On Nov 7, 2007 4:17 PM, Roman Shaposhnik <[EMAIL PROTECTED]> wrote:
>   I have troubles correlating the two statements you've made. Is it that
> you're suggesting NOT to use DTrace because it is slower than manually
> inserted timing calls around each pthread_mutex_[un]lock ?

Well... Where did I say that??

I am helping Neelam to understand the problem. You sure don't want to
use a stop watch to measure the latency of a cache miss, do you??

By the same token, if the overhead of getting to DTrace from the
userland is much greater than that of getting a lock, I am sure
picking DTrace is wrong...

BTW, this is not the first time I am seeing responses like this. Every
time I make the suggestion that DTrace is not the right tool for a
certain problem, someone from Sun would sure to defense. *Please*
understand that no tools can handle all the performance issues!!

Rayson




>
> Thanks,
> Roman.
>
>
_______________________________________________
dtrace-discuss mailing list
[email protected]

Reply via email to