Quantifying the Performance of Garbage Collection vs. Explicit Memory Management

[BCS]

Craig Black wrote:
> 
> If I understand the article correctly, I think you are missing the main 
> point of it.  It is not merely saying ,"We ran conclusive test: GC loses 
> to explicit memory management!"  They went much further than that, and 
> identified the primary bottleneck in modern GC implementations.  Namely, 
> that GC doesn't cooperate well with virtual memory.  GC typically scans 
> way more memory than the rest of the application, and consequently 
> causes the most cache misses/page faults.  This article is not bashing 
> GC.  I think it is indicating to us how we can best improve it.  Perhaps 
> some GC algorithm could be developed that is optimized specifically to 
> produce the fewer page faults and cache misses.
> 

I didn't read the whole article (only the segments that were quoted) so 
I may have missed the point. The quoting article seem to me to be using 
this to claim that GC looses. If that's not the main point... Ok, my bad.

> Thoughts?

I built a version of lisp a few months back that needed some sort of 
libsegv library for it's GC. it sounds like it might be of use. 
Something like only scanning pages that have changed and caching the rest.

> 
> -Craig
>