Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1549257

[RFC 1/3] sched: set loop_max after rq lock is taken

Show all headers | View raw

From: Uladzislau 2 Rezki <uladzislau2.rezki@sonymobile.com>

While doing a load balance there is a race in setting
loop_max variable since nr_running can be changed causing
incorect iteration loops.

As a result we may skip some candidates or check the same
tasks again.

Signed-off-by: Uladzislau 2 Rezki <uladzislau2.rezki@sonymobile.com>
---
 kernel/sched/fair.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c242944..c5d9351 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7744,12 +7744,17 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		 * correctly treated as an imbalance.
 		 */
 		env.flags |= LBF_ALL_PINNED;
-		env.loop_max  = min(sysctl_sched_nr_migrate, busiest->nr_running);
 
 more_balance:
 		raw_spin_lock_irqsave(&busiest->lock, flags);
 
 		/*
+		 * Set loop_max when rq's lock is taken to prevent a race.
+		 */
+		env.loop_max = min(sysctl_sched_nr_migrate,
+						busiest->nr_running);
+
+		/*
 		 * cur_ld_moved - load moved in current iteration
 		 * ld_moved     - cumulative load moved across iterations
 		 */
-- 
2.1.4

Back to linux.kernel | Previous | Next — Next in thread | Find similar | Unroll thread

Thread

[RFC 1/3] sched: set loop_max after rq lock is taken Uladzislau Rezki <urezki@gmail.com> - 2017-01-02 16:50 +0100
  [RFC 3/3] sched: ignore task_h_load for CPU_NEWLY_IDLE Uladzislau Rezki <urezki@gmail.com> - 2017-01-02 16:50 +0100
  [RFC 2/3] sched: set number of iterations to h_nr_running Uladzislau Rezki <urezki@gmail.com> - 2017-01-02 16:50 +0100

csiph-web