# Percentage of time spent in method dispatch?

**URL:** <https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399>\
**Category:** Ruby\
**Created:** [August 17, 2006, 11:06pm UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399 "2006-08-17T23:06:23Z")\
**Posts on this page:** 9\
**Page:** 1

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 17, 2006, 11:06pm UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/1 "2006-08-17T23:06:23Z")

</div>

I was wondering if anyone had taken a look at what % of time that ruby  
spends doing method dispatch?

I’ll eventually do the experiments myself, but I wanted to check with  
y’all to see if someone had already done some investigations. It would  
be an interesting experiment to see how much you can improve method  
dispatch performance by caching the reference to the method call  
target, and invalidating it when the call context changes.

Thanks,  
-John

> **[John Lam's Blog](https://www.iunknown.com/)**
>
> Since 1997

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 18, 2006, 12:12am UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/2 "2006-08-18T00:12:32Z")

</div>

On Aug 17, 2006, at 5:05 PM, John L. wrote:

> I’ll eventually do the experiments myself, but I wanted to check with  
> y’all to see if someone had already done some investigations. It would  
> be an interesting experiment to see how much you can improve method  
> dispatch performance by caching the reference to the method call  
> target, and invalidating it when the call context changes.

I’m not an internals expert, but I think the difficulty in optimizing  
Ruby  
method dispatch is that the result of a dispatch is not determined  
by the local context but instead is determined by the state of all  
the module objects searched during method dispatch:  
singleton class  
class and super classes  
included modules in all of the above

Gary W.

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 18, 2006, 4:49am UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/3 "2006-08-18T04:49:21Z")

</div>

I’d be interested in doing some experiments with DynamicMethods in the  
CLR to see what kind of performance gains can happen with method  
dispatch. And direct method dispatch in the CLR is _very_ fast, if we  
consider that each parameter is a boxed object reference (4 bytes) and  
the actuall call is a call indirect instruction. Dealing with closures  
is a bit more problematic though, and making that go fast could be  
difficult.

It’s also fairly straightforward to substitute one dynamic method for  
another one when a cache invalidation event occurs. It would be very  
interesting to study the existing implementation’s method cache to see  
what the triggers for cache invalidation look like …

Thanks for the input!  
-John

> **[John Lam's Blog](https://www.iunknown.com/)**
>
> Since 1997

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 18, 2006, 12:54am UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/4 "2006-08-18T00:54:36Z")

</div>

On Fri, Aug 18, 2006 at 06:05:12AM +0900, John L. wrote:

> I was wondering if anyone had taken a look at what % of time that ruby  
> spends doing method dispatch?
> 
> I’ll eventually do the experiments myself, but I wanted to check with  
> y’all to see if someone had already done some investigations. It would  
> be an interesting experiment to see how much you can improve method  
> dispatch performance by caching the reference to the method call  
> target, and invalidating it when the call context changes.

## The current implementation has a method cache whose hit rate is above 95% or so (don’t remember the exact figure; it’s not hard to reproduce anyway)

full method lookups are relatively rare.

Method dispatching is still fairly slow, though; I once measured that it  
took  
some ~200 instructions to run a CFUNC, and about half as much with YARV.  
Last time I read YARV’s sources, it didn’t have inline method caches  
(but it  
was caching constants, IIRC), but it’s been a while and they might have  
been  
implemented meanwhile.

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 18, 2006, 4:58am UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/5 "2006-08-18T04:58:23Z")

</div>

Mauricio F. wrote:

> The current implementation has a method cache whose hit rate is above 95% or  
> so (don’t remember the exact figure; it’s not hard to reproduce anyway) —  
> full method lookups are relatively rare.
> 
> Method dispatching is still fairly slow, though; I once measured that it took  
> some ~200 instructions to run a CFUNC, and about half as much with YARV.  
> Last time I read YARV’s sources, it didn’t have inline method caches (but it  
> was caching constants, IIRC), but it’s been a while and they might have been  
> implemented meanwhile.

I’m about to re-post my profiling of Ruby on a moderate-sized “Matrix”  
benchmark. I’ll post the link as soon as I get it re-run.

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 18, 2006, 6:19am UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/6 "2006-08-18T06:19:29Z")

</div>

Hi,

On Thu, 17 Aug 2006 23:05:12 +0200, John L. [removed\_email\_address@domain.invalid](mailto:removed_email_address@domain.invalid) wrote:

> I was wondering if anyone had taken a look at what % of time that ruby  
> spends doing method dispatch?

Here are some numbers. Running this code:

max = 2000  
z = x = 0  
while (x+=1) \<= max  
y = 0  
while (y+=1) \<= max  
z = (x+y-z) % 32000  
end  
end

takes about 5.5s in plain Ruby 1.8.4 (on my machine).

Compiling it with Ruby2CExtension (latest version, all optimizations  
turned on) and then running it takes about 0.9s.

One of the optimizations is to bypass rb\_call and calling the C  
functions  
of those methods (almost) directly (when possible).

If this optimization is turned off then running the compiled code takes  
about 3.1s. These additional 2.2s are all spent for method dispatch.

Plain Ruby spends at least the same time for method dispatch, so Ruby  
spends at least 40% of the time doing method dispatch (in this case).

I hope that helps,  
Dominik

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 18, 2006, 7:25am UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/7 "2006-08-18T07:25:42Z")

</div>

M. Edward (Ed) Borasky wrote:

> > The current implementation has a method cache whose hit rate is above 95% or  
> > benchmark. I’ll post the link as soon as I get it re-run.

All done and uploaded … the link is

[http://rubyforge.org/cgi-bin/viewvc.cgi/MatrixBenchmark/?root=cougar](http://rubyforge.org/cgi-bin/viewvc.cgi/MatrixBenchmark/?root=cougar)

I re-ran this in single-user mode, so there is little interference from  
X, etc.

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 21, 2006, 2:33pm UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/8 "2006-08-21T14:33:16Z")

</div>

M. Edward (Ed) Borasky wrote:

> > 
> 
> All done and uploaded … the link is
> 
> [http://rubyforge.org/cgi-bin/viewvc.cgi/MatrixBenchmark/?root=cougar](http://rubyforge.org/cgi-bin/viewvc.cgi/MatrixBenchmark/?root=cougar)
> 
> I re-ran this in single-user mode, so there is little interference from  
> X, etc.

Updated over the weekend. YARV is about four times as fast as Ruby  
1.8.5! I’ll probably rerun the profiling using “oprofile”, though.  
“gprof” seems to have too low a sampling frequency to determine what’s  
really going on with “reasonable” run times – 1 to 10 minutes.

---

<div class="post-metadata">

**Author:** ![johnlester](https://www.ruby-forum.com/letter_avatar_proxy/v4/letter/j/e480ec/32.png) [@johnlester](https://www.ruby-forum.com/u/johnlester)\
**Post date:** [August 21, 2006, 2:17pm UTC](https://www.ruby-forum.com/t/percentage-of-time-spent-in-method-dispatch/65399/9 "2006-08-21T14:17:15Z")

</div>

Hi,

Mauricio F. wrote:

> Method dispatching is still fairly slow, though; I once measured that it took  
> some ~200 instructions to run a CFUNC, and about half as much with YARV.  
> Last time I read YARV’s sources, it didn’t have inline method caches (but it  
> was caching constants, IIRC), but it’s been a while and they might have been  
> implemented meanwhile.

YARV already has inline method cache (see vm.c).