>
> There's actually no real difference performance-wise
> between the above
> and the following:
>
> this->foo = (char *)copyin(arg1, arg2);
> this->foo[arg2 + 1] = '\0';
> printf("%s\n", stringof(this->foo));
> e copyin() and the alloca() allocate space out of
> scratch
> space, and in fact, they share the same code path to
> do so. The only
> performance penalty being paid here is in doing this
> as two separate
> subroutine calls rather than a single one. The
> alloca() is safer,
> though, because it covers that edge case where the
> copyin() would use
> the remaining scratch space, making this->foo[arg2 +
> 1] an illegal
> address.
Makes sense...
> Also, the space allocated by alloca() is only valid
> within that
> clause, so it has to be clause-local.
Ooops. I should have caught then when I read up on alloca(). Thanks.
Since I have all of your help here (and thanks much!).... what is your thought
on changing the provider to give DTrace a string to work with? That would move
the overhead for that processing to be in the code path for the process when
the probe is enabled I gather, and the payoff is easier to use/read DTrace
providers. Is this a recommended thing to do?
- Matt
--
This message posted from opensolaris.org
_______________________________________________
dtrace-discuss mailing list
dtrace-discuss@opensolaris.org
