Re: [PATCH RFC tip/core/rcu] Add shrinker to shift to fast/inefficient GP mode

[Andrew Morton <akpm@linux-foundation.org>]

On Wed, 6 May 2020 17:42:40 -0700 "Paul E. McKenney" <paulmck@kernel.org> wrote:

> This commit adds a shrinker so as to inform RCU when memory is scarce.
> RCU responds by shifting into the same fast and inefficient mode that is
> used in the presence of excessive numbers of RCU callbacks.  RCU remains
> in this state for one-tenth of a second, though this time window can be
> extended by another call to the shrinker.
> 
> If it proves feasible, a later commit might add a function call directly
> indicating the end of the period of scarce memory.

(Cc David Chinner, who often has opinions on shrinkers ;))

It's a bit abusive of the intent of the slab shrinkers, but I don't
immediately see a problem with it.  Always returning 0 from
->scan_objects might cause a problem in some situations(?).

Perhaps we should have a formal "system getting low on memory, please
do something" notification API.

How significant is this?  How much memory can RCU consume?

> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2368,8 +2368,15 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
>  	struct rcu_data *rdp;
>  	struct rcu_node *rnp;
>  
> -	rcu_state.cbovld = rcu_state.cbovldnext;
> +	// Load .oomovld before .oomovldend, pairing with .oomovld set.
> +	rcu_state.cbovld = smp_load_acquire(&rcu_state.oomovld) || // ^^^
> +			   rcu_state.cbovldnext;
>  	rcu_state.cbovldnext = false;
> +	if (READ_ONCE(rcu_state.oomovld) &&
> +	    time_after(jiffies, READ_ONCE(rcu_state.oomovldend))) {
> +		WRITE_ONCE(rcu_state.oomovld, false);
> +		pr_info("%s: Ending OOM-mode grace periods.\n", __func__);
> +	}
>  	rcu_for_each_leaf_node(rnp) {
>  		cond_resched_tasks_rcu_qs();
>  		mask = 0;
> @@ -2697,6 +2704,35 @@ static void check_cb_ovld(struct rcu_data *rdp)
>  	raw_spin_unlock_rcu_node(rnp);
>  }
>  
> +/* Return a rough count of the RCU callbacks outstanding. */
> +static unsigned long rcu_oom_count(struct shrinker *unused1,
> +				   struct shrink_control *unused2)
> +{
> +	int cpu;
> +	unsigned long ncbs = 0;
> +
> +	for_each_possible_cpu(cpu)
> +		ncbs += rcu_get_n_cbs_cpu(cpu);
> +	return ncbs;
> +}
> +
> +/* Start up an interval of fast high-overhead grace periods. */
> +static unsigned long rcu_oom_scan(struct shrinker *unused1,
> +				  struct shrink_control *unused2)
> +{
> +	pr_info("%s: Starting OOM-mode grace periods.\n", __func__);
> +	WRITE_ONCE(rcu_state.oomovldend, jiffies + HZ / 10);
> +	smp_store_release(&rcu_state.oomovld, true); // After .oomovldend
> +	rcu_force_quiescent_state();  // Kick grace period
> +	return 0;  // We haven't actually reclaimed anything yet.
> +}
> +
> +static struct shrinker rcu_shrinker = {
> +	.count_objects = rcu_oom_count,
> +	.scan_objects = rcu_oom_scan,
> +	.seeks = DEFAULT_SEEKS,
> +};
> +
>  /* Helper function for call_rcu() and friends.  */
>  static void
>  __call_rcu(struct rcu_head *head, rcu_callback_t func)
> @@ -4146,6 +4182,7 @@ void __init rcu_init(void)
>  		qovld_calc = DEFAULT_RCU_QOVLD_MULT * qhimark;
>  	else
>  		qovld_calc = qovld;
> +	WARN_ON(register_shrinker(&rcu_shrinker));
>  }
>  
>  #include "tree_stall.h"
> diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
> index 2d7fcb9..c4d8e96 100644
> --- a/kernel/rcu/tree.h
> +++ b/kernel/rcu/tree.h
> @@ -326,6 +326,8 @@ struct rcu_state {
>  	int ncpus_snap;				/* # CPUs seen last time. */
>  	u8 cbovld;				/* Callback overload now? */
>  	u8 cbovldnext;				/* ^        ^  next time? */
> +	u8 oomovld;				/* OOM overload? */
> +	unsigned long oomovldend;		/* OOM ovld end, jiffies. */
>  
>  	unsigned long jiffies_force_qs;		/* Time at which to invoke */
>  						/*  force_quiescent_state(). */