| 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: <20100428111656.7954.19756.stgit@kitami.corp.google.com>
Date: Wed, 28 Apr 2010 04:16:56 -0700
From: Paul Turner <pjt@...gle.com>
To: linux-kernel@...r.kernel.org
Cc: Paul Menage <menage@...gle.com>,
Srivatsa Vaddagiri <vatsa@...ibm.com>,
Dhaval Giani <dhaval@...ux.vnet.ibm.com>,
Gautham R Shenoy <ego@...ibm.com>,
Kamalesh Babulal <kamalesh@...ux.vnet.ibm.com>,
Herbert Poetzl <herbert@...hfloor.at>,
Balbir Singh <balbir@...ux.vnet.ibm.com>,
Chris Friesen <cfriesen@...tel.com>,
Avi Kivity <avi@...hat.com>,
Bharata B Rao <bharata@...ux.vnet.ibm.com>,
Nikhil Rao <ncrao@...gle.com>, Ingo Molnar <mingo@...e.hu>,
Pavel Emelyanov <xemul@...nvz.org>,
Mike Waychison <mikew@...gle.com>,
Vaidyanathan Srinivasan <svaidy@...ux.vnet.ibm.com>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>
Subject: [PATCH v2 2/6] sched: accumulate per-cfs_rq cpu usage
Introduce account_cfs_rq_quota() to account bandwidth usage on the cfs_rq
level versus task_groups for which bandwidth has been assigned. This is
tracked by whether the local cfs_rq->quota_assigned is finite or infinite
(RUNTIME_INF).
For cfs_rq's that belong to a bandwidth constrained task_group we introduce
tg_request_cfs_quota() which attempts to allocate quota from the global pool
for use locally. Updates involving the global pool are currently protected
under cfs_bandwidth->lock, local pools are protected by rq->lock.
This patch only attempts to assign and track quota, no action is taken in the
case that cfs_rq->quota_used exceeds cfs_rq->quota_assigned.
Signed-off-by: Paul Turner <pjt@...gle.com>
Signed-off-by: Nikhil Rao <ncrao@...gle.com>
---
include/linux/sched.h | 4 ++++
kernel/sched.c | 13 +++++++++++++
kernel/sched_fair.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++++
kernel/sysctl.c | 10 ++++++++++
4 files changed, 77 insertions(+), 0 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dad7f66..8603645 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1903,6 +1903,10 @@ int sched_rt_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos);
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#endif
+
extern unsigned int sysctl_sched_compat_yield;
#ifdef CONFIG_RT_MUTEXES
diff --git a/kernel/sched.c b/kernel/sched.c
index 96db602..3b53695 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1912,6 +1912,19 @@ static const struct sched_class rt_sched_class;
* default: 0.5s
*/
static u64 sched_cfs_bandwidth_period = 500000000ULL;
+
+/*
+ * default slice of quota to allocate from global tg to local cfs_rq pool on
+ * each refresh
+ * default: 10ms
+ */
+unsigned int sysctl_sched_cfs_bandwidth_slice = 10000UL;
+
+static inline u64 sched_cfs_bandwidth_slice(void)
+{
+ return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
+}
+
#endif
#define sched_class_highest (&rt_sched_class)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a61bc24..1db1991 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -267,6 +267,16 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse)
#endif /* CONFIG_FAIR_GROUP_SCHED */
+#ifdef CONFIG_CFS_BANDWIDTH
+static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
+{
+ return &tg->cfs_bandwidth;
+}
+
+static void account_cfs_rq_quota(struct cfs_rq *cfs_rq,
+ unsigned long delta_exec);
+#endif
+
/**************************************************************
* Scheduling class tree data structure manipulation methods:
@@ -546,6 +556,9 @@ static void update_curr(struct cfs_rq *cfs_rq)
cpuacct_charge(curtask, delta_exec);
account_group_exec_runtime(curtask, delta_exec);
}
+#ifdef CONFIG_CFS_BANDWIDTH
+ account_cfs_rq_quota(cfs_rq, delta_exec);
+#endif
}
static inline void
@@ -1148,6 +1161,43 @@ static void yield_task_fair(struct rq *rq)
}
#ifdef CONFIG_CFS_BANDWIDTH
+static u64 tg_request_cfs_quota(struct task_group *tg)
+{
+ struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
+ u64 delta = 0;
+
+ if (cfs_b->runtime > 0 || cfs_b->quota == RUNTIME_INF) {
+ raw_spin_lock(&cfs_b->lock);
+ /*
+ * it's possible a bandwidth update has changed the global
+ * pool.
+ */
+ if (cfs_b->quota == RUNTIME_INF)
+ delta = sched_cfs_bandwidth_slice();
+ else {
+ delta = min(cfs_b->runtime,
+ sched_cfs_bandwidth_slice());
+ cfs_b->runtime -= delta;
+ }
+ raw_spin_unlock(&cfs_b->lock);
+ }
+ return delta;
+}
+
+static void account_cfs_rq_quota(struct cfs_rq *cfs_rq,
+ unsigned long delta_exec)
+{
+ if (cfs_rq->quota_assigned == RUNTIME_INF)
+ return;
+
+ cfs_rq->quota_used += delta_exec;
+
+ if (cfs_rq->quota_used < cfs_rq->quota_assigned)
+ return;
+
+ cfs_rq->quota_assigned += tg_request_cfs_quota(cfs_rq->tg);
+}
+
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
{
return 1;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8686b0f..d0e17ca 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -354,6 +354,16 @@ static struct ctl_table kern_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+#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",
--
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