The cost of stack traces

[Andrew Haley]

Anthony Green writes:
 > On Wed, 2006-05-10 at 14:47 -0400, Andrew Haley wrote:
 > > As some of you may be aware, I've been doing benchmarking of servers
 > > with a mind to improving gcj performance.
 > 
 > Is it worth considering caching stack trace results?  I'm not sure
 > exactly how it would work, but I imagine there must be some way to take
 > advantage of the fact that many stack traces will share a common bottom
 > portion of the stack, so we would only have to trace the unknown
 > portion.

Yes.  All we have to do is keep a table that maps IP address -> filename.

Andrew.