sched: make double-lock-balance fair

double_lock balance() currently favors logically lower cpus since they
often do not have to release their own lock to acquire a second lock.
The result is that logically higher cpus can get starved when there is
a lot of pressure on the RQs.  This can result in higher latencies on
higher cpu-ids.

This patch makes the algorithm more fair by forcing all paths to have
to release both locks before acquiring them again.  Since callsites to
double_lock_balance already consider it a potential preemption/reschedule
point, they have the proper logic to recheck for atomicity violations.

Signed-off-by: Gregory Haskins <ghaskins@novell.com>

diff --git a/kernel/sched.c b/kernel/sched.c
index 94d9a6c5ff94cb7b7fb2ea71038d7e95ac099abc..8fca364f3593ac3ce48409faa6b0a5119285f44d 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1608,21 +1608,42 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 #endif
 
+#ifdef CONFIG_PREEMPT
+
 /*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ * fair double_lock_balance: Safely acquires both rq->locks in a fair
+ * way at the expense of forcing extra atomic operations in all
+ * invocations.  This assures that the double_lock is acquired using the
+ * same underlying policy as the spinlock_t on this architecture, which
+ * reduces latency compared to the unfair variant below.  However, it
+ * also adds more overhead and therefore may reduce throughput.
  */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
+       __releases(this_rq->lock)
+       __acquires(busiest->lock)
+       __acquires(this_rq->lock)
+{
+       spin_unlock(&this_rq->lock);
+       double_rq_lock(this_rq, busiest);
+
+       return 1;
+}
+
+#else
+/*
+ * Unfair double_lock_balance: Optimizes throughput at the expense of
+ * latency by eliminating extra atomic operations when the locks are
+ * already in proper order on entry.  This favors lower cpu-ids and will
+ * grant the double lock to lower cpus over higher ids under contention,
+ * regardless of entry order into the function.
+ */
+static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
        __releases(this_rq->lock)
        __acquires(busiest->lock)
        __acquires(this_rq->lock)
 {
        int ret = 0;
 
-       if (unlikely(!irqs_disabled())) {
-               /* printk() doesn't work good under rq->lock */
-               spin_unlock(&this_rq->lock);
-               BUG_ON(1);
-       }
        if (unlikely(!spin_trylock(&busiest->lock))) {
                if (busiest < this_rq) {
                        spin_unlock(&this_rq->lock);
@@ -1635,6 +1656,22 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
        return ret;
 }
 
+#endif /* CONFIG_PREEMPT */
+
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+{
+       if (unlikely(!irqs_disabled())) {
+               /* printk() doesn't work good under rq->lock */
+               spin_unlock(&this_rq->lock);
+               BUG_ON(1);
+       }
+
+       return _double_lock_balance(this_rq, busiest);
+}
+
 static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
        __releases(busiest->lock)
 {