On Jul 6, 2011, at 2:48 AM, KOSAKI Motohiro wrote:

>> Here are the average differences from 1.9.2-p180:
>> 
>> stock ruby trunk:       6.953
>> --disable-gems: -12.919
>> rubygems patches:       -9.959
>> 
>> Is the slowdown of 2.96 seconds between --disable-gems and my fixes across all benchmarks acceptable?
>> 
>> Should I look for additional improvements?
> 
> Great!
> 
> Can you please tell us a result of vm3_gc and io_file_read? They have
> most big degressions and I'm worry about it.

io_file_read

--disable-gems:	3.978	3.768	4.007
rubygems patch:	3.944	3.960	4.072

vm3_gc

--disable-gems:	1.166	1.157	1.154
rubygems patch:	1.616	1.630	1.632

I poked at setting RUBY_HEAP_MIN_SLOTS=40000 when starting up ruby with rubygems enabled.  This allowed ruby to start up without running the garbage collector and didn't affect the resident size of the process much.

I didn't run a full `make benchmark` to see if it made any larger difference.

> Anyway, personally I think it is acceptable and no more improvemnt
> because usually people only compare 1.9.2 and 1.9.3 and don't compare individual patches in 1.9.3 changes.