diff options
Diffstat (limited to 'read-cache.c')
-rw-r--r-- | read-cache.c | 385 |
1 files changed, 341 insertions, 44 deletions
diff --git a/read-cache.c b/read-cache.c index 248432af43..acfb028f48 100644 --- a/read-cache.c +++ b/read-cache.c @@ -5,6 +5,7 @@ */ #define NO_THE_INDEX_COMPATIBILITY_MACROS #include "cache.h" +#include "config.h" #include "tempfile.h" #include "lockfile.h" #include "cache-tree.h" @@ -156,12 +157,12 @@ void fill_stat_cache_info(struct cache_entry *ce, struct stat *st) static int ce_compare_data(const struct cache_entry *ce, struct stat *st) { int match = -1; - int fd = open(ce->name, O_RDONLY); + int fd = git_open_cloexec(ce->name, O_RDONLY); if (fd >= 0) { unsigned char sha1[20]; if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0)) - match = hashcmp(sha1, ce->sha1); + match = hashcmp(sha1, ce->oid.hash); /* index_fd() closed the file descriptor already */ } return match; @@ -178,7 +179,7 @@ static int ce_compare_link(const struct cache_entry *ce, size_t expected_size) if (strbuf_readlink(&sb, ce->name, expected_size)) return -1; - buffer = read_sha1_file(ce->sha1, &type, &size); + buffer = read_sha1_file(ce->oid.hash, &type, &size); if (buffer) { if (size == sb.len) match = memcmp(buffer, sb.buf, size); @@ -202,7 +203,7 @@ static int ce_compare_gitlink(const struct cache_entry *ce) */ if (resolve_gitlink_ref(ce->name, "HEAD", sha1) < 0) return 0; - return hashcmp(sha1, ce->sha1); + return hashcmp(sha1, ce->oid.hash); } static int ce_modified_check_fs(const struct cache_entry *ce, struct stat *st) @@ -262,7 +263,7 @@ static int ce_match_stat_basic(const struct cache_entry *ce, struct stat *st) /* Racily smudged entry? */ if (!ce->ce_stat_data.sd_size) { - if (!is_empty_blob_sha1(ce->sha1)) + if (!is_empty_blob_sha1(ce->oid.hash)) changed |= DATA_CHANGED; } @@ -503,7 +504,6 @@ int index_name_pos(const struct index_state *istate, const char *name, int namel return index_name_stage_pos(istate, name, namelen, 0); } -/* Remove entry, return true if there are more entries to go.. */ int remove_index_entry_at(struct index_state *istate, int pos) { struct cache_entry *ce = istate->cache[pos]; @@ -515,9 +515,8 @@ int remove_index_entry_at(struct index_state *istate, int pos) istate->cache_nr--; if (pos >= istate->cache_nr) return 0; - memmove(istate->cache + pos, - istate->cache + pos + 1, - (istate->cache_nr - pos) * sizeof(struct cache_entry *)); + MOVE_ARRAY(istate->cache + pos, istate->cache + pos + 1, + istate->cache_nr - pos); return 1; } @@ -624,7 +623,7 @@ void set_object_name_for_intent_to_add_entry(struct cache_entry *ce) unsigned char sha1[20]; if (write_sha1_file("", 0, blob_type, sha1)) die("cannot create an empty blob in the object database"); - hashcpy(ce->sha1, sha1); + hashcpy(ce->oid.hash, sha1); } int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags) @@ -690,7 +689,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, return 0; } if (!intent_only) { - if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT)) { + if (index_path(ce->oid.hash, path, st, HASH_WRITE_OBJECT)) { free(ce); return error("unable to index file %s", path); } @@ -704,7 +703,7 @@ int add_to_index(struct index_state *istate, const char *path, struct stat *st, /* It was suspected to be racily clean, but it turns out to be Ok */ was_same = (alias && !ce_stage(alias) && - !hashcmp(alias->sha1, ce->sha1) && + !oidcmp(&alias->oid, &ce->oid) && ce->ce_mode == alias->ce_mode); if (pretend) @@ -742,7 +741,7 @@ struct cache_entry *make_cache_entry(unsigned int mode, size = cache_entry_size(len); ce = xcalloc(1, size); - hashcpy(ce->sha1, sha1); + hashcpy(ce->oid.hash, sha1); memcpy(ce->name, path, len); ce->ce_flags = create_ce_flags(stage); ce->ce_namelen = len; @@ -888,9 +887,32 @@ static int has_file_name(struct index_state *istate, return retval; } + +/* + * Like strcmp(), but also return the offset of the first change. + * If strings are equal, return the length. + */ +int strcmp_offset(const char *s1, const char *s2, size_t *first_change) +{ + size_t k; + + if (!first_change) + return strcmp(s1, s2); + + for (k = 0; s1[k] == s2[k]; k++) + if (s1[k] == '\0') + break; + + *first_change = k; + return (unsigned char)s1[k] - (unsigned char)s2[k]; +} + /* * Do we have another file with a pathname that is a proper * subset of the name we're trying to add? + * + * That is, is there another file in the index with a path + * that matches a sub-directory in the given entry? */ static int has_dir_name(struct index_state *istate, const struct cache_entry *ce, int pos, int ok_to_replace) @@ -899,9 +921,51 @@ static int has_dir_name(struct index_state *istate, int stage = ce_stage(ce); const char *name = ce->name; const char *slash = name + ce_namelen(ce); + size_t len_eq_last; + int cmp_last = 0; + + /* + * We are frequently called during an iteration on a sorted + * list of pathnames and while building a new index. Therefore, + * there is a high probability that this entry will eventually + * be appended to the index, rather than inserted in the middle. + * If we can confirm that, we can avoid binary searches on the + * components of the pathname. + * + * Compare the entry's full path with the last path in the index. + */ + if (istate->cache_nr > 0) { + cmp_last = strcmp_offset(name, + istate->cache[istate->cache_nr - 1]->name, + &len_eq_last); + if (cmp_last > 0) { + if (len_eq_last == 0) { + /* + * The entry sorts AFTER the last one in the + * index and their paths have no common prefix, + * so there cannot be a F/D conflict. + */ + return retval; + } else { + /* + * The entry sorts AFTER the last one in the + * index, but has a common prefix. Fall through + * to the loop below to disect the entry's path + * and see where the difference is. + */ + } + } else if (cmp_last == 0) { + /* + * The entry exactly matches the last one in the + * index, but because of multiple stage and CE_REMOVE + * items, we fall through and let the regular search + * code handle it. + */ + } + } for (;;) { - int len; + size_t len; for (;;) { if (*--slash == '/') @@ -911,6 +975,67 @@ static int has_dir_name(struct index_state *istate, } len = slash - name; + if (cmp_last > 0) { + /* + * (len + 1) is a directory boundary (including + * the trailing slash). And since the loop is + * decrementing "slash", the first iteration is + * the longest directory prefix; subsequent + * iterations consider parent directories. + */ + + if (len + 1 <= len_eq_last) { + /* + * The directory prefix (including the trailing + * slash) also appears as a prefix in the last + * entry, so the remainder cannot collide (because + * strcmp said the whole path was greater). + * + * EQ: last: xxx/A + * this: xxx/B + * + * LT: last: xxx/file_A + * this: xxx/file_B + */ + return retval; + } + + if (len > len_eq_last) { + /* + * This part of the directory prefix (excluding + * the trailing slash) is longer than the known + * equal portions, so this sub-directory cannot + * collide with a file. + * + * GT: last: xxxA + * this: xxxB/file + */ + return retval; + } + + if (istate->cache_nr > 0 && + ce_namelen(istate->cache[istate->cache_nr - 1]) > len) { + /* + * The directory prefix lines up with part of + * a longer file or directory name, but sorts + * after it, so this sub-directory cannot + * collide with a file. + * + * last: xxx/yy-file (because '-' sorts before '/') + * this: xxx/yy/abc + */ + return retval; + } + + /* + * This is a possible collision. Fall through and + * let the regular search code handle it. + * + * last: xxx + * this: xxx/file + */ + } + pos = index_name_stage_pos(istate, name, len, stage); if (pos >= 0) { /* @@ -1002,7 +1127,16 @@ static int add_index_entry_with_check(struct index_state *istate, struct cache_e if (!(option & ADD_CACHE_KEEP_CACHE_TREE)) cache_tree_invalidate_path(istate, ce->name); - pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce)); + + /* + * If this entry's path sorts after the last entry in the index, + * we can avoid searching for it. + */ + if (istate->cache_nr > 0 && + strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0) + pos = -istate->cache_nr - 1; + else + pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce)); /* existing match? Just replace it. */ if (pos >= 0) { @@ -1372,6 +1506,9 @@ struct ondisk_cache_entry_extended { ondisk_cache_entry_extended_size(ce_namelen(ce)) : \ ondisk_cache_entry_size(ce_namelen(ce))) +/* Allow fsck to force verification of the index checksum. */ +int verify_index_checksum; + static int verify_hdr(struct cache_header *hdr, unsigned long size) { git_SHA_CTX c; @@ -1383,6 +1520,10 @@ static int verify_hdr(struct cache_header *hdr, unsigned long size) hdr_version = ntohl(hdr->hdr_version); if (hdr_version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < hdr_version) return error("bad index version %d", hdr_version); + + if (!verify_index_checksum) + return 0; + git_SHA1_Init(&c); git_SHA1_Update(&c, hdr, size - 20); git_SHA1_Final(sha1, &c); @@ -1418,12 +1559,9 @@ static int read_index_extension(struct index_state *istate, return 0; } -int hold_locked_index(struct lock_file *lk, int die_on_error) +int hold_locked_index(struct lock_file *lk, int lock_flags) { - return hold_lock_file_for_update(lk, get_index_file(), - die_on_error - ? LOCK_DIE_ON_ERROR - : 0); + return hold_lock_file_for_update(lk, get_index_file(), lock_flags); } int read_index(struct index_state *istate) @@ -1451,7 +1589,7 @@ static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *on ce->ce_flags = flags & ~CE_NAMEMASK; ce->ce_namelen = len; ce->index = 0; - hashcpy(ce->sha1, ondisk->sha1); + hashcpy(ce->oid.hash, ondisk->sha1); memcpy(ce->name, name, len); ce->name[len] = '\0'; return ce; @@ -1562,10 +1700,27 @@ static void tweak_untracked_cache(struct index_state *istate) } } +static void tweak_split_index(struct index_state *istate) +{ + switch (git_config_get_split_index()) { + case -1: /* unset: do nothing */ + break; + case 0: /* false */ + remove_split_index(istate); + break; + case 1: /* true */ + add_split_index(istate); + break; + default: /* unknown value: do nothing */ + break; + } +} + static void post_read_index_from(struct index_state *istate) { check_ce_order(istate); tweak_untracked_cache(istate); + tweak_split_index(istate); } /* remember to discard_cache() before reading a different cache! */ @@ -1661,10 +1816,26 @@ unmap: die("index file corrupt"); } +/* + * Signal that the shared index is used by updating its mtime. + * + * This way, shared index can be removed if they have not been used + * for some time. + */ +static void freshen_shared_index(char *base_sha1_hex, int warn) +{ + char *shared_index = git_pathdup("sharedindex.%s", base_sha1_hex); + if (!check_and_freshen_file(shared_index, 1) && warn) + warning("could not freshen shared index '%s'", shared_index); + free(shared_index); +} + int read_index_from(struct index_state *istate, const char *path) { struct split_index *split_index; int ret; + char *base_sha1_hex; + const char *base_path; /* istate->initialized covers both .git/index and .git/sharedindex.xxx */ if (istate->initialized) @@ -1682,15 +1853,16 @@ int read_index_from(struct index_state *istate, const char *path) discard_index(split_index->base); else split_index->base = xcalloc(1, sizeof(*split_index->base)); - ret = do_read_index(split_index->base, - git_path("sharedindex.%s", - sha1_to_hex(split_index->base_sha1)), 1); + + base_sha1_hex = sha1_to_hex(split_index->base_sha1); + base_path = git_path("sharedindex.%s", base_sha1_hex); + ret = do_read_index(split_index->base, base_path, 1); if (hashcmp(split_index->base_sha1, split_index->base->sha1)) die("broken index, expect %s in %s, got %s", - sha1_to_hex(split_index->base_sha1), - git_path("sharedindex.%s", - sha1_to_hex(split_index->base_sha1)), + base_sha1_hex, base_path, sha1_to_hex(split_index->base->sha1)); + + freshen_shared_index(base_sha1_hex, 0); merge_base_index(istate); post_read_index_from(istate); return ret; @@ -1722,8 +1894,7 @@ int discard_index(struct index_state *istate) free_name_hash(istate); cache_tree_free(&(istate->cache_tree)); istate->initialized = 0; - free(istate->cache); - istate->cache = NULL; + FREE_AND_NULL(istate->cache); istate->cache_alloc = 0; discard_split_index(istate); free_untracked_cache(istate->untracked); @@ -1876,7 +2047,7 @@ static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk, ondisk->uid = htonl(ce->ce_stat_data.sd_uid); ondisk->gid = htonl(ce->ce_stat_data.sd_gid); ondisk->size = htonl(ce->ce_stat_data.sd_size); - hashcpy(ondisk->sha1, ce->sha1); + hashcpy(ondisk->sha1, ce->oid.hash); flags = ce->ce_flags & ~CE_NAMEMASK; flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce)); @@ -2015,9 +2186,10 @@ void update_index_if_able(struct index_state *istate, struct lock_file *lockfile rollback_lock_file(lockfile); } -static int do_write_index(struct index_state *istate, int newfd, +static int do_write_index(struct index_state *istate, struct tempfile *tempfile, int strip_extensions) { + int newfd = tempfile->fd; git_SHA_CTX c; struct cache_header hdr; int i, err, removed, extended, hdr_version; @@ -2025,6 +2197,7 @@ static int do_write_index(struct index_state *istate, int newfd, int entries = istate->cache_nr; struct stat st; struct strbuf previous_name_buf = STRBUF_INIT, *previous_name; + int drop_cache_tree = 0; for (i = removed = extended = 0; i < entries; i++) { if (cache[i]->ce_flags & CE_REMOVE) @@ -2065,7 +2238,7 @@ static int do_write_index(struct index_state *istate, int newfd, continue; if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce)) ce_smudge_racily_clean_entry(ce); - if (is_null_sha1(ce->sha1)) { + if (is_null_oid(&ce->oid)) { static const char msg[] = "cache entry has null sha1: %s"; static int allow = -1; @@ -2075,6 +2248,8 @@ static int do_write_index(struct index_state *istate, int newfd, warning(msg, ce->name); else return error(msg, ce->name); + + drop_cache_tree = 1; } if (ce_write_entry(&c, newfd, ce, previous_name) < 0) return -1; @@ -2093,7 +2268,7 @@ static int do_write_index(struct index_state *istate, int newfd, if (err) return -1; } - if (!strip_extensions && istate->cache_tree) { + if (!strip_extensions && !drop_cache_tree && istate->cache_tree) { struct strbuf sb = STRBUF_INIT; cache_tree_write(&sb, istate->cache_tree); @@ -2126,7 +2301,11 @@ static int do_write_index(struct index_state *istate, int newfd, return -1; } - if (ce_flush(&c, newfd, istate->sha1) || fstat(newfd, &st)) + if (ce_flush(&c, newfd, istate->sha1)) + return -1; + if (close_tempfile(tempfile)) + return error(_("could not close '%s'"), tempfile->filename.buf); + if (stat(tempfile->filename.buf, &st)) return -1; istate->timestamp.sec = (unsigned int)st.st_mtime; istate->timestamp.nsec = ST_MTIME_NSEC(st); @@ -2149,7 +2328,7 @@ static int commit_locked_index(struct lock_file *lk) static int do_write_locked_index(struct index_state *istate, struct lock_file *lock, unsigned flags) { - int ret = do_write_index(istate, get_lock_file_fd(lock), 0); + int ret = do_write_index(istate, &lock->tempfile, 0); if (ret) return ret; assert((flags & (COMMIT_LOCK | CLOSE_LOCK)) != @@ -2173,6 +2352,65 @@ static int write_split_index(struct index_state *istate, return ret; } +static const char *shared_index_expire = "2.weeks.ago"; + +static unsigned long get_shared_index_expire_date(void) +{ + static unsigned long shared_index_expire_date; + static int shared_index_expire_date_prepared; + + if (!shared_index_expire_date_prepared) { + git_config_get_expiry("splitindex.sharedindexexpire", + &shared_index_expire); + shared_index_expire_date = approxidate(shared_index_expire); + shared_index_expire_date_prepared = 1; + } + + return shared_index_expire_date; +} + +static int should_delete_shared_index(const char *shared_index_path) +{ + struct stat st; + unsigned long expiration; + + /* Check timestamp */ + expiration = get_shared_index_expire_date(); + if (!expiration) + return 0; + if (stat(shared_index_path, &st)) + return error_errno(_("could not stat '%s'"), shared_index_path); + if (st.st_mtime > expiration) + return 0; + + return 1; +} + +static int clean_shared_index_files(const char *current_hex) +{ + struct dirent *de; + DIR *dir = opendir(get_git_dir()); + + if (!dir) + return error_errno(_("unable to open git dir: %s"), get_git_dir()); + + while ((de = readdir(dir)) != NULL) { + const char *sha1_hex; + const char *shared_index_path; + if (!skip_prefix(de->d_name, "sharedindex.", &sha1_hex)) + continue; + if (!strcmp(sha1_hex, current_hex)) + continue; + shared_index_path = git_path("%s", de->d_name); + if (should_delete_shared_index(shared_index_path) > 0 && + unlink(shared_index_path)) + warning_errno(_("unable to unlink: %s"), shared_index_path); + } + closedir(dir); + + return 0; +} + static struct tempfile temporary_sharedindex; static int write_shared_index(struct index_state *istate, @@ -2187,21 +2425,63 @@ static int write_shared_index(struct index_state *istate, return do_write_locked_index(istate, lock, flags); } move_cache_to_base_index(istate); - ret = do_write_index(si->base, fd, 1); + ret = do_write_index(si->base, &temporary_sharedindex, 1); + if (ret) { + delete_tempfile(&temporary_sharedindex); + return ret; + } + ret = adjust_shared_perm(get_tempfile_path(&temporary_sharedindex)); if (ret) { + int save_errno = errno; + error("cannot fix permission bits on %s", get_tempfile_path(&temporary_sharedindex)); delete_tempfile(&temporary_sharedindex); + errno = save_errno; return ret; } ret = rename_tempfile(&temporary_sharedindex, git_path("sharedindex.%s", sha1_to_hex(si->base->sha1))); - if (!ret) + if (!ret) { hashcpy(si->base_sha1, si->base->sha1); + clean_shared_index_files(sha1_to_hex(si->base->sha1)); + } + return ret; } +static const int default_max_percent_split_change = 20; + +static int too_many_not_shared_entries(struct index_state *istate) +{ + int i, not_shared = 0; + int max_split = git_config_get_max_percent_split_change(); + + switch (max_split) { + case -1: + /* not or badly configured: use the default value */ + max_split = default_max_percent_split_change; + break; + case 0: + return 1; /* 0% means always write a new shared index */ + case 100: + return 0; /* 100% means never write a new shared index */ + default: + break; /* just use the configured value */ + } + + /* Count not shared entries */ + for (i = 0; i < istate->cache_nr; i++) { + struct cache_entry *ce = istate->cache[i]; + if (!ce->index) + not_shared++; + } + + return (int64_t)istate->cache_nr * max_split < (int64_t)not_shared * 100; +} + int write_locked_index(struct index_state *istate, struct lock_file *lock, unsigned flags) { + int new_shared_index, ret; struct split_index *si = istate->split_index; if (!si || alternate_index_output || @@ -2216,13 +2496,24 @@ int write_locked_index(struct index_state *istate, struct lock_file *lock, if ((v & 15) < 6) istate->cache_changed |= SPLIT_INDEX_ORDERED; } - if (istate->cache_changed & SPLIT_INDEX_ORDERED) { - int ret = write_shared_index(istate, lock, flags); + if (too_many_not_shared_entries(istate)) + istate->cache_changed |= SPLIT_INDEX_ORDERED; + + new_shared_index = istate->cache_changed & SPLIT_INDEX_ORDERED; + + if (new_shared_index) { + ret = write_shared_index(istate, lock, flags); if (ret) return ret; } - return write_split_index(istate, lock, flags); + ret = write_split_index(istate, lock, flags); + + /* Freshen the shared index only if the split-index was written */ + if (!ret && !new_shared_index) + freshen_shared_index(sha1_to_hex(si->base_sha1), 1); + + return ret; } /* @@ -2288,7 +2579,8 @@ int index_name_is_other(const struct index_state *istate, const char *name, return 1; } -void *read_blob_data_from_index(struct index_state *istate, const char *path, unsigned long *size) +void *read_blob_data_from_index(const struct index_state *istate, + const char *path, unsigned long *size) { int pos, len; unsigned long sz; @@ -2312,7 +2604,7 @@ void *read_blob_data_from_index(struct index_state *istate, const char *path, un } if (pos < 0) return NULL; - data = read_sha1_file(istate->cache[pos]->sha1, &type, &sz); + data = read_sha1_file(istate->cache[pos]->oid.hash, &type, &sz); if (!data || type != OBJ_BLOB) { free(data); return NULL; @@ -2324,8 +2616,7 @@ void *read_blob_data_from_index(struct index_state *istate, const char *path, un void stat_validity_clear(struct stat_validity *sv) { - free(sv->sd); - sv->sd = NULL; + FREE_AND_NULL(sv->sd); } int stat_validity_check(struct stat_validity *sv, const char *path) @@ -2351,3 +2642,9 @@ void stat_validity_update(struct stat_validity *sv, int fd) fill_stat_data(sv->sd, &st); } } + +void move_index_extensions(struct index_state *dst, struct index_state *src) +{ + dst->untracked = src->untracked; + src->untracked = NULL; +} |