lock contention etc.

[Kris Kennaway]

On Thu, Feb 01, 2007 at 11:35:47AM -0800, Julian Elischer wrote:
> here's an intersting set of numbers..
> 
> notice the increase in 'system time' for the same work done when  there
> is more parallelism.
> 
> make buildworld
>     3762.94 real      2627.66 user      1275.78 sys
>     3763.32 real      2632.04 user      1271.80 sys
>     3763.34 real      2627.99 user      1276.39 sys
>     3763.03 real      2632.50 user      1270.91 sys
> 
> make -j 2 buildworld
>     2465.10 real      2958.94 user      1918.64 sys
>     2463.97 real      2968.43 user      1910.65 sys
>     2472.13 real      2978.64 user      1912.80 sys
>     2582.83 real      2965.51 user      2047.19 sys
> 
> make -j 4 buildworld
>     2262.88 real      4322.31 user      3333.58 sys
>     2255.88 real      4330.32 user      3319.48 sys
>     2256.09 real      4318.84 user      3336.57 sys
>     2257.63 real      4338.34 user      3313.07 sys
> 
> (2 processors with HTT)  (looks like 4 processors)
> -current, sched_4bsd
> 
> I'm guessing that the extra system time represents a lot of
> contention somewhere.
> 
> What is the best way to get actual numbers on this?

LOCK_PROFILING.

Kris
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 187 bytes
Desc: not available
Url : http://lists.freebsd.org/pipermail/freebsd-current/attachments/20070201/b91dc42c/attachment.pgp