Re: [PATCH] rcu/tree: Force quiescent state on callback overload

[Neeraj Upadhyay]

Hi Paul,

On 6/22/2020 8:43 AM, Paul E. McKenney wrote:
> On Mon, Jun 22, 2020 at 01:30:31AM +0530, Neeraj Upadhyay wrote:
> > Hi Paul,
> >
> > On 6/22/2020 1:20 AM, Paul E. McKenney wrote:
> > > On Mon, Jun 22, 2020 at 12:07:27AM +0530, Neeraj Upadhyay wrote:
> > > > On callback overload, we want to force quiescent state immediately,
> > > > for the first and second fqs. Enforce the same, by including
> > > > RCU_GP_FLAG_OVLD flag, in fqsstart check.
> > > >
> > > > Signed-off-by: Neeraj Upadhyay <neeraju@xxxxxxxxxxxxxx>
> > >
> > > Good catch!
> > >
> > > But what did you do to verify that this change does the right thing?
> > >
> > > 						Thanx, Paul
> >
> > I haven't done a runtime verification of this code path; I posted this,
> > based on review of this code.
>
> My concern is that under overload, the FQS scans would happen continuously
> rather than accelerating only the first such scan in a given grace period.
> This would of course result in a CPU-bound grace-period kthread, which
> users might not be all that happy with.
>
> Or am I missing something subtle that prevents this?

Looks like under overload, only the first and second scans are accelerated?

    gf = 0;
    if (first_gp_fqs) {
         first_gp_fqs = false;
          gf = rcu_state.cbovld ? RCU_GP_FLAG_OVLD : 0;
    }


Thanks
Neeraj

> But yes, it does look like the current mainline code fails to do the
> first scan immediately, so again, good catch!
>
> 							Thanx, Paul

> > Thanks
> > Neeraj
> >
> > > > ---
> > > >    kernel/rcu/tree.c | 2 +-
> > > >    1 file changed, 1 insertion(+), 1 deletion(-)
> > > >
> > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > > > index d0988a1..6226bfb 100644
> > > > --- a/kernel/rcu/tree.c
> > > > +++ b/kernel/rcu/tree.c
> > > > @@ -1865,7 +1865,7 @@ static void rcu_gp_fqs_loop(void)
> > > >    			break;
> > > >    		/* If time for quiescent-state forcing, do it. */
> > > >    		if (!time_after(rcu_state.jiffies_force_qs, jiffies) ||
> > > > -		    (gf & RCU_GP_FLAG_FQS)) {
> > > > +		    (gf & (RCU_GP_FLAG_FQS | RCU_GP_FLAG_OVLD))) {
> > > >    			trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq,
> > > >    					       TPS("fqsstart"));
> > > >    			rcu_gp_fqs(first_gp_fqs);
> > > > --
> > > > The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
> > > > a Linux Foundation Collaborative Project
> >
> > --
> > QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a member of
> > the Code Aurora Forum, hosted by The Linux Foundation

--
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a 
member of the Code Aurora Forum, hosted by The Linux Foundation