summaryrefslogtreecommitdiffstats
path: root/kernel/sched/rt.c
diff options
context:
space:
mode:
authorSteven Rostedt <rostedt@goodmis.org>2015-03-18 14:49:46 -0400
committerIngo Molnar <mingo@kernel.org>2015-03-23 10:55:22 +0100
commitb6366f048e0caff28af5335b7af2031266e1b06b (patch)
tree41e0f5adf67d4a6c8b53d7f32bbdb0fbe329aeaf /kernel/sched/rt.c
parent71ad00d61ec861dc68b4544887729850e58cb99b (diff)
downloadop-kernel-dev-b6366f048e0caff28af5335b7af2031266e1b06b.zip
op-kernel-dev-b6366f048e0caff28af5335b7af2031266e1b06b.tar.gz
sched/rt: Use IPI to trigger RT task push migration instead of pulling
When debugging the latencies on a 40 core box, where we hit 300 to 500 microsecond latencies, I found there was a huge contention on the runqueue locks. Investigating it further, running ftrace, I found that it was due to the pulling of RT tasks. The test that was run was the following: cyclictest --numa -p95 -m -d0 -i100 This created a thread on each CPU, that would set its wakeup in iterations of 100 microseconds. The -d0 means that all the threads had the same interval (100us). Each thread sleeps for 100us and wakes up and measures its latencies. cyclictest is maintained at: git://git.kernel.org/pub/scm/linux/kernel/git/clrkwllms/rt-tests.git What happened was another RT task would be scheduled on one of the CPUs that was running our test, when the other CPU tests went to sleep and scheduled idle. This caused the "pull" operation to execute on all these CPUs. Each one of these saw the RT task that was overloaded on the CPU of the test that was still running, and each one tried to grab that task in a thundering herd way. To grab the task, each thread would do a double rq lock grab, grabbing its own lock as well as the rq of the overloaded CPU. As the sched domains on this box was rather flat for its size, I saw up to 12 CPUs block on this lock at once. This caused a ripple affect with the rq locks especially since the taking was done via a double rq lock, which means that several of the CPUs had their own rq locks held while trying to take this rq lock. As these locks were blocked, any wakeups or load balanceing on these CPUs would also block on these locks, and the wait time escalated. I've tried various methods to lessen the load, but things like an atomic counter to only let one CPU grab the task wont work, because the task may have a limited affinity, and we may pick the wrong CPU to take that lock and do the pull, to only find out that the CPU we picked isn't in the task's affinity. Instead of doing the PULL, I now have the CPUs that want the pull to send over an IPI to the overloaded CPU, and let that CPU pick what CPU to push the task to. No more need to grab the rq lock, and the push/pull algorithm still works fine. With this patch, the latency dropped to just 150us over a 20 hour run. Without the patch, the huge latencies would trigger in seconds. I've created a new sched feature called RT_PUSH_IPI, which is enabled by default. When RT_PUSH_IPI is not enabled, the old method of grabbing the rq locks and having the pulling CPU do the work is implemented. When RT_PUSH_IPI is enabled, the IPI is sent to the overloaded CPU to do a push. To enabled or disable this at run time: # mount -t debugfs nodev /sys/kernel/debug # echo RT_PUSH_IPI > /sys/kernel/debug/sched_features or # echo NO_RT_PUSH_IPI > /sys/kernel/debug/sched_features Update: This original patch would send an IPI to all CPUs in the RT overload list. But that could theoretically cause the reverse issue. That is, there could be lots of overloaded RT queues and one CPU lowers its priority. It would then send an IPI to all the overloaded RT queues and they could then all try to grab the rq lock of the CPU lowering its priority, and then we have the same problem. The latest design sends out only one IPI to the first overloaded CPU. It tries to push any tasks that it can, and then looks for the next overloaded CPU that can push to the source CPU. The IPIs stop when all overloaded CPUs that have pushable tasks that have priorities greater than the source CPU are covered. In case the source CPU lowers its priority again, a flag is set to tell the IPI traversal to restart with the first RT overloaded CPU after the source CPU. Parts-suggested-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Joern Engel <joern@purestorage.com> Cc: Clark Williams <williams@redhat.com> Cc: Mike Galbraith <umgwanakikbuti@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/20150318144946.2f3cc982@gandalf.local.home Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched/rt.c')
-rw-r--r--kernel/sched/rt.c177
1 files changed, 177 insertions, 0 deletions
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f4d4b07..ad02415 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -6,6 +6,7 @@
#include "sched.h"
#include <linux/slab.h>
+#include <linux/irq_work.h>
int sched_rr_timeslice = RR_TIMESLICE;
@@ -59,6 +60,10 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
raw_spin_unlock(&rt_b->rt_runtime_lock);
}
+#ifdef CONFIG_SMP
+static void push_irq_work_func(struct irq_work *work);
+#endif
+
void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
{
struct rt_prio_array *array;
@@ -78,7 +83,14 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
plist_head_init(&rt_rq->pushable_tasks);
+
+#ifdef HAVE_RT_PUSH_IPI
+ rt_rq->push_flags = 0;
+ rt_rq->push_cpu = nr_cpu_ids;
+ raw_spin_lock_init(&rt_rq->push_lock);
+ init_irq_work(&rt_rq->push_work, push_irq_work_func);
#endif
+#endif /* CONFIG_SMP */
/* We start is dequeued state, because no RT tasks are queued */
rt_rq->rt_queued = 0;
@@ -1778,6 +1790,164 @@ static void push_rt_tasks(struct rq *rq)
;
}
+#ifdef HAVE_RT_PUSH_IPI
+/*
+ * The search for the next cpu always starts at rq->cpu and ends
+ * when we reach rq->cpu again. It will never return rq->cpu.
+ * This returns the next cpu to check, or nr_cpu_ids if the loop
+ * is complete.
+ *
+ * rq->rt.push_cpu holds the last cpu returned by this function,
+ * or if this is the first instance, it must hold rq->cpu.
+ */
+static int rto_next_cpu(struct rq *rq)
+{
+ int prev_cpu = rq->rt.push_cpu;
+ int cpu;
+
+ cpu = cpumask_next(prev_cpu, rq->rd->rto_mask);
+
+ /*
+ * If the previous cpu is less than the rq's CPU, then it already
+ * passed the end of the mask, and has started from the beginning.
+ * We end if the next CPU is greater or equal to rq's CPU.
+ */
+ if (prev_cpu < rq->cpu) {
+ if (cpu >= rq->cpu)
+ return nr_cpu_ids;
+
+ } else if (cpu >= nr_cpu_ids) {
+ /*
+ * We passed the end of the mask, start at the beginning.
+ * If the result is greater or equal to the rq's CPU, then
+ * the loop is finished.
+ */
+ cpu = cpumask_first(rq->rd->rto_mask);
+ if (cpu >= rq->cpu)
+ return nr_cpu_ids;
+ }
+ rq->rt.push_cpu = cpu;
+
+ /* Return cpu to let the caller know if the loop is finished or not */
+ return cpu;
+}
+
+static int find_next_push_cpu(struct rq *rq)
+{
+ struct rq *next_rq;
+ int cpu;
+
+ while (1) {
+ cpu = rto_next_cpu(rq);
+ if (cpu >= nr_cpu_ids)
+ break;
+ next_rq = cpu_rq(cpu);
+
+ /* Make sure the next rq can push to this rq */
+ if (next_rq->rt.highest_prio.next < rq->rt.highest_prio.curr)
+ break;
+ }
+
+ return cpu;
+}
+
+#define RT_PUSH_IPI_EXECUTING 1
+#define RT_PUSH_IPI_RESTART 2
+
+static void tell_cpu_to_push(struct rq *rq)
+{
+ int cpu;
+
+ if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
+ raw_spin_lock(&rq->rt.push_lock);
+ /* Make sure it's still executing */
+ if (rq->rt.push_flags & RT_PUSH_IPI_EXECUTING) {
+ /*
+ * Tell the IPI to restart the loop as things have
+ * changed since it started.
+ */
+ rq->rt.push_flags |= RT_PUSH_IPI_RESTART;
+ raw_spin_unlock(&rq->rt.push_lock);
+ return;
+ }
+ raw_spin_unlock(&rq->rt.push_lock);
+ }
+
+ /* When here, there's no IPI going around */
+
+ rq->rt.push_cpu = rq->cpu;
+ cpu = find_next_push_cpu(rq);
+ if (cpu >= nr_cpu_ids)
+ return;
+
+ rq->rt.push_flags = RT_PUSH_IPI_EXECUTING;
+
+ irq_work_queue_on(&rq->rt.push_work, cpu);
+}
+
+/* Called from hardirq context */
+static void try_to_push_tasks(void *arg)
+{
+ struct rt_rq *rt_rq = arg;
+ struct rq *rq, *src_rq;
+ int this_cpu;
+ int cpu;
+
+ this_cpu = rt_rq->push_cpu;
+
+ /* Paranoid check */
+ BUG_ON(this_cpu != smp_processor_id());
+
+ rq = cpu_rq(this_cpu);
+ src_rq = rq_of_rt_rq(rt_rq);
+
+again:
+ if (has_pushable_tasks(rq)) {
+ raw_spin_lock(&rq->lock);
+ push_rt_task(rq);
+ raw_spin_unlock(&rq->lock);
+ }
+
+ /* Pass the IPI to the next rt overloaded queue */
+ raw_spin_lock(&rt_rq->push_lock);
+ /*
+ * If the source queue changed since the IPI went out,
+ * we need to restart the search from that CPU again.
+ */
+ if (rt_rq->push_flags & RT_PUSH_IPI_RESTART) {
+ rt_rq->push_flags &= ~RT_PUSH_IPI_RESTART;
+ rt_rq->push_cpu = src_rq->cpu;
+ }
+
+ cpu = find_next_push_cpu(src_rq);
+
+ if (cpu >= nr_cpu_ids)
+ rt_rq->push_flags &= ~RT_PUSH_IPI_EXECUTING;
+ raw_spin_unlock(&rt_rq->push_lock);
+
+ if (cpu >= nr_cpu_ids)
+ return;
+
+ /*
+ * It is possible that a restart caused this CPU to be
+ * chosen again. Don't bother with an IPI, just see if we
+ * have more to push.
+ */
+ if (unlikely(cpu == rq->cpu))
+ goto again;
+
+ /* Try the next RT overloaded CPU */
+ irq_work_queue_on(&rt_rq->push_work, cpu);
+}
+
+static void push_irq_work_func(struct irq_work *work)
+{
+ struct rt_rq *rt_rq = container_of(work, struct rt_rq, push_work);
+
+ try_to_push_tasks(rt_rq);
+}
+#endif /* HAVE_RT_PUSH_IPI */
+
static int pull_rt_task(struct rq *this_rq)
{
int this_cpu = this_rq->cpu, ret = 0, cpu;
@@ -1793,6 +1963,13 @@ static int pull_rt_task(struct rq *this_rq)
*/
smp_rmb();
+#ifdef HAVE_RT_PUSH_IPI
+ if (sched_feat(RT_PUSH_IPI)) {
+ tell_cpu_to_push(this_rq);
+ return 0;
+ }
+#endif
+
for_each_cpu(cpu, this_rq->rd->rto_mask) {
if (this_cpu == cpu)
continue;
OpenPOWER on IntegriCloud