* gc.c, parse.y: support generational Symbol relatetd marking.

  Each symbols has String objects respectively to represent
  Symbols.
  These objects are marked only when:
* full marking
* new symbols are added
  This hack reduce symbols (related strings) marking time.
  For example, on my Linux environment, the following code
  "20_000_000.times{''}"
  with 40k symbols (similar symbol number on Rails 3.2.14 app,
  @jugyo tells me) boosts, from 7.3sec to 4.2sec.



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@43255 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

4 files changed, 29 insertions, 6 deletions

diff --git a/ChangeLog b/ChangeLog
index 40222351df..922d3f4081 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,19 @@
+Fri Oct 11 20:35:59 2013  Koichi Sasada  <ko1@atdot.net>
+
+	* gc.c, parse.y: support generational Symbol relatetd marking.
+	  Each symbols has String objects respectively to represent
+	  Symbols.
+	  These objects are marked only when:
+	  * full marking
+	  * new symbols are added
+	  This hack reduce symbols (related strings) marking time.
+	  For example, on my Linux environment, the following code
+	    "20_000_000.times{''}"
+	  with 40k symbols (similar symbol number on Rails 3.2.14 app,
+	  @jugyo tells me) boosts, from 7.3sec to 4.2sec.
+
+`	* internal.h: change prototype of rb_gc_mark_symbols().
+
 Fri Oct 11 19:27:22 2013  Akinori MUSHA  <knu@iDaemons.org>
 
 	* misc/ruby-electric.el: Import ruby-electric.el 2.0.1 which fixes
diff --git a/gc.c b/gc.c
index fae65e1d78..a696fb2ef0 100644
--- a/gc.c
+++ b/gc.c
@@ -3580,7 +3580,7 @@ gc_marks_body(rb_objspace_t *objspace, int minor_gc)
     mark_current_machine_context(objspace, th);
 
     MARK_CHECKPOINT;
-    rb_gc_mark_symbols();
+    rb_gc_mark_symbols(minor_gc == 0);
 
     MARK_CHECKPOINT;
     rb_gc_mark_encodings();
diff --git a/internal.h b/internal.h
index 7d9a8aa6c0..2260fe9944 100644
--- a/internal.h
+++ b/internal.h
@@ -578,7 +578,7 @@ int rb_is_local_name(VALUE name);
 int rb_is_method_name(VALUE name);
 int rb_is_junk_name(VALUE name);
 void rb_gc_mark_parser(void);
-void rb_gc_mark_symbols(void);
+void rb_gc_mark_symbols(int full_marking);
 
 /* proc.c */
 VALUE rb_proc_location(VALUE self);
diff --git a/parse.y b/parse.y
index 5ae81267e3..47ea9a3d07 100644
--- a/parse.y
+++ b/parse.y
@@ -10183,6 +10183,7 @@ static struct symbols {
     st_table *id_ivar2;
 #endif
     VALUE op_sym[tLAST_OP_ID];
+    int minor_marked;
 } global_symbols = {tLAST_TOKEN};
 
 static const struct st_hash_type symhash = {
@@ -10237,11 +10238,14 @@ Init_sym(void)
 }
 
 void
-rb_gc_mark_symbols(void)
+rb_gc_mark_symbols(int full_marking)
 {
-    rb_mark_tbl(global_symbols.id_str);
-    rb_gc_mark_locations(global_symbols.op_sym,
-			 global_symbols.op_sym + numberof(global_symbols.op_sym));
+    if (full_marking || global_symbols.minor_marked == 0) {
+	rb_mark_tbl(global_symbols.id_str);
+	rb_gc_mark_locations(global_symbols.op_sym,
+			     global_symbols.op_sym + numberof(global_symbols.op_sym));
+	global_symbols.minor_marked = 1;
+    }
 }
 #endif /* !RIPPER */
 
@@ -10425,6 +10429,7 @@ register_symid_str(ID id, VALUE str)
 
     st_add_direct(global_symbols.sym_id, (st_data_t)str, id);
     st_add_direct(global_symbols.id_str, id, (st_data_t)str);
+    global_symbols.minor_marked = 0;
     return id;
 }
 
@@ -10628,6 +10633,7 @@ rb_id2str(ID id)
 		str = rb_usascii_str_new(name, 1);
 		OBJ_FREEZE(str);
 		global_symbols.op_sym[i] = str;
+		global_symbols.minor_marked = 0;
 	    }
 	    return str;
 	}
@@ -10638,6 +10644,7 @@ rb_id2str(ID id)
 		    str = rb_usascii_str_new2(op_tbl[i].name);
 		    OBJ_FREEZE(str);
 		    global_symbols.op_sym[i] = str;
+		    global_symbols.minor_marked = 0;
 		}
 		return str;
 	    }