BlenRead: Add GHash-based search for already read linked IDs.

Ths commit adds a new `IDNameLibMap` to `Main`, used during file reading
to quickly find already read linked IDs.

Without that, search would use string-based search over list of linked
data, which becomes extremely slow and inneficient in cases where a lot
of IDs are linked from a same library. See also {T89194}.

Extrem-usecase reported in T89194 is now about 4 times faster in linked
data reading (about 2 times faster for the whole .blend file loading).

More normal cases (like Sprites studio production files) have barely
measurable speed improvements, a few percents at best.

NOTE: `main_idmap` API was extended to support insertion and removal of
IDs from the mapping, avoids having to re-create the whole thing several
time during libraries expansion in readcode.

Differential Revision: https://developer.blender.org/D11757

source/blender/blenkernel/BKE_main.h

@@ -48,6 +48,7 @@ struct BLI_mempool;
 struct BlendThumbnail;
 struct GHash;
 struct GSet;
+struct IDNameLib_Map;
 struct ImBuf;
 struct Library;
 struct MainLock;
@@ -191,6 +192,9 @@ typedef struct Main {
    */
   struct MainIDRelations *relations;
 
+  /* IDMap of IDs. Currently used when reading (expanding) libraries. */
+  struct IDNameLib_Map *id_map;
+
   struct MainLock *lock;
 } Main;
 

source/blender/blenkernel/BKE_main_idmap.h

@@ -50,8 +50,13 @@ struct IDNameLib_Map *BKE_main_idmap_create(struct Main *bmain,
                                             const int idmap_types) ATTR_WARN_UNUSED_RESULT
     ATTR_NONNULL(1);
 void BKE_main_idmap_destroy(struct IDNameLib_Map *id_map) ATTR_NONNULL();
+
+void BKE_main_idmap_insert_id(struct IDNameLib_Map *id_map, struct ID *id) ATTR_NONNULL();
+void BKE_main_idmap_remove_id(struct IDNameLib_Map *id_map, struct ID *id) ATTR_NONNULL();
+
 struct Main *BKE_main_idmap_main_get(struct IDNameLib_Map *id_map) ATTR_WARN_UNUSED_RESULT
     ATTR_NONNULL();
+
 struct ID *BKE_main_idmap_lookup_name(struct IDNameLib_Map *id_map,
                                       short id_type,
                                       const char *name,

source/blender/blenkernel/intern/main.c

@@ -38,6 +38,7 @@
 #include "BKE_lib_id.h"
 #include "BKE_lib_query.h"
 #include "BKE_main.h"
+#include "BKE_main_idmap.h"
 
 #include "IMB_imbuf.h"
 #include "IMB_imbuf_types.h"
@@ -194,6 +195,10 @@ void BKE_main_free(Main *mainvar)
     BKE_main_relations_free(mainvar);
   }
 
+  if (mainvar->id_map) {
+    BKE_main_idmap_destroy(mainvar->id_map);
+  }
+
   BLI_spin_end((SpinLock *)mainvar->lock);
   MEM_freeN(mainvar->lock);
   MEM_freeN(mainvar);

source/blender/blenkernel/intern/main_idmap.c

@@ -21,6 +21,7 @@
 
 #include "BLI_ghash.h"
 #include "BLI_listbase.h"
+#include "BLI_mempool.h"
 #include "BLI_utildefines.h"
 
 #include "DNA_ID.h"
@@ -58,8 +59,6 @@ struct IDNameLib_Key {
 struct IDNameLib_TypeMap {
   GHash *map;
   short id_type;
-  /* only for storage of keys in the ghash, avoid many single allocs */
-  struct IDNameLib_Key *keys;
 };
 
 /**
@@ -71,6 +70,9 @@ struct IDNameLib_Map {
   struct Main *bmain;
   struct GSet *valid_id_pointers;
   int idmap_types;
+
+  /* For storage of keys for the TypeMap ghash, avoids many single allocs. */
+  BLI_mempool *type_maps_keys_pool;
 };
 
 static struct IDNameLib_TypeMap *main_idmap_from_idcode(struct IDNameLib_Map *id_map,
@@ -115,6 +117,7 @@ struct IDNameLib_Map *BKE_main_idmap_create(struct Main *bmain,
     BLI_assert(type_map->id_type != 0);
   }
   BLI_assert(index == INDEX_ID_MAX);
+  id_map->type_maps_keys_pool = NULL;
 
   if (idmap_types & MAIN_IDMAP_TYPE_UUID) {
     ID *id;
@@ -148,6 +151,60 @@ struct IDNameLib_Map *BKE_main_idmap_create(struct Main *bmain,
   return id_map;
 }
 
+void BKE_main_idmap_insert_id(struct IDNameLib_Map *id_map, ID *id)
+{
+  if (id_map->idmap_types & MAIN_IDMAP_TYPE_NAME) {
+    const short id_type = GS(id->name);
+    struct IDNameLib_TypeMap *type_map = main_idmap_from_idcode(id_map, id_type);
+
+    /* No need to do anything if map has not been lazyly created yet. */
+    if (LIKELY(type_map != NULL) && type_map->map != NULL) {
+      BLI_assert(id_map->type_maps_keys_pool != NULL);
+
+      struct IDNameLib_Key *key = BLI_mempool_alloc(id_map->type_maps_keys_pool);
+      key->name = id->name + 2;
+      key->lib = id->lib;
+      BLI_ghash_insert(type_map->map, key, id);
+    }
+  }
+
+  if (id_map->idmap_types & MAIN_IDMAP_TYPE_UUID) {
+    BLI_assert(id_map->uuid_map != NULL);
+    BLI_assert(id->session_uuid != MAIN_ID_SESSION_UUID_UNSET);
+    void **id_ptr_v;
+    const bool existing_key = BLI_ghash_ensure_p(
+        id_map->uuid_map, POINTER_FROM_UINT(id->session_uuid), &id_ptr_v);
+    BLI_assert(existing_key == false);
+    UNUSED_VARS_NDEBUG(existing_key);
+
+    *id_ptr_v = id;
+  }
+}
+
+void BKE_main_idmap_remove_id(struct IDNameLib_Map *id_map, ID *id)
+{
+  if (id_map->idmap_types & MAIN_IDMAP_TYPE_NAME) {
+    const short id_type = GS(id->name);
+    struct IDNameLib_TypeMap *type_map = main_idmap_from_idcode(id_map, id_type);
+
+    /* No need to do anything if map has not been lazyly created yet. */
+    if (LIKELY(type_map != NULL) && type_map->map != NULL) {
+      BLI_assert(id_map->type_maps_keys_pool != NULL);
+
+      /* NOTE: We cannot free the key from the MemPool here, would need new API from GHash to also
+       * retrieve key pointer. Not a big deal for now */
+      BLI_ghash_remove(type_map->map, &(struct IDNameLib_Key){id->name + 2, id->lib}, NULL, NULL);
+    }
+  }
+
+  if (id_map->idmap_types & MAIN_IDMAP_TYPE_UUID) {
+    BLI_assert(id_map->uuid_map != NULL);
+    BLI_assert(id->session_uuid != MAIN_ID_SESSION_UUID_UNSET);
+
+    BLI_ghash_remove(id_map->uuid_map, POINTER_FROM_UINT(id->session_uuid), NULL, NULL);
+  }
+}
+
 struct Main *BKE_main_idmap_main_get(struct IDNameLib_Map *id_map)
 {
   return id_map->bmain;
@@ -181,20 +238,17 @@ ID *BKE_main_idmap_lookup_name(struct IDNameLib_Map *id_map,
     return NULL;
   }
 
-  /* lazy init */
+  /* Lazy init. */
   if (type_map->map == NULL) {
-    ListBase *lb = which_libbase(id_map->bmain, id_type);
-    const int lb_len = BLI_listbase_count(lb);
-    if (lb_len == 0) {
-      return NULL;
+    if (id_map->type_maps_keys_pool == NULL) {
+      id_map->type_maps_keys_pool = BLI_mempool_create(
+          sizeof(struct IDNameLib_Key), 1024, 1024, BLI_MEMPOOL_NOP);
     }
-    type_map->map = BLI_ghash_new_ex(idkey_hash, idkey_cmp, __func__, lb_len);
-    type_map->keys = MEM_mallocN(sizeof(struct IDNameLib_Key) * lb_len, __func__);
 
-    GHash *map = type_map->map;
-    struct IDNameLib_Key *key = type_map->keys;
-
-    for (ID *id = lb->first; id; id = id->next, key++) {
+    GHash *map = type_map->map = BLI_ghash_new(idkey_hash, idkey_cmp, __func__);
+    ListBase *lb = which_libbase(id_map->bmain, id_type);
+    for (ID *id = lb->first; id; id = id->next) {
+      struct IDNameLib_Key *key = BLI_mempool_alloc(id_map->type_maps_keys_pool);
       key->name = id->name + 2;
       key->lib = id->lib;
       BLI_ghash_insert(map, key, id);
@@ -235,14 +289,19 @@ void BKE_main_idmap_destroy(struct IDNameLib_Map *id_map)
       if (type_map->map) {
         BLI_ghash_free(type_map->map, NULL, NULL);
         type_map->map = NULL;
-        MEM_freeN(type_map->keys);
       }
     }
+    if (id_map->type_maps_keys_pool != NULL) {
+      BLI_mempool_destroy(id_map->type_maps_keys_pool);
+      id_map->type_maps_keys_pool = NULL;
+    }
   }
   if (id_map->idmap_types & MAIN_IDMAP_TYPE_UUID) {
     BLI_ghash_free(id_map->uuid_map, NULL, NULL);
   }
 
+  BLI_assert(id_map->type_maps_keys_pool == NULL);
+
   if (id_map->valid_id_pointers != NULL) {
     BLI_gset_free(id_map->valid_id_pointers, NULL);
   }

source/blender/blenloader/intern/readfile.c

@@ -464,6 +464,13 @@ void blo_join_main(ListBase *mainlist)
   Main *tojoin, *mainl;
 
   mainl = mainlist->first;
+
+  if (mainl->id_map != NULL) {
+    /* Cannot keep this since we add some IDs from joined mains. */
+    BKE_main_idmap_destroy(mainl->id_map);
+    mainl->id_map = NULL;
+  }
+
   while ((tojoin = mainl->next)) {
     add_main_to_main(mainl, tojoin);
     BLI_remlink(mainlist, tojoin);
@@ -502,6 +509,12 @@ void blo_split_main(ListBase *mainlist, Main *main)
     return;
   }
 
+  if (main->id_map != NULL) {
+    /* Cannot keep this since we remove some IDs from given main. */
+    BKE_main_idmap_destroy(main->id_map);
+    main->id_map = NULL;
+  }
+
   /* (Library.temp_index -> Main), lookup table */
   const uint lib_main_array_len = BLI_listbase_count(&main->libraries);
   Main **lib_main_array = MEM_malloc_arrayN(lib_main_array_len, sizeof(*lib_main_array), __func__);
@@ -3209,6 +3222,10 @@ static ID *create_placeholder(Main *mainvar, const short idcode, const char *idn
   BLI_addtail(lb, ph_id);
   id_sort_by_name(lb, ph_id, NULL);
 
+  if (mainvar->id_map != NULL) {
+    BKE_main_idmap_insert_id(mainvar->id_map, ph_id);
+  }
+
   if ((tag & LIB_TAG_TEMP_MAIN) == 0) {
     BKE_lib_libblock_session_uuid_ensure(ph_id);
   }
@@ -3667,6 +3684,10 @@ static BHead *read_libblock(FileData *fd,
       if (r_id) {
         *r_id = id_old;
       }
+      if (main->id_map != NULL) {
+        BKE_main_idmap_insert_id(main->id_map, id_old);
+      }
+
       return blo_bhead_next(fd, bhead);
     }
   }
@@ -3725,6 +3746,11 @@ static BHead *read_libblock(FileData *fd,
     }
 
     direct_link_id(fd, main, id_tag, id, id_old);
+
+    if (main->id_map != NULL) {
+      BKE_main_idmap_insert_id(main->id_map, id);
+    }
+
     return blo_bhead_next(fd, bhead);
   }
 
@@ -3748,6 +3774,13 @@ static BHead *read_libblock(FileData *fd,
   else if (id_old) {
     /* For undo, store contents read into id at id_old. */
     read_libblock_undo_restore_at_old_address(fd, main, id, id_old);
+
+    if (main->id_map != NULL) {
+      BKE_main_idmap_insert_id(main->id_map, id_old);
+    }
+  }
+  else if (main->id_map != NULL) {
+    BKE_main_idmap_insert_id(main->id_map, id);
   }
 
   return bhead;
@@ -4299,6 +4332,8 @@ BlendFileData *blo_read_file_internal(FileData *fd, const char *filepath)
 
   fd->mainlist = NULL; /* Safety, this is local variable, shall not be used afterward. */
 
+  BLI_assert(bfd->main->id_map == NULL);
+
   return bfd;
 }
 
@@ -4443,9 +4478,16 @@ static BHead *find_bhead_from_idname(FileData *fd, const char *idname)
 
 static ID *is_yet_read(FileData *fd, Main *mainvar, BHead *bhead)
 {
+  if (mainvar->id_map == NULL) {
+    mainvar->id_map = BKE_main_idmap_create(mainvar, false, NULL, MAIN_IDMAP_TYPE_NAME);
+  }
+  BLI_assert(BKE_main_idmap_main_get(mainvar->id_map) == mainvar);
+
   const char *idname = blo_bhead_id_name(fd, bhead);
-  /* which_libbase can be NULL, intentionally not using idname+2 */
-  return BLI_findstring(which_libbase(mainvar, GS(idname)), idname, offsetof(ID, name));
+
+  ID *id = BKE_main_idmap_lookup_name(mainvar->id_map, GS(idname), idname + 2, mainvar->curlib);
+  BLI_assert(id == BLI_findstring(which_libbase(mainvar, GS(idname)), idname, offsetof(ID, name)));
+  return id;
 }
 
 /** \} */
@@ -5196,6 +5238,10 @@ static void library_link_end(Main *mainl,
   Main *mainvar;
   Library *curlib;
 
+  if (mainl->id_map == NULL) {
+    mainl->id_map = BKE_main_idmap_create(mainl, false, NULL, MAIN_IDMAP_TYPE_NAME);
+  }
+
   /* expander now is callback function */
   BLO_main_expander(expand_doit_library);
 
@@ -5401,6 +5447,9 @@ static void read_library_linked_ids(FileData *basefd,
       ID *id_next = id->next;
       if ((id->tag & LIB_TAG_ID_LINK_PLACEHOLDER) && !(id->flag & LIB_INDIRECT_WEAK_LINK)) {
         BLI_remlink(lbarray[a], id);
+        if (mainvar->id_map != NULL) {
+          BKE_main_idmap_remove_id(mainvar->id_map, id);
+        }
 
         /* When playing with lib renaming and such, you may end with cases where
          * you have more than one linked ID of the same data-block from same
@@ -5569,6 +5618,10 @@ static void read_libraries(FileData *basefd, ListBase *mainlist)
 
         if (fd) {
           do_it = true;
+
+          if (mainptr->id_map == NULL) {
+            mainptr->id_map = BKE_main_idmap_create(mainptr, false, NULL, MAIN_IDMAP_TYPE_NAME);
+          }
         }
 
         /* Read linked data-locks for each link placeholder, and replace