Heavy I/O blocks FreeBSD box for several seconds

[Steve Kargl]

On Mon, Jul 11, 2011 at 11:42:02PM +0800, Adrian Chadd wrote:
> That top output is averaged and slow to adjust.
> Using "top" as an indication as to what's really going on is likely
> not a good idea.
> 

Restoring top output here:

>   PID USERNAME  THR PRI NICE   SIZE    RES STATE   C   TIME    CPU COMMAND
>  1318 kargl       1 103    0   370M   294M CPU0    0   1:31 100.00% sasmp
>  1319 kargl       1 103    0   370M   294M RUN     1   1:29 100.00% sasmp
>  1322 kargl       1  99    0   370M   294M CPU2    2   1:03 87.26% sasmp
>  1320 kargl       1  91    0   370M   294M RUN     3   1:07 60.79% sasmp
>  1321 kargl       1  89    0   370M   294M CPU3    3   1:06 55.18% sasmp

That TIME column is a very good indication of problem.

I can assure you that wall-clock time for the application
under ULE is far longer than under 4BSD.

IIRC (because its been awhile since I looked at problem), guess
what happens when pid 1318 or 1319 finishes?  Did you guess that
pid 1320 and 1321 are still stuck on the same cpu?

-- 
Steve