Commit fb77dccf authored Apr 12, 2022 by Paul E. McKenney

rcu: Decrease FQS scan wait time in case of callback overloading



The force-quiesce-state loop function rcu_gp_fqs_loop() checks for
callback overloading and does an immediate initial scan for idle CPUs
if so.  However, subsequent rescans will be carried out at as leisurely a
rate as they always are, as specified by the rcutree.jiffies_till_next_fqs
module parameter.  It might be tempting to just continue immediately
rescanning, but this turns the RCU grace-period kthread into a CPU hog.
It might also be tempting to reduce the time between rescans to a single
jiffy, but this can be problematic on larger systems.

This commit therefore divides the normal time between rescans by three,
rounding up.  Thus a small system running at HZ=1000 that is suffering
from callback overload will wait only one jiffy instead of the normal
three between rescans.

[ paulmck: Apply Neeraj Upadhyay feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>

parent 4f2bfd94

kernel/rcu/tree.c

+6 −1

Original line number	Original line	Diff line number	Diff line
	@@ -1983,7 +1983,12 @@ static noinline_for_stack void rcu_gp_fqs_loop(void)
	gf = RCU_GP_FLAG_OVLD;		gf = RCU_GP_FLAG_OVLD;
	ret = 0;		ret = 0;
	for (;;) {		for (;;) {
	if (!ret) {		if (rcu_state.cbovld) {
			j = (j + 2) / 3;
			if (j <= 0)
			j = 1;
			}
			if (!ret \|\| time_before(jiffies + j, rcu_state.jiffies_force_qs)) {
	WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j);		WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j);
	/*		/*
	* jiffies_force_qs before RCU_GP_WAIT_FQS state		* jiffies_force_qs before RCU_GP_WAIT_FQS state