JVM Usenix paper got rejected

Jeff Sturm jsturm@detroit.appnet.com
Sat Dec 16 22:59:00 GMT 2000


Bryce McKinlay wrote:
> > It was many individual runs.  But javac's performance may have been
> > limited by runtime factors anyway... has anybody noticed that libgcj's
> > classloader is far slower than Sun's when reading compressed .jar files?
> 
> Doesn't surprise me. There are certainly plenty of opportunities for
> optimizations and cleanups in the classloader stuff. Was the slowness you saw
> actually specific to zip files (and if so, specific to compressed zip files?) or
> was it just slow classloader in general?

IIRC the real slowdown was in reading compressed jar files.  If I
extracted classes.zip or rearchived it without compression, class
loading was significantly faster.

Jeff


More information about the Java mailing list