Subj : Re: Solaris real-time thread capabilities
To   : comp.unix.solaris,comp.programming.threads
From : Ian
Date : Wed Sep 07 2005 02:50 pm

Eric Sosman wrote:
> 
>     FWIW, I just ran a brief test on my desktop system, a
> venerable Ultra-10 running Solaris 9 on an ancient UltraSPARC-II
> processor at a whopping 360 MHz.  I ran this simple loop:
> 
> 	for (i = 0;  i < 101;  ++i)
> 	    when[i] = gethrtime();
> 
> ... and then post-analyzed the 100 sample-to-sample intervals.
> The slowest observed was 692 ns, the fastest was 291 ns, the
> average was 296 ns, and the standard deviation was 40 ns.
> That's reasonably close to the 320 ns figure cited in the
> book, but nothing at all like your 320,000,000 ns ...
> 
My Pentium M laptop gives:

min  = 200
max  = 256
mean = 206
sd   = 8

But the figures are way off for longer runs (10000 or more) once the 
process looses the CPU.

min  = 200
max  = 7437
mean = 213.874800
sd = 203.604031

capnwhit, are you sure you are running an RT thread? Looks like you are 
seeing the scheduler swapping your process out.

Ian

.