RE: [PATCH v2] rcu/nocb: Avoid polling when myrdp->nocb_head_rdp list is empty

From: Zhang, Qiang1
Date: Tue Jun 07 2022 - 23:28:11 EST


On Tue, Jun 07, 2022 at 03:50:57PM +0800, Zqiang wrote:
> Currently, If the 'rcu_nocb_poll' bootargs is enable, all rcuog
> kthreads enter polling mode. however, due to only insert CPU's rdp
> which belong to rcu_nocb_mask to 'nocb_head_rdp' list or all CPU's rdp
> served by rcuog kthread have been de-offloaded, these cause the
> 'nocb_head_rdp' list served by rcuog kthread is empty, when the
> 'nocb_head_rdp' is empty, the rcuog kthread in polling mode not
> actually do anything. fix it by exiting polling mode when the
> 'nocb_head_rdp'list is empty, otherwise entering polling mode.
>
> Signed-off-by: Zqiang <qiang1.zhang@xxxxxxxxx>
>
>This looks a bit more plausible, but what have you done to test this?

Yes , I have only tested as follows and I added two trace events.

+ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("EnterNoPoll"));
rcu_wait(READ_ONCE(my_rdp->nocb_toggling_rdp));
+ trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("ExitNoPoll"));

runqemu kvm slirp nographic qemuparams="-m 2048 -smp 4" bootparams="rcu_nocbs=2,3 rcutree.dump_tree=1 rcu_nocb_poll rcutorture.nocbs_nthreads=4 rcutorture.test_boost=0" -d

Thanks
Zqiang

>
> Thanx, Paul
>
> ---
> v1->v2:
> Move rcu_nocb_poll flags check from rdp_offload_toggle() to
> rcu_nocb_rdp_offload/deoffload(), avoid unnecessary setting of
> rdp_gp->nocb_gp_sleep flags, because when rcu_nocb_poll is set the
> rdp_gp->nocb_gp_sleep is not used.
>
> kernel/rcu/tree_nocb.h | 16 ++++++++++------
> 1 file changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index
> fa8e4f82e60c..2a52c9abc681 100644
> --- a/kernel/rcu/tree_nocb.h
> +++ b/kernel/rcu/tree_nocb.h
> @@ -698,10 +698,14 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
> TPS("WakeBypassIsDeferred"));
> }
> if (rcu_nocb_poll) {
> - /* Polling, so trace if first poll in the series. */
> - if (gotcbs)
> - trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
> - schedule_timeout_idle(1);
> + if (list_empty(&my_rdp->nocb_head_rdp)) {
> + rcu_wait(READ_ONCE(my_rdp->nocb_toggling_rdp));
> + } else {
> + /* Polling, so trace if first poll in the series. */
> + if (gotcbs)
> + trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Poll"));
> + schedule_timeout_idle(1);
> + }
> } else if (!needwait_gp) {
> /* Wait for callbacks to appear. */
> trace_rcu_nocb_wake(rcu_state.name, cpu, TPS("Sleep")); @@ -1030,7
> +1034,7 @@ static long rcu_nocb_rdp_deoffload(void *arg)
>
> mutex_lock(&rdp_gp->nocb_gp_kthread_mutex);
> if (rdp_gp->nocb_gp_kthread) {
> - if (wake_gp)
> + if (wake_gp || rcu_nocb_poll)
> wake_up_process(rdp_gp->nocb_gp_kthread);
>
> /*
> @@ -1152,7 +1156,7 @@ static long rcu_nocb_rdp_offload(void *arg)
> * rcu_nocb_unlock() rcu_nocb_unlock()
> */
> wake_gp = rdp_offload_toggle(rdp, true, flags);
> - if (wake_gp)
> + if (wake_gp || rcu_nocb_poll)
> wake_up_process(rdp_gp->nocb_gp_kthread);
> swait_event_exclusive(rdp->nocb_state_wq,
> rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB) &&
> --
> 2.25.1
>