[Gnash-dev] Gnash memory allocation statistics

[Albert Lee]

Hi,

I probed malloc calls in Gnash on a whim and have some surprising (to me)
results.
This is a typical distribution of allocation sizes while running TeddyMark
(which runs slightly faster with Mozilla's jemalloc than ptmalloc version
2):

           value  ------------- Distribution ------------- count    
               0 |                                         0        
               1 |                                         41       
               2 |                                         1        
               4 |                                         68       
               8 |@@@                                      2259     
              16 |@@@@@@@@@@@@@@@                          11378    
              32 |@                                        893      
              64 |@@@                                      2703     
             128 |@@                                       1431     
             256 |@@@@@@                                   4369     
             512 |@@                                       1168     
            1024 |@@@@                                     3006     
            2048 |@@                                       1860     
            4096 |@                                        1036     
            8192 |                                         0        
           16384 |                                         0        
           32768 |                                         0        
           65536 |@                                        830      
          131072 |                                         3        
          262144 |                                         0  

The main culprit for 16-byte allocations seems to be:
CPU     ID                    FUNCTION:NAME
  0  69953                     malloc:entry 
              libc.so.1`malloc
              libCrun.so.1`void*operator new(unsigned)+0x38
              libgnashcore-0.8.6.so`void
gnash::DisplayObject::queueEvent(const gnash::event_id&,int)+0x35
              libgnashcore-0.8.6.so`void gnash::MovieClip::advance()+0xfc
              libgnashcore-0.8.6.so`void
gnash::movie_root::advanceLiveChar(boost::intrusive_ptr<gnash::DisplayObject>)+0x72
              libgnashcore-0.8.6.so`__type_1
std::for_each<std::_List_iterator<gnash::DisplayObject*,std::_Nonconst_traits<gnash::DisplayObject*>
>,boost::_bi::bind_t<void,void(*)(boost::intrusive_ptr<gnash::DisplayObject>),boost::_bi::list1<boost::arg<1>
> > >(__type_0,__type_0,__type_1)+0x41
              libgnashcore-0.8.6.so`void
gnash::movie_root::advanceLiveChars()+0x61
              libgnashcore-0.8.6.so`void
gnash::movie_root::advanceMovie()+0x2c
              libgnashcore-0.8.6.so`bool gnash::movie_root::advance()+0x68
              gtk-gnash`bool gnash::Gui::advanceMovie()+0x3a
              libglib-2.0.so.0.2200.2`g_timeout_dispatch+0x23
              libglib-2.0.so.0.2200.2`g_main_context_dispatch+0x262
              libglib-2.0.so.0.2200.2`g_main_context_iterate+0x483
              libglib-2.0.so.0.2200.2`g_main_loop_run+0x1dd
              libgtk-x11-2.0.so.0.1800.3`gtk_main+0xb7
              gtk-gnash`bool gnash::GtkGui::run()+0x1c
              gtk-gnash`int gnash::Player::run(int,char**,const
std::string &,const std::string &)+0x1656
              gtk-gnash`main+0xac
              gtk-gnash`_start+0x7d

I get a similar preponderance of 16-byte allocs with other Flash movies.
Maybe QueuedEvent objects could be created by a different method?

There's probably useful tests I can also run. Suggestions welcome.

-Albert