statically linked executable size

Bryce McKinlay mckinlay@redhat.com
Thu Jul 6 04:20:00 GMT 2006


Per Bothner wrote:
> The idea that users should have to specify which libraries to link
> with is something I find totally lame. 

I agree completely, and for me this is a show-stopper to splitting the 
library until the linking can be made transparent to the user. The good 
news is that it would be transparent once we switch to the BC-ABI by 
default - any dependent classes would be found and loaded automatically 
by the db mechanism. But, we're not there yet.
Splitting AWT, etc, out would likely have some effect on startup times 
for simple apps, but it isn't clear how significant that would be. Most 
large apps probably reference a few AWT classes anyway so they would see 
little benefit. We do know that a lot of startup time is spent in the 
dynamic linker. But, I think it would be more effective in the general 
case to implement pointer-free metadata and build libgcj itself with 
-findirect-classes, reducing reloc processing and the amount of 
copy-on-write-ed .so data.
Bryce


More information about the Java mailing list

AltStyle によって変換されたページ (->オリジナル) /