> It looks strange, but for the operating system it isn't - those threads
> (or LWPs, as the man page reads) are waiting for an event or signal, at
> which point they will swap back in.

IIRC, there was a bug about this a while ago.  Essentially, the FX and
RT scheduling classes didn't implement CL_SWAPIN().  If a process was
unfortuante enough to get swapped out and then be changed to the FX or
RT class, it would never swap back in again.  This has been fixed in
Nevada and S10u5.  However, I doubt this is the problem.

I think this was CR 6222906.

        http://bugs.opensolaris.org/view_bug.do?bug_id=6222906

It would be easy enough to check for this condition, once the PIDs of
the swapped processes have been identified.

-j

_______________________________________________
perf-discuss mailing list
perf-discuss@opensolaris.org

Reply via email to