[tip:branch?] sched: Strengthen buddies and mitigate buddy induced latencies

From: tip-bot for Mike Galbraith
Date: Fri Oct 23 2009 - 21:05:59 EST


Commit-ID: f685ceacab07d3f6c236f04803e2f2f0dbcc5afb
Gitweb: http://git.kernel.org/tip/f685ceacab07d3f6c236f04803e2f2f0dbcc5afb
Author: Mike Galbraith <efault@xxxxxx>
AuthorDate: Fri, 23 Oct 2009 23:09:22 +0200
Committer: Ingo Molnar <mingo@xxxxxxx>
CommitDate: Fri, 23 Oct 2009 23:48:28 +0200

sched: Strengthen buddies and mitigate buddy induced latencies

This patch restores the effectiveness of LAST_BUDDY in preventing
pgsql+oltp from collapsing due to wakeup preemption. It also
switches LAST_BUDDY to exclusively do what it does best, namely
mitigate the effects of aggressive wakeup preemption, which
improves vmark throughput markedly, and restores mysql+oltp
scalability.

Since buddies are about scalability, enable them beginning at the
point where we begin expanding sched_latency, namely
sched_nr_latency. Previously, buddies were cleared aggressively,
which seriously reduced their effectiveness. Not clearing
aggressively however, produces a small drop in mysql+oltp
throughput immediately after peak, indicating that LAST_BUDDY is
actually doing some harm. This is right at the point where X on the
desktop in competition with another load wants low latency service.
Ergo, do not enable until we need to scale.

To mitigate latency induced by buddies, or by a task just missing
wakeup preemption, check latency at tick time.

Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via
CACHE_HOT_BUDDY.

Supporting performance tests:

tip = v2.6.32-rc5-1497-ga525b32
tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies
tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs

(Three run averages except where noted.)

vmark:
------
tip 108466 messages per second
tip+ 125307 messages per second
tip+x 125335 messages per second
tipx 117781 messages per second
2.6.31.3 122729 messages per second

mysql+oltp:
-----------
clients 1 2 4 8 16 32 64 128 256
..........................................................................................
tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08
tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47
tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18
2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86

pgsql+oltp:
-----------
clients 1 2 4 8 16 32 64 128 256
..........................................................................................
tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35
tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94
tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00
tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84
2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25

Signed-off-by: Mike Galbraith <efault@xxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
kernel/sched.c | 2 +-
kernel/sched_fair.c | 73 ++++++++++++++++++++++++++++++++------------------
2 files changed, 48 insertions(+), 27 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 789001d..cae6700 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2008,7 +2008,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
/*
* Buddy candidates are cache hot:
*/
- if (sched_feat(CACHE_HOT_BUDDY) &&
+ if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
(&p->se == cfs_rq_of(&p->se)->next ||
&p->se == cfs_rq_of(&p->se)->last))
return 1;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c32c3e6..37087a7 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
* re-elected due to buddy favours.
*/
clear_buddies(cfs_rq, curr);
+ return;
+ }
+
+ /*
+ * Ensure that a task that missed wakeup preemption by a
+ * narrow margin doesn't have to wait for a full slice.
+ * This also mitigates buddy induced latencies under load.
+ */
+ if (!sched_feat(WAKEUP_PREEMPT))
+ return;
+
+ if (delta_exec < sysctl_sched_min_granularity)
+ return;
+
+ if (cfs_rq->nr_running > 1) {
+ struct sched_entity *se = __pick_next_entity(cfs_rq);
+ s64 delta = curr->vruntime - se->vruntime;
+
+ if (delta > ideal_runtime)
+ resched_task(rq_of(cfs_rq)->curr);
}
}

@@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = __pick_next_entity(cfs_rq);
- struct sched_entity *buddy;
+ struct sched_entity *left = se;

- if (cfs_rq->next) {
- buddy = cfs_rq->next;
- cfs_rq->next = NULL;
- if (wakeup_preempt_entity(buddy, se) < 1)
- return buddy;
- }
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+ se = cfs_rq->next;

- if (cfs_rq->last) {
- buddy = cfs_rq->last;
- cfs_rq->last = NULL;
- if (wakeup_preempt_entity(buddy, se) < 1)
- return buddy;
- }
+ /*
+ * Prefer last buddy, try to return the CPU to a preempted task.
+ */
+ if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+ se = cfs_rq->last;
+
+ clear_buddies(cfs_rq, se);

return se;
}
@@ -1577,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int sync = wake_flags & WF_SYNC;
+ int scale = cfs_rq->nr_running >= sched_nr_latency;

update_curr(cfs_rq);

@@ -1591,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
if (unlikely(se == pse))
return;

- /*
- * Only set the backward buddy when the current task is still on the
- * rq. This can happen when a wakeup gets interleaved with schedule on
- * the ->pre_schedule() or idle_balance() point, either of which can
- * drop the rq lock.
- *
- * Also, during early boot the idle thread is in the fair class, for
- * obvious reasons its a bad idea to schedule back to the idle thread.
- */
- if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
- set_last_buddy(se);
- if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+ if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
set_next_buddy(pse);

/*
@@ -1648,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_

BUG_ON(!pse);

- if (wakeup_preempt_entity(se, pse) == 1)
+ if (wakeup_preempt_entity(se, pse) == 1) {
resched_task(curr);
+ /*
+ * Only set the backward buddy when the current task is still
+ * on the rq. This can happen when a wakeup gets interleaved
+ * with schedule on the ->pre_schedule() or idle_balance()
+ * point, either of which can * drop the rq lock.
+ *
+ * Also, during early boot the idle thread is in the fair class,
+ * for obvious reasons its a bad idea to schedule back to it.
+ */
+ if (unlikely(!se->on_rq || curr == rq->idle))
+ return;
+ if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+ set_last_buddy(se);
+ }
}

static struct task_struct *pick_next_task_fair(struct rq *rq)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/