[tip/core/rcu,21/22] rcu: Allow RCU grace-period cleanup to be preempt...

My dashboard
Submitter Paul E. McKenney
Subject [tip/core/rcu,21/22] rcu: Allow RCU grace-period cleanup to be preempted
Date June 22, 2012, 3:17 p.m.
List thread <1340378241-6458-21-git-send-email-paulmck@linux.vnet.ibm.com>
Project linux-kernel
State New
Headers show

Comments

Paul E. McKenney - June 22, 2012, 3:17 p.m.
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>

RCU grace-period cleanup is currently carried out with interrupts
disabled, which can result in excessive latency spikes on large systems
(many hundreds or thousands of CPUs).  This patch therefore makes the
RCU grace-period cleanup be preemptible, including voluntary preemption
points, which should eliminate those latency spikes.  Similar spikes from
forcing of quiescent states will be dealt with similarly by later patches.

Reported-by: Mike Galbraith <mgalbraith@suse.de>
Reported-by: Dimitri Sivanich <sivanich@sgi.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   11 +++++------
 1 files changed, 5 insertions(+), 6 deletions(-)

Patch

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 4a3f6b0..d21c2d3 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -1160,7 +1160,7 @@  static int rcu_gp_kthread(void *arg)
 		 * completed.
 		 */
 		if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) {
-			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
 			/*
 			 * Propagate new ->completed value to rcu_node
@@ -1169,14 +1169,13 @@  static int rcu_gp_kthread(void *arg)
 			 * to process their callbacks.
 			 */
 			rcu_for_each_node_breadth_first(rsp, rnp) {
-				/* irqs already disabled. */
-				raw_spin_lock(&rnp->lock);
+				raw_spin_lock_irqsave(&rnp->lock, flags);
 				rnp->completed = rsp->gpnum;
-				/* irqs remain disabled. */
-				raw_spin_unlock(&rnp->lock);
+				raw_spin_unlock_irqrestore(&rnp->lock, flags);
+				cond_resched();
 			}
 			rnp = rcu_get_root(rsp);
-			raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+			raw_spin_lock_irqsave(&rnp->lock, flags);
 		}
 
 		rsp->completed = rsp->gpnum; /* Declare grace period done. */