Re: dtrace profile timers still unstable?

On Fri, 16 Oct 2009, Robert Watson wrote:
> In the past, I've had little luck using the DTrace profile timers on FreeBSD 
> for much without crashes, and this morning was no different.  I attempted to 
> use the following(ish) script:
>
>  profile-1ms
>  {
>
>          _at_data[stack()] = count();
>  }
>
> The result was:
>
> spin lock 0x849747d8 (cyclic cpu) held by 0x85442b40 (tid 100539) too long
> panic: spin lock held too long

[...]

> (I've seen panics with it pretty deterministically on i386 and amd64)

Is there any particular technique to get this to panic?  I've been trying 
to get a panic from the above script (using "dtrace -s prof.d") for a few 
hours now without success...

Gavin