From 394f2769aa0dbcf027bae6fb52835e25e05d332e Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 26 Jun 2012 17:00:35 -0700 Subject: rcu: Prevent force_quiescent_state() memory contention Large systems running RCU_FAST_NO_HZ kernels see extreme memory contention on the rcu_state structure's ->fqslock field. This can be avoided by disabling RCU_FAST_NO_HZ, either at compile time or at boot time (via the nohz kernel boot parameter), but large systems will no doubt become sensitive to energy consumption. This commit therefore uses a combining-tree approach to spread the memory contention across new cache lines in the leaf rcu_node structures. This can be thought of as a tournament lock that has only a try-lock acquisition primitive. The effect on small systems is minimal, because such systems have an rcu_node "tree" consisting of a single node. In addition, this functionality is not used on fastpaths. Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcutree.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/rcutree.h') diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 7fb93cedc76a..8f0293ce1517 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -202,6 +202,7 @@ struct rcu_node { /* per-CPU kthreads as needed. */ unsigned int node_kthread_status; /* State of node_kthread_task for tracing. */ + raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; } ____cacheline_internodealigned_in_smp; /* -- cgit v1.2.3-70-g09d2