter("midx", "find_commits_for_midx_bitmap", ctx->repo); cb.ctx = ctx; - repo_init_revisions(the_repository, &revs, NULL); + repo_init_revisions(ctx->repo, &revs, NULL); if (refs_snapshot) { read_refs_snapshot(refs_snapshot, &revs); } else { setup_revisions(0, NULL, &revs, NULL); - refs_for_each_ref(get_main_ref_store(the_repository), + refs_for_each_ref(get_main_ref_store(ctx->repo), add_ref_to_pending, &revs); } @@ -822,8 +824,7 @@ static struct commit **find_commits_for_midx_bitmap(uint32_t *indexed_commits_nr release_revisions(&revs); - trace2_region_leave("midx", "find_commits_for_midx_bitmap", - the_repository); + trace2_region_leave("midx", "find_commits_for_midx_bitmap", ctx->repo); return cb.commits; } @@ -945,7 +946,7 @@ static int fill_packs_from_midx(struct write_midx_context *ctx, */ if (flags & MIDX_WRITE_REV_INDEX || preferred_pack_name) { - if (prepare_midx_pack(the_repository, m, + if (prepare_midx_pack(ctx->repo, m, m->num_packs_in_base + i)) { error(_("could not load pack")); return 1; @@ -1073,6 +1074,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, trace2_region_enter("midx", "write_midx_internal", r); + ctx.repo = r; ctx.incremental = !!(flags & MIDX_WRITE_INCREMENTAL); if (ctx.incremental && (flags & MIDX_WRITE_BITMAP)) @@ -1469,7 +1471,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, } if (ctx.m || ctx.base_midx) - close_object_store(the_repository->objects); + close_object_store(ctx.repo->objects); if (commit_lock_file(&lk) < 0) die_errno(_("could not write multi-pack-index")); From 2fed09aa9b82e4710fb4049e18280df8270eb0b2 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:29 +0100 Subject: [PATCH 14/18] midx-write: pass down repository to `write_midx_file[_only]` In a previous commit, we passed the repository field to all subcommands in the `builtin/` directory. Utilize this to pass the repository field down to the `write_midx_file[_only]` functions to remove the usage of `the_repository` global variables. With this, all usage of global variables in `midx-write.c` is removed, hence, remove the `USE_THE_REPOSITORY_VARIABLE` guard from the file. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- builtin/multi-pack-index.c | 6 +++--- builtin/repack.c | 2 +- midx-write.c | 22 +++++++++------------- midx.h | 10 ++++------ 4 files changed, 17 insertions(+), 23 deletions(-) diff --git a/builtin/multi-pack-index.c b/builtin/multi-pack-index.c index 85e40a4b6d..2a938466f5 100644 --- a/builtin/multi-pack-index.c +++ b/builtin/multi-pack-index.c @@ -120,7 +120,7 @@ static void read_packs_from_stdin(struct string_list *to) static int cmd_multi_pack_index_write(int argc, const char **argv, const char *prefix, - struct repository *repo UNUSED) + struct repository *repo) { struct option *options; static struct option builtin_multi_pack_index_write_options[] = { @@ -165,7 +165,7 @@ static int cmd_multi_pack_index_write(int argc, const char **argv, read_packs_from_stdin(&packs); - ret = write_midx_file_only(opts.object_dir, &packs, + ret = write_midx_file_only(repo, opts.object_dir, &packs, opts.preferred_pack, opts.refs_snapshot, opts.flags); @@ -176,7 +176,7 @@ static int cmd_multi_pack_index_write(int argc, const char **argv, } - ret = write_midx_file(opts.object_dir, opts.preferred_pack, + ret = write_midx_file(repo, opts.object_dir, opts.preferred_pack, opts.refs_snapshot, opts.flags); free(opts.refs_snapshot); diff --git a/builtin/repack.c b/builtin/repack.c index 96a4fa234b..9c21fc482d 100644 --- a/builtin/repack.c +++ b/builtin/repack.c @@ -1569,7 +1569,7 @@ int cmd_repack(int argc, unsigned flags = 0; if (git_env_bool(GIT_TEST_MULTI_PACK_INDEX_WRITE_INCREMENTAL, 0)) flags |= MIDX_WRITE_INCREMENTAL; - write_midx_file(repo_get_object_directory(the_repository), + write_midx_file(the_repository, repo_get_object_directory(the_repository), NULL, NULL, flags); } diff --git a/midx-write.c b/midx-write.c index 1c355cdf8d..1bc2f52569 100644 --- a/midx-write.c +++ b/midx-write.c @@ -1,5 +1,3 @@ -#define USE_THE_REPOSITORY_VARIABLE - #include "git-compat-util.h" #include "abspath.h" #include "config.h" @@ -1505,24 +1503,22 @@ cleanup: return result; } -int write_midx_file(const char *object_dir, +int write_midx_file(struct repository *r, const char *object_dir, const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags) + const char *refs_snapshot, unsigned flags) { - return write_midx_internal(the_repository, object_dir, NULL, NULL, - preferred_pack_name, refs_snapshot, flags); + return write_midx_internal(r, object_dir, NULL, NULL, + preferred_pack_name, refs_snapshot, + flags); } -int write_midx_file_only(const char *object_dir, +int write_midx_file_only(struct repository *r, const char *object_dir, struct string_list *packs_to_include, const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags) + const char *refs_snapshot, unsigned flags) { - return write_midx_internal(the_repository, object_dir, packs_to_include, - NULL, preferred_pack_name, refs_snapshot, - flags); + return write_midx_internal(r, object_dir, packs_to_include, NULL, + preferred_pack_name, refs_snapshot, flags); } int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags) diff --git a/midx.h b/midx.h index 3b0ac4d878..c37ad5b524 100644 --- a/midx.h +++ b/midx.h @@ -123,15 +123,13 @@ int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, i * Variant of write_midx_file which writes a MIDX containing only the packs * specified in packs_to_include. */ -int write_midx_file(const char *object_dir, - const char *preferred_pack_name, - const char *refs_snapshot, +int write_midx_file(struct repository *r, const char *object_dir, + const char *preferred_pack_name, const char *refs_snapshot, unsigned flags); -int write_midx_file_only(const char *object_dir, +int write_midx_file_only(struct repository *r, const char *object_dir, struct string_list *packs_to_include, const char *preferred_pack_name, - const char *refs_snapshot, - unsigned flags); + const char *refs_snapshot, unsigned flags); void clear_midx_file(struct repository *r); int verify_midx_file(struct repository *r, const char *object_dir, unsigned flags); int expire_midx_packs(struct repository *r, const char *object_dir, unsigned flags); From fae9bae7091958255fa7729f6cedb8cc4f9a3387 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:30 +0100 Subject: [PATCH 15/18] midx: cleanup internal usage of `the_repository` and `the_hash_algo` In the `midx.c` file, there are multiple usages of `the_repository` and `the_hash_algo` within static functions of the file. Some of the usages can be simply swapped out with the available `repository` struct. While some of them can be swapped out by passing the repository to the required functions. This leaves out only some other usages of `the_repository` and `the_hash_algo` in the file in non-static functions, which we'll tackle in upcoming commits. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 49 +++++++++++++++++++++++++++---------------------- 1 file changed, 27 insertions(+), 22 deletions(-) diff --git a/midx.c b/midx.c index 079c45a1aa..6f0fb8285a 100644 --- a/midx.c +++ b/midx.c @@ -25,7 +25,7 @@ int cmp_idx_or_pack_name(const char *idx_or_pack_name, const unsigned char *get_midx_checksum(struct multi_pack_index *m) { - return m->data + m->data_len - the_hash_algo->rawsz; + return m->data + m->data_len - m->repo->hash_algo->rawsz; } void get_midx_filename(struct strbuf *out, const char *object_dir) @@ -94,7 +94,8 @@ static int midx_read_object_offsets(const unsigned char *chunk_start, #define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz) -static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir, +static struct multi_pack_index *load_multi_pack_index_one(struct repository *r, + const char *object_dir, const char *midx_name, int local) { @@ -131,7 +132,7 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->data = midx_map; m->data_len = midx_size; m->local = local; - m->repo = the_repository; + m->repo = r; m->signature = get_be32(m->data); if (m->signature != MIDX_SIGNATURE) @@ -144,12 +145,12 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->version); hash_version = m->data[MIDX_BYTE_HASH_VERSION]; - if (hash_version != oid_version(the_hash_algo)) { + if (hash_version != oid_version(r->hash_algo)) { error(_("multi-pack-index hash version %u does not match version %u"), - hash_version, oid_version(the_hash_algo)); + hash_version, oid_version(r->hash_algo)); goto cleanup_fail; } - m->hash_len = the_hash_algo->rawsz; + m->hash_len = r->hash_algo->rawsz; m->num_chunks = m->data[MIDX_BYTE_NUM_CHUNKS]; @@ -206,8 +207,8 @@ static struct multi_pack_index *load_multi_pack_index_one(const char *object_dir m->pack_names[i]); } - trace2_data_intmax("midx", the_repository, "load/num_packs", m->num_packs); - trace2_data_intmax("midx", the_repository, "load/num_objects", m->num_objects); + trace2_data_intmax("midx", r, "load/num_packs", m->num_packs); + trace2_data_intmax("midx", r, "load/num_objects", m->num_objects); free_chunkfile(cf); return m; @@ -240,8 +241,9 @@ void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, strbuf_addf(buf, "/multi-pack-index-%s.%s", hash_to_hex(hash), ext); } -static int open_multi_pack_index_chain(const char *chain_file, - int *fd, struct stat *st) +static int open_multi_pack_index_chain(const struct git_hash_algo *hash_algo, + const char *chain_file, int *fd, + struct stat *st) { *fd = git_open(chain_file); if (*fd < 0) @@ -250,7 +252,7 @@ static int open_multi_pack_index_chain(const char *chain_file, close(*fd); return 0; } - if (st->st_size < the_hash_algo->hexsz) { + if (st->st_size < hash_algo->hexsz) { close(*fd); if (!st->st_size) { /* treat empty files the same as missing */ @@ -292,7 +294,8 @@ static int add_midx_to_chain(struct multi_pack_index *midx, return 1; } -static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, +static struct multi_pack_index *load_midx_chain_fd_st(struct repository *r, + const char *object_dir, int local, int fd, struct stat *st, int *incomplete_chain) @@ -303,7 +306,7 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, uint32_t i, count; FILE *fp = xfdopen(fd, "r"); - count = st->st_size / (the_hash_algo->hexsz + 1); + count = st->st_size / (r->hash_algo->hexsz + 1); for (i = 0; i < count; i++) { struct multi_pack_index *m; @@ -312,7 +315,7 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, if (strbuf_getline_lf(&buf, fp) == EOF) break; - if (get_oid_hex(buf.buf, &layer)) { + if (get_oid_hex_algop(buf.buf, &layer, r->hash_algo)) { warning(_("invalid multi-pack-index chain: line '%s' " "not a hash"), buf.buf); @@ -325,7 +328,7 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, strbuf_reset(&buf); get_split_midx_filename_ext(&buf, object_dir, layer.hash, MIDX_EXT_MIDX); - m = load_multi_pack_index_one(object_dir, buf.buf, local); + m = load_multi_pack_index_one(r, object_dir, buf.buf, local); if (m) { if (add_midx_to_chain(m, midx_chain)) { @@ -348,7 +351,8 @@ static struct multi_pack_index *load_midx_chain_fd_st(const char *object_dir, return midx_chain; } -static struct multi_pack_index *load_multi_pack_index_chain(const char *object_dir, +static struct multi_pack_index *load_multi_pack_index_chain(struct repository *r, + const char *object_dir, int local) { struct strbuf chain_file = STRBUF_INIT; @@ -357,10 +361,10 @@ static struct multi_pack_index *load_multi_pack_index_chain(const char *object_d struct multi_pack_index *m = NULL; get_midx_chain_filename(&chain_file, object_dir); - if (open_multi_pack_index_chain(chain_file.buf, &fd, &st)) { + if (open_multi_pack_index_chain(r->hash_algo, chain_file.buf, &fd, &st)) { int incomplete; /* ownership of fd is taken over by load function */ - m = load_midx_chain_fd_st(object_dir, local, fd, &st, + m = load_midx_chain_fd_st(r, object_dir, local, fd, &st, &incomplete); } @@ -376,9 +380,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, get_midx_filename(&midx_name, object_dir); - m = load_multi_pack_index_one(object_dir, midx_name.buf, local); + m = load_multi_pack_index_one(the_repository, object_dir, + midx_name.buf, local); if (!m) - m = load_multi_pack_index_chain(object_dir, local); + m = load_multi_pack_index_chain(the_repository, object_dir, local); strbuf_release(&midx_name); @@ -520,7 +525,7 @@ int bsearch_one_midx(const struct object_id *oid, struct multi_pack_index *m, uint32_t *result) { int ret = bsearch_hash(oid->hash, m->chunk_oid_fanout, - m->chunk_oid_lookup, the_hash_algo->rawsz, + m->chunk_oid_lookup, m->repo->hash_algo->rawsz, result); if (result) *result += m->num_objects_in_base; @@ -551,7 +556,7 @@ struct object_id *nth_midxed_object_oid(struct object_id *oid, n = midx_for_object(&m, n); oidread(oid, m->chunk_oid_lookup + st_mult(m->hash_len, n), - the_repository->hash_algo); + m->repo->hash_algo); return oid; } From d5c2ca576a47480b03a83821041955a21a645d1a Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:31 +0100 Subject: [PATCH 16/18] midx: pass `repository` to `load_multi_pack_index` The `load_multi_pack_index` function in midx uses `the_repository` variable to access the `repository` struct. Modify the function and its callee's to send the `repository` field. This moves usage of `the_repository` to the `test-read-midx.c` file. While that is not optimal, it is okay, since the upcoming commits will slowly move the usage of `the_repository` up the layers and remove it eventually. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 11 ++++++----- midx.h | 4 +++- t/helper/test-read-midx.c | 8 ++++---- 3 files changed, 13 insertions(+), 10 deletions(-) diff --git a/midx.c b/midx.c index 6f0fb8285a..98ee84d4a8 100644 --- a/midx.c +++ b/midx.c @@ -372,7 +372,8 @@ static struct multi_pack_index *load_multi_pack_index_chain(struct repository *r return m; } -struct multi_pack_index *load_multi_pack_index(const char *object_dir, +struct multi_pack_index *load_multi_pack_index(struct repository *r, + const char *object_dir, int local) { struct strbuf midx_name = STRBUF_INIT; @@ -380,10 +381,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, get_midx_filename(&midx_name, object_dir); - m = load_multi_pack_index_one(the_repository, object_dir, + m = load_multi_pack_index_one(r, object_dir, midx_name.buf, local); if (!m) - m = load_multi_pack_index_chain(the_repository, object_dir, local); + m = load_multi_pack_index_chain(r, object_dir, local); strbuf_release(&midx_name); @@ -727,7 +728,7 @@ int prepare_multi_pack_index_one(struct repository *r, const char *object_dir, i if (!strcmp(object_dir, m_search->object_dir)) return 1; - m = load_multi_pack_index(object_dir, local); + m = load_multi_pack_index(r, object_dir, local); if (m) { struct multi_pack_index *mp = r->objects->multi_pack_index; @@ -881,7 +882,7 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag struct pair_pos_vs_id *pairs = NULL; uint32_t i; struct progress *progress = NULL; - struct multi_pack_index *m = load_multi_pack_index(object_dir, 1); + struct multi_pack_index *m = load_multi_pack_index(r, object_dir, 1); struct multi_pack_index *curr; verify_midx_error = 0; diff --git a/midx.h b/midx.h index c37ad5b524..78efa28d35 100644 --- a/midx.h +++ b/midx.h @@ -97,7 +97,9 @@ void get_midx_chain_filename(struct strbuf *buf, const char *object_dir); void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, const unsigned char *hash, const char *ext); -struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local); +struct multi_pack_index *load_multi_pack_index(struct repository *r, + const char *object_dir, + int local); int prepare_midx_pack(struct repository *r, struct multi_pack_index *m, uint32_t pack_int_id); struct packed_git *nth_midxed_pack(struct multi_pack_index *m, uint32_t pack_int_id); diff --git a/t/helper/test-read-midx.c b/t/helper/test-read-midx.c index 438fb9fc61..fc63236961 100644 --- a/t/helper/test-read-midx.c +++ b/t/helper/test-read-midx.c @@ -18,7 +18,7 @@ static int read_midx_file(const char *object_dir, const char *checksum, struct multi_pack_index *m; setup_git_directory(); - m = load_multi_pack_index(object_dir, 1); + m = load_multi_pack_index(the_repository, object_dir, 1); if (!m) return 1; @@ -82,7 +82,7 @@ static int read_midx_checksum(const char *object_dir) struct multi_pack_index *m; setup_git_directory(); - m = load_multi_pack_index(object_dir, 1); + m = load_multi_pack_index(the_repository, object_dir, 1); if (!m) return 1; printf("%s\n", hash_to_hex(get_midx_checksum(m))); @@ -98,7 +98,7 @@ static int read_midx_preferred_pack(const char *object_dir) setup_git_directory(); - midx = load_multi_pack_index(object_dir, 1); + midx = load_multi_pack_index(the_repository, object_dir, 1); if (!midx) return 1; @@ -121,7 +121,7 @@ static int read_midx_bitmapped_packs(const char *object_dir) setup_git_directory(); - midx = load_multi_pack_index(object_dir, 1); + midx = load_multi_pack_index(the_repository, object_dir, 1); if (!midx) return 1; From f59de71cf700f9f8da27023ec8b5df117f99d9c8 Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:32 +0100 Subject: [PATCH 17/18] midx: pass down `hash_algo` to functions using global variables The functions `get_split_midx_filename_ext()`, `get_midx_filename()` and `get_midx_filename_ext()` use `hash_to_hex()` which internally uses the `the_hash_algo` global variable. Remove this dependency on global variables by passing down the `hash_algo` through to the functions mentioned and instead calling `hash_to_hex_algop()` along with the obtained `hash_algo`. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx-write.c | 22 +++++++++++----------- midx.c | 26 +++++++++++++++----------- midx.h | 10 +++++++--- pack-bitmap.c | 6 +++--- pack-revindex.c | 2 +- 5 files changed, 37 insertions(+), 29 deletions(-) diff --git a/midx-write.c b/midx-write.c index 1bc2f52569..bcd1d50eb0 100644 --- a/midx-write.c +++ b/midx-write.c @@ -991,9 +991,10 @@ static int link_midx_to_chain(struct multi_pack_index *m) for (i = 0; i < ARRAY_SIZE(midx_exts); i++) { const unsigned char *hash = get_midx_checksum(m); - get_midx_filename_ext(&from, m->object_dir, hash, - midx_exts[i].non_split); - get_split_midx_filename_ext(&to, m->object_dir, hash, + get_midx_filename_ext(m->repo->hash_algo, &from, m->object_dir, + hash, midx_exts[i].non_split); + get_split_midx_filename_ext(m->repo->hash_algo, &to, + m->object_dir, hash, midx_exts[i].split); if (link(from.buf, to.buf) < 0 && errno != ENOENT) { @@ -1012,9 +1013,8 @@ done: return ret; } -static void clear_midx_files(const char *object_dir, - const char **hashes, - uint32_t hashes_nr, +static void clear_midx_files(struct repository *r, const char *object_dir, + const char **hashes, uint32_t hashes_nr, unsigned incremental) { /* @@ -1039,7 +1039,7 @@ static void clear_midx_files(const char *object_dir, } if (incremental) - get_midx_filename(&buf, object_dir); + get_midx_filename(r->hash_algo, &buf, object_dir); else get_midx_chain_filename(&buf, object_dir); @@ -1083,7 +1083,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, "%s/pack/multi-pack-index.d/tmp_midx_XXXXXX", object_dir); else - get_midx_filename(&midx_name, object_dir); + get_midx_filename(r->hash_algo, &midx_name, object_dir); if (safe_create_leading_directories(midx_name.buf)) die_errno(_("unable to create leading directories of %s"), midx_name.buf); @@ -1440,8 +1440,8 @@ static int write_midx_internal(struct repository *r, const char *object_dir, if (link_midx_to_chain(ctx.base_midx) < 0) return -1; - get_split_midx_filename_ext(&final_midx_name, object_dir, - midx_hash, MIDX_EXT_MIDX); + get_split_midx_filename_ext(r->hash_algo, &final_midx_name, + object_dir, midx_hash, MIDX_EXT_MIDX); if (rename_tempfile(&incr, final_midx_name.buf) < 0) { error_errno(_("unable to rename new multi-pack-index layer")); @@ -1474,7 +1474,7 @@ static int write_midx_internal(struct repository *r, const char *object_dir, if (commit_lock_file(&lk) < 0) die_errno(_("could not write multi-pack-index")); - clear_midx_files(object_dir, keep_hashes, + clear_midx_files(r, object_dir, keep_hashes, ctx.num_multi_pack_indexes_before + 1, ctx.incremental); diff --git a/midx.c b/midx.c index 98ee84d4a8..f45ea842cd 100644 --- a/midx.c +++ b/midx.c @@ -28,17 +28,19 @@ const unsigned char *get_midx_checksum(struct multi_pack_index *m) return m->data + m->data_len - m->repo->hash_algo->rawsz; } -void get_midx_filename(struct strbuf *out, const char *object_dir) +void get_midx_filename(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir) { - get_midx_filename_ext(out, object_dir, NULL, NULL); + get_midx_filename_ext(hash_algo, out, object_dir, NULL, NULL); } -void get_midx_filename_ext(struct strbuf *out, const char *object_dir, +void get_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir, const unsigned char *hash, const char *ext) { strbuf_addf(out, "%s/pack/multi-pack-index", object_dir); if (ext) - strbuf_addf(out, "-%s.%s", hash_to_hex(hash), ext); + strbuf_addf(out, "-%s.%s", hash_to_hex_algop(hash, hash_algo), ext); } static int midx_read_oid_fanout(const unsigned char *chunk_start, @@ -234,11 +236,13 @@ void get_midx_chain_filename(struct strbuf *buf, const char *object_dir) strbuf_addstr(buf, "/multi-pack-index-chain"); } -void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, +void get_split_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *buf, const char *object_dir, const unsigned char *hash, const char *ext) { get_midx_chain_dirname(buf, object_dir); - strbuf_addf(buf, "/multi-pack-index-%s.%s", hash_to_hex(hash), ext); + strbuf_addf(buf, "/multi-pack-index-%s.%s", + hash_to_hex_algop(hash, hash_algo), ext); } static int open_multi_pack_index_chain(const struct git_hash_algo *hash_algo, @@ -326,8 +330,8 @@ static struct multi_pack_index *load_midx_chain_fd_st(struct repository *r, valid = 0; strbuf_reset(&buf); - get_split_midx_filename_ext(&buf, object_dir, layer.hash, - MIDX_EXT_MIDX); + get_split_midx_filename_ext(r->hash_algo, &buf, object_dir, + layer.hash, MIDX_EXT_MIDX); m = load_multi_pack_index_one(r, object_dir, buf.buf, local); if (m) { @@ -379,7 +383,7 @@ struct multi_pack_index *load_multi_pack_index(struct repository *r, struct strbuf midx_name = STRBUF_INIT; struct multi_pack_index *m; - get_midx_filename(&midx_name, object_dir); + get_midx_filename(r->hash_algo, &midx_name, object_dir); m = load_multi_pack_index_one(r, object_dir, midx_name.buf, local); @@ -822,7 +826,7 @@ void clear_midx_file(struct repository *r) { struct strbuf midx = STRBUF_INIT; - get_midx_filename(&midx, r->objects->odb->path); + get_midx_filename(r->hash_algo, &midx, r->objects->odb->path); if (r->objects && r->objects->multi_pack_index) { close_midx(r->objects->multi_pack_index); @@ -891,7 +895,7 @@ int verify_midx_file(struct repository *r, const char *object_dir, unsigned flag struct stat sb; struct strbuf filename = STRBUF_INIT; - get_midx_filename(&filename, object_dir); + get_midx_filename(r->hash_algo, &filename, object_dir); if (!stat(filename.buf, &sb)) { error(_("multi-pack-index file exists, but failed to parse")); diff --git a/midx.h b/midx.h index 78efa28d35..9d1374cbd5 100644 --- a/midx.h +++ b/midx.h @@ -7,6 +7,7 @@ struct object_id; struct pack_entry; struct repository; struct bitmapped_pack; +struct git_hash_algo; #define MIDX_SIGNATURE 0x4d494458 /* "MIDX" */ #define MIDX_VERSION 1 @@ -89,12 +90,15 @@ struct multi_pack_index { #define MIDX_EXT_MIDX "midx" const unsigned char *get_midx_checksum(struct multi_pack_index *m); -void get_midx_filename(struct strbuf *out, const char *object_dir); -void get_midx_filename_ext(struct strbuf *out, const char *object_dir, +void get_midx_filename(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir); +void get_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *out, const char *object_dir, const unsigned char *hash, const char *ext); void get_midx_chain_dirname(struct strbuf *buf, const char *object_dir); void get_midx_chain_filename(struct strbuf *buf, const char *object_dir); -void get_split_midx_filename_ext(struct strbuf *buf, const char *object_dir, +void get_split_midx_filename_ext(const struct git_hash_algo *hash_algo, + struct strbuf *buf, const char *object_dir, const unsigned char *hash, const char *ext); struct multi_pack_index *load_multi_pack_index(struct repository *r, diff --git a/pack-bitmap.c b/pack-bitmap.c index 0cb1b56c9d..7b62d099ca 100644 --- a/pack-bitmap.c +++ b/pack-bitmap.c @@ -375,8 +375,8 @@ static int load_bitmap_entries_v1(struct bitmap_index *index) char *midx_bitmap_filename(struct multi_pack_index *midx) { struct strbuf buf = STRBUF_INIT; - get_midx_filename_ext(&buf, midx->object_dir, get_midx_checksum(midx), - MIDX_EXT_BITMAP); + get_midx_filename_ext(midx->repo->hash_algo, &buf, midx->object_dir, + get_midx_checksum(midx), MIDX_EXT_BITMAP); return strbuf_detach(&buf, NULL); } @@ -415,7 +415,7 @@ static int open_midx_bitmap_1(struct bitmap_index *bitmap_git, if (bitmap_git->pack || bitmap_git->midx) { struct strbuf buf = STRBUF_INIT; - get_midx_filename(&buf, midx->object_dir); + get_midx_filename(midx->repo->hash_algo, &buf, midx->object_dir); trace2_data_string("bitmap", bitmap_repo(bitmap_git), "ignoring extra midx bitmap file", buf.buf); close(fd); diff --git a/pack-revindex.c b/pack-revindex.c index 22d3c23464..d3832478d9 100644 --- a/pack-revindex.c +++ b/pack-revindex.c @@ -383,7 +383,7 @@ int load_midx_revindex(struct multi_pack_index *m) trace2_data_string("load_midx_revindex", the_repository, "source", "rev"); - get_midx_filename_ext(&revindex_name, m->object_dir, + get_midx_filename_ext(m->repo->hash_algo, &revindex_name, m->object_dir, get_midx_checksum(m), MIDX_EXT_REV); ret = load_revindex_from_disk(revindex_name.buf, From 24d3dd79e4810ae7bafb3180664ac435fecd567f Mon Sep 17 00:00:00 2001 From: Karthik Nayak Date: Wed, 27 Nov 2024 17:28:33 +0100 Subject: [PATCH 18/18] midx: inline the `MIDX_MIN_SIZE` definition The `MIDX_MIN_SIZE` definition is used to check the midx_size in `local_multi_pack_index_one`. This definition relies on the `the_hash_algo` global variable. Inline this and remove the global variable usage. With this, remove `USE_THE_REPOSITORY_VARIABLE` usage from `midx.c`. Signed-off-by: Karthik Nayak Signed-off-by: Junio C Hamano --- midx.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/midx.c b/midx.c index f45ea842cd..e0eae1c25e 100644 --- a/midx.c +++ b/midx.c @@ -1,5 +1,3 @@ -#define USE_THE_REPOSITORY_VARIABLE - #include "git-compat-util.h" #include "config.h" #include "dir.h" @@ -94,8 +92,6 @@ static int midx_read_object_offsets(const unsigned char *chunk_start, return 0; } -#define MIDX_MIN_SIZE (MIDX_HEADER_SIZE + the_hash_algo->rawsz) - static struct multi_pack_index *load_multi_pack_index_one(struct repository *r, const char *object_dir, const char *midx_name, @@ -122,7 +118,7 @@ static struct multi_pack_index *load_multi_pack_index_one(struct repository *r, midx_size = xsize_t(st.st_size); - if (midx_size < MIDX_MIN_SIZE) { + if (midx_size < (MIDX_HEADER_SIZE + r->hash_algo->rawsz)) { error(_("multi-pack-index file %s is too small"), midx_name); goto cleanup_fail; }