>>> On Mon, Jun 30, 2008 at 9:15 AM, in message <20080630131511.GA7506@xxxxxxx>, Ingo Molnar <mingo@xxxxxxx> wrote: > * Gregory Haskins <ghaskins@xxxxxxxxxx> wrote: > >> Hi Ingo, >> The following patches apply to linux-tip/sched/devel and enhance the >> performance of the kernel (specifically in PREEMPT_RT, though they do >> not regress mainline performance as far as I can tell). They offer >> somewhere between 50-100% speedups in netperf performance, depending >> on the test. > > -tip testing found this boot hang: I may have found the issue: It looks like the hunk that initially disables interrupts in load_balance_newidle() was inadvertently applied to load_balance() instead during the merge to linux-tip. If you fold the following patch into my original patch, it should set things right again. ----- sched: fix merge problem with newidle enhancement patch From: Gregory Haskins <ghaskins@xxxxxxxxxx> commit cc8160c56843201891766660e3816d2e546c1b17 introduces a locking enhancement for newidle. However, one hunk misapplied to load_balance instead of load_balance_newidle. This fixes the issue. Signed-off-by: Gregory Haskins <ghaskins@xxxxxxxxxx> --- kernel/sched.c | 18 +++++++++--------- 1 files changed, 9 insertions(+), 9 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index f35d73c..f36406f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3459,15 +3459,6 @@ static int load_balance(int this_cpu, struct rq *this_rq, cpus_setall(*cpus); - schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); - - /* - * We are in a preempt-disabled section, so dropping the lock/irq - * here simply means that other cores may acquire the lock, - * and interrupts may occur. - */ - spin_unlock_irq(&this_rq->lock); - /* * When power savings policy is enabled for the parent domain, idle * sibling can pick up load irrespective of busy siblings. In this case, @@ -3630,6 +3621,15 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, cpus_setall(*cpus); + schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); + + /* + * We are in a preempt-disabled section, so dropping the lock/irq + * here simply means that other cores may acquire the lock, + * and interrupts may occur. + */ + spin_unlock_irq(&this_rq->lock); + /* * When power savings policy is enabled for the parent domain, idle * sibling can pick up load irrespective of busy siblings. In this case, -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
