- Pass the priority argument from *sleep() into sleepq and down into

   sched_sleep().  This removes extra thread_lock() acquisition and
   allows the scheduler to decide what to do with the static boost.
 - Change the priority arguments to cv_* to match sleepq/msleep/etc.
   where 0 means no priority change.  Catch -1 in cv_broadcastpri() and
   convert it to 0 for now.
 - Set a flag when sleeping in a way that is compatible with swapping
   since direct priority comparisons are meaningless now.
 - Add a sysctl to ule, kern.sched.static_boost, that defaults to on which
   controls the boost behavior.  Turning it off gives better performance
   in some workloads but needs more investigation.
 - While we're modifying sleepq, change signal and broadcast to both
   return with the lock held as the lock was held on enter.

Reviewed by:	jhb, peter

1 files changed, 9 insertions, 1 deletions

diff --git a/sys/kern/sched_ule.c b/sys/kern/sched_ule.c
index c89e45b..ebdc5e0 100644
--- a/sys/kern/sched_ule.c
+++ b/sys/kern/sched_ule.c
@@ -185,6 +185,7 @@ static int preempt_thresh = PRI_MIN_KERN;
 #else 
 static int preempt_thresh = 0;
 #endif
+static int static_boost = 1;
 
 /*
  * tdq - per processor runqs and statistics.  All fields are protected by the
@@ -1856,12 +1857,16 @@ sched_nice(struct proc *p, int nice)
  * Record the sleep time for the interactivity scorer.
  */
 void
-sched_sleep(struct thread *td)
+sched_sleep(struct thread *td, int prio)
 {
 
 	THREAD_LOCK_ASSERT(td, MA_OWNED);
 
 	td->td_slptick = ticks;
+	if (TD_IS_SUSPENDED(td) || prio <= PSOCK)
+		td->td_flags |= TDF_CANSWAP;
+	if (static_boost && prio)
+		sched_prio(td, prio);
 }
 
 /*
@@ -1876,6 +1881,7 @@ sched_wakeup(struct thread *td)
 
 	THREAD_LOCK_ASSERT(td, MA_OWNED);
 	ts = td->td_sched;
+	td->td_flags &= ~TDF_CANSWAP;
 	/*
 	 * If we slept for more than a tick update our interactivity and
 	 * priority.
@@ -2555,6 +2561,8 @@ SYSCTL_INT(_kern_sched, OID_AUTO, interact, CTLFLAG_RW, &sched_interact, 0,
      "Interactivity score threshold");
 SYSCTL_INT(_kern_sched, OID_AUTO, preempt_thresh, CTLFLAG_RW, &preempt_thresh,
      0,"Min priority for preemption, lower priorities have greater precedence");
+SYSCTL_INT(_kern_sched, OID_AUTO, static_boost, CTLFLAG_RW, &static_boost,
+     0,"Controls whether static kernel priorities are assigned to sleeping threads.");
 #ifdef SMP
 SYSCTL_INT(_kern_sched, OID_AUTO, affinity, CTLFLAG_RW, &affinity, 0,
     "Number of hz ticks to keep thread affinity for");