On Tue, 2011-08-16 at 12:31 -0700, Paul E. McKenney wrote:

On Tue, Aug 16, 2011 at 05:10:08PM +0200, Mike Galbraith wrote:

quoted

On Tue, 2011-08-16 at 07:17 -0700, Nivedita Singhvi wrote:

quoted

Mike,

Which test were you running? Because I'm not seeing it
on our x3550 M3..

-rt11 did not trip up just idling along like a couple earlier releases
did, but did stall when I tried to run ltp realtime testcases.

But please note that if your realtime workload is CPU-bound with prio
greater than that of RCU_SOFTIRQ, stalls would be expected.

The (broken) jitter testcase runs two threads, an interrupter thread at
prio 80, and a worker at 10.  Both sleep.  I just ran the testcase
standalone, and no stall happened, so perhaps something from an earlier
testcase got stuck.. or something.

I'll try maxing out boost, and see what happens.  It was set to 50.

	-Mike