Speed up rebuilding the loaded feature index

jeremyevans · jeremyevans · commit 61b974629e35 · 2023-04-12T12:33:16.000-07:00
Rebuilding the loaded feature index slowed down with the bug fix for #17885 in 79a4484. The slowdown was extreme if realpath emulation was used, but even when not emulated, it could be about 10x slower. This adds loaded_features_realpath_map to rb_vm_struct. This is a hidden hash mapping loaded feature paths to realpaths. When rebuilding the loaded feature index, look at this hash to get cached realpath values, and skip calling rb_check_realpath if a cached value is found. Fixes [Bug #19246]
diff --git a/load.c b/load.c
@@ -163,6 +163,12 @@ get_loaded_features_realpaths(rb_vm_t *vm)
     return vm->loaded_features_realpaths;
 }
 
+static VALUE
+get_loaded_features_realpath_map(rb_vm_t *vm)
+{
+    return vm->loaded_features_realpath_map;
+}
+
 static VALUE
 get_LOADED_FEATURES(ID _x, VALUE *_y)
 {
@@ -361,7 +367,10 @@ get_loaded_features_index(rb_vm_t *vm)
         st_foreach(vm->loaded_features_index, loaded_features_index_clear_i, 0);
 
         VALUE realpaths = vm->loaded_features_realpaths;
+        VALUE realpath_map = vm->loaded_features_realpath_map;
+        VALUE previous_realpath_map = rb_hash_dup(realpath_map);
         rb_hash_clear(realpaths);
+        rb_hash_clear(realpath_map);
         features = vm->loaded_features;
         for (i = 0; i < RARRAY_LEN(features); i++) {
             VALUE entry, as_str;
@@ -378,9 +387,14 @@ get_loaded_features_index(rb_vm_t *vm)
         long j = RARRAY_LEN(features);
         for (i = 0; i < j; i++) {
             VALUE as_str = rb_ary_entry(features, i);
-            VALUE realpath = rb_check_realpath(Qnil, as_str, NULL);
-            if (NIL_P(realpath)) realpath = as_str;
-            rb_hash_aset(realpaths, rb_fstring(realpath), Qtrue);
+            VALUE realpath = rb_hash_aref(previous_realpath_map, as_str);
+            if (NIL_P(realpath)) {
+                realpath = rb_check_realpath(Qnil, as_str, NULL);
+                if (NIL_P(realpath)) realpath = as_str;
+                realpath = rb_fstring(realpath);
+            }
+            rb_hash_aset(realpaths, realpath, Qtrue);
+            rb_hash_aset(realpath_map, as_str, realpath);
         }
     }
     return vm->loaded_features_index;
@@ -1161,6 +1175,7 @@ require_internal(rb_execution_context_t *ec, VALUE fname, int exception, bool wa
     volatile VALUE saved_path;
     volatile VALUE realpath = 0;
     VALUE realpaths = get_loaded_features_realpaths(th->vm);
+    VALUE realpath_map = get_loaded_features_realpath_map(th->vm);
     volatile bool reset_ext_config = false;
     struct rb_ext_config prev_ext_config;
 
@@ -1252,7 +1267,9 @@ require_internal(rb_execution_context_t *ec, VALUE fname, int exception, bool wa
         rb_provide_feature(th2->vm, path);
         VALUE real = realpath;
         if (real) {
-            rb_hash_aset(realpaths, rb_fstring(real), Qtrue);
+            real = rb_fstring(real);
+            rb_hash_aset(realpaths, real, Qtrue);
+            rb_hash_aset(realpath_map, path, real);
         }
     }
     ec->errinfo = saved.errinfo;
@@ -1473,6 +1490,8 @@ Init_load(void)
     vm->loaded_features_index = st_init_numtable();
     vm->loaded_features_realpaths = rb_hash_new();
     rb_obj_hide(vm->loaded_features_realpaths);
+    vm->loaded_features_realpath_map = rb_hash_new();
+    rb_obj_hide(vm->loaded_features_realpath_map);
 
     rb_define_global_function("load", rb_f_load, -1);
     rb_define_global_function("require", rb_f_require, 1);
diff --git a/vm.c b/vm.c
@@ -2699,6 +2699,7 @@ rb_vm_update_references(void *ptr)
         vm->loaded_features = rb_gc_location(vm->loaded_features);
         vm->loaded_features_snapshot = rb_gc_location(vm->loaded_features_snapshot);
         vm->loaded_features_realpaths = rb_gc_location(vm->loaded_features_realpaths);
+        vm->loaded_features_realpath_map = rb_gc_location(vm->loaded_features_realpath_map);
         vm->top_self = rb_gc_location(vm->top_self);
         vm->orig_progname = rb_gc_location(vm->orig_progname);
 
@@ -2790,6 +2791,7 @@ rb_vm_mark(void *ptr)
         rb_gc_mark_movable(vm->loaded_features);
         rb_gc_mark_movable(vm->loaded_features_snapshot);
         rb_gc_mark_movable(vm->loaded_features_realpaths);
+        rb_gc_mark_movable(vm->loaded_features_realpath_map);
         rb_gc_mark_movable(vm->top_self);
         rb_gc_mark_movable(vm->orig_progname);
         RUBY_MARK_MOVABLE_UNLESS_NULL(vm->coverages);
diff --git a/vm_core.h b/vm_core.h
@@ -676,6 +676,7 @@ typedef struct rb_vm_struct {
     VALUE loaded_features;
     VALUE loaded_features_snapshot;
     VALUE loaded_features_realpaths;
+    VALUE loaded_features_realpath_map;
     struct st_table *loaded_features_index;
     struct st_table *loading_table;
 #if EXTSTATIC
