From: Paul Turner <pjt@google.com>
To: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
Bharata B Rao <bharata@linux.vnet.ibm.com>,
Dhaval Giani <dhaval.giani@gmail.com>,
Balbir Singh <balbir@linux.vnet.ibm.com>,
Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>,
Srivatsa Vaddagiri <vatsa@in.ibm.com>,
Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>,
Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>,
Ingo Molnar <mingo@elte.hu>, Pavel Emelyanov <xemul@openvz.org>,
Hu Tao <hutao@cn.fujitsu.com>, Nikhil Rao <ncrao@google.com>
Subject: [patch 05/17] sched: accumulate per-cfs_rq cpu usage and charge against bandwidth
Date: Wed, 06 Jul 2011 22:30:41 -0700 [thread overview]
Message-ID: <20110707053100.169988098@google.com> (raw)
In-Reply-To: 20110707053036.173186930@google.com
[-- Attachment #1: sched-bwc-account_cfs_rq_runtime.patch --]
[-- Type: text/plain, Size: 6175 bytes --]
Account bandwidth usage on the cfs_rq level versus the task_groups to which
they belong. Whether we are tracking bandwidth on a given cfs_rq is maintained
under cfs_rq->runtime_enabled.
cfs_rq's which belong to a bandwidth constrained task_group have their runtime
accounted via the update_curr() path, which withdraws bandwidth from the global
pool as desired. Updates involving the global pool are currently protected
under cfs_bandwidth->lock, local runtime is protected by rq->lock.
This patch only assigns and tracks quota, no action is taken in the case that
cfs_rq->runtime_used exceeds cfs_rq->runtime_assigned.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
---
include/linux/sched.h | 4 ++
kernel/sched.c | 4 ++
kernel/sched_fair.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++--
kernel/sysctl.c | 10 +++++++
4 files changed, 84 insertions(+), 3 deletions(-)
Index: tip/kernel/sched_fair.c
===================================================================
--- tip.orig/kernel/sched_fair.c
+++ tip/kernel/sched_fair.c
@@ -89,6 +89,20 @@ const_debug unsigned int sysctl_sched_mi
*/
unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
+#ifdef CONFIG_CFS_BANDWIDTH
+/*
+ * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool
+ * each time a cfs_rq requests quota.
+ *
+ * Note: in the case that the slice exceeds the runtime remaining (either due
+ * to consumption or the quota being specified to be smaller than the slice)
+ * we will always only issue the remaining available time.
+ *
+ * default: 5 msec, units: microseconds
+ */
+unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
+#endif
+
static const struct sched_class fair_sched_class;
/**************************************************************
@@ -305,6 +319,8 @@ find_matching_se(struct sched_entity **s
#endif /* CONFIG_FAIR_GROUP_SCHED */
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
+ unsigned long delta_exec);
/**************************************************************
* Scheduling class tree data structure manipulation methods:
@@ -602,6 +618,8 @@ static void update_curr(struct cfs_rq *c
cpuacct_charge(curtask, delta_exec);
account_group_exec_runtime(curtask, delta_exec);
}
+
+ account_cfs_rq_runtime(cfs_rq, delta_exec);
}
static inline void
@@ -1270,6 +1288,48 @@ static inline u64 default_cfs_period(voi
{
return 100000000ULL;
}
+
+static inline u64 sched_cfs_bandwidth_slice(void)
+{
+ return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
+}
+
+static void 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);
+ u64 amount = 0, min_amount;
+
+ /* note: this is a positive sum as runtime_remaining <= 0 */
+ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
+
+ raw_spin_lock(&cfs_b->lock);
+ if (cfs_b->quota == RUNTIME_INF)
+ amount = min_amount;
+ else if (cfs_b->runtime > 0) {
+ amount = min(cfs_b->runtime, min_amount);
+ cfs_b->runtime -= amount;
+ }
+ raw_spin_unlock(&cfs_b->lock);
+
+ cfs_rq->runtime_remaining += amount;
+}
+
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
+ unsigned long delta_exec)
+{
+ if (!cfs_rq->runtime_enabled)
+ return;
+
+ cfs_rq->runtime_remaining -= delta_exec;
+ if (cfs_rq->runtime_remaining > 0)
+ return;
+
+ assign_cfs_rq_runtime(cfs_rq);
+}
+#else
+static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
+ unsigned long delta_exec) {}
#endif
/**************************************************
@@ -4262,8 +4322,13 @@ static void set_curr_task_fair(struct rq
{
struct sched_entity *se = &rq->curr->se;
- for_each_sched_entity(se)
- set_next_entity(cfs_rq_of(se), se);
+ for_each_sched_entity(se) {
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+
+ set_next_entity(cfs_rq, se);
+ /* ensure bandwidth has been allocated on our new cfs_rq */
+ account_cfs_rq_runtime(cfs_rq, 0);
+ }
}
#ifdef CONFIG_FAIR_GROUP_SCHED
Index: tip/kernel/sysctl.c
===================================================================
--- tip.orig/kernel/sysctl.c
+++ tip/kernel/sysctl.c
@@ -379,6 +379,16 @@ static struct ctl_table kern_table[] = {
.extra2 = &one,
},
#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+ {
+ .procname = "sched_cfs_bandwidth_slice_us",
+ .data = &sysctl_sched_cfs_bandwidth_slice,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
+ },
+#endif
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
Index: tip/kernel/sched.c
===================================================================
--- tip.orig/kernel/sched.c
+++ tip/kernel/sched.c
@@ -248,7 +248,7 @@ struct cfs_bandwidth {
#ifdef CONFIG_CFS_BANDWIDTH
raw_spinlock_t lock;
ktime_t period;
- u64 quota;
+ u64 quota, runtime;
s64 hierarchal_quota;
#endif
};
@@ -403,6 +403,7 @@ static inline u64 default_cfs_period(voi
static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
raw_spin_lock_init(&cfs_b->lock);
+ cfs_b->runtime = 0;
cfs_b->quota = RUNTIME_INF;
cfs_b->period = ns_to_ktime(default_cfs_period());
}
@@ -8920,6 +8921,7 @@ static int tg_set_cfs_bandwidth(struct t
raw_spin_lock_irq(&cfs_b->lock);
cfs_b->period = ns_to_ktime(period);
cfs_b->quota = quota;
+ cfs_b->runtime = quota;
raw_spin_unlock_irq(&cfs_b->lock);
for_each_possible_cpu(i) {
Index: tip/include/linux/sched.h
===================================================================
--- tip.orig/include/linux/sched.h
+++ tip/include/linux/sched.h
@@ -2012,6 +2012,10 @@ static inline void sched_autogroup_fork(
static inline void sched_autogroup_exit(struct signal_struct *sig) { }
#endif
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#endif
+
#ifdef CONFIG_RT_MUTEXES
extern int rt_mutex_getprio(struct task_struct *p);
extern void rt_mutex_setprio(struct task_struct *p, int prio);
next prev parent reply other threads:[~2011-07-07 5:34 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-07-07 5:30 [patch 00/17] CFS Bandwidth Control v7.1 Paul Turner
2011-07-07 5:30 ` [patch 01/17] sched: (fixlet) dont update shares twice on on_rq parent Paul Turner
2011-07-21 18:28 ` [tip:sched/core] sched: Don't " tip-bot for Paul Turner
2011-07-07 5:30 ` [patch 02/17] sched: hierarchical task accounting for SCHED_OTHER Paul Turner
2011-07-07 5:30 ` [patch 03/17] sched: introduce primitives to account for CFS bandwidth tracking Paul Turner
2011-07-07 13:48 ` Peter Zijlstra
2011-07-07 21:30 ` Paul Turner
2011-07-07 5:30 ` [patch 04/17] sched: validate CFS quota hierarchies Paul Turner
2011-07-07 5:30 ` Paul Turner [this message]
2011-07-07 5:30 ` [patch 06/17] sched: add a timer to handle CFS bandwidth refresh Paul Turner
2011-07-07 5:30 ` [patch 07/17] sched: expire invalid runtime Paul Turner
2011-07-07 5:30 ` [patch 08/17] sched: add support for throttling group entities Paul Turner
2011-07-07 5:30 ` [patch 09/17] sched: add support for unthrottling " Paul Turner
2011-07-07 5:30 ` [patch 10/17] sched: allow for positional tg_tree walks Paul Turner
2011-07-07 5:30 ` [patch 11/17] sched: prevent interactions with throttled entities Paul Turner
2011-07-07 5:30 ` [patch 12/17] sched: prevent buddy " Paul Turner
2011-07-07 5:30 ` [patch 13/17] sched: migrate throttled tasks on HOTPLUG Paul Turner
2011-07-07 5:30 ` [patch 14/17] sched: throttle entities exceeding their allowed bandwidth Paul Turner
2011-07-07 5:30 ` [patch 15/17] sched: add exports tracking cfs bandwidth control statistics Paul Turner
2011-07-07 5:30 ` [patch 16/17] sched: return unused runtime on group dequeue Paul Turner
2011-07-07 5:30 ` [patch 17/17] sched: add documentation for bandwidth control Paul Turner
2011-07-07 11:13 ` [patch 00/17] CFS Bandwidth Control v7.1 Peter Zijlstra
2011-07-11 1:22 ` Hu Tao
2011-07-07 11:23 ` Ingo Molnar
2011-07-07 11:28 ` Peter Zijlstra
2011-07-07 14:38 ` Peter Zijlstra
2011-07-07 14:51 ` Ingo Molnar
2011-07-07 14:54 ` Peter Zijlstra
2011-07-07 14:56 ` Ingo Molnar
2011-07-07 16:23 ` Jason Baron
2011-07-07 17:20 ` Peter Zijlstra
2011-07-07 18:15 ` Jason Baron
2011-07-07 20:36 ` jump_label defaults (was Re: [patch 00/17] CFS Bandwidth Control v7.1) Peter Zijlstra
2011-07-08 9:20 ` Peter Zijlstra
2011-07-08 15:47 ` Jason Baron
2011-07-07 16:52 ` [patch 00/17] CFS Bandwidth Control v7.1 Andi Kleen
2011-07-07 17:08 ` Peter Zijlstra
2011-07-07 17:59 ` Peter Zijlstra
2011-07-07 19:36 ` Jason Baron
2011-07-08 7:45 ` Paul Turner
2011-07-08 7:39 ` Paul Turner
2011-07-08 10:32 ` Peter Zijlstra
2011-07-09 7:34 ` Paul Turner
2011-07-10 18:12 ` Ingo Molnar
2011-07-07 14:06 ` Peter Zijlstra
2011-07-08 7:35 ` Paul Turner
2011-07-11 1:22 ` Hu Tao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20110707053100.169988098@google.com \
--to=pjt@google.com \
--cc=a.p.zijlstra@chello.nl \
--cc=balbir@linux.vnet.ibm.com \
--cc=bharata@linux.vnet.ibm.com \
--cc=dhaval.giani@gmail.com \
--cc=hutao@cn.fujitsu.com \
--cc=kamalesh@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=ncrao@google.com \
--cc=seto.hidetoshi@jp.fujitsu.com \
--cc=svaidy@linux.vnet.ibm.com \
--cc=vatsa@in.ibm.com \
--cc=xemul@openvz.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).