| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <tip-85dac906bec3bb41bfaa7ccaa65c4706de5cfdf8@git.kernel.org>
Date: Sun, 14 Aug 2011 16:26:21 GMT
From: tip-bot for Paul Turner <pjt@...gle.com>
To: linux-tip-commits@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
a.p.zijlstra@...llo.nl, pjt@...gle.com, tglx@...utronix.de,
mingo@...e.hu
Subject: [tip:sched/core] sched: Add support for throttling group entities
Commit-ID: 85dac906bec3bb41bfaa7ccaa65c4706de5cfdf8
Gitweb: http://git.kernel.org/tip/85dac906bec3bb41bfaa7ccaa65c4706de5cfdf8
Author: Paul Turner <pjt@...gle.com>
AuthorDate: Thu, 21 Jul 2011 09:43:33 -0700
Committer: Ingo Molnar <mingo@...e.hu>
CommitDate: Sun, 14 Aug 2011 12:03:34 +0200
sched: Add support for throttling group entities
Now that consumption is tracked (via update_curr()) we add support to throttle
group entities (and their corresponding cfs_rqs) in the case where this is no
run-time remaining.
Throttled entities are dequeued to prevent scheduling, additionally we mark
them as throttled (using cfs_rq->throttled) to prevent them from becoming
re-enqueued until they are unthrottled. A list of a task_group's throttled
entities are maintained on the cfs_bandwidth structure.
Note: While the machinery for throttling is added in this patch the act of
throttling an entity exceeding its bandwidth is deferred until later within
the series.
Signed-off-by: Paul Turner <pjt@...gle.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Link: http://lkml.kernel.org/r/20110721184757.480608533@google.com
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
kernel/sched.c | 7 ++++
kernel/sched_fair.c | 89 ++++++++++++++++++++++++++++++++++++++++++++++++--
2 files changed, 92 insertions(+), 4 deletions(-)
diff --git a/kernel/sched.c b/kernel/sched.c
index a2d5514..044260a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -260,6 +260,8 @@ struct cfs_bandwidth {
int idle, timer_active;
struct hrtimer period_timer;
+ struct list_head throttled_cfs_rq;
+
#endif
};
@@ -399,6 +401,9 @@ struct cfs_rq {
int runtime_enabled;
u64 runtime_expires;
s64 runtime_remaining;
+
+ int throttled;
+ struct list_head throttled_list;
#endif
#endif
};
@@ -441,6 +446,7 @@ static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
+ INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq);
hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->period_timer.function = sched_cfs_period_timer;
}
@@ -448,6 +454,7 @@ static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
cfs_rq->runtime_enabled = 0;
+ INIT_LIST_HEAD(&cfs_rq->throttled_list);
}
/* requires cfs_b->lock, may release to reprogram timer */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 9d1adbd..72c9d4e 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1291,7 +1291,8 @@ static void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
}
-static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+/* returns 0 on failure to allocate runtime */
+static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
@@ -1332,6 +1333,8 @@ static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
*/
if ((s64)(expires - cfs_rq->runtime_expires) > 0)
cfs_rq->runtime_expires = expires;
+
+ return cfs_rq->runtime_remaining > 0;
}
/*
@@ -1378,7 +1381,12 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
if (likely(cfs_rq->runtime_remaining > 0))
return;
- assign_cfs_rq_runtime(cfs_rq);
+ /*
+ * if we're unable to extend our runtime we resched so that the active
+ * hierarchy can be throttled
+ */
+ if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
+ resched_task(rq_of(cfs_rq)->curr);
}
static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
@@ -1390,6 +1398,47 @@ static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
__account_cfs_rq_runtime(cfs_rq, delta_exec);
}
+static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
+{
+ return cfs_rq->throttled;
+}
+
+static __used void throttle_cfs_rq(struct cfs_rq *cfs_rq)
+{
+ struct rq *rq = rq_of(cfs_rq);
+ struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+ struct sched_entity *se;
+ long task_delta, dequeue = 1;
+
+ se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
+
+ /* account load preceding throttle */
+ update_cfs_load(cfs_rq, 0);
+
+ task_delta = cfs_rq->h_nr_running;
+ for_each_sched_entity(se) {
+ struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+ /* throttled entity or throttle-on-deactivate */
+ if (!se->on_rq)
+ break;
+
+ if (dequeue)
+ dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
+ qcfs_rq->h_nr_running -= task_delta;
+
+ if (qcfs_rq->load.weight)
+ dequeue = 0;
+ }
+
+ if (!se)
+ rq->nr_running -= task_delta;
+
+ cfs_rq->throttled = 1;
+ raw_spin_lock(&cfs_b->lock);
+ list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ raw_spin_unlock(&cfs_b->lock);
+}
+
/*
* Responsible for refilling a task_group's bandwidth and unthrottling its
* cfs_rqs as appropriate. If there has been no activity within the last
@@ -1425,6 +1474,11 @@ out_unlock:
#else
static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
unsigned long delta_exec) {}
+
+static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
+{
+ return 0;
+}
#endif
/**************************************************
@@ -1503,7 +1557,17 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
break;
cfs_rq = cfs_rq_of(se);
enqueue_entity(cfs_rq, se, flags);
+
+ /*
+ * end evaluation on encountering a throttled cfs_rq
+ *
+ * note: in the case of encountering a throttled cfs_rq we will
+ * post the final h_nr_running increment below.
+ */
+ if (cfs_rq_throttled(cfs_rq))
+ break;
cfs_rq->h_nr_running++;
+
flags = ENQUEUE_WAKEUP;
}
@@ -1511,11 +1575,15 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running++;
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+
update_cfs_load(cfs_rq, 0);
update_cfs_shares(cfs_rq);
}
- inc_nr_running(rq);
+ if (!se)
+ inc_nr_running(rq);
hrtick_update(rq);
}
@@ -1535,6 +1603,15 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, flags);
+
+ /*
+ * end evaluation on encountering a throttled cfs_rq
+ *
+ * note: in the case of encountering a throttled cfs_rq we will
+ * post the final h_nr_running decrement below.
+ */
+ if (cfs_rq_throttled(cfs_rq))
+ break;
cfs_rq->h_nr_running--;
/* Don't dequeue parent if it has other entities besides us */
@@ -1557,11 +1634,15 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
cfs_rq = cfs_rq_of(se);
cfs_rq->h_nr_running--;
+ if (cfs_rq_throttled(cfs_rq))
+ break;
+
update_cfs_load(cfs_rq, 0);
update_cfs_shares(cfs_rq);
}
- dec_nr_running(rq);
+ if (!se)
+ dec_nr_running(rq);
hrtick_update(rq);
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists