diff --git a/cache.h b/cache.h index a50a61a197..35d58f83e1 100644 --- a/cache.h +++ b/cache.h @@ -173,6 +173,9 @@ struct cache_entry { unsigned int ce_flags; unsigned int ce_namelen; unsigned int index; /* for link extension */ + unsigned int precompute_hash_state; + unsigned int precompute_hash_name; + unsigned int precompute_hash_dir; struct object_id oid; char name[FLEX_ARRAY]; /* more */ }; @@ -229,6 +232,19 @@ struct cache_entry { #error "CE_EXTENDED_FLAGS out of range" #endif +/* + * Bit set if preload-index precomputed the hash value(s) + * for this cache-entry. + */ +#define CE_PRECOMPUTE_HASH_STATE__SET (1 << 0) +/* + * Bit set if precompute-index also precomputed the hash value + * for the parent directory. + */ +#define CE_PRECOMPUTE_HASH_STATE__DIR (1 << 1) + +void precompute_istate_hashes(struct cache_entry *ce); + /* Forward structure decls */ struct pathspec; struct child_process; diff --git a/name-hash.c b/name-hash.c index 860b8dd0c7..7a220187ad 100644 --- a/name-hash.c +++ b/name-hash.c @@ -50,6 +50,17 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate, */ struct dir_entry *dir; unsigned int hash; + int use_precomputed_dir_hash = 0; + + if (ce->precompute_hash_state & CE_PRECOMPUTE_HASH_STATE__SET) { + if (!(ce->precompute_hash_state & CE_PRECOMPUTE_HASH_STATE__DIR)) + return NULL; /* item does not have a parent directory */ + if (namelen == ce_namelen(ce)) { + /* dir hash only valid for outer-most call (not recursive ones) */ + use_precomputed_dir_hash = 1; + hash = ce->precompute_hash_dir; + } + } /* get length of parent directory */ while (namelen > 0 && !is_dir_sep(ce->name[namelen - 1])) @@ -59,7 +70,8 @@ static struct dir_entry *hash_dir_entry(struct index_state *istate, namelen--; /* lookup existing entry for that directory */ - hash = memihash(ce->name, namelen); + if (!use_precomputed_dir_hash) + hash = memihash(ce->name, namelen); dir = find_dir_entry__hash(istate, ce->name, namelen, hash); if (!dir) { /* not found, create it and add to hash table */ @@ -99,10 +111,18 @@ static void remove_dir_entry(struct index_state *istate, struct cache_entry *ce) static void hash_index_entry(struct index_state *istate, struct cache_entry *ce) { + unsigned int h; + if (ce->ce_flags & CE_HASHED) return; ce->ce_flags |= CE_HASHED; - hashmap_entry_init(ce, memihash(ce->name, ce_namelen(ce))); + + if (ce->precompute_hash_state & CE_PRECOMPUTE_HASH_STATE__SET) + h = ce->precompute_hash_name; + else + h = memihash(ce->name, ce_namelen(ce)); + + hashmap_entry_init(ce, h); hashmap_add(&istate->name_hash, ce); if (ignore_case) @@ -244,3 +264,45 @@ void free_name_hash(struct index_state *istate) hashmap_free(&istate->name_hash, 0); hashmap_free(&istate->dir_hash, 1); } + +/* + * Precompute the hash values for this cache_entry + * for use in the istate.name_hash and istate.dir_hash. + * + * If the item is in the root directory, just compute the + * hash value (for istate.name_hash) on the full path. + * + * If the item is in a subdirectory, first compute the + * hash value for the immediate parent directory (for + * istate.dir_hash) and then the hash value for the full + * path by continuing the computation. + * + * Note that these hashes will be used by + * wt_status_collect_untracked() as it scans the worktree + * and maps observed paths back to the index (optionally + * ignoring case). Therefore, we probably only *NEED* to + * precompute this for non-skip-worktree items (since + * status should not observe skipped items), but because + * lazy_init_name_hash() hashes everything, we force it + * here. + */ +void precompute_istate_hashes(struct cache_entry *ce) +{ + int namelen = ce_namelen(ce); + + while (namelen > 0 && !is_dir_sep(ce->name[namelen - 1])) + namelen--; + + if (namelen <= 0) { + ce->precompute_hash_name = memihash(ce->name, ce_namelen(ce)); + ce->precompute_hash_state = CE_PRECOMPUTE_HASH_STATE__SET; + } else { + namelen--; + ce->precompute_hash_dir = memihash(ce->name, namelen); + ce->precompute_hash_name = memihash_cont( + ce->precompute_hash_dir, &ce->name[namelen], + ce_namelen(ce) - namelen); + ce->precompute_hash_state = + CE_PRECOMPUTE_HASH_STATE__SET | CE_PRECOMPUTE_HASH_STATE__DIR; + } +} diff --git a/preload-index.c b/preload-index.c index c1fe3a3ef9..602737f9d0 100644 --- a/preload-index.c +++ b/preload-index.c @@ -47,6 +47,8 @@ static void *preload_thread(void *_data) struct cache_entry *ce = *cep++; struct stat st; + precompute_istate_hashes(ce); + if (ce_stage(ce)) continue; if (S_ISGITLINK(ce->ce_mode)) diff --git a/read-cache.c b/read-cache.c index db5d910642..7fbe993dd7 100644 --- a/read-cache.c +++ b/read-cache.c @@ -73,6 +73,7 @@ void rename_index_entry_at(struct index_state *istate, int nr, const char *new_n copy_cache_entry(new, old); new->ce_flags &= ~CE_HASHED; new->ce_namelen = namelen; + new->precompute_hash_state = 0; new->index = 0; memcpy(new->name, new_name, namelen + 1); @@ -622,6 +623,7 @@ static struct cache_entry *create_alias_ce(struct index_state *istate, new = xcalloc(1, cache_entry_size(len)); memcpy(new->name, alias->name, len); copy_cache_entry(new, ce); + new->precompute_hash_state = 0; save_or_free_index_entry(istate, ce); return new; } @@ -1457,6 +1459,7 @@ static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *on ce->ce_stat_data.sd_size = get_be32(&ondisk->size); ce->ce_flags = flags & ~CE_NAMEMASK; ce->ce_namelen = len; + ce->precompute_hash_state = 0; ce->index = 0; hashcpy(ce->oid.hash, ondisk->sha1); memcpy(ce->name, name, len);