Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-05 Thread Ingo Molnar
* Peter Zijlstra wrote: > On Wed, Apr 04, 2018 at 09:15:39AM -0700, Davidlohr Bueso wrote: > > On Mon, 02 Apr 2018, Davidlohr Bueso wrote: > > > > > The case for the rt task throttling (which this workload also hits) can > > > be ignored in > > > that the skip_update

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-05 Thread Ingo Molnar
* Peter Zijlstra wrote: > On Wed, Apr 04, 2018 at 09:15:39AM -0700, Davidlohr Bueso wrote: > > On Mon, 02 Apr 2018, Davidlohr Bueso wrote: > > > > > The case for the rt task throttling (which this workload also hits) can > > > be ignored in > > > that the skip_update call is actually bogus

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-04 Thread Peter Zijlstra
On Wed, Apr 04, 2018 at 09:15:39AM -0700, Davidlohr Bueso wrote: > On Mon, 02 Apr 2018, Davidlohr Bueso wrote: > > > The case for the rt task throttling (which this workload also hits) can be > > ignored in > > that the skip_update call is actually bogus and quite the contrary (the > > request

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-04 Thread Peter Zijlstra
On Wed, Apr 04, 2018 at 09:15:39AM -0700, Davidlohr Bueso wrote: > On Mon, 02 Apr 2018, Davidlohr Bueso wrote: > > > The case for the rt task throttling (which this workload also hits) can be > > ignored in > > that the skip_update call is actually bogus and quite the contrary (the > > request

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-04 Thread Davidlohr Bueso
On Mon, 02 Apr 2018, Davidlohr Bueso wrote: The case for the rt task throttling (which this workload also hits) can be ignored in that the skip_update call is actually bogus and quite the contrary (the request bits are removed/reverted). While at it, how about this trivial patch?

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-04 Thread Davidlohr Bueso
On Mon, 02 Apr 2018, Davidlohr Bueso wrote: The case for the rt task throttling (which this workload also hits) can be ignored in that the skip_update call is actually bogus and quite the contrary (the request bits are removed/reverted). While at it, how about this trivial patch?

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-04 Thread Peter Zijlstra
On Mon, Apr 02, 2018 at 09:49:54AM -0700, Davidlohr Bueso wrote: > While running rt-tests' pi_stress program I got the following splat: > > 444.884597] [ cut here ] > [ 444.894784] rq->clock_update_flags < RQCF_ACT_SKIP > [ 444.894798] WARNING: CPU: 27 PID: 0 at

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-04 Thread Peter Zijlstra
On Mon, Apr 02, 2018 at 09:49:54AM -0700, Davidlohr Bueso wrote: > While running rt-tests' pi_stress program I got the following splat: > > 444.884597] [ cut here ] > [ 444.894784] rq->clock_update_flags < RQCF_ACT_SKIP > [ 444.894798] WARNING: CPU: 27 PID: 0 at

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-03 Thread Matt Fleming
On Mon, 02 Apr, at 09:49:54AM, Davidlohr Bueso wrote: > > We can get rid of it be the "traditional" means of adding an > update_rq_clock() call > after acquiring the rq->lock in do_sched_rt_period_timer(). > > The case for the rt task throttling (which this workload also hits) can be > ignored

Re: [PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-03 Thread Matt Fleming
On Mon, 02 Apr, at 09:49:54AM, Davidlohr Bueso wrote: > > We can get rid of it be the "traditional" means of adding an > update_rq_clock() call > after acquiring the rq->lock in do_sched_rt_period_timer(). > > The case for the rt task throttling (which this workload also hits) can be > ignored

[PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-02 Thread Davidlohr Bueso
While running rt-tests' pi_stress program I got the following splat: 444.884597] [ cut here ] [ 444.894784] rq->clock_update_flags < RQCF_ACT_SKIP [ 444.894798] WARNING: CPU: 27 PID: 0 at kernel/sched/sched.h:960 assert_clock_updated.isra.38.part.39+0x13/0x20 [

[PATCH] sched/rt: Fix rq->clock_update_flags < RQCF_ACT_SKIP warning

2018-04-02 Thread Davidlohr Bueso
While running rt-tests' pi_stress program I got the following splat: 444.884597] [ cut here ] [ 444.894784] rq->clock_update_flags < RQCF_ACT_SKIP [ 444.894798] WARNING: CPU: 27 PID: 0 at kernel/sched/sched.h:960 assert_clock_updated.isra.38.part.39+0x13/0x20 [